From 1b7844cf8d6fdd2b631e0b731edf75fb756390ea Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Mon, 10 Jun 2024 12:21:05 -0600
Subject: [PATCH 01/40] Create qcdataframe.py

---
 src/cosmicqc/qcdataframe.py | 63 +++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 src/cosmicqc/qcdataframe.py

diff --git a/src/cosmicqc/qcdataframe.py b/src/cosmicqc/qcdataframe.py
new file mode 100644
index 0000000..ba25c6f
--- /dev/null
+++ b/src/cosmicqc/qcdataframe.py
@@ -0,0 +1,63 @@
+"""
+Defines a QCDataFrame class for use in coSMicQC.
+"""
+
+import pandas as pd
+from typing import Union
+
+class QCDataFrame:
+    """
+    A class to handle and load different types of data files into a pandas DataFrame.
+
+    This class can initialize with either a pandas DataFrame or a file path (CSV, TSV,
+    TXT, or Parquet). When initialized with a file path, it reads the data into a
+    pandas DataFrame.
+
+    Attributes:
+        reference (str):
+            A string indicating the type of data source, either 'pd.DataFrame'
+            or the file path.
+        data (pd.DataFrame):
+            The loaded data in a pandas DataFrame.
+
+    Methods:
+        __call__():
+            Returns the underlying pandas DataFrame.
+    """
+
+    def __init__(self, data: Union[pd.DataFrame, str], **kwargs) -> None:
+        """
+        Initializes the QCDataFrame with either a DataFrame or a file path.
+
+        Args:
+            data (Union[pd.DataFrame, str]):
+                The data source, either a pandas DataFrame or a file path.
+            **kwargs:
+                Additional keyword arguments to pass to the pandas read functions.
+        """
+        if isinstance(data, pd.DataFrame):
+            # if data is a pd.DataFrame, remember this within the reference attr
+            self.reference = "pd.DataFrame"
+            self.data = data
+        elif isinstance(data, str):
+            # if the data is a string, remember the original source
+            # through a reference attr
+            self.reference = data
+
+            # Read the data from the file based on its extension
+            if data.endswith(".csv"):
+                self.data = pd.read_csv(data, **kwargs)
+            elif data.endswith(".tsv") or data.endswith(".txt"):
+                self.data = pd.read_csv(data, delimiter="\t", **kwargs)
+            elif data.endswith(".parquet"):
+                self.data = pd.read_parquet(data, **kwargs)
+
+    def __call__(self) -> pd.DataFrame:
+        """
+        Returns the underlying pandas DataFrame.
+
+        Returns:
+            pd.DataFrame: The data in a pandas DataFrame.
+        """
+        return self.data
+

From 978484127fd4bf00a96547d0b8b08bcd68495755 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Mon, 10 Jun 2024 12:33:33 -0600
Subject: [PATCH 02/40] linting

---
 src/cosmicqc/qcdataframe.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/src/cosmicqc/qcdataframe.py b/src/cosmicqc/qcdataframe.py
index ba25c6f..7a229fb 100644
--- a/src/cosmicqc/qcdataframe.py
+++ b/src/cosmicqc/qcdataframe.py
@@ -2,8 +2,10 @@
 Defines a QCDataFrame class for use in coSMicQC.
 """
 
+from typing import Any, Dict, Self, Union
+
 import pandas as pd
-from typing import Union
+
 
 class QCDataFrame:
     """
@@ -25,7 +27,9 @@ class QCDataFrame:
             Returns the underlying pandas DataFrame.
     """
 
-    def __init__(self, data: Union[pd.DataFrame, str], **kwargs) -> None:
+    def __init__(
+        self: Self, data: Union[pd.DataFrame, str], **kwargs: Dict[str, Any]
+    ) -> None:
         """
         Initializes the QCDataFrame with either a DataFrame or a file path.
 
@@ -52,7 +56,7 @@ def __init__(self, data: Union[pd.DataFrame, str], **kwargs) -> None:
             elif data.endswith(".parquet"):
                 self.data = pd.read_parquet(data, **kwargs)
 
-    def __call__(self) -> pd.DataFrame:
+    def __call__(self: Self) -> pd.DataFrame:
         """
         Returns the underlying pandas DataFrame.
 
@@ -60,4 +64,3 @@ def __call__(self) -> pd.DataFrame:
             pd.DataFrame: The data in a pandas DataFrame.
         """
         return self.data
-

From c39e2b0c4f000289ffcb87b107ce964bb1ef80fe Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Mon, 10 Jun 2024 14:04:42 -0600
Subject: [PATCH 03/40] add qcdataframe

---
 src/cosmicqc/__init__.py    |  1 +
 src/cosmicqc/analyze.py     | 32 ++++++++++++++------
 src/cosmicqc/qcdataframe.py | 58 ++++++++++++++++++++++++++++++++++---
 tests/conftest.py           | 41 ++++++++++++++++++++++++++
 tests/test_analyze.py       | 18 +++++++++++-
 tests/test_qcdataframe.py   | 42 +++++++++++++++++++++++++++
 6 files changed, 178 insertions(+), 14 deletions(-)
 create mode 100644 tests/test_qcdataframe.py

diff --git a/src/cosmicqc/__init__.py b/src/cosmicqc/__init__.py
index aca6bd8..82f4e10 100644
--- a/src/cosmicqc/__init__.py
+++ b/src/cosmicqc/__init__.py
@@ -3,6 +3,7 @@
 """
 
 from .analyze import find_outliers
+from .qcdataframe import QCDataFrame
 
 # note: version placeholder is updated during build
 # by poetry-dynamic-versioning.
diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index 9f33c4b..70833a6 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -11,13 +11,15 @@
 import yaml
 from scipy.stats import zscore as scipy_zscore
 
+from .qcdataframe import QCDataFrame
+
 DEFAULT_QC_THRESHOLD_FILE = (
     f"{pathlib.Path(__file__).parent!s}/data/qc_nuclei_thresholds_default.yml"
 )
 
 
 def identify_outliers(
-    df: pd.DataFrame,
+    df: Union[QCDataFrame, pd.DataFrame, str],
     feature_thresholds: Union[Dict[str, float], str],
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
     include_threshold_scores: bool = False,
@@ -30,8 +32,8 @@ def identify_outliers(
     threshold of 0 as that would represent the whole dataset.
 
     Args:
-        df: pd.DataFrame
-            Data frame with converted output from CytoTable.
+        df: Union[QCDataFrame, pd.DataFrame, str]
+            DataFrame or file with converted output from CytoTable.
         metadata_columns: List[str]
             List of metadata columns that should be outputted with the outlier data.
         feature_thresholds: Dict[str, float]
@@ -52,6 +54,10 @@ def identify_outliers(
             or not for use within other functions.
     """
 
+    # interpret the df as QCDataFrame
+    if not isinstance(df, QCDataFrame):
+        df = QCDataFrame(data=df)
+
     # create a copy of the dataframe to ensure
     # we don't modify the supplied dataframe inplace.
     outlier_df = df.copy()
@@ -107,7 +113,7 @@ def identify_outliers(
 
 
 def find_outliers(
-    df: pd.DataFrame,
+    df: Union[QCDataFrame, pd.DataFrame, str],
     metadata_columns: List[str],
     feature_thresholds: Union[Dict[str, float], str],
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
@@ -117,8 +123,8 @@ def find_outliers(
     with only the outliers and provided metadata columns.
 
     Args:
-        df: pd.DataFrame
-            Data frame with converted output from CytoTable.
+        df: Union[QCDataFrame, pd.DataFrame, str]
+            DataFrame or file with converted output from CytoTable.
         metadata_columns: List[str]
             List of metadata columns that should be outputted with the outlier data.
         feature_thresholds: Dict[str, float]
@@ -138,6 +144,10 @@ def find_outliers(
             Outlier data frame for the given conditions.
     """
 
+    # interpret the df as QCDataFrame
+    if not isinstance(df, QCDataFrame):
+        df = QCDataFrame(data=df)
+
     if isinstance(feature_thresholds, str):
         feature_thresholds = read_thresholds_set_from_file(
             feature_thresholds=feature_thresholds,
@@ -169,7 +179,7 @@ def find_outliers(
 
 
 def label_outliers(
-    df: pd.DataFrame,
+    df: Union[QCDataFrame, pd.DataFrame, str],
     feature_thresholds: Optional[Union[Dict[str, float], str]] = None,
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
     include_threshold_scores: bool = False,
@@ -179,8 +189,8 @@ def label_outliers(
     where a cell passed or failed the quality control condition(s).
 
         Args:
-            df: pd.DataFrame
-                Data frame with converted output from CytoTable.
+            df: Union[QCDataFrame, pd.DataFrame, str]
+                DataFrame or file with converted output from CytoTable.
             feature_thresholds: Dict[str, float]
                 One of two options:
                 A dictionary with the feature name(s) as the key(s) and their assigned
@@ -201,6 +211,10 @@ def label_outliers(
                 Full dataframe with optional scores and outlier boolean column.
     """
 
+    # interpret the df as QCDataFrame
+    if not isinstance(df, QCDataFrame):
+        df = QCDataFrame(data=df)
+
     # for single outlier processing
     if isinstance(feature_thresholds, (str, dict)):
         # return the outlier dataframe for one threshold rule
diff --git a/src/cosmicqc/qcdataframe.py b/src/cosmicqc/qcdataframe.py
index 7a229fb..3ed24fa 100644
--- a/src/cosmicqc/qcdataframe.py
+++ b/src/cosmicqc/qcdataframe.py
@@ -2,6 +2,7 @@
 Defines a QCDataFrame class for use in coSMicQC.
 """
 
+import pathlib
 from typing import Any, Dict, Self, Union
 
 import pandas as pd
@@ -39,23 +40,38 @@ def __init__(
             **kwargs:
                 Additional keyword arguments to pass to the pandas read functions.
         """
+
+        # print(data)
+        # print(type(data))
+        # print(isinstance(data, QCDataFrame))
+
         if isinstance(data, pd.DataFrame):
             # if data is a pd.DataFrame, remember this within the reference attr
             self.reference = "pd.DataFrame"
             self.data = data
-        elif isinstance(data, str):
+
+        elif isinstance(data, pathlib.Path | str):
             # if the data is a string, remember the original source
             # through a reference attr
             self.reference = data
 
+            # interpret the data through pathlib
+            data_path = pathlib.Path(data)
+
             # Read the data from the file based on its extension
-            if data.endswith(".csv"):
+            if data_path.suffix == ".csv":
+                # read as a CSV
                 self.data = pd.read_csv(data, **kwargs)
-            elif data.endswith(".tsv") or data.endswith(".txt"):
+            elif data_path.suffix in (".tsv", ".txt"):
+                # read as a TSV
                 self.data = pd.read_csv(data, delimiter="\t", **kwargs)
-            elif data.endswith(".parquet"):
+            elif data_path.suffix == ".parquet":
+                # read as a Parquet file
                 self.data = pd.read_parquet(data, **kwargs)
 
+        else:
+            raise ValueError("Unsupported file format for QCDataFrame.")
+
     def __call__(self: Self) -> pd.DataFrame:
         """
         Returns the underlying pandas DataFrame.
@@ -64,3 +80,37 @@ def __call__(self: Self) -> pd.DataFrame:
             pd.DataFrame: The data in a pandas DataFrame.
         """
         return self.data
+
+    def __repr__(self: Self) -> pd.DataFrame:
+        """
+        Returns the underlying pandas DataFrame.
+
+        Returns:
+            pd.DataFrame: The data in a pandas DataFrame.
+        """
+        return self.data
+
+    def __getattr__(self: Self, attr: str) -> Any:  # noqa: ANN401
+        """
+        Intercept attribute accesses and delegate them to the underlying
+        pandas DataFrame.
+
+        Args:
+            attr (str): The name of the attribute being accessed.
+
+        Returns:
+            Any: The value of the attribute from the pandas DataFrame.
+        """
+        return getattr(self.data, attr)
+
+    def __getitem__(self: Self, key: Union[int, str]) -> Any:  # noqa: ANN401
+        """
+        Returns an element or a slice of the underlying pandas DataFrame.
+
+        Args:
+            key: The key or slice to access the data.
+
+        Returns:
+            pd.DataFrame or any: The selected element or slice of data.
+        """
+        return self.data[key]
diff --git a/tests/conftest.py b/tests/conftest.py
index a8f796a..967ad2a 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -4,6 +4,8 @@
 https://docs.pytest.org/en/7.1.x/explanation/fixtures.html
 """
 
+import pathlib
+
 import pandas as pd
 import pytest
 
@@ -24,3 +26,42 @@ def fixture_basic_outlier_dataframe():
     Creates basic example data for use in tests
     """
     return pd.DataFrame({"example_feature": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})
+
+
+@pytest.fixture(name="basic_outlier_csv")
+def fixture_basic_outlier_csv(
+    tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
+):
+    """
+    Creates basic example data csv for use in tests
+    """
+
+    basic_outlier_dataframe.to_csv(csv_path := tmp_path / "example.csv")
+
+    return csv_path
+
+
+@pytest.fixture(name="basic_outlier_tsv")
+def fixture_basic_outlier_tsv(
+    tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
+):
+    """
+    Creates basic example data tsv for use in tests
+    """
+
+    basic_outlier_dataframe.to_csv(tsv_path := tmp_path / "example.tsv", sep="\t")
+
+    return tsv_path
+
+
+@pytest.fixture(name="basic_outlier_parquet")
+def fixture_basic_outlier_parquet(
+    tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
+):
+    """
+    Creates basic example data parquet for use in tests
+    """
+
+    basic_outlier_dataframe.to_parquet(parquet_path := tmp_path / "example.parquet")
+
+    return parquet_path
diff --git a/tests/test_analyze.py b/tests/test_analyze.py
index 6c7a879..a55cf6b 100644
--- a/tests/test_analyze.py
+++ b/tests/test_analyze.py
@@ -7,7 +7,7 @@
 from cosmicqc import analyze
 
 
-def test_find_outliers_basic(basic_outlier_dataframe: pd.DataFrame):
+def test_find_outliers_basic_dataframe(basic_outlier_dataframe: pd.DataFrame):
     """
     Testing find_outliers with basic/simulated data.
     """
@@ -27,6 +27,21 @@ def test_find_outliers_basic(basic_outlier_dataframe: pd.DataFrame):
     }
 
 
+def test_find_outliers_basic_csv(basic_outlier_csv: str):
+    """
+    Testing find_outliers with csv data.
+    """
+
+    # assert that we have the output we expect
+    assert analyze.find_outliers(
+        df=basic_outlier_csv,
+        feature_thresholds={"example_feature": 1},
+        metadata_columns=[],
+    ).to_dict(orient="dict") == {
+        "example_feature": {8: 9, 9: 10},
+    }
+
+
 def test_find_outliers_cfret(cytotable_CFReT_data_df: pd.DataFrame):
     """
     Testing find_outliers with CytoTable CFReT data.
@@ -315,6 +330,7 @@ def test_find_outliers_dict_and_default_config_cfret(
 
 def test_label_outliers(
     basic_outlier_dataframe: pd.DataFrame,
+    basic_outlier_csv: str,
     cytotable_CFReT_data_df: pd.DataFrame,
 ):
     """
diff --git a/tests/test_qcdataframe.py b/tests/test_qcdataframe.py
new file mode 100644
index 0000000..1124305
--- /dev/null
+++ b/tests/test_qcdataframe.py
@@ -0,0 +1,42 @@
+"""
+Tests cosmicqc qcdataframe module
+"""
+
+import pandas as pd
+from cosmicqc.qcdataframe import QCDataFrame
+
+def test_qcdataframe_init_with_dataframe(basic_outlier_dataframe: pd.DataFrame):
+    """
+    Tests QCDataFrame with pd.DataFrame input.
+    """
+    qc_df = QCDataFrame(data=basic_outlier_dataframe)
+    assert qc_df.reference == "pd.DataFrame"
+    assert qc_df.equals(basic_outlier_dataframe)
+
+def test_qcdataframe_init_with_csv(basic_outlier_csv:str):
+    """
+    Tests QCDataFrame with CSV input.
+    """
+    qc_df = QCDataFrame(data=basic_outlier_csv)
+    expected_df = pd.read_csv(basic_outlier_csv)
+    assert qc_df.reference == basic_outlier_csv
+    assert qc_df.equals(expected_df)
+
+def test_qcdataframe_init_with_tsv(basic_outlier_tsv:str):
+    """
+    Tests QCDataFrame with TSV input.
+    """
+    qc_df = QCDataFrame(data=basic_outlier_tsv)
+    expected_df = pd.read_csv(basic_outlier_tsv, delimiter='\t')
+    assert qc_df.reference == basic_outlier_tsv
+    assert qc_df.equals(expected_df)
+
+def test_qcdataframe_init_with_parquet(basic_outlier_parquet:str):
+    """
+    Tests QCDataFrame with TSV input.
+    """
+    qc_df = QCDataFrame(data=basic_outlier_parquet)
+    expected_df = pd.read_parquet(basic_outlier_parquet)
+    assert qc_df.reference == basic_outlier_parquet
+    assert qc_df.equals(expected_df)
+

From f3003e1de72a83a281308149acefc29fe4e63683 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Mon, 10 Jun 2024 14:04:54 -0600
Subject: [PATCH 04/40] linting

---
 tests/test_qcdataframe.py | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/tests/test_qcdataframe.py b/tests/test_qcdataframe.py
index 1124305..1b1fad4 100644
--- a/tests/test_qcdataframe.py
+++ b/tests/test_qcdataframe.py
@@ -5,6 +5,7 @@
 import pandas as pd
 from cosmicqc.qcdataframe import QCDataFrame
 
+
 def test_qcdataframe_init_with_dataframe(basic_outlier_dataframe: pd.DataFrame):
     """
     Tests QCDataFrame with pd.DataFrame input.
@@ -13,7 +14,8 @@ def test_qcdataframe_init_with_dataframe(basic_outlier_dataframe: pd.DataFrame):
     assert qc_df.reference == "pd.DataFrame"
     assert qc_df.equals(basic_outlier_dataframe)
 
-def test_qcdataframe_init_with_csv(basic_outlier_csv:str):
+
+def test_qcdataframe_init_with_csv(basic_outlier_csv: str):
     """
     Tests QCDataFrame with CSV input.
     """
@@ -22,16 +24,18 @@ def test_qcdataframe_init_with_csv(basic_outlier_csv:str):
     assert qc_df.reference == basic_outlier_csv
     assert qc_df.equals(expected_df)
 
-def test_qcdataframe_init_with_tsv(basic_outlier_tsv:str):
+
+def test_qcdataframe_init_with_tsv(basic_outlier_tsv: str):
     """
     Tests QCDataFrame with TSV input.
     """
     qc_df = QCDataFrame(data=basic_outlier_tsv)
-    expected_df = pd.read_csv(basic_outlier_tsv, delimiter='\t')
+    expected_df = pd.read_csv(basic_outlier_tsv, delimiter="\t")
     assert qc_df.reference == basic_outlier_tsv
     assert qc_df.equals(expected_df)
 
-def test_qcdataframe_init_with_parquet(basic_outlier_parquet:str):
+
+def test_qcdataframe_init_with_parquet(basic_outlier_parquet: str):
     """
     Tests QCDataFrame with TSV input.
     """
@@ -39,4 +43,3 @@ def test_qcdataframe_init_with_parquet(basic_outlier_parquet:str):
     expected_df = pd.read_parquet(basic_outlier_parquet)
     assert qc_df.reference == basic_outlier_parquet
     assert qc_df.equals(expected_df)
-

From b97f3a57aaa273b19fd61276db5bfe391b21de6d Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Mon, 10 Jun 2024 16:14:27 -0600
Subject: [PATCH 05/40] adding tests

---
 src/cosmicqc/qcdataframe.py |  4 ----
 tests/conftest.py           |  6 +++---
 tests/test_analyze.py       | 15 +++++++++++++++
 3 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/src/cosmicqc/qcdataframe.py b/src/cosmicqc/qcdataframe.py
index 3ed24fa..8498311 100644
--- a/src/cosmicqc/qcdataframe.py
+++ b/src/cosmicqc/qcdataframe.py
@@ -41,10 +41,6 @@ def __init__(
                 Additional keyword arguments to pass to the pandas read functions.
         """
 
-        # print(data)
-        # print(type(data))
-        # print(isinstance(data, QCDataFrame))
-
         if isinstance(data, pd.DataFrame):
             # if data is a pd.DataFrame, remember this within the reference attr
             self.reference = "pd.DataFrame"
diff --git a/tests/conftest.py b/tests/conftest.py
index 967ad2a..ad0c17e 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -36,7 +36,7 @@ def fixture_basic_outlier_csv(
     Creates basic example data csv for use in tests
     """
 
-    basic_outlier_dataframe.to_csv(csv_path := tmp_path / "example.csv")
+    basic_outlier_dataframe.to_csv(csv_path := tmp_path / "example.csv", index=False)
 
     return csv_path
 
@@ -49,7 +49,7 @@ def fixture_basic_outlier_tsv(
     Creates basic example data tsv for use in tests
     """
 
-    basic_outlier_dataframe.to_csv(tsv_path := tmp_path / "example.tsv", sep="\t")
+    basic_outlier_dataframe.to_csv(tsv_path := tmp_path / "example.tsv", sep="\t", index=False)
 
     return tsv_path
 
@@ -62,6 +62,6 @@ def fixture_basic_outlier_parquet(
     Creates basic example data parquet for use in tests
     """
 
-    basic_outlier_dataframe.to_parquet(parquet_path := tmp_path / "example.parquet")
+    basic_outlier_dataframe.to_parquet(parquet_path := tmp_path / "example.parquet", index=False)
 
     return parquet_path
diff --git a/tests/test_analyze.py b/tests/test_analyze.py
index a55cf6b..26ea6db 100644
--- a/tests/test_analyze.py
+++ b/tests/test_analyze.py
@@ -337,6 +337,21 @@ def test_label_outliers(
     Tests label_outliers
     """
 
+    pd.testing.assert_frame_equal(
+        analyze.label_outliers(
+            df=basic_outlier_dataframe,
+            feature_thresholds={"example_feature": 1},
+            include_threshold_scores=True,
+        ),
+        analyze.label_outliers(
+            df=basic_outlier_csv,
+            feature_thresholds={"example_feature": 1},
+            include_threshold_scores=True,
+        ),
+    )
+
+    
+
     # test basic single-column result with zscores
     assert analyze.label_outliers(
         df=basic_outlier_dataframe,

From 1069a4af958de2ff12041d4282ca55c457ce7143 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Mon, 10 Jun 2024 16:14:38 -0600
Subject: [PATCH 06/40] linting

---
 tests/conftest.py     | 8 ++++++--
 tests/test_analyze.py | 2 --
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index ad0c17e..e3fb24c 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -49,7 +49,9 @@ def fixture_basic_outlier_tsv(
     Creates basic example data tsv for use in tests
     """
 
-    basic_outlier_dataframe.to_csv(tsv_path := tmp_path / "example.tsv", sep="\t", index=False)
+    basic_outlier_dataframe.to_csv(
+        tsv_path := tmp_path / "example.tsv", sep="\t", index=False
+    )
 
     return tsv_path
 
@@ -62,6 +64,8 @@ def fixture_basic_outlier_parquet(
     Creates basic example data parquet for use in tests
     """
 
-    basic_outlier_dataframe.to_parquet(parquet_path := tmp_path / "example.parquet", index=False)
+    basic_outlier_dataframe.to_parquet(
+        parquet_path := tmp_path / "example.parquet", index=False
+    )
 
     return parquet_path
diff --git a/tests/test_analyze.py b/tests/test_analyze.py
index 26ea6db..21244b9 100644
--- a/tests/test_analyze.py
+++ b/tests/test_analyze.py
@@ -350,8 +350,6 @@ def test_label_outliers(
         ),
     )
 
-    
-
     # test basic single-column result with zscores
     assert analyze.label_outliers(
         df=basic_outlier_dataframe,

From d52a89f639fe9395f0a3384677333996a39b8233 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 08:48:27 -0600
Subject: [PATCH 07/40] update name, tests

---
 src/cosmicqc/__init__.py                      |  4 +-
 src/cosmicqc/analyze.py                       | 32 +++++++-------
 .../{qcdataframe.py => scdataframe.py}        | 33 ++++++++------
 tests/test_analyze.py                         | 16 +++++++
 tests/test_qcdataframe.py                     | 44 +++++++++----------
 5 files changed, 76 insertions(+), 53 deletions(-)
 rename src/cosmicqc/{qcdataframe.py => scdataframe.py} (77%)

diff --git a/src/cosmicqc/__init__.py b/src/cosmicqc/__init__.py
index 82f4e10..05b2bbe 100644
--- a/src/cosmicqc/__init__.py
+++ b/src/cosmicqc/__init__.py
@@ -3,8 +3,8 @@
 """
 
 from .analyze import find_outliers
-from .qcdataframe import QCDataFrame
+from .scdataframe import SCDataFrame
 
 # note: version placeholder is updated during build
 # by poetry-dynamic-versioning.
-__version__ = "0.0.1"
+__version__ = "0.0.0"
diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index 70833a6..d616f78 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -11,7 +11,7 @@
 import yaml
 from scipy.stats import zscore as scipy_zscore
 
-from .qcdataframe import QCDataFrame
+from .scdataframe import SCDataFrame
 
 DEFAULT_QC_THRESHOLD_FILE = (
     f"{pathlib.Path(__file__).parent!s}/data/qc_nuclei_thresholds_default.yml"
@@ -19,7 +19,7 @@
 
 
 def identify_outliers(
-    df: Union[QCDataFrame, pd.DataFrame, str],
+    df: Union[SCDataFrame, pd.DataFrame, str],
     feature_thresholds: Union[Dict[str, float], str],
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
     include_threshold_scores: bool = False,
@@ -32,7 +32,7 @@ def identify_outliers(
     threshold of 0 as that would represent the whole dataset.
 
     Args:
-        df: Union[QCDataFrame, pd.DataFrame, str]
+        df: Union[SCDataFrame, pd.DataFrame, str]
             DataFrame or file with converted output from CytoTable.
         metadata_columns: List[str]
             List of metadata columns that should be outputted with the outlier data.
@@ -54,9 +54,9 @@ def identify_outliers(
             or not for use within other functions.
     """
 
-    # interpret the df as QCDataFrame
-    if not isinstance(df, QCDataFrame):
-        df = QCDataFrame(data=df)
+    # interpret the df as SCDataFrame
+    if not isinstance(df, SCDataFrame):
+        df = SCDataFrame(data=df)
 
     # create a copy of the dataframe to ensure
     # we don't modify the supplied dataframe inplace.
@@ -113,7 +113,7 @@ def identify_outliers(
 
 
 def find_outliers(
-    df: Union[QCDataFrame, pd.DataFrame, str],
+    df: Union[SCDataFrame, pd.DataFrame, str],
     metadata_columns: List[str],
     feature_thresholds: Union[Dict[str, float], str],
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
@@ -123,7 +123,7 @@ def find_outliers(
     with only the outliers and provided metadata columns.
 
     Args:
-        df: Union[QCDataFrame, pd.DataFrame, str]
+        df: Union[SCDataFrame, pd.DataFrame, str]
             DataFrame or file with converted output from CytoTable.
         metadata_columns: List[str]
             List of metadata columns that should be outputted with the outlier data.
@@ -144,9 +144,9 @@ def find_outliers(
             Outlier data frame for the given conditions.
     """
 
-    # interpret the df as QCDataFrame
-    if not isinstance(df, QCDataFrame):
-        df = QCDataFrame(data=df)
+    # interpret the df as SCDataFrame
+    if not isinstance(df, SCDataFrame):
+        df = SCDataFrame(data=df)
 
     if isinstance(feature_thresholds, str):
         feature_thresholds = read_thresholds_set_from_file(
@@ -179,7 +179,7 @@ def find_outliers(
 
 
 def label_outliers(
-    df: Union[QCDataFrame, pd.DataFrame, str],
+    df: Union[SCDataFrame, pd.DataFrame, str],
     feature_thresholds: Optional[Union[Dict[str, float], str]] = None,
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
     include_threshold_scores: bool = False,
@@ -189,7 +189,7 @@ def label_outliers(
     where a cell passed or failed the quality control condition(s).
 
         Args:
-            df: Union[QCDataFrame, pd.DataFrame, str]
+            df: Union[SCDataFrame, pd.DataFrame, str]
                 DataFrame or file with converted output from CytoTable.
             feature_thresholds: Dict[str, float]
                 One of two options:
@@ -211,9 +211,9 @@ def label_outliers(
                 Full dataframe with optional scores and outlier boolean column.
     """
 
-    # interpret the df as QCDataFrame
-    if not isinstance(df, QCDataFrame):
-        df = QCDataFrame(data=df)
+    # interpret the df as SCDataFrame
+    if not isinstance(df, SCDataFrame):
+        df = SCDataFrame(data=df)
 
     # for single outlier processing
     if isinstance(feature_thresholds, (str, dict)):
diff --git a/src/cosmicqc/qcdataframe.py b/src/cosmicqc/scdataframe.py
similarity index 77%
rename from src/cosmicqc/qcdataframe.py
rename to src/cosmicqc/scdataframe.py
index 8498311..da0e1c1 100644
--- a/src/cosmicqc/qcdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -1,5 +1,5 @@
 """
-Defines a QCDataFrame class for use in coSMicQC.
+Defines a SCDataFrame class for use in coSMicQC.
 """
 
 import pathlib
@@ -8,7 +8,7 @@
 import pandas as pd
 
 
-class QCDataFrame:
+class SCDataFrame:
     """
     A class to handle and load different types of data files into a pandas DataFrame.
 
@@ -17,8 +17,8 @@ class QCDataFrame:
     pandas DataFrame.
 
     Attributes:
-        reference (str):
-            A string indicating the type of data source, either 'pd.DataFrame'
+        data_source (str):
+            A string indicating the data source, either 'pd.DataFrame'
             or the file path.
         data (pd.DataFrame):
             The loaded data in a pandas DataFrame.
@@ -26,13 +26,19 @@ class QCDataFrame:
     Methods:
         __call__():
             Returns the underlying pandas DataFrame.
+        __repr__():
+            Returns representation of underlying pandas DataFrame.
+        __getattr__():
+            Returns underlying attributes of pandas DataFrame.
+        __getitem__():
+            Returns slice of data from pandas DataFrame.
     """
 
     def __init__(
         self: Self, data: Union[pd.DataFrame, str], **kwargs: Dict[str, Any]
     ) -> None:
         """
-        Initializes the QCDataFrame with either a DataFrame or a file path.
+        Initializes the SCDataFrame with either a DataFrame or a file path.
 
         Args:
             data (Union[pd.DataFrame, str]):
@@ -42,14 +48,14 @@ def __init__(
         """
 
         if isinstance(data, pd.DataFrame):
-            # if data is a pd.DataFrame, remember this within the reference attr
-            self.reference = "pd.DataFrame"
+            # if data is a pd.DataFrame, remember this within the data_source attr
+            self.data_source = "pd.DataFrame"
             self.data = data
 
         elif isinstance(data, pathlib.Path | str):
             # if the data is a string, remember the original source
-            # through a reference attr
-            self.reference = data
+            # through a data_source attr
+            self.data_source = data
 
             # interpret the data through pathlib
             data_path = pathlib.Path(data)
@@ -64,9 +70,10 @@ def __init__(
             elif data_path.suffix == ".parquet":
                 # read as a Parquet file
                 self.data = pd.read_parquet(data, **kwargs)
-
+            else:
+                raise ValueError("Unsupported file format for SCDataFrame.")
         else:
-            raise ValueError("Unsupported file format for QCDataFrame.")
+            raise ValueError("Unsupported input type for SCDataFrame.")
 
     def __call__(self: Self) -> pd.DataFrame:
         """
@@ -79,12 +86,12 @@ def __call__(self: Self) -> pd.DataFrame:
 
     def __repr__(self: Self) -> pd.DataFrame:
         """
-        Returns the underlying pandas DataFrame.
+        Returns the representation of underlying pandas DataFrame.
 
         Returns:
             pd.DataFrame: The data in a pandas DataFrame.
         """
-        return self.data
+        return repr(self.data)
 
     def __getattr__(self: Self, attr: str) -> Any:  # noqa: ANN401
         """
diff --git a/tests/test_analyze.py b/tests/test_analyze.py
index 21244b9..6ade9a2 100644
--- a/tests/test_analyze.py
+++ b/tests/test_analyze.py
@@ -337,6 +337,7 @@ def test_label_outliers(
     Tests label_outliers
     """
 
+    # compare the dataframe vs csv output to make sure they are equivalent
     pd.testing.assert_frame_equal(
         analyze.label_outliers(
             df=basic_outlier_dataframe,
@@ -451,12 +452,27 @@ def test_label_outliers(
 
 def test_identify_outliers(
     basic_outlier_dataframe: pd.DataFrame,
+    basic_outlier_csv: str,
     cytotable_CFReT_data_df: pd.DataFrame,
 ):
     """
     Tests identify_outliers
     """
 
+    # show that dataframe and csv output are the same
+    pd.testing.assert_frame_equal(
+        analyze.identify_outliers(
+            df=basic_outlier_dataframe,
+            feature_thresholds={"example_feature": 1},
+            include_threshold_scores=True,
+        ),
+        analyze.identify_outliers(
+            df=basic_outlier_csv,
+            feature_thresholds={"example_feature": 1},
+            include_threshold_scores=True,
+        ),
+    )
+
     assert analyze.identify_outliers(
         df=basic_outlier_dataframe,
         feature_thresholds={"example_feature": 1},
diff --git a/tests/test_qcdataframe.py b/tests/test_qcdataframe.py
index 1b1fad4..d2ec019 100644
--- a/tests/test_qcdataframe.py
+++ b/tests/test_qcdataframe.py
@@ -1,45 +1,45 @@
 """
-Tests cosmicqc qcdataframe module
+Tests cosmicqc SCDataFrame module
 """
 
 import pandas as pd
-from cosmicqc.qcdataframe import QCDataFrame
+from cosmicqc.scdataframe import SCDataFrame
 
 
-def test_qcdataframe_init_with_dataframe(basic_outlier_dataframe: pd.DataFrame):
+def test_SCDataFrame_init_with_dataframe(basic_outlier_dataframe: pd.DataFrame):
     """
-    Tests QCDataFrame with pd.DataFrame input.
+    Tests SCDataFrame with pd.DataFrame input.
     """
-    qc_df = QCDataFrame(data=basic_outlier_dataframe)
-    assert qc_df.reference == "pd.DataFrame"
-    assert qc_df.equals(basic_outlier_dataframe)
+    sc_df = SCDataFrame(data=basic_outlier_dataframe)
+    assert sc_df.data_source == "pd.DataFrame"
+    assert sc_df.equals(basic_outlier_dataframe)
 
 
-def test_qcdataframe_init_with_csv(basic_outlier_csv: str):
+def test_SCDataFrame_init_with_csv(basic_outlier_csv: str):
     """
-    Tests QCDataFrame with CSV input.
+    Tests SCDataFrame with CSV input.
     """
-    qc_df = QCDataFrame(data=basic_outlier_csv)
+    sc_df = SCDataFrame(data=basic_outlier_csv)
     expected_df = pd.read_csv(basic_outlier_csv)
-    assert qc_df.reference == basic_outlier_csv
-    assert qc_df.equals(expected_df)
+    assert sc_df.data_source == basic_outlier_csv
+    assert sc_df.equals(expected_df)
 
 
-def test_qcdataframe_init_with_tsv(basic_outlier_tsv: str):
+def test_SCDataFrame_init_with_tsv(basic_outlier_tsv: str):
     """
-    Tests QCDataFrame with TSV input.
+    Tests SCDataFrame with TSV input.
     """
-    qc_df = QCDataFrame(data=basic_outlier_tsv)
+    sc_df = SCDataFrame(data=basic_outlier_tsv)
     expected_df = pd.read_csv(basic_outlier_tsv, delimiter="\t")
-    assert qc_df.reference == basic_outlier_tsv
-    assert qc_df.equals(expected_df)
+    assert sc_df.data_source == basic_outlier_tsv
+    assert sc_df.equals(expected_df)
 
 
-def test_qcdataframe_init_with_parquet(basic_outlier_parquet: str):
+def test_SCDataFrame_init_with_parquet(basic_outlier_parquet: str):
     """
-    Tests QCDataFrame with TSV input.
+    Tests SCDataFrame with TSV input.
     """
-    qc_df = QCDataFrame(data=basic_outlier_parquet)
+    sc_df = SCDataFrame(data=basic_outlier_parquet)
     expected_df = pd.read_parquet(basic_outlier_parquet)
-    assert qc_df.reference == basic_outlier_parquet
-    assert qc_df.equals(expected_df)
+    assert sc_df.data_source == basic_outlier_parquet
+    assert sc_df.equals(expected_df)

From 1bf8262dcdf160592ffef24cdb0c62b9c0c277a4 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 08:58:09 -0600
Subject: [PATCH 08/40] add back compat for self type

---
 src/cosmicqc/scdataframe.py | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index da0e1c1..37e52a7 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -3,10 +3,14 @@
 """
 
 import pathlib
-from typing import Any, Dict, Self, Union
+from typing import Any, Dict, TypeVar, Union
 
 import pandas as pd
 
+# provide backwards compatibility for Self type in earlier Python versions.
+# see: https://peps.python.org/pep-0484/#annotating-instance-and-class-methods
+Self_SCDataFrame = TypeVar("Self_SCDataFrame", bound="SCDataFrame")
+
 
 class SCDataFrame:
     """
@@ -35,7 +39,7 @@ class SCDataFrame:
     """
 
     def __init__(
-        self: Self, data: Union[pd.DataFrame, str], **kwargs: Dict[str, Any]
+        self: Self_SCDataFrame, data: Union[pd.DataFrame, str], **kwargs: Dict[str, Any]
     ) -> None:
         """
         Initializes the SCDataFrame with either a DataFrame or a file path.
@@ -75,7 +79,7 @@ def __init__(
         else:
             raise ValueError("Unsupported input type for SCDataFrame.")
 
-    def __call__(self: Self) -> pd.DataFrame:
+    def __call__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
         Returns the underlying pandas DataFrame.
 
@@ -84,7 +88,7 @@ def __call__(self: Self) -> pd.DataFrame:
         """
         return self.data
 
-    def __repr__(self: Self) -> pd.DataFrame:
+    def __repr__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
         Returns the representation of underlying pandas DataFrame.
 
@@ -93,7 +97,7 @@ def __repr__(self: Self) -> pd.DataFrame:
         """
         return repr(self.data)
 
-    def __getattr__(self: Self, attr: str) -> Any:  # noqa: ANN401
+    def __getattr__(self: Self_SCDataFrame, attr: str) -> Any:  # noqa: ANN401
         """
         Intercept attribute accesses and delegate them to the underlying
         pandas DataFrame.
@@ -106,7 +110,7 @@ def __getattr__(self: Self, attr: str) -> Any:  # noqa: ANN401
         """
         return getattr(self.data, attr)
 
-    def __getitem__(self: Self, key: Union[int, str]) -> Any:  # noqa: ANN401
+    def __getitem__(self: Self_SCDataFrame, key: Union[int, str]) -> Any:  # noqa: ANN401
         """
         Returns an element or a slice of the underlying pandas DataFrame.
 

From 772f89560e7fac449cd4bf6396779ef5182b46d9 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 09:07:13 -0600
Subject: [PATCH 09/40] back compat for isinstance

---
 src/cosmicqc/scdataframe.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 37e52a7..3fc349c 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -56,7 +56,7 @@ def __init__(
             self.data_source = "pd.DataFrame"
             self.data = data
 
-        elif isinstance(data, pathlib.Path | str):
+        elif isinstance(data, pathlib.Path) or isinstance(data, str): # noqa: PLR1701, SIM101
             # if the data is a string, remember the original source
             # through a data_source attr
             self.data_source = data

From d0ea33c83e114a1454ed7448e957da97b0b18e8d Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 09:08:18 -0600
Subject: [PATCH 10/40] linting

---
 src/cosmicqc/scdataframe.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 3fc349c..f94bdd2 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -56,7 +56,7 @@ def __init__(
             self.data_source = "pd.DataFrame"
             self.data = data
 
-        elif isinstance(data, pathlib.Path) or isinstance(data, str): # noqa: PLR1701, SIM101
+        elif isinstance(data, pathlib.Path) or isinstance(data, str):  # noqa: PLR1701, SIM101
             # if the data is a string, remember the original source
             # through a data_source attr
             self.data_source = data

From fe3fcf07dbedb13e33617d4add73e22753251443 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 15:13:02 -0600
Subject: [PATCH 11/40] add cli for cosmicqc

---
 poetry.lock         | 104 ++++++++++++++++++++++++++++----------------
 pyproject.toml      |   4 ++
 src/cosmicqc/cli.py |  25 +++++++++++
 3 files changed, 95 insertions(+), 38 deletions(-)
 create mode 100644 src/cosmicqc/cli.py

diff --git a/poetry.lock b/poetry.lock
index a932b27..a8a823e 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -25,6 +25,20 @@ files = [
 [package.extras]
 test = ["pytest (>=6)"]
 
+[[package]]
+name = "fire"
+version = "0.6.0"
+description = "A library for automatically generating command line interfaces."
+optional = false
+python-versions = "*"
+files = [
+    {file = "fire-0.6.0.tar.gz", hash = "sha256:54ec5b996ecdd3c0309c800324a0703d6da512241bc73b553db959d98de0aa66"},
+]
+
+[package.dependencies]
+six = "*"
+termcolor = "*"
+
 [[package]]
 name = "iniconfig"
 version = "2.0.0"
@@ -75,47 +89,47 @@ files = [
 
 [[package]]
 name = "numpy"
-version = "1.26.3"
+version = "1.26.4"
 description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "numpy-1.26.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:806dd64230dbbfaca8a27faa64e2f414bf1c6622ab78cc4264f7f5f028fee3bf"},
-    {file = "numpy-1.26.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:02f98011ba4ab17f46f80f7f8f1c291ee7d855fcef0a5a98db80767a468c85cd"},
-    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6d45b3ec2faed4baca41c76617fcdcfa4f684ff7a151ce6fc78ad3b6e85af0a6"},
-    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bdd2b45bf079d9ad90377048e2747a0c82351989a2165821f0c96831b4a2a54b"},
-    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:211ddd1e94817ed2d175b60b6374120244a4dd2287f4ece45d49228b4d529178"},
-    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b1240f767f69d7c4c8a29adde2310b871153df9b26b5cb2b54a561ac85146485"},
-    {file = "numpy-1.26.3-cp310-cp310-win32.whl", hash = "sha256:21a9484e75ad018974a2fdaa216524d64ed4212e418e0a551a2d83403b0531d3"},
-    {file = "numpy-1.26.3-cp310-cp310-win_amd64.whl", hash = "sha256:9e1591f6ae98bcfac2a4bbf9221c0b92ab49762228f38287f6eeb5f3f55905ce"},
-    {file = "numpy-1.26.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b831295e5472954104ecb46cd98c08b98b49c69fdb7040483aff799a755a7374"},
-    {file = "numpy-1.26.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9e87562b91f68dd8b1c39149d0323b42e0082db7ddb8e934ab4c292094d575d6"},
-    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c66d6fec467e8c0f975818c1796d25c53521124b7cfb760114be0abad53a0a2"},
-    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f25e2811a9c932e43943a2615e65fc487a0b6b49218899e62e426e7f0a57eeda"},
-    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:af36e0aa45e25c9f57bf684b1175e59ea05d9a7d3e8e87b7ae1a1da246f2767e"},
-    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:51c7f1b344f302067b02e0f5b5d2daa9ed4a721cf49f070280ac202738ea7f00"},
-    {file = "numpy-1.26.3-cp311-cp311-win32.whl", hash = "sha256:7ca4f24341df071877849eb2034948459ce3a07915c2734f1abb4018d9c49d7b"},
-    {file = "numpy-1.26.3-cp311-cp311-win_amd64.whl", hash = "sha256:39763aee6dfdd4878032361b30b2b12593fb445ddb66bbac802e2113eb8a6ac4"},
-    {file = "numpy-1.26.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a7081fd19a6d573e1a05e600c82a1c421011db7935ed0d5c483e9dd96b99cf13"},
-    {file = "numpy-1.26.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:12c70ac274b32bc00c7f61b515126c9205323703abb99cd41836e8125ea0043e"},
-    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f784e13e598e9594750b2ef6729bcd5a47f6cfe4a12cca13def35e06d8163e3"},
-    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f24750ef94d56ce6e33e4019a8a4d68cfdb1ef661a52cdaee628a56d2437419"},
-    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:77810ef29e0fb1d289d225cabb9ee6cf4d11978a00bb99f7f8ec2132a84e0166"},
-    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8ed07a90f5450d99dad60d3799f9c03c6566709bd53b497eb9ccad9a55867f36"},
-    {file = "numpy-1.26.3-cp312-cp312-win32.whl", hash = "sha256:f73497e8c38295aaa4741bdfa4fda1a5aedda5473074369eca10626835445511"},
-    {file = "numpy-1.26.3-cp312-cp312-win_amd64.whl", hash = "sha256:da4b0c6c699a0ad73c810736303f7fbae483bcb012e38d7eb06a5e3b432c981b"},
-    {file = "numpy-1.26.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1666f634cb3c80ccbd77ec97bc17337718f56d6658acf5d3b906ca03e90ce87f"},
-    {file = "numpy-1.26.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:18c3319a7d39b2c6a9e3bb75aab2304ab79a811ac0168a671a62e6346c29b03f"},
-    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b7e807d6888da0db6e7e75838444d62495e2b588b99e90dd80c3459594e857b"},
-    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4d362e17bcb0011738c2d83e0a65ea8ce627057b2fdda37678f4374a382a137"},
-    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b8c275f0ae90069496068c714387b4a0eba5d531aace269559ff2b43655edd58"},
-    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:cc0743f0302b94f397a4a65a660d4cd24267439eb16493fb3caad2e4389bccbb"},
-    {file = "numpy-1.26.3-cp39-cp39-win32.whl", hash = "sha256:9bc6d1a7f8cedd519c4b7b1156d98e051b726bf160715b769106661d567b3f03"},
-    {file = "numpy-1.26.3-cp39-cp39-win_amd64.whl", hash = "sha256:867e3644e208c8922a3be26fc6bbf112a035f50f0a86497f98f228c50c607bb2"},
-    {file = "numpy-1.26.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3c67423b3703f8fbd90f5adaa37f85b5794d3366948efe9a5190a5f3a83fc34e"},
-    {file = "numpy-1.26.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:46f47ee566d98849323f01b349d58f2557f02167ee301e5e28809a8c0e27a2d0"},
-    {file = "numpy-1.26.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a8474703bffc65ca15853d5fd4d06b18138ae90c17c8d12169968e998e448bb5"},
-    {file = "numpy-1.26.3.tar.gz", hash = "sha256:697df43e2b6310ecc9d95f05d5ef20eacc09c7c4ecc9da3f235d39e71b7da1e4"},
+    {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
+    {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
+    {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4"},
+    {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f"},
+    {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a"},
+    {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2"},
+    {file = "numpy-1.26.4-cp310-cp310-win32.whl", hash = "sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07"},
+    {file = "numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5"},
+    {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"},
+    {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"},
+    {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"},
+    {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"},
+    {file = "numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218"},
+    {file = "numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b"},
+    {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b"},
+    {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed"},
+    {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a"},
+    {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0"},
+    {file = "numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110"},
+    {file = "numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818"},
+    {file = "numpy-1.26.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c"},
+    {file = "numpy-1.26.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be"},
+    {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764"},
+    {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3"},
+    {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd"},
+    {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c"},
+    {file = "numpy-1.26.4-cp39-cp39-win32.whl", hash = "sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6"},
+    {file = "numpy-1.26.4-cp39-cp39-win_amd64.whl", hash = "sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"},
+    {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
 ]
 
 [[package]]
@@ -526,6 +540,20 @@ files = [
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
 
+[[package]]
+name = "termcolor"
+version = "2.4.0"
+description = "ANSI color formatting for output in terminal"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "termcolor-2.4.0-py3-none-any.whl", hash = "sha256:9297c0df9c99445c2412e832e882a7884038a25617c60cea2ad69488d4040d63"},
+    {file = "termcolor-2.4.0.tar.gz", hash = "sha256:aab9e56047c8ac41ed798fa36d892a37aca6b3e9159f3e0c24bc64a9b3ac7b7a"},
+]
+
+[package.extras]
+tests = ["pytest", "pytest-cov"]
+
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -551,4 +579,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8,<3.13"
-content-hash = "a001251df36357dba7b70e5c246a76022a313fb9e120ddc5e95f4cc1efa778b7"
+content-hash = "d905f4221fc9dac67766e214aa716fafe85597c04a86494d3bdbbefb70f04fbf"
diff --git a/pyproject.toml b/pyproject.toml
index f3231ed..d7ec4c6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,10 +19,14 @@ scipy = [
 ]
 pyarrow = "^16.0.0"
 pyyaml = "^6.0.1"
+fire = "^0.6.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.2.0"
 
+[tool.poetry.scripts]
+cosmicqc = "cosmicqc.cli:cli_analyze"
+
 [tool.isort]
 profile = "black"
 
diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
new file mode 100644
index 0000000..869ad4c
--- /dev/null
+++ b/src/cosmicqc/cli.py
@@ -0,0 +1,25 @@
+"""
+Setup coSMicQC CLI through python-fire
+"""
+
+import fire
+from . import analyze
+
+def cli_analyze():
+    """
+    Run the analyze module functions through python-fire CLI
+
+    This function serves as the CLI entry point for functions
+    within the analyze module.
+    """
+    fire.Fire(analyze)
+
+if __name__ == "__main__":
+    """
+    Setup the CLI with python-fire for the coSMicQC package.
+
+    This enables running the functions identify_outliers, find_outliers,
+    and label_outliers from the command line interface through analyze
+    """
+
+    fire.Fire(analyze)

From 30aae3eaff45ad19cf7e57ab7085b18cf6178603 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 15:13:35 -0600
Subject: [PATCH 12/40] linting

---
 src/cosmicqc/cli.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index 869ad4c..454bf55 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -3,9 +3,11 @@
 """
 
 import fire
+
 from . import analyze
 
-def cli_analyze():
+
+def cli_analyze() -> None:
     """
     Run the analyze module functions through python-fire CLI
 
@@ -14,6 +16,7 @@ def cli_analyze():
     """
     fire.Fire(analyze)
 
+
 if __name__ == "__main__":
     """
     Setup the CLI with python-fire for the coSMicQC package.

From 2bd3d5f79e37e7384ca09e2db82d745257eb7d20 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 16:43:53 -0600
Subject: [PATCH 13/40] add tests and wrappers

---
 example.csv              |  11 +++
 poetry.lock              | 162 ++++++++++++++++++++++++++++++---------
 pyproject.toml           |   1 +
 src/cosmicqc/__init__.py |   2 +-
 src/cosmicqc/analyze.py  |  19 +++--
 src/cosmicqc/utils.py    |  25 ++++++
 tests/__init__.py        |   0
 tests/test_cli.py        |  54 +++++++++++++
 tests/utils.py           |  20 +++++
 9 files changed, 248 insertions(+), 46 deletions(-)
 create mode 100644 example.csv
 create mode 100644 src/cosmicqc/utils.py
 create mode 100644 tests/__init__.py
 create mode 100644 tests/test_cli.py
 create mode 100644 tests/utils.py

diff --git a/example.csv b/example.csv
new file mode 100644
index 0000000..08055b3
--- /dev/null
+++ b/example.csv
@@ -0,0 +1,11 @@
+,example_feature
+0,1
+1,2
+2,3
+3,4
+4,5
+5,6
+6,7
+7,8
+8,9
+9,10
diff --git a/poetry.lock b/poetry.lock
index a8a823e..593a1ee 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -50,6 +50,92 @@ files = [
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
 ]
 
+[[package]]
+name = "jinja2"
+version = "3.1.4"
+description = "A very fast and expressive template engine."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "jinja2-3.1.4-py3-none-any.whl", hash = "sha256:bc5dd2abb727a5319567b7a813e6a2e7318c39f4f487cfe6c89c6f9c7d25197d"},
+    {file = "jinja2-3.1.4.tar.gz", hash = "sha256:4a3aee7acbbe7303aede8e9648d13b8bf88a429282aa6122a993f0ac800cb369"},
+]
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "markupsafe"
+version = "2.1.5"
+description = "Safely add untrusted strings to HTML/XML markup."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "MarkupSafe-2.1.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a17a92de5231666cfbe003f0e4b9b3a7ae3afb1ec2845aadc2bacc93ff85febc"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:72b6be590cc35924b02c78ef34b467da4ba07e4e0f0454a2c5907f473fc50ce5"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e61659ba32cf2cf1481e575d0462554625196a1f2fc06a1c777d3f48e8865d46"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2174c595a0d73a3080ca3257b40096db99799265e1c27cc5a610743acd86d62f"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae2ad8ae6ebee9d2d94b17fb62763125f3f374c25618198f40cbb8b525411900"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:075202fa5b72c86ad32dc7d0b56024ebdbcf2048c0ba09f1cde31bfdd57bcfff"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:598e3276b64aff0e7b3451b72e94fa3c238d452e7ddcd893c3ab324717456bad"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fce659a462a1be54d2ffcacea5e3ba2d74daa74f30f5f143fe0c58636e355fdd"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-win32.whl", hash = "sha256:d9fad5155d72433c921b782e58892377c44bd6252b5af2f67f16b194987338a4"},
+    {file = "MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl", hash = "sha256:bf50cd79a75d181c9181df03572cdce0fbb75cc353bc350712073108cba98de5"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:629ddd2ca402ae6dbedfceeba9c46d5f7b2a61d9749597d4307f943ef198fc1f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5b7b716f97b52c5a14bffdf688f971b2d5ef4029127f1ad7a513973cfd818df2"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ec585f69cec0aa07d945b20805be741395e28ac1627333b1c5b0105962ffced"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b91c037585eba9095565a3556f611e3cbfaa42ca1e865f7b8015fe5c7336d5a5"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7502934a33b54030eaf1194c21c692a534196063db72176b0c4028e140f8f32c"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0e397ac966fdf721b2c528cf028494e86172b4feba51d65f81ffd65c63798f3f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c061bb86a71b42465156a3ee7bd58c8c2ceacdbeb95d05a99893e08b8467359a"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3a57fdd7ce31c7ff06cdfbf31dafa96cc533c21e443d57f5b1ecc6cdc668ec7f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-win32.whl", hash = "sha256:397081c1a0bfb5124355710fe79478cdbeb39626492b15d399526ae53422b906"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-win_amd64.whl", hash = "sha256:2b7c57a4dfc4f16f7142221afe5ba4e093e09e728ca65c51f5620c9aaeb9a617"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:8dec4936e9c3100156f8a2dc89c4b88d5c435175ff03413b443469c7c8c5f4d1"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:3c6b973f22eb18a789b1460b4b91bf04ae3f0c4234a0a6aa6b0a92f6f7b951d4"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ac07bad82163452a6884fe8fa0963fb98c2346ba78d779ec06bd7a6262132aee"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5dfb42c4604dddc8e4305050aa6deb084540643ed5804d7455b5df8fe16f5e5"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ea3d8a3d18833cf4304cd2fc9cbb1efe188ca9b5efef2bdac7adc20594a0e46b"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d050b3361367a06d752db6ead6e7edeb0009be66bc3bae0ee9d97fb326badc2a"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bec0a414d016ac1a18862a519e54b2fd0fc8bbfd6890376898a6c0891dd82e9f"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:58c98fee265677f63a4385256a6d7683ab1832f3ddd1e66fe948d5880c21a169"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-win32.whl", hash = "sha256:8590b4ae07a35970728874632fed7bd57b26b0102df2d2b233b6d9d82f6c62ad"},
+    {file = "MarkupSafe-2.1.5-cp312-cp312-win_amd64.whl", hash = "sha256:823b65d8706e32ad2df51ed89496147a42a2a6e01c13cfb6ffb8b1e92bc910bb"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c8b29db45f8fe46ad280a7294f5c3ec36dbac9491f2d1c17345be8e69cc5928f"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec6a563cff360b50eed26f13adc43e61bc0c04d94b8be985e6fb24b81f6dcfdf"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a549b9c31bec33820e885335b451286e2969a2d9e24879f83fe904a5ce59d70a"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4f11aa001c540f62c6166c7726f71f7573b52c68c31f014c25cc7901deea0b52"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7b2e5a267c855eea6b4283940daa6e88a285f5f2a67f2220203786dfa59b37e9"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:2d2d793e36e230fd32babe143b04cec8a8b3eb8a3122d2aceb4a371e6b09b8df"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ce409136744f6521e39fd8e2a24c53fa18ad67aa5bc7c2cf83645cce5b5c4e50"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-win32.whl", hash = "sha256:4096e9de5c6fdf43fb4f04c26fb114f61ef0bf2e5604b6ee3019d51b69e8c371"},
+    {file = "MarkupSafe-2.1.5-cp37-cp37m-win_amd64.whl", hash = "sha256:4275d846e41ecefa46e2015117a9f491e57a71ddd59bbead77e904dc02b1bed2"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:656f7526c69fac7f600bd1f400991cc282b417d17539a1b228617081106feb4a"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:97cafb1f3cbcd3fd2b6fbfb99ae11cdb14deea0736fc2b0952ee177f2b813a46"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f3fbcb7ef1f16e48246f704ab79d79da8a46891e2da03f8783a5b6fa41a9532"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fa9db3f79de01457b03d4f01b34cf91bc0048eb2c3846ff26f66687c2f6d16ab"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffee1f21e5ef0d712f9033568f8344d5da8cc2869dbd08d87c84656e6a2d2f68"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5dedb4db619ba5a2787a94d877bc8ffc0566f92a01c0ef214865e54ecc9ee5e0"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:30b600cf0a7ac9234b2638fbc0fb6158ba5bdcdf46aeb631ead21248b9affbc4"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8dd717634f5a044f860435c1d8c16a270ddf0ef8588d4887037c5028b859b0c3"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-win32.whl", hash = "sha256:daa4ee5a243f0f20d528d939d06670a298dd39b1ad5f8a72a4275124a7819eff"},
+    {file = "MarkupSafe-2.1.5-cp38-cp38-win_amd64.whl", hash = "sha256:619bc166c4f2de5caa5a633b8b7326fbe98e0ccbfacabd87268a2b15ff73a029"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7a68b554d356a91cce1236aa7682dc01df0edba8d043fd1ce607c49dd3c1edcf"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:db0b55e0f3cc0be60c1f19efdde9a637c32740486004f20d1cff53c3c0ece4d2"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e53af139f8579a6d5f7b76549125f0d94d7e630761a2111bc431fd820e163b8"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:17b950fccb810b3293638215058e432159d2b71005c74371d784862b7e4683f3"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c31f53cdae6ecfa91a77820e8b151dba54ab528ba65dfd235c80b086d68a465"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bff1b4290a66b490a2f4719358c0cdcd9bafb6b8f061e45c7a2460866bf50c2e"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bc1667f8b83f48511b94671e0e441401371dfd0f0a795c7daa4a3cd1dde55bea"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5049256f536511ee3f7e1b3f87d1d1209d327e818e6ae1365e8653d7e3abb6a6"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-win32.whl", hash = "sha256:00e046b6dd71aa03a41079792f8473dc494d564611a8f89bbbd7cb93295ebdcf"},
+    {file = "MarkupSafe-2.1.5-cp39-cp39-win_amd64.whl", hash = "sha256:fa173ec60341d6bb97a89f5ea19c85c5643c1e7dedebc22f5181eb73573142c5"},
+    {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"},
+]
+
 [[package]]
 name = "numpy"
 version = "1.24.4"
@@ -89,47 +175,47 @@ files = [
 
 [[package]]
 name = "numpy"
-version = "1.26.4"
+version = "1.26.3"
 description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
-    {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
-    {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4"},
-    {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f"},
-    {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a"},
-    {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2"},
-    {file = "numpy-1.26.4-cp310-cp310-win32.whl", hash = "sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07"},
-    {file = "numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5"},
-    {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"},
-    {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"},
-    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"},
-    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"},
-    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"},
-    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"},
-    {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"},
-    {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"},
-    {file = "numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218"},
-    {file = "numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b"},
-    {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b"},
-    {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed"},
-    {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a"},
-    {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0"},
-    {file = "numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110"},
-    {file = "numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818"},
-    {file = "numpy-1.26.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c"},
-    {file = "numpy-1.26.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be"},
-    {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764"},
-    {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3"},
-    {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd"},
-    {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c"},
-    {file = "numpy-1.26.4-cp39-cp39-win32.whl", hash = "sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6"},
-    {file = "numpy-1.26.4-cp39-cp39-win_amd64.whl", hash = "sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea"},
-    {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"},
-    {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"},
-    {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"},
-    {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
+    {file = "numpy-1.26.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:806dd64230dbbfaca8a27faa64e2f414bf1c6622ab78cc4264f7f5f028fee3bf"},
+    {file = "numpy-1.26.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:02f98011ba4ab17f46f80f7f8f1c291ee7d855fcef0a5a98db80767a468c85cd"},
+    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6d45b3ec2faed4baca41c76617fcdcfa4f684ff7a151ce6fc78ad3b6e85af0a6"},
+    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bdd2b45bf079d9ad90377048e2747a0c82351989a2165821f0c96831b4a2a54b"},
+    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:211ddd1e94817ed2d175b60b6374120244a4dd2287f4ece45d49228b4d529178"},
+    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b1240f767f69d7c4c8a29adde2310b871153df9b26b5cb2b54a561ac85146485"},
+    {file = "numpy-1.26.3-cp310-cp310-win32.whl", hash = "sha256:21a9484e75ad018974a2fdaa216524d64ed4212e418e0a551a2d83403b0531d3"},
+    {file = "numpy-1.26.3-cp310-cp310-win_amd64.whl", hash = "sha256:9e1591f6ae98bcfac2a4bbf9221c0b92ab49762228f38287f6eeb5f3f55905ce"},
+    {file = "numpy-1.26.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b831295e5472954104ecb46cd98c08b98b49c69fdb7040483aff799a755a7374"},
+    {file = "numpy-1.26.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9e87562b91f68dd8b1c39149d0323b42e0082db7ddb8e934ab4c292094d575d6"},
+    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c66d6fec467e8c0f975818c1796d25c53521124b7cfb760114be0abad53a0a2"},
+    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f25e2811a9c932e43943a2615e65fc487a0b6b49218899e62e426e7f0a57eeda"},
+    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:af36e0aa45e25c9f57bf684b1175e59ea05d9a7d3e8e87b7ae1a1da246f2767e"},
+    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:51c7f1b344f302067b02e0f5b5d2daa9ed4a721cf49f070280ac202738ea7f00"},
+    {file = "numpy-1.26.3-cp311-cp311-win32.whl", hash = "sha256:7ca4f24341df071877849eb2034948459ce3a07915c2734f1abb4018d9c49d7b"},
+    {file = "numpy-1.26.3-cp311-cp311-win_amd64.whl", hash = "sha256:39763aee6dfdd4878032361b30b2b12593fb445ddb66bbac802e2113eb8a6ac4"},
+    {file = "numpy-1.26.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a7081fd19a6d573e1a05e600c82a1c421011db7935ed0d5c483e9dd96b99cf13"},
+    {file = "numpy-1.26.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:12c70ac274b32bc00c7f61b515126c9205323703abb99cd41836e8125ea0043e"},
+    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f784e13e598e9594750b2ef6729bcd5a47f6cfe4a12cca13def35e06d8163e3"},
+    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f24750ef94d56ce6e33e4019a8a4d68cfdb1ef661a52cdaee628a56d2437419"},
+    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:77810ef29e0fb1d289d225cabb9ee6cf4d11978a00bb99f7f8ec2132a84e0166"},
+    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8ed07a90f5450d99dad60d3799f9c03c6566709bd53b497eb9ccad9a55867f36"},
+    {file = "numpy-1.26.3-cp312-cp312-win32.whl", hash = "sha256:f73497e8c38295aaa4741bdfa4fda1a5aedda5473074369eca10626835445511"},
+    {file = "numpy-1.26.3-cp312-cp312-win_amd64.whl", hash = "sha256:da4b0c6c699a0ad73c810736303f7fbae483bcb012e38d7eb06a5e3b432c981b"},
+    {file = "numpy-1.26.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1666f634cb3c80ccbd77ec97bc17337718f56d6658acf5d3b906ca03e90ce87f"},
+    {file = "numpy-1.26.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:18c3319a7d39b2c6a9e3bb75aab2304ab79a811ac0168a671a62e6346c29b03f"},
+    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b7e807d6888da0db6e7e75838444d62495e2b588b99e90dd80c3459594e857b"},
+    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4d362e17bcb0011738c2d83e0a65ea8ce627057b2fdda37678f4374a382a137"},
+    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b8c275f0ae90069496068c714387b4a0eba5d531aace269559ff2b43655edd58"},
+    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:cc0743f0302b94f397a4a65a660d4cd24267439eb16493fb3caad2e4389bccbb"},
+    {file = "numpy-1.26.3-cp39-cp39-win32.whl", hash = "sha256:9bc6d1a7f8cedd519c4b7b1156d98e051b726bf160715b769106661d567b3f03"},
+    {file = "numpy-1.26.3-cp39-cp39-win_amd64.whl", hash = "sha256:867e3644e208c8922a3be26fc6bbf112a035f50f0a86497f98f228c50c607bb2"},
+    {file = "numpy-1.26.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3c67423b3703f8fbd90f5adaa37f85b5794d3366948efe9a5190a5f3a83fc34e"},
+    {file = "numpy-1.26.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:46f47ee566d98849323f01b349d58f2557f02167ee301e5e28809a8c0e27a2d0"},
+    {file = "numpy-1.26.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a8474703bffc65ca15853d5fd4d06b18138ae90c17c8d12169968e998e448bb5"},
+    {file = "numpy-1.26.3.tar.gz", hash = "sha256:697df43e2b6310ecc9d95f05d5ef20eacc09c7c4ecc9da3f235d39e71b7da1e4"},
 ]
 
 [[package]]
@@ -579,4 +665,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8,<3.13"
-content-hash = "d905f4221fc9dac67766e214aa716fafe85597c04a86494d3bdbbefb70f04fbf"
+content-hash = "097ed443c49a9a397d357d315b58cd467ca0e90047f8c624b77a3d4569c14ef2"
diff --git a/pyproject.toml b/pyproject.toml
index d7ec4c6..1d1e05c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -20,6 +20,7 @@ scipy = [
 pyarrow = "^16.0.0"
 pyyaml = "^6.0.1"
 fire = "^0.6.0"
+jinja2 = "^3.1.4"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.2.0"
diff --git a/src/cosmicqc/__init__.py b/src/cosmicqc/__init__.py
index 05b2bbe..447c688 100644
--- a/src/cosmicqc/__init__.py
+++ b/src/cosmicqc/__init__.py
@@ -7,4 +7,4 @@
 
 # note: version placeholder is updated during build
 # by poetry-dynamic-versioning.
-__version__ = "0.0.0"
+__version__ = "0.0.5.post12.dev0+30aae3e"
diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index d616f78..4baecee 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -6,18 +6,18 @@
 import pathlib
 from functools import reduce
 from typing import Dict, List, Optional, Union
-
+import sys
 import pandas as pd
 import yaml
 from scipy.stats import zscore as scipy_zscore
 
 from .scdataframe import SCDataFrame
+from .utils import print_if_cli
 
 DEFAULT_QC_THRESHOLD_FILE = (
     f"{pathlib.Path(__file__).parent!s}/data/qc_nuclei_thresholds_default.yml"
 )
 
-
 def identify_outliers(
     df: Union[SCDataFrame, pd.DataFrame, str],
     feature_thresholds: Union[Dict[str, float], str],
@@ -34,8 +34,6 @@ def identify_outliers(
     Args:
         df: Union[SCDataFrame, pd.DataFrame, str]
             DataFrame or file with converted output from CytoTable.
-        metadata_columns: List[str]
-            List of metadata columns that should be outputted with the outlier data.
         feature_thresholds: Dict[str, float]
             One of two options:
             A dictionary with the feature name(s) as the key(s) and their assigned
@@ -47,6 +45,9 @@ def identify_outliers(
         feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
             An optional feature thresholds file where thresholds may be
             defined within a file.
+        include_threshold_scores: bool
+            Whether to include the threshold scores in addition to whether
+            the threshold set passes per row.
 
     Returns:
         Union[pd.Series, pd.DataFrame]:
@@ -54,6 +55,10 @@ def identify_outliers(
             or not for use within other functions.
     """
 
+    print("THRESHOOLD FILE:",)
+    print(df, feature_thresholds, feature_thresholds_file, include_threshold_scores)
+
+
     # interpret the df as SCDataFrame
     if not isinstance(df, SCDataFrame):
         df = SCDataFrame(data=df)
@@ -95,7 +100,7 @@ def identify_outliers(
             condition = outlier_df[zscore_columns[feature]] < threshold
         conditions.append(condition)
 
-    return (
+    return print_if_cli(
         # create a boolean pd.series identifier for dataframe
         # based on all conditions for use within other functions.
         reduce(operator.and_, conditions)
@@ -175,7 +180,7 @@ def find_outliers(
     columns_to_include = list(feature_thresholds.keys()) + metadata_columns
 
     # Return outliers DataFrame with specified columns
-    return outliers_df[columns_to_include]
+    return print_if_cli(outliers_df[columns_to_include])
 
 
 def label_outliers(
@@ -265,7 +270,7 @@ def label_outliers(
             axis=1,
         )
         # return a dataframe with a deduplicated columns by name
-        return labeled_df.loc[:, ~labeled_df.columns.duplicated()]
+        return print_if_cli(labeled_df.loc[:, ~labeled_df.columns.duplicated()])
 
 
 def read_thresholds_set_from_file(
diff --git a/src/cosmicqc/utils.py b/src/cosmicqc/utils.py
new file mode 100644
index 0000000..15eb35d
--- /dev/null
+++ b/src/cosmicqc/utils.py
@@ -0,0 +1,25 @@
+"""
+Utility functions for coSMicQC
+"""
+
+import sys
+from typing import Optional
+from .scdataframe import SCDataFrame
+
+def print_if_cli(data: SCDataFrame) -> Optional[SCDataFrame]:
+    """
+    Prints the data if the script is invoked from the cosmicqc command-line interface.
+
+    Args:
+        data (SCDataFrame):
+            The data to print or return.
+
+    Returns:
+        Optional[SCDataFrame]:
+            Returns the SCDataFrame if not run through CLI
+            otherwise prints the SCDataFrame and returns None.
+    """
+    if any("bin/cosmicqc" in path for path in sys.argv):
+        print(data)
+    return False
+
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/test_cli.py b/tests/test_cli.py
new file mode 100644
index 0000000..e33e791
--- /dev/null
+++ b/tests/test_cli.py
@@ -0,0 +1,54 @@
+import subprocess
+import pytest
+import json
+import os
+import pathlib
+from .utils import run_cli_command
+
+
+
+def test_cli_util():
+    """
+    Test the `identify_outliers` function of the CLI.
+    """
+
+    command = f"""echo 'hello world'"""
+    stdout, stderr, returncode = run_cli_command(command)
+
+    assert returncode == 0
+
+def test_cli_identify_outliers(basic_outlier_csv):
+    """
+    Test the `identify_outliers` function of the CLI.
+    """
+
+    command = f"""cosmicqc identify_outliers --df {basic_outlier_csv} --feature_thresholds {"col1":1.0}"""
+    stdout, stderr, returncode = run_cli_command(command)
+
+    print(stderr)
+    print(stdout)
+
+    assert returncode == 0
+    assert "outlier_custom" in stdout or "outlier_custom" in stderr
+
+def test_cli_find_outliers(basic_outlier_csv):
+    """
+    Test the `find_outliers` function of the CLI.
+    """
+
+    command = f"""cosmicqc find_outliers {basic_outlier_csv} --metadata_columns '[\"col1\"]' --feature_thresholds '{"col1": 1.0}'"""
+    stdout, stderr, returncode = run_cli_command(command)
+
+    assert returncode == 0
+    assert "outlier_custom" in stdout or "outlier_custom" in stderr
+
+def test_cli_label_outliers(basic_outlier_csv):
+    """
+    Test the `label_outliers` function of the CLI.
+    """
+
+    command = f"""cosmicqc label_outliers {basic_outlier_csv} --feature_thresholds '{"col1": 1.0}'"""
+    stdout, stderr, returncode = run_cli_command(command)
+
+    assert returncode == 0
+    assert "outlier_custom" in stdout or "outlier_custom" in stderr
diff --git a/tests/utils.py b/tests/utils.py
new file mode 100644
index 0000000..d7cb882
--- /dev/null
+++ b/tests/utils.py
@@ -0,0 +1,20 @@
+"""
+Utilities for running pytest tests in coSMicQC
+"""
+
+import subprocess
+from typing import List
+
+def run_cli_command(command: str):
+    """
+    Run a CLI command using subprocess and capture the output and return code.
+
+    Args:
+        command (list): The command to run as a list of strings.
+
+    Returns:
+        tuple: (stdout, stderr, returncode)
+    """
+
+    result = subprocess.run(command.split(" "), capture_output=True, text=True)
+    return result.stdout, result.stderr, result.returncode

From b5c9997aba5d4cb89034188bf721d67dcaa50602 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 11 Jun 2024 19:55:14 -0600
Subject: [PATCH 14/40] linting and test adjustment

---
 src/cosmicqc/analyze.py |  8 +++++---
 src/cosmicqc/utils.py   |  5 +++--
 tests/test_cli.py       | 41 +++++++++++++++++++++++++----------------
 tests/utils.py          |  6 ++++--
 4 files changed, 37 insertions(+), 23 deletions(-)

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index 4baecee..52e7969 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -6,7 +6,7 @@
 import pathlib
 from functools import reduce
 from typing import Dict, List, Optional, Union
-import sys
+
 import pandas as pd
 import yaml
 from scipy.stats import zscore as scipy_zscore
@@ -18,6 +18,7 @@
     f"{pathlib.Path(__file__).parent!s}/data/qc_nuclei_thresholds_default.yml"
 )
 
+
 def identify_outliers(
     df: Union[SCDataFrame, pd.DataFrame, str],
     feature_thresholds: Union[Dict[str, float], str],
@@ -55,10 +56,11 @@ def identify_outliers(
             or not for use within other functions.
     """
 
-    print("THRESHOOLD FILE:",)
+    print(
+        "THRESHOOLD FILE:",
+    )
     print(df, feature_thresholds, feature_thresholds_file, include_threshold_scores)
 
-
     # interpret the df as SCDataFrame
     if not isinstance(df, SCDataFrame):
         df = SCDataFrame(data=df)
diff --git a/src/cosmicqc/utils.py b/src/cosmicqc/utils.py
index 15eb35d..1ec1183 100644
--- a/src/cosmicqc/utils.py
+++ b/src/cosmicqc/utils.py
@@ -4,8 +4,10 @@
 
 import sys
 from typing import Optional
+
 from .scdataframe import SCDataFrame
 
+
 def print_if_cli(data: SCDataFrame) -> Optional[SCDataFrame]:
     """
     Prints the data if the script is invoked from the cosmicqc command-line interface.
@@ -21,5 +23,4 @@ def print_if_cli(data: SCDataFrame) -> Optional[SCDataFrame]:
     """
     if any("bin/cosmicqc" in path for path in sys.argv):
         print(data)
-    return False
-
+    return data
diff --git a/tests/test_cli.py b/tests/test_cli.py
index e33e791..2952ba5 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -1,29 +1,28 @@
-import subprocess
-import pytest
-import json
-import os
-import pathlib
 from .utils import run_cli_command
 
 
-
 def test_cli_util():
     """
     Test the `identify_outliers` function of the CLI.
     """
 
-    command = f"""echo 'hello world'"""
+    command = """echo 'hello world'"""
     stdout, stderr, returncode = run_cli_command(command)
 
     assert returncode == 0
 
-def test_cli_identify_outliers(basic_outlier_csv):
+
+def test_cli_identify_outliers(basic_outlier_csv: str):
     """
     Test the `identify_outliers` function of the CLI.
     """
 
-    command = f"""cosmicqc identify_outliers --df {basic_outlier_csv} --feature_thresholds {"col1":1.0}"""
-    stdout, stderr, returncode = run_cli_command(command)
+    stdout, stderr, returncode = run_cli_command(
+        (
+            f"""cosmicqc identify_outliers --df {basic_outlier_csv}"""
+            """ --feature_thresholds {"example_feature":1.0}"""
+        )
+    )
 
     print(stderr)
     print(stdout)
@@ -31,24 +30,34 @@ def test_cli_identify_outliers(basic_outlier_csv):
     assert returncode == 0
     assert "outlier_custom" in stdout or "outlier_custom" in stderr
 
-def test_cli_find_outliers(basic_outlier_csv):
+
+def test_cli_find_outliers(basic_outlier_csv: str):
     """
     Test the `find_outliers` function of the CLI.
     """
 
-    command = f"""cosmicqc find_outliers {basic_outlier_csv} --metadata_columns '[\"col1\"]' --feature_thresholds '{"col1": 1.0}'"""
-    stdout, stderr, returncode = run_cli_command(command)
+    stdout, stderr, returncode = run_cli_command(
+        (
+            f"""cosmicqc find_outliers {basic_outlier_csv}"""
+            """ --metadata_columns '[\"col1\"]' --feature_thresholds '{"example_feature": 1.0}'"""
+        )
+    )
 
     assert returncode == 0
     assert "outlier_custom" in stdout or "outlier_custom" in stderr
 
-def test_cli_label_outliers(basic_outlier_csv):
+
+def test_cli_label_outliers(basic_outlier_csv: str):
     """
     Test the `label_outliers` function of the CLI.
     """
 
-    command = f"""cosmicqc label_outliers {basic_outlier_csv} --feature_thresholds '{"col1": 1.0}'"""
-    stdout, stderr, returncode = run_cli_command(command)
+    stdout, stderr, returncode = run_cli_command(
+        (
+            f"""cosmicqc label_outliers {basic_outlier_csv}"""
+            """ --feature_thresholds '{"example_feature": 1.0}'"""
+        )
+    )
 
     assert returncode == 0
     assert "outlier_custom" in stdout or "outlier_custom" in stderr
diff --git a/tests/utils.py b/tests/utils.py
index d7cb882..c3abfc3 100644
--- a/tests/utils.py
+++ b/tests/utils.py
@@ -3,7 +3,7 @@
 """
 
 import subprocess
-from typing import List
+
 
 def run_cli_command(command: str):
     """
@@ -16,5 +16,7 @@ def run_cli_command(command: str):
         tuple: (stdout, stderr, returncode)
     """
 
-    result = subprocess.run(command.split(" "), capture_output=True, text=True)
+    result = subprocess.run(
+        command.split(" "), capture_output=True, text=True, check=False
+    )
     return result.stdout, result.stderr, result.returncode

From bf40aedc90d33eac5eb9353c28f500ef0e463924 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 12 Jun 2024 06:11:33 -0600
Subject: [PATCH 15/40] attempting wrapper

---
 src/cosmicqc/analyze.py |  8 ++++----
 src/cosmicqc/cli.py     | 20 ++++++++++++++++++++
 src/cosmicqc/utils.py   | 15 ++++++++++++++-
 3 files changed, 38 insertions(+), 5 deletions(-)

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index 52e7969..8cfe8a8 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -12,7 +12,7 @@
 from scipy.stats import zscore as scipy_zscore
 
 from .scdataframe import SCDataFrame
-from .utils import print_if_cli
+from .cli import cli_df_to_string
 
 DEFAULT_QC_THRESHOLD_FILE = (
     f"{pathlib.Path(__file__).parent!s}/data/qc_nuclei_thresholds_default.yml"
@@ -102,7 +102,7 @@ def identify_outliers(
             condition = outlier_df[zscore_columns[feature]] < threshold
         conditions.append(condition)
 
-    return print_if_cli(
+    return (
         # create a boolean pd.series identifier for dataframe
         # based on all conditions for use within other functions.
         reduce(operator.and_, conditions)
@@ -182,7 +182,7 @@ def find_outliers(
     columns_to_include = list(feature_thresholds.keys()) + metadata_columns
 
     # Return outliers DataFrame with specified columns
-    return print_if_cli(outliers_df[columns_to_include])
+    return outliers_df[columns_to_include]
 
 
 def label_outliers(
@@ -272,7 +272,7 @@ def label_outliers(
             axis=1,
         )
         # return a dataframe with a deduplicated columns by name
-        return print_if_cli(labeled_df.loc[:, ~labeled_df.columns.duplicated()])
+        return labeled_df.loc[:, ~labeled_df.columns.duplicated()]
 
 
 def read_thresholds_set_from_file(
diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index 454bf55..2da1cd6 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -4,8 +4,23 @@
 
 import fire
 
+from functools import wraps
 from . import analyze
 
+def cli_df_to_string(func: object) -> object:
+    """
+    See https://github.com/google/python-fire/issues/274
+    for why we need this (for now)
+    """
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        import sys
+        print(sys.argv)
+        if any("bin/cosmicqc" in path for path in sys.argv):
+            return str(func(*args, **kwargs))
+        else:
+            return func(*args, **kwargs)
+    return wrapper
 
 def cli_analyze() -> None:
     """
@@ -14,6 +29,11 @@ def cli_analyze() -> None:
     This function serves as the CLI entry point for functions
     within the analyze module.
     """
+
+    for key, value in analyze.__dict__.items( ):
+        if not key.startswith('_') and hasattr(value, '__call__' ):
+            setattr(analyze, key, cli_df_to_string(value))
+
     fire.Fire(analyze)
 
 
diff --git a/src/cosmicqc/utils.py b/src/cosmicqc/utils.py
index 1ec1183..924b3e5 100644
--- a/src/cosmicqc/utils.py
+++ b/src/cosmicqc/utils.py
@@ -5,6 +5,8 @@
 import sys
 from typing import Optional
 
+from functools import wraps
+
 from .scdataframe import SCDataFrame
 
 
@@ -23,4 +25,15 @@ def print_if_cli(data: SCDataFrame) -> Optional[SCDataFrame]:
     """
     if any("bin/cosmicqc" in path for path in sys.argv):
         print(data)
-    return data
+    else:
+        return data
+
+def df_to_string(func):
+    """
+    See https://github.com/google/python-fire/issues/274
+    for why we need this (for now)
+    """
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        return str(func(*args, **kwargs))
+    return wrapper

From feec9a4897b2286b8264731ca452472a43265fe5 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 12 Jun 2024 08:54:32 -0600
Subject: [PATCH 16/40] patch python-fire; fix tests

---
 src/cosmicqc/analyze.py |  6 ---
 src/cosmicqc/cli.py     | 99 +++++++++++++++++++++++++++++++++--------
 src/cosmicqc/utils.py   | 39 ----------------
 tests/test_cli.py       | 52 +++++++++++++++++-----
 4 files changed, 123 insertions(+), 73 deletions(-)
 delete mode 100644 src/cosmicqc/utils.py

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index 8cfe8a8..08649f9 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -12,7 +12,6 @@
 from scipy.stats import zscore as scipy_zscore
 
 from .scdataframe import SCDataFrame
-from .cli import cli_df_to_string
 
 DEFAULT_QC_THRESHOLD_FILE = (
     f"{pathlib.Path(__file__).parent!s}/data/qc_nuclei_thresholds_default.yml"
@@ -56,11 +55,6 @@ def identify_outliers(
             or not for use within other functions.
     """
 
-    print(
-        "THRESHOOLD FILE:",
-    )
-    print(df, feature_thresholds, feature_thresholds_file, include_threshold_scores)
-
     # interpret the df as SCDataFrame
     if not isinstance(df, SCDataFrame):
         df = SCDataFrame(data=df)
diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index 2da1cd6..fb7ebcf 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -2,25 +2,92 @@
 Setup coSMicQC CLI through python-fire
 """
 
+import inspect
+import sys
+import types
+from typing import Optional
+
 import fire
+from fire import helptext, inspectutils, value_types
+from fire.core import Display, FireError, _DictAsString, _OneLineResult
+from fire.trace import FireTrace
 
-from functools import wraps
 from . import analyze
 
-def cli_df_to_string(func: object) -> object:
-    """
-    See https://github.com/google/python-fire/issues/274
-    for why we need this (for now)
+
+# referenced from https://github.com/google/python-fire/pull/446
+# to be removed after python-fire merges changes (uncertain of timeline)
+def HasCustomRepr(component: object) -> bool:
+    """Reproduces above HasCustomStr function to determine if component has a
+    custom __repr__ method.
+
+    ...
+
+    Args:
+      component: The object to check for a custom __repr__ method.
+    Returns:
+      Whether `component` has a custom __repr__ method.
     """
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        import sys
-        print(sys.argv)
-        if any("bin/cosmicqc" in path for path in sys.argv):
-            return str(func(*args, **kwargs))
-        else:
-            return func(*args, **kwargs)
-    return wrapper
+    if hasattr(component, "__repr__"):
+        class_attrs = inspectutils.GetClassAttrsDict(type(component)) or {}
+        repr_attr = class_attrs.get("__repr__")
+        if repr_attr and repr_attr.defining_class is not object:
+            return True
+    return False
+
+
+# referenced with modifications from https://github.com/google/python-fire/pull/446
+# to be removed after python-fire merges changes (uncertain of timeline)
+# ruff: noqa: C901
+def _PrintResult(
+    component_trace: FireTrace, verbose: bool = False, serialize: Optional[bool] = None
+) -> None:
+    """Prints the result of the Fire call to stdout in a human readable way."""
+    # TODO(dbieber): Design human readable deserializable serialization method
+    # and move serialization to its own module.
+    result = component_trace.GetResult()
+    # Allow users to modify the return value of the component and provide
+    # custom formatting.
+    if serialize:
+        if not callable(serialize):
+            raise FireError(
+                "The argument `serialize` must be empty or callable:", serialize
+            )
+        result = serialize(result)
+    if value_types.HasCustomStr(result):
+        # If the object has a custom __str__ method, rather than one inherited from
+        # object, then we use that to serialize the object.
+        print(str(result))
+        return
+
+    elif HasCustomRepr(result):
+        # Same as above, but for __repr__.
+        # For pandas.DataFrame, __str__ is inherited from object, but __repr__ has
+        # a custom implementation (see pandas.core.frame.DataFrame.__repr__)
+        print(str(result))
+        return
+
+    if isinstance(result, (list, set, frozenset, types.GeneratorType)):
+        for i in result:
+            print(_OneLineResult(i))
+    elif inspect.isgeneratorfunction(result):
+        raise NotImplementedError
+    elif isinstance(result, dict) and value_types.IsSimpleGroup(result):
+        print(_DictAsString(result, verbose))
+    elif isinstance(result, tuple):
+        print(_OneLineResult(result))
+    elif isinstance(result, value_types.VALUE_TYPES):
+        if result is not None:
+            print(result)
+    else:
+        help_text = helptext.HelpText(result, trace=component_trace, verbose=verbose)
+        output = [help_text]
+        Display(output, out=sys.stdout)
+
+
+# replace the _PrintResult function with a fix for pandas dataframes
+fire.core._PrintResult = _PrintResult
+
 
 def cli_analyze() -> None:
     """
@@ -30,10 +97,6 @@ def cli_analyze() -> None:
     within the analyze module.
     """
 
-    for key, value in analyze.__dict__.items( ):
-        if not key.startswith('_') and hasattr(value, '__call__' ):
-            setattr(analyze, key, cli_df_to_string(value))
-
     fire.Fire(analyze)
 
 
diff --git a/src/cosmicqc/utils.py b/src/cosmicqc/utils.py
deleted file mode 100644
index 924b3e5..0000000
--- a/src/cosmicqc/utils.py
+++ /dev/null
@@ -1,39 +0,0 @@
-"""
-Utility functions for coSMicQC
-"""
-
-import sys
-from typing import Optional
-
-from functools import wraps
-
-from .scdataframe import SCDataFrame
-
-
-def print_if_cli(data: SCDataFrame) -> Optional[SCDataFrame]:
-    """
-    Prints the data if the script is invoked from the cosmicqc command-line interface.
-
-    Args:
-        data (SCDataFrame):
-            The data to print or return.
-
-    Returns:
-        Optional[SCDataFrame]:
-            Returns the SCDataFrame if not run through CLI
-            otherwise prints the SCDataFrame and returns None.
-    """
-    if any("bin/cosmicqc" in path for path in sys.argv):
-        print(data)
-    else:
-        return data
-
-def df_to_string(func):
-    """
-    See https://github.com/google/python-fire/issues/274
-    for why we need this (for now)
-    """
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        return str(func(*args, **kwargs))
-    return wrapper
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 2952ba5..1513b74 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -24,11 +24,21 @@ def test_cli_identify_outliers(basic_outlier_csv: str):
         )
     )
 
-    print(stderr)
-    print(stdout)
-
     assert returncode == 0
-    assert "outlier_custom" in stdout or "outlier_custom" in stderr
+    assert (
+        stdout.strip()
+        == """0    False
+1    False
+2    False
+3    False
+4    False
+5    False
+6    False
+7    False
+8     True
+9     True
+Name: Z_Score_example_feature, dtype: bool""".strip()
+    )
 
 
 def test_cli_find_outliers(basic_outlier_csv: str):
@@ -38,13 +48,22 @@ def test_cli_find_outliers(basic_outlier_csv: str):
 
     stdout, stderr, returncode = run_cli_command(
         (
-            f"""cosmicqc find_outliers {basic_outlier_csv}"""
-            """ --metadata_columns '[\"col1\"]' --feature_thresholds '{"example_feature": 1.0}'"""
+            f"""cosmicqc find_outliers --df {basic_outlier_csv}"""
+            """ --metadata_columns [] --feature_thresholds {"example_feature":1.0}"""
         )
     )
 
     assert returncode == 0
-    assert "outlier_custom" in stdout or "outlier_custom" in stderr
+    assert (
+        stdout.strip()
+        == """Number of outliers: 2
+Outliers Range:
+example_feature Min: 9
+example_feature Max: 10
+   example_feature
+8                9
+9               10""".strip()
+    )
 
 
 def test_cli_label_outliers(basic_outlier_csv: str):
@@ -54,10 +73,23 @@ def test_cli_label_outliers(basic_outlier_csv: str):
 
     stdout, stderr, returncode = run_cli_command(
         (
-            f"""cosmicqc label_outliers {basic_outlier_csv}"""
-            """ --feature_thresholds '{"example_feature": 1.0}'"""
+            f"""cosmicqc label_outliers --df {basic_outlier_csv}"""
+            """ --feature_thresholds {"example_feature":1.0}"""
         )
     )
 
     assert returncode == 0
-    assert "outlier_custom" in stdout or "outlier_custom" in stderr
+    assert (
+        stdout.strip()
+        == """example_feature  outlier_custom
+0                1           False
+1                2           False
+2                3           False
+3                4           False
+4                5           False
+5                6           False
+6                7           False
+7                8           False
+8                9            True
+9               10            True""".strip()
+    )

From d7519a8614703bbea51c7330881e361f42c24b7a Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 12 Jun 2024 09:08:10 -0600
Subject: [PATCH 17/40] add docstring to top of test

---
 tests/test_cli.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tests/test_cli.py b/tests/test_cli.py
index 1513b74..f7cfaac 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -1,3 +1,7 @@
+"""
+Tests cosmicqc cli module
+"""
+
 from .utils import run_cli_command
 
 

From f8773b26de54a6ac306ae9ac1c1a220aa21ae427 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Fri, 14 Jun 2024 15:42:39 -0600
Subject: [PATCH 18/40] add csv.gz compatibility

---
 src/cosmicqc/scdataframe.py |  3 +++
 tests/conftest.py           | 15 +++++++++++++++
 tests/test_qcdataframe.py   | 10 ++++++++++
 3 files changed, 28 insertions(+)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index f94bdd2..a06b643 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -68,6 +68,9 @@ def __init__(
             if data_path.suffix == ".csv":
                 # read as a CSV
                 self.data = pd.read_csv(data, **kwargs)
+            elif data_path.suffixes == [".csv", ".gz"]:
+                # read as a CSV.GZ file
+                self.data = pd.read_csv(data, compression="gzip", **kwargs)
             elif data_path.suffix in (".tsv", ".txt"):
                 # read as a TSV
                 self.data = pd.read_csv(data, delimiter="\t", **kwargs)
diff --git a/tests/conftest.py b/tests/conftest.py
index e3fb24c..ed8591e 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -41,6 +41,21 @@ def fixture_basic_outlier_csv(
     return csv_path
 
 
+@pytest.fixture(name="basic_outlier_csv_gz")
+def fixture_basic_outlier_csv_gz(
+    tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
+):
+    """
+    Creates basic example data csv for use in tests
+    """
+
+    basic_outlier_dataframe.to_csv(
+        csv_gz_path := tmp_path / "example.csv.gz", index=False, compression="gzip"
+    )
+
+    return csv_gz_path
+
+
 @pytest.fixture(name="basic_outlier_tsv")
 def fixture_basic_outlier_tsv(
     tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
diff --git a/tests/test_qcdataframe.py b/tests/test_qcdataframe.py
index d2ec019..75e7448 100644
--- a/tests/test_qcdataframe.py
+++ b/tests/test_qcdataframe.py
@@ -25,6 +25,16 @@ def test_SCDataFrame_init_with_csv(basic_outlier_csv: str):
     assert sc_df.equals(expected_df)
 
 
+def test_SCDataFrame_init_with_csv_gz(basic_outlier_csv_gz: str):
+    """
+    Tests SCDataFrame with CSV input.
+    """
+    sc_df = SCDataFrame(data=basic_outlier_csv_gz)
+    expected_df = pd.read_csv(basic_outlier_csv_gz)
+    assert sc_df.data_source == basic_outlier_csv_gz
+    assert sc_df.equals(expected_df)
+
+
 def test_SCDataFrame_init_with_tsv(basic_outlier_tsv: str):
     """
     Tests SCDataFrame with TSV input.

From 0ad522f32b8008b2176a9f41a47f6754bde6f637 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 18 Jun 2024 09:17:31 -0600
Subject: [PATCH 19/40] add export capabilities

---
 src/cosmicqc/scdataframe.py | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index a06b643..730718a 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -81,6 +81,32 @@ def __init__(
                 raise ValueError("Unsupported file format for SCDataFrame.")
         else:
             raise ValueError("Unsupported input type for SCDataFrame.")
+        
+    def export(self: Self_SCDataFrame, file_path: str, **kwargs: Dict[str, Any]) -> None:
+        """
+        Exports the underlying pandas DataFrame to a file.
+
+        Args:
+            file_path (str): The path where the DataFrame should be saved.
+            **kwargs: Additional keyword arguments to pass to the pandas to_* methods.
+        """
+
+        data_path = pathlib.Path(file_path)
+
+        # export to csv
+        if data_path.suffix == ".csv":
+            self.data.to_csv(file_path, **kwargs)
+
+        # export to tsv
+        elif data_path.suffix in (".tsv", ".txt"):
+            self.data.to_csv(file_path, sep='\t', **kwargs)
+
+        # export to parquet
+        elif data_path.suffix == ".parquet":
+            self.data.to_parquet(file_path, **kwargs)
+
+        else:
+            raise ValueError("Unsupported file format for export.")
 
     def __call__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
@@ -100,10 +126,10 @@ def __repr__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
         return repr(self.data)
 
-    def __getattr__(self: Self_SCDataFrame, attr: str) -> Any:  # noqa: ANN401
+    def __getattr__(self, attr: str) -> Any:  # noqa: ANN401
         """
         Intercept attribute accesses and delegate them to the underlying
-        pandas DataFrame.
+        pandas DataFrame, except for custom methods.
 
         Args:
             attr (str): The name of the attribute being accessed.
@@ -111,6 +137,8 @@ def __getattr__(self: Self_SCDataFrame, attr: str) -> Any:  # noqa: ANN401
         Returns:
             Any: The value of the attribute from the pandas DataFrame.
         """
+        if attr in self.__dict__:
+            return self.__dict__[attr]
         return getattr(self.data, attr)
 
     def __getitem__(self: Self_SCDataFrame, key: Union[int, str]) -> Any:  # noqa: ANN401

From 6d33de4e8571bfb780fa64ce277814b56c84adbf Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 18 Jun 2024 09:18:00 -0600
Subject: [PATCH 20/40] rename file to correct module name

---
 tests/{test_qcdataframe.py => test_scdataframe.py} | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename tests/{test_qcdataframe.py => test_scdataframe.py} (100%)

diff --git a/tests/test_qcdataframe.py b/tests/test_scdataframe.py
similarity index 100%
rename from tests/test_qcdataframe.py
rename to tests/test_scdataframe.py

From 34cf9bfc796f084a205a0e74075c41f2236e8c81 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 18 Jun 2024 09:58:03 -0600
Subject: [PATCH 21/40] add export capabilities

---
 src/cosmicqc/scdataframe.py | 17 +++++-----
 tests/test_scdataframe.py   | 62 ++++++++++++++++++++++++++++++++++---
 2 files changed, 65 insertions(+), 14 deletions(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 730718a..4a4acae 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -81,8 +81,10 @@ def __init__(
                 raise ValueError("Unsupported file format for SCDataFrame.")
         else:
             raise ValueError("Unsupported input type for SCDataFrame.")
-        
-    def export(self: Self_SCDataFrame, file_path: str, **kwargs: Dict[str, Any]) -> None:
+
+    def export(
+        self: Self_SCDataFrame, file_path: str, **kwargs: Dict[str, Any]
+    ) -> None:
         """
         Exports the underlying pandas DataFrame to a file.
 
@@ -94,17 +96,14 @@ def export(self: Self_SCDataFrame, file_path: str, **kwargs: Dict[str, Any]) ->
         data_path = pathlib.Path(file_path)
 
         # export to csv
-        if data_path.suffix == ".csv":
+        if ".csv" in data_path.suffixes:
             self.data.to_csv(file_path, **kwargs)
-
         # export to tsv
-        elif data_path.suffix in (".tsv", ".txt"):
-            self.data.to_csv(file_path, sep='\t', **kwargs)
-
+        elif any(elem in data_path.suffixes for elem in (".tsv", ".txt")):
+            self.data.to_csv(file_path, sep="\t", **kwargs)
         # export to parquet
         elif data_path.suffix == ".parquet":
             self.data.to_parquet(file_path, **kwargs)
-
         else:
             raise ValueError("Unsupported file format for export.")
 
@@ -126,7 +125,7 @@ def __repr__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
         return repr(self.data)
 
-    def __getattr__(self, attr: str) -> Any:  # noqa: ANN401
+    def __getattr__(self: Self_SCDataFrame, attr: str) -> Any:  # noqa: ANN401
         """
         Intercept attribute accesses and delegate them to the underlying
         pandas DataFrame, except for custom methods.
diff --git a/tests/test_scdataframe.py b/tests/test_scdataframe.py
index 75e7448..78e5dd9 100644
--- a/tests/test_scdataframe.py
+++ b/tests/test_scdataframe.py
@@ -2,54 +2,106 @@
 Tests cosmicqc SCDataFrame module
 """
 
+import pathlib
+
 import pandas as pd
 from cosmicqc.scdataframe import SCDataFrame
+from pyarrow import parquet
 
 
-def test_SCDataFrame_init_with_dataframe(basic_outlier_dataframe: pd.DataFrame):
+def test_SCDataFrame_with_dataframe(
+    tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
+):
     """
     Tests SCDataFrame with pd.DataFrame input.
     """
+
     sc_df = SCDataFrame(data=basic_outlier_dataframe)
+
+    # test that we ingested the data properly
     assert sc_df.data_source == "pd.DataFrame"
     assert sc_df.equals(basic_outlier_dataframe)
 
+    # test export
+    basic_outlier_dataframe.to_parquet(
+        control_path := f"{tmp_path}/df_input_example.parquet"
+    )
+    sc_df.export(test_path := f"{tmp_path}/df_input_example1.parquet")
 
-def test_SCDataFrame_init_with_csv(basic_outlier_csv: str):
+    assert parquet.read_table(control_path).equals(parquet.read_table(test_path))
+
+
+def test_SCDataFrame_with_csv(tmp_path: pathlib.Path, basic_outlier_csv: str):
     """
     Tests SCDataFrame with CSV input.
     """
+
     sc_df = SCDataFrame(data=basic_outlier_csv)
     expected_df = pd.read_csv(basic_outlier_csv)
+
+    # test that we ingested the data properly
     assert sc_df.data_source == basic_outlier_csv
     assert sc_df.equals(expected_df)
 
+    # test export
+    sc_df.export(test_path := f"{tmp_path}/df_input_example.csv", index=False)
+
+    pd.testing.assert_frame_equal(expected_df, pd.read_csv(test_path))
+
 
-def test_SCDataFrame_init_with_csv_gz(basic_outlier_csv_gz: str):
+def test_SCDataFrame_with_csv_gz(tmp_path: pathlib.Path, basic_outlier_csv_gz: str):
     """
     Tests SCDataFrame with CSV input.
     """
+
     sc_df = SCDataFrame(data=basic_outlier_csv_gz)
     expected_df = pd.read_csv(basic_outlier_csv_gz)
+
+    # test that we ingested the data properly
     assert sc_df.data_source == basic_outlier_csv_gz
     assert sc_df.equals(expected_df)
 
+    # test export
+    sc_df.export(test_path := f"{tmp_path}/df_input_example.csv.gz", index=False)
 
-def test_SCDataFrame_init_with_tsv(basic_outlier_tsv: str):
+    pd.testing.assert_frame_equal(
+        expected_df, pd.read_csv(test_path, compression="gzip")
+    )
+
+
+def test_SCDataFrame_with_tsv(tmp_path: pathlib.Path, basic_outlier_tsv: str):
     """
     Tests SCDataFrame with TSV input.
     """
+
     sc_df = SCDataFrame(data=basic_outlier_tsv)
     expected_df = pd.read_csv(basic_outlier_tsv, delimiter="\t")
+
+    # test that we ingested the data properly
     assert sc_df.data_source == basic_outlier_tsv
     assert sc_df.equals(expected_df)
 
+    # test export
+    sc_df.export(test_path := f"{tmp_path}/df_input_example.tsv", index=False)
+
+    pd.testing.assert_frame_equal(expected_df, pd.read_csv(test_path, sep="\t"))
 
-def test_SCDataFrame_init_with_parquet(basic_outlier_parquet: str):
+
+def test_SCDataFrame_with_parquet(tmp_path: pathlib.Path, basic_outlier_parquet: str):
     """
     Tests SCDataFrame with TSV input.
     """
+
     sc_df = SCDataFrame(data=basic_outlier_parquet)
     expected_df = pd.read_parquet(basic_outlier_parquet)
+
+    # test that we ingested the data properly
     assert sc_df.data_source == basic_outlier_parquet
     assert sc_df.equals(expected_df)
+
+    # test export
+    sc_df.export(test_path := f"{tmp_path}/df_input_example2.parquet")
+
+    assert parquet.read_table(basic_outlier_parquet).equals(
+        parquet.read_table(test_path)
+    )

From 09d815c384d6e52ffe47c1ce97bc0349fb420b7f Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 18 Jun 2024 15:23:07 -0600
Subject: [PATCH 22/40] add output capabilities

---
 src/cosmicqc/analyze.py | 37 +++++++++++++++++++++++++++++++++----
 src/cosmicqc/cli.py     |  2 +-
 2 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index 08649f9..da43fcc 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -23,6 +23,7 @@ def identify_outliers(
     feature_thresholds: Union[Dict[str, float], str],
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
     include_threshold_scores: bool = False,
+    export_path: Optional[str] = None,
 ) -> Union[pd.Series, pd.DataFrame]:
     """
     This function uses z-scoring to format the data for detecting outlier
@@ -48,6 +49,9 @@ def identify_outliers(
         include_threshold_scores: bool
             Whether to include the threshold scores in addition to whether
             the threshold set passes per row.
+        export_path: Optional[str] = None
+            An optional path to export the data using SCDataFrame export
+            capabilities. If None no export is performed.
 
     Returns:
         Union[pd.Series, pd.DataFrame]:
@@ -96,7 +100,7 @@ def identify_outliers(
             condition = outlier_df[zscore_columns[feature]] < threshold
         conditions.append(condition)
 
-    return (
+    result = (
         # create a boolean pd.series identifier for dataframe
         # based on all conditions for use within other functions.
         reduce(operator.and_, conditions)
@@ -112,12 +116,18 @@ def identify_outliers(
         )
     )
 
+    if export_path is not None:
+        SCDataFrame(data=result).export(file_path=export_path)
+
+    return result
+
 
 def find_outliers(
     df: Union[SCDataFrame, pd.DataFrame, str],
     metadata_columns: List[str],
     feature_thresholds: Union[Dict[str, float], str],
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
+    export_path: Optional[str] = None,
 ) -> pd.DataFrame:
     """
     This function uses identify_outliers to return a dataframe
@@ -139,6 +149,9 @@ def find_outliers(
         feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
             An optional feature thresholds file where thresholds may be
             defined within a file.
+        export_path: Optional[str] = None
+            An optional path to export the data using SCDataFrame export
+            capabilities. If None no export is performed.
 
     Returns:
         pd.DataFrame:
@@ -175,8 +188,14 @@ def find_outliers(
     # Include metadata columns in the output DataFrame
     columns_to_include = list(feature_thresholds.keys()) + metadata_columns
 
+    result = outliers_df[columns_to_include]
+
+    # export the file if specified
+    if export_path is not None:
+        SCDataFrame(data=result).export(file_path=export_path)
+
     # Return outliers DataFrame with specified columns
-    return outliers_df[columns_to_include]
+    return result
 
 
 def label_outliers(
@@ -184,6 +203,7 @@ def label_outliers(
     feature_thresholds: Optional[Union[Dict[str, float], str]] = None,
     feature_thresholds_file: Optional[str] = DEFAULT_QC_THRESHOLD_FILE,
     include_threshold_scores: bool = False,
+    export_path: Optional[str] = None,
 ) -> pd.DataFrame:
     """
     Use identify_outliers to label the original dataset for
@@ -206,6 +226,9 @@ def label_outliers(
             include_threshold_scores: bool = False
                 Whether to include the scores in addition to whether an outlier
                 was detected or not.
+            export_path: Optional[str] = None
+                An optional path to export the data using SCDataFrame export
+                capabilities. If None no export is performed.
 
         Returns:
             pd.DataFrame:
@@ -225,7 +248,7 @@ def label_outliers(
             feature_thresholds_file=feature_thresholds_file,
             include_threshold_scores=include_threshold_scores,
         )
-        return pd.concat(
+        result = pd.concat(
             [
                 df,
                 (
@@ -266,7 +289,13 @@ def label_outliers(
             axis=1,
         )
         # return a dataframe with a deduplicated columns by name
-        return labeled_df.loc[:, ~labeled_df.columns.duplicated()]
+        result = labeled_df.loc[:, ~labeled_df.columns.duplicated()]
+
+    # export the file if specified
+    if export_path is not None:
+        SCDataFrame(data=result).export(file_path=export_path)
+
+    return result
 
 
 def read_thresholds_set_from_file(
diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index fb7ebcf..b290ef1 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -108,4 +108,4 @@ def cli_analyze() -> None:
     and label_outliers from the command line interface through analyze
     """
 
-    fire.Fire(analyze)
+    cli_analyze()

From fbedb7dfa5302d1ae5dd436cc052ebc6ede116b8 Mon Sep 17 00:00:00 2001
From: Dave Bunten <ekgto445@gmail.com>
Date: Tue, 18 Jun 2024 16:53:09 -0600
Subject: [PATCH 23/40] Apply suggestions from code review

Co-authored-by: Gregory Way <gregory.way@gmail.com>
---
 src/cosmicqc/scdataframe.py | 6 +++---
 tests/conftest.py           | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 4a4acae..d364764 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -31,9 +31,9 @@ class SCDataFrame:
         __call__():
             Returns the underlying pandas DataFrame.
         __repr__():
-            Returns representation of underlying pandas DataFrame.
+            Returns a representation of the underlying pandas DataFrame.
         __getattr__():
-            Returns underlying attributes of pandas DataFrame.
+            Returns the underlying attributes of the pandas DataFrame.
         __getitem__():
             Returns slice of data from pandas DataFrame.
     """
@@ -118,7 +118,7 @@ def __call__(self: Self_SCDataFrame) -> pd.DataFrame:
 
     def __repr__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
-        Returns the representation of underlying pandas DataFrame.
+        Returns the representation of the underlying pandas DataFrame.
 
         Returns:
             pd.DataFrame: The data in a pandas DataFrame.
diff --git a/tests/conftest.py b/tests/conftest.py
index ed8591e..bc2883d 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -36,7 +36,7 @@ def fixture_basic_outlier_csv(
     Creates basic example data csv for use in tests
     """
 
-    basic_outlier_dataframe.to_csv(csv_path := tmp_path / "example.csv", index=False)
+    basic_outlier_dataframe.to_csv(csv_path := tmp_path / "basic_example.csv", index=False)
 
     return csv_path
 

From 025701497204e9bae941a5ccdf1b4123741c3290 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 18 Jun 2024 17:00:49 -0600
Subject: [PATCH 24/40] update tests and docs

---
 pyproject.toml              |  2 +-
 src/cosmicqc/scdataframe.py | 20 +++++++++-----------
 tests/conftest.py           |  4 +++-
 tests/test_scdataframe.py   | 15 ++++++---------
 4 files changed, 19 insertions(+), 22 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index f3231ed..67af76e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -62,7 +62,7 @@ select = [
 # Ignore `E402` and `F401` (unused imports) in all `__init__.py` files
 "__init__.py" = ["E402", "F401"]
 # ignore typing rules for tests
-"tests/*" = ["ANN201"]
+"tests/*" = ["ANN201", "PLR0913"]
 
 # set dynamic versioning capabilities for project
 [tool.poetry-dynamic-versioning]
diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index d364764..17dd0ce 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -31,7 +31,7 @@ class SCDataFrame:
         __call__():
             Returns the underlying pandas DataFrame.
         __repr__():
-            Returns a representation of the underlying pandas DataFrame.
+            Returns a representational string of the underlying pandas DataFrame.
         __getattr__():
             Returns the underlying attributes of the pandas DataFrame.
         __getitem__():
@@ -53,10 +53,10 @@ def __init__(
 
         if isinstance(data, pd.DataFrame):
             # if data is a pd.DataFrame, remember this within the data_source attr
-            self.data_source = "pd.DataFrame"
+            self.data_source = "pandas.DataFrame"
             self.data = data
 
-        elif isinstance(data, pathlib.Path) or isinstance(data, str):  # noqa: PLR1701, SIM101
+        elif isinstance(data, pathlib.Path | str):
             # if the data is a string, remember the original source
             # through a data_source attr
             self.data_source = data
@@ -65,15 +65,13 @@ def __init__(
             data_path = pathlib.Path(data)
 
             # Read the data from the file based on its extension
-            if data_path.suffix == ".csv":
-                # read as a CSV
+            if (
+                data_path.suffix == ".csv"
+                or data_path.suffix in (".tsv", ".txt")
+                or data_path.suffixes == [".csv", ".gz"]
+            ):
+                # read as a CSV, CSV.GZ, .TSV, or .TXT file
                 self.data = pd.read_csv(data, **kwargs)
-            elif data_path.suffixes == [".csv", ".gz"]:
-                # read as a CSV.GZ file
-                self.data = pd.read_csv(data, compression="gzip", **kwargs)
-            elif data_path.suffix in (".tsv", ".txt"):
-                # read as a TSV
-                self.data = pd.read_csv(data, delimiter="\t", **kwargs)
             elif data_path.suffix == ".parquet":
                 # read as a Parquet file
                 self.data = pd.read_parquet(data, **kwargs)
diff --git a/tests/conftest.py b/tests/conftest.py
index bc2883d..8f97176 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -36,7 +36,9 @@ def fixture_basic_outlier_csv(
     Creates basic example data csv for use in tests
     """
 
-    basic_outlier_dataframe.to_csv(csv_path := tmp_path / "basic_example.csv", index=False)
+    basic_outlier_dataframe.to_csv(
+        csv_path := tmp_path / "basic_example.csv", index=False
+    )
 
     return csv_path
 
diff --git a/tests/test_scdataframe.py b/tests/test_scdataframe.py
index 78e5dd9..713fc97 100644
--- a/tests/test_scdataframe.py
+++ b/tests/test_scdataframe.py
@@ -10,7 +10,12 @@
 
 
 def test_SCDataFrame_with_dataframe(
-    tmp_path: pathlib.Path, basic_outlier_dataframe: pd.DataFrame
+    tmp_path: pathlib.Path,
+    basic_outlier_dataframe: pd.DataFrame,
+    basic_outlier_csv: str,
+    basic_outlier_csv_gz: str,
+    basic_outlier_tsv: str,
+    basic_outlier_parquet: str,
 ):
     """
     Tests SCDataFrame with pd.DataFrame input.
@@ -30,8 +35,6 @@ def test_SCDataFrame_with_dataframe(
 
     assert parquet.read_table(control_path).equals(parquet.read_table(test_path))
 
-
-def test_SCDataFrame_with_csv(tmp_path: pathlib.Path, basic_outlier_csv: str):
     """
     Tests SCDataFrame with CSV input.
     """
@@ -48,8 +51,6 @@ def test_SCDataFrame_with_csv(tmp_path: pathlib.Path, basic_outlier_csv: str):
 
     pd.testing.assert_frame_equal(expected_df, pd.read_csv(test_path))
 
-
-def test_SCDataFrame_with_csv_gz(tmp_path: pathlib.Path, basic_outlier_csv_gz: str):
     """
     Tests SCDataFrame with CSV input.
     """
@@ -68,8 +69,6 @@ def test_SCDataFrame_with_csv_gz(tmp_path: pathlib.Path, basic_outlier_csv_gz: s
         expected_df, pd.read_csv(test_path, compression="gzip")
     )
 
-
-def test_SCDataFrame_with_tsv(tmp_path: pathlib.Path, basic_outlier_tsv: str):
     """
     Tests SCDataFrame with TSV input.
     """
@@ -86,8 +85,6 @@ def test_SCDataFrame_with_tsv(tmp_path: pathlib.Path, basic_outlier_tsv: str):
 
     pd.testing.assert_frame_equal(expected_df, pd.read_csv(test_path, sep="\t"))
 
-
-def test_SCDataFrame_with_parquet(tmp_path: pathlib.Path, basic_outlier_parquet: str):
     """
     Tests SCDataFrame with TSV input.
     """

From 985a6dda77d5d57fe894f262ba1aa6e3538eb6a6 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 19 Jun 2024 08:31:14 -0600
Subject: [PATCH 25/40] fix tests

---
 pyproject.toml              | 2 +-
 src/cosmicqc/scdataframe.py | 6 ++++--
 tests/test_scdataframe.py   | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 67af76e..5adde66 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -30,7 +30,7 @@ profile = "black"
 exclude_dirs = ["tests"]
 
 [tool.ruff]
-target-version = "py311"
+target-version = "py38"
 line-length = 88
 fix = true
 
diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 17dd0ce..d96cbee 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -39,7 +39,9 @@ class SCDataFrame:
     """
 
     def __init__(
-        self: Self_SCDataFrame, data: Union[pd.DataFrame, str], **kwargs: Dict[str, Any]
+        self: Self_SCDataFrame,
+        data: Union[pd.DataFrame, str, pathlib.Path],
+        **kwargs: Dict[str, Any],
     ) -> None:
         """
         Initializes the SCDataFrame with either a DataFrame or a file path.
@@ -56,7 +58,7 @@ def __init__(
             self.data_source = "pandas.DataFrame"
             self.data = data
 
-        elif isinstance(data, pathlib.Path | str):
+        elif isinstance(data, (pathlib.Path, str)):
             # if the data is a string, remember the original source
             # through a data_source attr
             self.data_source = data
diff --git a/tests/test_scdataframe.py b/tests/test_scdataframe.py
index 713fc97..bcb520c 100644
--- a/tests/test_scdataframe.py
+++ b/tests/test_scdataframe.py
@@ -24,7 +24,7 @@ def test_SCDataFrame_with_dataframe(
     sc_df = SCDataFrame(data=basic_outlier_dataframe)
 
     # test that we ingested the data properly
-    assert sc_df.data_source == "pd.DataFrame"
+    assert sc_df.data_source == "pandas.DataFrame"
     assert sc_df.equals(basic_outlier_dataframe)
 
     # test export

From 5034a0727473fd382944761e4ccce8754d628795 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 19 Jun 2024 11:01:36 -0600
Subject: [PATCH 26/40] update tests; add constructor path for scdataframe

---
 src/cosmicqc/analyze.py     |  9 +++------
 src/cosmicqc/scdataframe.py | 25 +++++++++++++++----------
 tests/test_scdataframe.py   | 31 +++++++++++--------------------
 3 files changed, 29 insertions(+), 36 deletions(-)

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index d616f78..abe43d6 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -55,8 +55,7 @@ def identify_outliers(
     """
 
     # interpret the df as SCDataFrame
-    if not isinstance(df, SCDataFrame):
-        df = SCDataFrame(data=df)
+    df = SCDataFrame(data=df)
 
     # create a copy of the dataframe to ensure
     # we don't modify the supplied dataframe inplace.
@@ -145,8 +144,7 @@ def find_outliers(
     """
 
     # interpret the df as SCDataFrame
-    if not isinstance(df, SCDataFrame):
-        df = SCDataFrame(data=df)
+    df = SCDataFrame(data=df)
 
     if isinstance(feature_thresholds, str):
         feature_thresholds = read_thresholds_set_from_file(
@@ -212,8 +210,7 @@ def label_outliers(
     """
 
     # interpret the df as SCDataFrame
-    if not isinstance(df, SCDataFrame):
-        df = SCDataFrame(data=df)
+    df = SCDataFrame(data=df)
 
     # for single outlier processing
     if isinstance(feature_thresholds, (str, dict)):
diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index d96cbee..bbe29db 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -9,7 +9,7 @@
 
 # provide backwards compatibility for Self type in earlier Python versions.
 # see: https://peps.python.org/pep-0484/#annotating-instance-and-class-methods
-Self_SCDataFrame = TypeVar("Self_SCDataFrame", bound="SCDataFrame")
+SCDataFrame_type = TypeVar("SCDataFrame_type", bound="SCDataFrame")
 
 
 class SCDataFrame:
@@ -39,8 +39,8 @@ class SCDataFrame:
     """
 
     def __init__(
-        self: Self_SCDataFrame,
-        data: Union[pd.DataFrame, str, pathlib.Path],
+        self: SCDataFrame_type,
+        data: Union[SCDataFrame_type, pd.DataFrame, str, pathlib.Path],
         **kwargs: Dict[str, Any],
     ) -> None:
         """
@@ -53,7 +53,12 @@ def __init__(
                 Additional keyword arguments to pass to the pandas read functions.
         """
 
-        if isinstance(data, pd.DataFrame):
+        if isinstance(data, SCDataFrame):
+            # if data is an instance of SCDataFrame, use its data_source and data
+            self.data_source = data.data_source
+            self.data = data.data
+
+        elif isinstance(data, pd.DataFrame):
             # if data is a pd.DataFrame, remember this within the data_source attr
             self.data_source = "pandas.DataFrame"
             self.data = data
@@ -80,10 +85,10 @@ def __init__(
             else:
                 raise ValueError("Unsupported file format for SCDataFrame.")
         else:
-            raise ValueError("Unsupported input type for SCDataFrame.")
+            raise ValueError("Unsupported data type for SCDataFrame.")
 
     def export(
-        self: Self_SCDataFrame, file_path: str, **kwargs: Dict[str, Any]
+        self: SCDataFrame_type, file_path: str, **kwargs: Dict[str, Any]
     ) -> None:
         """
         Exports the underlying pandas DataFrame to a file.
@@ -107,7 +112,7 @@ def export(
         else:
             raise ValueError("Unsupported file format for export.")
 
-    def __call__(self: Self_SCDataFrame) -> pd.DataFrame:
+    def __call__(self: SCDataFrame_type) -> pd.DataFrame:
         """
         Returns the underlying pandas DataFrame.
 
@@ -116,7 +121,7 @@ def __call__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
         return self.data
 
-    def __repr__(self: Self_SCDataFrame) -> pd.DataFrame:
+    def __repr__(self: SCDataFrame_type) -> pd.DataFrame:
         """
         Returns the representation of the underlying pandas DataFrame.
 
@@ -125,7 +130,7 @@ def __repr__(self: Self_SCDataFrame) -> pd.DataFrame:
         """
         return repr(self.data)
 
-    def __getattr__(self: Self_SCDataFrame, attr: str) -> Any:  # noqa: ANN401
+    def __getattr__(self: SCDataFrame_type, attr: str) -> Any:  # noqa: ANN401
         """
         Intercept attribute accesses and delegate them to the underlying
         pandas DataFrame, except for custom methods.
@@ -140,7 +145,7 @@ def __getattr__(self: Self_SCDataFrame, attr: str) -> Any:  # noqa: ANN401
             return self.__dict__[attr]
         return getattr(self.data, attr)
 
-    def __getitem__(self: Self_SCDataFrame, key: Union[int, str]) -> Any:  # noqa: ANN401
+    def __getitem__(self: SCDataFrame_type, key: Union[int, str]) -> Any:  # noqa: ANN401
         """
         Returns an element or a slice of the underlying pandas DataFrame.
 
diff --git a/tests/test_scdataframe.py b/tests/test_scdataframe.py
index bcb520c..2627b88 100644
--- a/tests/test_scdataframe.py
+++ b/tests/test_scdataframe.py
@@ -17,10 +17,8 @@ def test_SCDataFrame_with_dataframe(
     basic_outlier_tsv: str,
     basic_outlier_parquet: str,
 ):
-    """
-    Tests SCDataFrame with pd.DataFrame input.
-    """
-
+    
+    # Tests SCDataFrame with pd.DataFrame input.
     sc_df = SCDataFrame(data=basic_outlier_dataframe)
 
     # test that we ingested the data properly
@@ -35,10 +33,7 @@ def test_SCDataFrame_with_dataframe(
 
     assert parquet.read_table(control_path).equals(parquet.read_table(test_path))
 
-    """
-    Tests SCDataFrame with CSV input.
-    """
-
+    # Tests SCDataFrame with CSV input.
     sc_df = SCDataFrame(data=basic_outlier_csv)
     expected_df = pd.read_csv(basic_outlier_csv)
 
@@ -51,10 +46,7 @@ def test_SCDataFrame_with_dataframe(
 
     pd.testing.assert_frame_equal(expected_df, pd.read_csv(test_path))
 
-    """
-    Tests SCDataFrame with CSV input.
-    """
-
+    # Tests SCDataFrame with CSV input.
     sc_df = SCDataFrame(data=basic_outlier_csv_gz)
     expected_df = pd.read_csv(basic_outlier_csv_gz)
 
@@ -69,10 +61,7 @@ def test_SCDataFrame_with_dataframe(
         expected_df, pd.read_csv(test_path, compression="gzip")
     )
 
-    """
-    Tests SCDataFrame with TSV input.
-    """
-
+    # Tests SCDataFrame with TSV input.
     sc_df = SCDataFrame(data=basic_outlier_tsv)
     expected_df = pd.read_csv(basic_outlier_tsv, delimiter="\t")
 
@@ -85,10 +74,7 @@ def test_SCDataFrame_with_dataframe(
 
     pd.testing.assert_frame_equal(expected_df, pd.read_csv(test_path, sep="\t"))
 
-    """
-    Tests SCDataFrame with TSV input.
-    """
-
+    # Tests SCDataFrame with parquet input.
     sc_df = SCDataFrame(data=basic_outlier_parquet)
     expected_df = pd.read_parquet(basic_outlier_parquet)
 
@@ -102,3 +88,8 @@ def test_SCDataFrame_with_dataframe(
     assert parquet.read_table(basic_outlier_parquet).equals(
         parquet.read_table(test_path)
     )
+
+    # test SCDataFrame with SCDataFrame input
+    copy_sc_df = SCDataFrame(data=sc_df)
+
+    pd.testing.assert_frame_equal(copy_sc_df.data, sc_df.data)

From fd818685c9b3d4ae5dea88d7ca3a40a5e1c3615f Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 19 Jun 2024 11:01:48 -0600
Subject: [PATCH 27/40] linting

---
 tests/test_scdataframe.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tests/test_scdataframe.py b/tests/test_scdataframe.py
index 2627b88..2781c8c 100644
--- a/tests/test_scdataframe.py
+++ b/tests/test_scdataframe.py
@@ -17,7 +17,6 @@ def test_SCDataFrame_with_dataframe(
     basic_outlier_tsv: str,
     basic_outlier_parquet: str,
 ):
-    
     # Tests SCDataFrame with pd.DataFrame input.
     sc_df = SCDataFrame(data=basic_outlier_dataframe)
 

From 3bab60f581e93c23360bfa2506c014f7dc87d201 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 19 Jun 2024 11:34:41 -0600
Subject: [PATCH 28/40] modify tests

---
 src/cosmicqc/scdataframe.py |  5 +++++
 tests/test_cli.py           | 12 ++++++++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index bbe29db..9ec6bf7 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -62,6 +62,11 @@ def __init__(
             # if data is a pd.DataFrame, remember this within the data_source attr
             self.data_source = "pandas.DataFrame"
             self.data = data
+        
+        elif isinstance(data, pd.Series):
+            # if data is a pd.DataFrame, remember this within the data_source attr
+            self.data_source = "pandas.Series"
+            self.data = pd.DataFrame(data)
 
         elif isinstance(data, (pathlib.Path, str)):
             # if the data is a string, remember the original source
diff --git a/tests/test_cli.py b/tests/test_cli.py
index f7cfaac..f3ebf7f 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -3,7 +3,8 @@
 """
 
 from .utils import run_cli_command
-
+import pathlib
+from pyarrow import parquet
 
 def test_cli_util():
     """
@@ -16,7 +17,7 @@ def test_cli_util():
     assert returncode == 0
 
 
-def test_cli_identify_outliers(basic_outlier_csv: str):
+def test_cli_identify_outliers(tmp_path: pathlib.Path, basic_outlier_csv: str):
     """
     Test the `identify_outliers` function of the CLI.
     """
@@ -25,9 +26,12 @@ def test_cli_identify_outliers(basic_outlier_csv: str):
         (
             f"""cosmicqc identify_outliers --df {basic_outlier_csv}"""
             """ --feature_thresholds {"example_feature":1.0}"""
+            f" --export_path {tmp_path}/identify_outliers_output.parquet"
+            
         )
     )
 
+    print(stderr)
     assert returncode == 0
     assert (
         stdout.strip()
@@ -44,6 +48,10 @@ def test_cli_identify_outliers(basic_outlier_csv: str):
 Name: Z_Score_example_feature, dtype: bool""".strip()
     )
 
+    
+    print(parquet.read_table(f"{tmp_path}/identify_outliers_output.parquet").to_pydict())
+    assert parquet.read_table(f"{tmp_path}/identify_outliers_output.parquet").to_pydict() == {}
+
 
 def test_cli_find_outliers(basic_outlier_csv: str):
     """

From 6d61bf3d0cec43780dea125c14bae4a9f27e8724 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 19 Jun 2024 11:39:05 -0600
Subject: [PATCH 29/40] enable pd.series compatibility

---
 src/cosmicqc/scdataframe.py | 6 ++++++
 tests/test_scdataframe.py   | 7 +++++++
 2 files changed, 13 insertions(+)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index bbe29db..50eb0f8 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -58,6 +58,12 @@ def __init__(
             self.data_source = data.data_source
             self.data = data.data
 
+        elif isinstance(data, pd.Series):
+            # if data is a pd.Series, remember this within the data_source attr
+            self.data_source = "pandas.Series"
+            # also cast the series to a dataframe
+            self.data = pd.DataFrame(data)
+
         elif isinstance(data, pd.DataFrame):
             # if data is a pd.DataFrame, remember this within the data_source attr
             self.data_source = "pandas.DataFrame"
diff --git a/tests/test_scdataframe.py b/tests/test_scdataframe.py
index 2781c8c..2ddcb03 100644
--- a/tests/test_scdataframe.py
+++ b/tests/test_scdataframe.py
@@ -32,6 +32,13 @@ def test_SCDataFrame_with_dataframe(
 
     assert parquet.read_table(control_path).equals(parquet.read_table(test_path))
 
+    # Tests SCDataFrame with pd.Series input.
+    sc_df = SCDataFrame(data=basic_outlier_dataframe.loc[0])
+
+    # test that we ingested the data properly
+    assert sc_df.data_source == "pandas.Series"
+    assert sc_df.equals(pd.DataFrame(basic_outlier_dataframe.loc[0]))
+
     # Tests SCDataFrame with CSV input.
     sc_df = SCDataFrame(data=basic_outlier_csv)
     expected_df = pd.read_csv(basic_outlier_csv)

From 90c2088d65c58ff10adfa24f5238a6874ea38104 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 19 Jun 2024 13:25:19 -0600
Subject: [PATCH 30/40] update for exports via cli

---
 src/cosmicqc/scdataframe.py |  2 +-
 tests/test_cli.py           | 57 +++++++++++++++++++++++++++++++------
 2 files changed, 49 insertions(+), 10 deletions(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 27de981..7030745 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -68,7 +68,7 @@ def __init__(
             # if data is a pd.DataFrame, remember this within the data_source attr
             self.data_source = "pandas.DataFrame"
             self.data = data
-        
+
         elif isinstance(data, pd.Series):
             # if data is a pd.DataFrame, remember this within the data_source attr
             self.data_source = "pandas.Series"
diff --git a/tests/test_cli.py b/tests/test_cli.py
index f3ebf7f..95b1151 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -2,10 +2,13 @@
 Tests cosmicqc cli module
 """
 
-from .utils import run_cli_command
 import pathlib
+
 from pyarrow import parquet
 
+from .utils import run_cli_command
+
+
 def test_cli_util():
     """
     Test the `identify_outliers` function of the CLI.
@@ -27,7 +30,6 @@ def test_cli_identify_outliers(tmp_path: pathlib.Path, basic_outlier_csv: str):
             f"""cosmicqc identify_outliers --df {basic_outlier_csv}"""
             """ --feature_thresholds {"example_feature":1.0}"""
             f" --export_path {tmp_path}/identify_outliers_output.parquet"
-            
         )
     )
 
@@ -48,12 +50,25 @@ def test_cli_identify_outliers(tmp_path: pathlib.Path, basic_outlier_csv: str):
 Name: Z_Score_example_feature, dtype: bool""".strip()
     )
 
-    
-    print(parquet.read_table(f"{tmp_path}/identify_outliers_output.parquet").to_pydict())
-    assert parquet.read_table(f"{tmp_path}/identify_outliers_output.parquet").to_pydict() == {}
-
-
-def test_cli_find_outliers(basic_outlier_csv: str):
+    assert parquet.read_table(
+        f"{tmp_path}/identify_outliers_output.parquet"
+    ).to_pydict() == {
+        "Z_Score_example_feature": [
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            True,
+            True,
+        ]
+    }
+
+
+def test_cli_find_outliers(tmp_path: pathlib.Path, basic_outlier_csv: str):
     """
     Test the `find_outliers` function of the CLI.
     """
@@ -62,6 +77,7 @@ def test_cli_find_outliers(basic_outlier_csv: str):
         (
             f"""cosmicqc find_outliers --df {basic_outlier_csv}"""
             """ --metadata_columns [] --feature_thresholds {"example_feature":1.0}"""
+            f" --export_path {tmp_path}/find_outliers_output.parquet"
         )
     )
 
@@ -77,8 +93,12 @@ def test_cli_find_outliers(basic_outlier_csv: str):
 9               10""".strip()
     )
 
+    assert parquet.read_table(
+        f"{tmp_path}/find_outliers_output.parquet"
+    ).to_pydict() == {"example_feature": [9, 10], "__index_level_0__": [8, 9]}
 
-def test_cli_label_outliers(basic_outlier_csv: str):
+
+def test_cli_label_outliers(tmp_path: pathlib.Path, basic_outlier_csv: str):
     """
     Test the `label_outliers` function of the CLI.
     """
@@ -87,6 +107,7 @@ def test_cli_label_outliers(basic_outlier_csv: str):
         (
             f"""cosmicqc label_outliers --df {basic_outlier_csv}"""
             """ --feature_thresholds {"example_feature":1.0}"""
+            f" --export_path {tmp_path}/label_outliers_output.parquet"
         )
     )
 
@@ -105,3 +126,21 @@ def test_cli_label_outliers(basic_outlier_csv: str):
 8                9            True
 9               10            True""".strip()
     )
+
+    assert parquet.read_table(
+        f"{tmp_path}/label_outliers_output.parquet"
+    ).to_pydict() == {
+        "example_feature": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+        "outlier_custom": [
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            False,
+            True,
+            True,
+        ],
+    }

From c966ce872638d7905f9ccf955ee98238c5d96dfe Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 25 Jun 2024 13:36:44 -0600
Subject: [PATCH 31/40] fix docstring

---
 src/cosmicqc/scdataframe.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 799afab..32f60a3 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -142,7 +142,7 @@ def __repr__(self: SCDataFrame_type) -> str:
         Returns the representation of the underlying pandas DataFrame.
 
         Returns:
-            pd.DataFrame: The data in a pandas DataFrame.
+            str: The string-based representation of a pandas DataFrame.
         """
         return repr(self.data)
 

From ac734ca47ddefc2582c079f05931907a7fa395f3 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Tue, 25 Jun 2024 13:41:28 -0600
Subject: [PATCH 32/40] add return types for test util

---
 tests/utils.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tests/utils.py b/tests/utils.py
index c3abfc3..a3d6373 100644
--- a/tests/utils.py
+++ b/tests/utils.py
@@ -3,9 +3,10 @@
 """
 
 import subprocess
+from typing import Tuple
 
 
-def run_cli_command(command: str):
+def run_cli_command(command: str) -> Tuple[str, str, int]:
     """
     Run a CLI command using subprocess and capture the output and return code.
 
@@ -13,7 +14,7 @@ def run_cli_command(command: str):
         command (list): The command to run as a list of strings.
 
     Returns:
-        tuple: (stdout, stderr, returncode)
+        tuple: (str: stdout, str: stderr, int: returncode)
     """
 
     result = subprocess.run(

From 812b171a22e84c079d15a722daf8ea8f3f40d0a8 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:23:38 -0600
Subject: [PATCH 33/40] fix deps

---
 poetry.lock    | 171 ++++++++++++++-----------------------------------
 pyproject.toml |   1 -
 2 files changed, 47 insertions(+), 125 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 593a1ee..d12396d 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -50,92 +50,6 @@ files = [
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
 ]
 
-[[package]]
-name = "jinja2"
-version = "3.1.4"
-description = "A very fast and expressive template engine."
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "jinja2-3.1.4-py3-none-any.whl", hash = "sha256:bc5dd2abb727a5319567b7a813e6a2e7318c39f4f487cfe6c89c6f9c7d25197d"},
-    {file = "jinja2-3.1.4.tar.gz", hash = "sha256:4a3aee7acbbe7303aede8e9648d13b8bf88a429282aa6122a993f0ac800cb369"},
-]
-
-[package.dependencies]
-MarkupSafe = ">=2.0"
-
-[package.extras]
-i18n = ["Babel (>=2.7)"]
-
-[[package]]
-name = "markupsafe"
-version = "2.1.5"
-description = "Safely add untrusted strings to HTML/XML markup."
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "MarkupSafe-2.1.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a17a92de5231666cfbe003f0e4b9b3a7ae3afb1ec2845aadc2bacc93ff85febc"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:72b6be590cc35924b02c78ef34b467da4ba07e4e0f0454a2c5907f473fc50ce5"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e61659ba32cf2cf1481e575d0462554625196a1f2fc06a1c777d3f48e8865d46"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2174c595a0d73a3080ca3257b40096db99799265e1c27cc5a610743acd86d62f"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae2ad8ae6ebee9d2d94b17fb62763125f3f374c25618198f40cbb8b525411900"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:075202fa5b72c86ad32dc7d0b56024ebdbcf2048c0ba09f1cde31bfdd57bcfff"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:598e3276b64aff0e7b3451b72e94fa3c238d452e7ddcd893c3ab324717456bad"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fce659a462a1be54d2ffcacea5e3ba2d74daa74f30f5f143fe0c58636e355fdd"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-win32.whl", hash = "sha256:d9fad5155d72433c921b782e58892377c44bd6252b5af2f67f16b194987338a4"},
-    {file = "MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl", hash = "sha256:bf50cd79a75d181c9181df03572cdce0fbb75cc353bc350712073108cba98de5"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:629ddd2ca402ae6dbedfceeba9c46d5f7b2a61d9749597d4307f943ef198fc1f"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5b7b716f97b52c5a14bffdf688f971b2d5ef4029127f1ad7a513973cfd818df2"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ec585f69cec0aa07d945b20805be741395e28ac1627333b1c5b0105962ffced"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b91c037585eba9095565a3556f611e3cbfaa42ca1e865f7b8015fe5c7336d5a5"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7502934a33b54030eaf1194c21c692a534196063db72176b0c4028e140f8f32c"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0e397ac966fdf721b2c528cf028494e86172b4feba51d65f81ffd65c63798f3f"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c061bb86a71b42465156a3ee7bd58c8c2ceacdbeb95d05a99893e08b8467359a"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3a57fdd7ce31c7ff06cdfbf31dafa96cc533c21e443d57f5b1ecc6cdc668ec7f"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-win32.whl", hash = "sha256:397081c1a0bfb5124355710fe79478cdbeb39626492b15d399526ae53422b906"},
-    {file = "MarkupSafe-2.1.5-cp311-cp311-win_amd64.whl", hash = "sha256:2b7c57a4dfc4f16f7142221afe5ba4e093e09e728ca65c51f5620c9aaeb9a617"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:8dec4936e9c3100156f8a2dc89c4b88d5c435175ff03413b443469c7c8c5f4d1"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:3c6b973f22eb18a789b1460b4b91bf04ae3f0c4234a0a6aa6b0a92f6f7b951d4"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ac07bad82163452a6884fe8fa0963fb98c2346ba78d779ec06bd7a6262132aee"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5dfb42c4604dddc8e4305050aa6deb084540643ed5804d7455b5df8fe16f5e5"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ea3d8a3d18833cf4304cd2fc9cbb1efe188ca9b5efef2bdac7adc20594a0e46b"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d050b3361367a06d752db6ead6e7edeb0009be66bc3bae0ee9d97fb326badc2a"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bec0a414d016ac1a18862a519e54b2fd0fc8bbfd6890376898a6c0891dd82e9f"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:58c98fee265677f63a4385256a6d7683ab1832f3ddd1e66fe948d5880c21a169"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-win32.whl", hash = "sha256:8590b4ae07a35970728874632fed7bd57b26b0102df2d2b233b6d9d82f6c62ad"},
-    {file = "MarkupSafe-2.1.5-cp312-cp312-win_amd64.whl", hash = "sha256:823b65d8706e32ad2df51ed89496147a42a2a6e01c13cfb6ffb8b1e92bc910bb"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c8b29db45f8fe46ad280a7294f5c3ec36dbac9491f2d1c17345be8e69cc5928f"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec6a563cff360b50eed26f13adc43e61bc0c04d94b8be985e6fb24b81f6dcfdf"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a549b9c31bec33820e885335b451286e2969a2d9e24879f83fe904a5ce59d70a"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4f11aa001c540f62c6166c7726f71f7573b52c68c31f014c25cc7901deea0b52"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7b2e5a267c855eea6b4283940daa6e88a285f5f2a67f2220203786dfa59b37e9"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:2d2d793e36e230fd32babe143b04cec8a8b3eb8a3122d2aceb4a371e6b09b8df"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ce409136744f6521e39fd8e2a24c53fa18ad67aa5bc7c2cf83645cce5b5c4e50"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-win32.whl", hash = "sha256:4096e9de5c6fdf43fb4f04c26fb114f61ef0bf2e5604b6ee3019d51b69e8c371"},
-    {file = "MarkupSafe-2.1.5-cp37-cp37m-win_amd64.whl", hash = "sha256:4275d846e41ecefa46e2015117a9f491e57a71ddd59bbead77e904dc02b1bed2"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:656f7526c69fac7f600bd1f400991cc282b417d17539a1b228617081106feb4a"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:97cafb1f3cbcd3fd2b6fbfb99ae11cdb14deea0736fc2b0952ee177f2b813a46"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f3fbcb7ef1f16e48246f704ab79d79da8a46891e2da03f8783a5b6fa41a9532"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fa9db3f79de01457b03d4f01b34cf91bc0048eb2c3846ff26f66687c2f6d16ab"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffee1f21e5ef0d712f9033568f8344d5da8cc2869dbd08d87c84656e6a2d2f68"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5dedb4db619ba5a2787a94d877bc8ffc0566f92a01c0ef214865e54ecc9ee5e0"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:30b600cf0a7ac9234b2638fbc0fb6158ba5bdcdf46aeb631ead21248b9affbc4"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8dd717634f5a044f860435c1d8c16a270ddf0ef8588d4887037c5028b859b0c3"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-win32.whl", hash = "sha256:daa4ee5a243f0f20d528d939d06670a298dd39b1ad5f8a72a4275124a7819eff"},
-    {file = "MarkupSafe-2.1.5-cp38-cp38-win_amd64.whl", hash = "sha256:619bc166c4f2de5caa5a633b8b7326fbe98e0ccbfacabd87268a2b15ff73a029"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7a68b554d356a91cce1236aa7682dc01df0edba8d043fd1ce607c49dd3c1edcf"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:db0b55e0f3cc0be60c1f19efdde9a637c32740486004f20d1cff53c3c0ece4d2"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e53af139f8579a6d5f7b76549125f0d94d7e630761a2111bc431fd820e163b8"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:17b950fccb810b3293638215058e432159d2b71005c74371d784862b7e4683f3"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c31f53cdae6ecfa91a77820e8b151dba54ab528ba65dfd235c80b086d68a465"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bff1b4290a66b490a2f4719358c0cdcd9bafb6b8f061e45c7a2460866bf50c2e"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bc1667f8b83f48511b94671e0e441401371dfd0f0a795c7daa4a3cd1dde55bea"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5049256f536511ee3f7e1b3f87d1d1209d327e818e6ae1365e8653d7e3abb6a6"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-win32.whl", hash = "sha256:00e046b6dd71aa03a41079792f8473dc494d564611a8f89bbbd7cb93295ebdcf"},
-    {file = "MarkupSafe-2.1.5-cp39-cp39-win_amd64.whl", hash = "sha256:fa173ec60341d6bb97a89f5ea19c85c5643c1e7dedebc22f5181eb73573142c5"},
-    {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"},
-]
-
 [[package]]
 name = "numpy"
 version = "1.24.4"
@@ -175,47 +89,56 @@ files = [
 
 [[package]]
 name = "numpy"
-version = "1.26.3"
+version = "2.0.0"
 description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "numpy-1.26.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:806dd64230dbbfaca8a27faa64e2f414bf1c6622ab78cc4264f7f5f028fee3bf"},
-    {file = "numpy-1.26.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:02f98011ba4ab17f46f80f7f8f1c291ee7d855fcef0a5a98db80767a468c85cd"},
-    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6d45b3ec2faed4baca41c76617fcdcfa4f684ff7a151ce6fc78ad3b6e85af0a6"},
-    {file = "numpy-1.26.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bdd2b45bf079d9ad90377048e2747a0c82351989a2165821f0c96831b4a2a54b"},
-    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:211ddd1e94817ed2d175b60b6374120244a4dd2287f4ece45d49228b4d529178"},
-    {file = "numpy-1.26.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b1240f767f69d7c4c8a29adde2310b871153df9b26b5cb2b54a561ac85146485"},
-    {file = "numpy-1.26.3-cp310-cp310-win32.whl", hash = "sha256:21a9484e75ad018974a2fdaa216524d64ed4212e418e0a551a2d83403b0531d3"},
-    {file = "numpy-1.26.3-cp310-cp310-win_amd64.whl", hash = "sha256:9e1591f6ae98bcfac2a4bbf9221c0b92ab49762228f38287f6eeb5f3f55905ce"},
-    {file = "numpy-1.26.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b831295e5472954104ecb46cd98c08b98b49c69fdb7040483aff799a755a7374"},
-    {file = "numpy-1.26.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9e87562b91f68dd8b1c39149d0323b42e0082db7ddb8e934ab4c292094d575d6"},
-    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c66d6fec467e8c0f975818c1796d25c53521124b7cfb760114be0abad53a0a2"},
-    {file = "numpy-1.26.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f25e2811a9c932e43943a2615e65fc487a0b6b49218899e62e426e7f0a57eeda"},
-    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:af36e0aa45e25c9f57bf684b1175e59ea05d9a7d3e8e87b7ae1a1da246f2767e"},
-    {file = "numpy-1.26.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:51c7f1b344f302067b02e0f5b5d2daa9ed4a721cf49f070280ac202738ea7f00"},
-    {file = "numpy-1.26.3-cp311-cp311-win32.whl", hash = "sha256:7ca4f24341df071877849eb2034948459ce3a07915c2734f1abb4018d9c49d7b"},
-    {file = "numpy-1.26.3-cp311-cp311-win_amd64.whl", hash = "sha256:39763aee6dfdd4878032361b30b2b12593fb445ddb66bbac802e2113eb8a6ac4"},
-    {file = "numpy-1.26.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a7081fd19a6d573e1a05e600c82a1c421011db7935ed0d5c483e9dd96b99cf13"},
-    {file = "numpy-1.26.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:12c70ac274b32bc00c7f61b515126c9205323703abb99cd41836e8125ea0043e"},
-    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f784e13e598e9594750b2ef6729bcd5a47f6cfe4a12cca13def35e06d8163e3"},
-    {file = "numpy-1.26.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f24750ef94d56ce6e33e4019a8a4d68cfdb1ef661a52cdaee628a56d2437419"},
-    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:77810ef29e0fb1d289d225cabb9ee6cf4d11978a00bb99f7f8ec2132a84e0166"},
-    {file = "numpy-1.26.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8ed07a90f5450d99dad60d3799f9c03c6566709bd53b497eb9ccad9a55867f36"},
-    {file = "numpy-1.26.3-cp312-cp312-win32.whl", hash = "sha256:f73497e8c38295aaa4741bdfa4fda1a5aedda5473074369eca10626835445511"},
-    {file = "numpy-1.26.3-cp312-cp312-win_amd64.whl", hash = "sha256:da4b0c6c699a0ad73c810736303f7fbae483bcb012e38d7eb06a5e3b432c981b"},
-    {file = "numpy-1.26.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1666f634cb3c80ccbd77ec97bc17337718f56d6658acf5d3b906ca03e90ce87f"},
-    {file = "numpy-1.26.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:18c3319a7d39b2c6a9e3bb75aab2304ab79a811ac0168a671a62e6346c29b03f"},
-    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b7e807d6888da0db6e7e75838444d62495e2b588b99e90dd80c3459594e857b"},
-    {file = "numpy-1.26.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4d362e17bcb0011738c2d83e0a65ea8ce627057b2fdda37678f4374a382a137"},
-    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b8c275f0ae90069496068c714387b4a0eba5d531aace269559ff2b43655edd58"},
-    {file = "numpy-1.26.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:cc0743f0302b94f397a4a65a660d4cd24267439eb16493fb3caad2e4389bccbb"},
-    {file = "numpy-1.26.3-cp39-cp39-win32.whl", hash = "sha256:9bc6d1a7f8cedd519c4b7b1156d98e051b726bf160715b769106661d567b3f03"},
-    {file = "numpy-1.26.3-cp39-cp39-win_amd64.whl", hash = "sha256:867e3644e208c8922a3be26fc6bbf112a035f50f0a86497f98f228c50c607bb2"},
-    {file = "numpy-1.26.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3c67423b3703f8fbd90f5adaa37f85b5794d3366948efe9a5190a5f3a83fc34e"},
-    {file = "numpy-1.26.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:46f47ee566d98849323f01b349d58f2557f02167ee301e5e28809a8c0e27a2d0"},
-    {file = "numpy-1.26.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a8474703bffc65ca15853d5fd4d06b18138ae90c17c8d12169968e998e448bb5"},
-    {file = "numpy-1.26.3.tar.gz", hash = "sha256:697df43e2b6310ecc9d95f05d5ef20eacc09c7c4ecc9da3f235d39e71b7da1e4"},
+    {file = "numpy-2.0.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:04494f6ec467ccb5369d1808570ae55f6ed9b5809d7f035059000a37b8d7e86f"},
+    {file = "numpy-2.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2635dbd200c2d6faf2ef9a0d04f0ecc6b13b3cad54f7c67c61155138835515d2"},
+    {file = "numpy-2.0.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:0a43f0974d501842866cc83471bdb0116ba0dffdbaac33ec05e6afed5b615238"},
+    {file = "numpy-2.0.0-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:8d83bb187fb647643bd56e1ae43f273c7f4dbcdf94550d7938cfc32566756514"},
+    {file = "numpy-2.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79e843d186c8fb1b102bef3e2bc35ef81160ffef3194646a7fdd6a73c6b97196"},
+    {file = "numpy-2.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d7696c615765091cc5093f76fd1fa069870304beaccfd58b5dcc69e55ef49c1"},
+    {file = "numpy-2.0.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b4c76e3d4c56f145d41b7b6751255feefae92edbc9a61e1758a98204200f30fc"},
+    {file = "numpy-2.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:acd3a644e4807e73b4e1867b769fbf1ce8c5d80e7caaef0d90dcdc640dfc9787"},
+    {file = "numpy-2.0.0-cp310-cp310-win32.whl", hash = "sha256:cee6cc0584f71adefe2c908856ccc98702baf95ff80092e4ca46061538a2ba98"},
+    {file = "numpy-2.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:ed08d2703b5972ec736451b818c2eb9da80d66c3e84aed1deeb0c345fefe461b"},
+    {file = "numpy-2.0.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ad0c86f3455fbd0de6c31a3056eb822fc939f81b1618f10ff3406971893b62a5"},
+    {file = "numpy-2.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e7f387600d424f91576af20518334df3d97bc76a300a755f9a8d6e4f5cadd289"},
+    {file = "numpy-2.0.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:34f003cb88b1ba38cb9a9a4a3161c1604973d7f9d5552c38bc2f04f829536609"},
+    {file = "numpy-2.0.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:b6f6a8f45d0313db07d6d1d37bd0b112f887e1369758a5419c0370ba915b3871"},
+    {file = "numpy-2.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f64641b42b2429f56ee08b4f427a4d2daf916ec59686061de751a55aafa22e4"},
+    {file = "numpy-2.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7039a136017eaa92c1848152827e1424701532ca8e8967fe480fe1569dae581"},
+    {file = "numpy-2.0.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:46e161722e0f619749d1cd892167039015b2c2817296104487cd03ed4a955995"},
+    {file = "numpy-2.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0e50842b2295ba8414c8c1d9d957083d5dfe9e16828b37de883f51fc53c4016f"},
+    {file = "numpy-2.0.0-cp311-cp311-win32.whl", hash = "sha256:2ce46fd0b8a0c947ae047d222f7136fc4d55538741373107574271bc00e20e8f"},
+    {file = "numpy-2.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:fbd6acc766814ea6443628f4e6751d0da6593dae29c08c0b2606164db026970c"},
+    {file = "numpy-2.0.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:354f373279768fa5a584bac997de6a6c9bc535c482592d7a813bb0c09be6c76f"},
+    {file = "numpy-2.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4d2f62e55a4cd9c58c1d9a1c9edaedcd857a73cb6fda875bf79093f9d9086f85"},
+    {file = "numpy-2.0.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:1e72728e7501a450288fc8e1f9ebc73d90cfd4671ebbd631f3e7857c39bd16f2"},
+    {file = "numpy-2.0.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:84554fc53daa8f6abf8e8a66e076aff6ece62de68523d9f665f32d2fc50fd66e"},
+    {file = "numpy-2.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c73aafd1afca80afecb22718f8700b40ac7cab927b8abab3c3e337d70e10e5a2"},
+    {file = "numpy-2.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:49d9f7d256fbc804391a7f72d4a617302b1afac1112fac19b6c6cec63fe7fe8a"},
+    {file = "numpy-2.0.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:0ec84b9ba0654f3b962802edc91424331f423dcf5d5f926676e0150789cb3d95"},
+    {file = "numpy-2.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:feff59f27338135776f6d4e2ec7aeeac5d5f7a08a83e80869121ef8164b74af9"},
+    {file = "numpy-2.0.0-cp312-cp312-win32.whl", hash = "sha256:c5a59996dc61835133b56a32ebe4ef3740ea5bc19b3983ac60cc32be5a665d54"},
+    {file = "numpy-2.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:a356364941fb0593bb899a1076b92dfa2029f6f5b8ba88a14fd0984aaf76d0df"},
+    {file = "numpy-2.0.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e61155fae27570692ad1d327e81c6cf27d535a5d7ef97648a17d922224b216de"},
+    {file = "numpy-2.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4554eb96f0fd263041baf16cf0881b3f5dafae7a59b1049acb9540c4d57bc8cb"},
+    {file = "numpy-2.0.0-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:903703372d46bce88b6920a0cd86c3ad82dae2dbef157b5fc01b70ea1cfc430f"},
+    {file = "numpy-2.0.0-cp39-cp39-macosx_14_0_x86_64.whl", hash = "sha256:3e8e01233d57639b2e30966c63d36fcea099d17c53bf424d77f088b0f4babd86"},
+    {file = "numpy-2.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1cde1753efe513705a0c6d28f5884e22bdc30438bf0085c5c486cdaff40cd67a"},
+    {file = "numpy-2.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:821eedb7165ead9eebdb569986968b541f9908979c2da8a4967ecac4439bae3d"},
+    {file = "numpy-2.0.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9a1712c015831da583b21c5bfe15e8684137097969c6d22e8316ba66b5baabe4"},
+    {file = "numpy-2.0.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:9c27f0946a3536403efb0e1c28def1ae6730a72cd0d5878db38824855e3afc44"},
+    {file = "numpy-2.0.0-cp39-cp39-win32.whl", hash = "sha256:63b92c512d9dbcc37f9d81b123dec99fdb318ba38c8059afc78086fe73820275"},
+    {file = "numpy-2.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:3f6bed7f840d44c08ebdb73b1825282b801799e325bcbdfa6bc5c370e5aecc65"},
+    {file = "numpy-2.0.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9416a5c2e92ace094e9f0082c5fd473502c91651fb896bc17690d6fc475128d6"},
+    {file = "numpy-2.0.0-pp39-pypy39_pp73-macosx_14_0_x86_64.whl", hash = "sha256:17067d097ed036636fa79f6a869ac26df7db1ba22039d962422506640314933a"},
+    {file = "numpy-2.0.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:38ecb5b0582cd125f67a629072fed6f83562d9dd04d7e03256c9829bdec027ad"},
+    {file = "numpy-2.0.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:cef04d068f5fb0518a77857953193b6bb94809a806bd0a14983a8f12ada060c9"},
+    {file = "numpy-2.0.0.tar.gz", hash = "sha256:cf5d1c9e6837f8af9f92b6bd3e86d513cdc11f60fd62185cc49ec7d1aba34864"},
 ]
 
 [[package]]
@@ -665,4 +588,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8,<3.13"
-content-hash = "097ed443c49a9a397d357d315b58cd467ca0e90047f8c624b77a3d4569c14ef2"
+content-hash = "d905f4221fc9dac67766e214aa716fafe85597c04a86494d3bdbbefb70f04fbf"
diff --git a/pyproject.toml b/pyproject.toml
index b6dbb5b..f99302b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -20,7 +20,6 @@ scipy = [
 pyarrow = "^16.0.0"
 pyyaml = "^6.0.1"
 fire = "^0.6.0"
-jinja2 = "^3.1.4"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.2.0"

From 2e18455e13723f28b000e485302157e3f9acd0ee Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:25:42 -0600
Subject: [PATCH 34/40] add to docs on exports

---
 src/cosmicqc/analyze.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
index eb54de7..4c649e4 100644
--- a/src/cosmicqc/analyze.py
+++ b/src/cosmicqc/analyze.py
@@ -53,6 +53,7 @@ def identify_outliers(
         export_path: Optional[str] = None
             An optional path to export the data using SCDataFrame export
             capabilities. If None no export is performed.
+            Note: compatible exports are CSV's, TSV's, and parquet.
 
     Returns:
         Union[pd.Series, pd.DataFrame]:
@@ -153,6 +154,7 @@ def find_outliers(
         export_path: Optional[str] = None
             An optional path to export the data using SCDataFrame export
             capabilities. If None no export is performed.
+            Note: compatible exports are CSV's, TSV's, and parquet.
 
     Returns:
         pd.DataFrame:
@@ -230,6 +232,7 @@ def label_outliers(
             export_path: Optional[str] = None
                 An optional path to export the data using SCDataFrame export
                 capabilities. If None no export is performed.
+                Note: compatible exports are CSV's, TSV's, and parquet.
 
         Returns:
             pd.DataFrame:

From 273acf1f52f46db0b14cb6838200377f4e6d99fb Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:38:12 -0600
Subject: [PATCH 35/40] add docs for context

---
 src/cosmicqc/cli.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index b290ef1..ec306f2 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -15,6 +15,7 @@
 from . import analyze
 
 
+# used to avoid bugs with python-fire and pandas string-based repr compatibility.
 # referenced from https://github.com/google/python-fire/pull/446
 # to be removed after python-fire merges changes (uncertain of timeline)
 def HasCustomRepr(component: object) -> bool:
@@ -35,11 +36,10 @@ def HasCustomRepr(component: object) -> bool:
             return True
     return False
 
-
+# used to avoid bugs with python-fire and pandas string-based repr compatibility.
 # referenced with modifications from https://github.com/google/python-fire/pull/446
 # to be removed after python-fire merges changes (uncertain of timeline)
-# ruff: noqa: C901
-def _PrintResult(
+def _PrintResult( # noqa: C901
     component_trace: FireTrace, verbose: bool = False, serialize: Optional[bool] = None
 ) -> None:
     """Prints the result of the Fire call to stdout in a human readable way."""

From 77c27e138ba5942c6774a67e482cc42cbbc3d725 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:39:20 -0600
Subject: [PATCH 36/40] note about ignore rule

---
 src/cosmicqc/cli.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index ec306f2..9713789 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -36,10 +36,12 @@ def HasCustomRepr(component: object) -> bool:
             return True
     return False
 
+
 # used to avoid bugs with python-fire and pandas string-based repr compatibility.
 # referenced with modifications from https://github.com/google/python-fire/pull/446
 # to be removed after python-fire merges changes (uncertain of timeline)
-def _PrintResult( # noqa: C901
+# ignore rule below added to help avoid triggering ruff linting checks on temporary fix.
+def _PrintResult(  # noqa: C901
     component_trace: FireTrace, verbose: bool = False, serialize: Optional[bool] = None
 ) -> None:
     """Prints the result of the Fire call to stdout in a human readable way."""

From 4d57177ff61da2d76611efa719a9531c5c28e889 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:39:46 -0600
Subject: [PATCH 37/40] remove todo

---
 src/cosmicqc/cli.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index 9713789..1fd7599 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -45,8 +45,6 @@ def _PrintResult(  # noqa: C901
     component_trace: FireTrace, verbose: bool = False, serialize: Optional[bool] = None
 ) -> None:
     """Prints the result of the Fire call to stdout in a human readable way."""
-    # TODO(dbieber): Design human readable deserializable serialization method
-    # and move serialization to its own module.
     result = component_trace.GetResult()
     # Allow users to modify the return value of the component and provide
     # custom formatting.

From 1900c65a9f34378923c809cc5029ab84544728b5 Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:43:01 -0600
Subject: [PATCH 38/40] minor comment about display

---
 src/cosmicqc/cli.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/cosmicqc/cli.py b/src/cosmicqc/cli.py
index 1fd7599..e0d0a51 100644
--- a/src/cosmicqc/cli.py
+++ b/src/cosmicqc/cli.py
@@ -82,6 +82,7 @@ def _PrintResult(  # noqa: C901
     else:
         help_text = helptext.HelpText(result, trace=component_trace, verbose=verbose)
         output = [help_text]
+        # used for displaying output through python-fire
         Display(output, out=sys.stdout)
 
 

From 0a46f408ea2423b412882959764c6057b29662bd Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:43:44 -0600
Subject: [PATCH 39/40] retain code comment

---
 src/cosmicqc/scdataframe.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/cosmicqc/scdataframe.py b/src/cosmicqc/scdataframe.py
index 32f60a3..177683a 100644
--- a/src/cosmicqc/scdataframe.py
+++ b/src/cosmicqc/scdataframe.py
@@ -77,7 +77,7 @@ def __init__(
             self.data = pd.DataFrame(data)
 
         elif isinstance(data, (pathlib.Path, str)):
-            # if the data is a string, remember the original source
+            # if the data is a string or a pathlib path, remember the original source
             # through a data_source attr
             self.data_source = data
 

From 5d5257bae935d444808a10a98633d22d29df8d7a Mon Sep 17 00:00:00 2001
From: d33bs <dave.bunten@cuanschutz.edu>
Date: Wed, 26 Jun 2024 15:45:04 -0600
Subject: [PATCH 40/40] correct code comment

---
 tests/test_cli.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_cli.py b/tests/test_cli.py
index 95b1151..622bd7e 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -11,7 +11,7 @@
 
 def test_cli_util():
     """
-    Test the `identify_outliers` function of the CLI.
+    Test the run_cli_command for successful output
     """
 
     command = """echo 'hello world'"""