From 028451efaee0a3f5c2de0df0f74f37e3426a4b0f Mon Sep 17 00:00:00 2001 From: Fabiana Clemente Date: Tue, 7 May 2024 08:56:55 -0700 Subject: [PATCH 1/8] fix: class exception --- src/ydata_profiling/model/description.py | 2 +- src/ydata_profiling/profile_report.py | 3 ++- src/ydata_profiling/utils/common.py | 11 ++++++----- src/ydata_profiling/utils/logger.py | 7 ------- 4 files changed, 9 insertions(+), 14 deletions(-) diff --git a/src/ydata_profiling/model/description.py b/src/ydata_profiling/model/description.py index c738ec1c7..6c386704e 100644 --- a/src/ydata_profiling/model/description.py +++ b/src/ydata_profiling/model/description.py @@ -37,7 +37,7 @@ def duration(self) -> Union[timedelta, List[timedelta]]: for i in range(len(self.date_start)) ] else: - raise ValueError() + raise TypeError() @dataclass diff --git a/src/ydata_profiling/profile_report.py b/src/ydata_profiling/profile_report.py index 2d5cc9bfd..d18834f52 100644 --- a/src/ydata_profiling/profile_report.py +++ b/src/ydata_profiling/profile_report.py @@ -95,7 +95,8 @@ def __init__( Args: df: a pandas or spark.sql DataFrame minimal: minimal mode is a default configuration with minimal computation - ts_mode: activates time-series analysis for all the numerical variables from the dataset. Only available for pd.DataFrame + ts_mode: activates time-series analysis for all the numerical variables from the dataset. + Only available for pd.DataFrame sort_by: ignored if ts_mode=False. Order the dataset by a provided column. sensitive: hides the values for categorical and text variables for report privacy config_file: a config file (.yml), mutually exclusive with `minimal` diff --git a/src/ydata_profiling/utils/common.py b/src/ydata_profiling/utils/common.py index 92dce9c70..6d223e022 100644 --- a/src/ydata_profiling/utils/common.py +++ b/src/ydata_profiling/utils/common.py @@ -1,4 +1,6 @@ """Common util functions (e.g. missing in Python).""" +import contextlib + import collections.abc import os import platform @@ -96,12 +98,12 @@ def convert_timestamp_to_datetime(timestamp: int) -> datetime: else: return datetime(1970, 1, 1) + timedelta(seconds=int(timestamp)) - -def analytics_features(dataframe, datatype: bool, report_type: bool): +def analytics_features(dataframe, datatype: str, report_type: str): endpoint = "https://packages.ydata.ai/ydata-profiling?" if os.getenv("YDATA_PROFILING_NO_ANALYTICS") != True: package_version = __version__ + try: subprocess.check_output("nvidia-smi") gpu_present = True @@ -110,7 +112,7 @@ def analytics_features(dataframe, datatype: bool, report_type: bool): python_version = ".".join(platform.python_version().split(".")[:2]) - try: + with contextlib.suppress(Exception): request_message = ( f"{endpoint}version={package_version}" f"&python_version={python_version}" @@ -122,5 +124,4 @@ def analytics_features(dataframe, datatype: bool, report_type: bool): ) requests.get(request_message) - except Exception: - pass + diff --git a/src/ydata_profiling/utils/logger.py b/src/ydata_profiling/utils/logger.py index dc70c3208..ed90e7ab7 100644 --- a/src/ydata_profiling/utils/logger.py +++ b/src/ydata_profiling/utils/logger.py @@ -8,17 +8,10 @@ from ydata_profiling.utils.common import analytics_features - class ProfilingLogger(logging.Logger): def __init__(self, name, level=logging.INFO): super().__init__(name, level) - def info( - self, - msg: object, - ) -> None: - super().info(f"[PROFILING] - {msg}.") - def info_def_report(self, dataframe, timeseries: bool): if dataframe == pd.DataFrame: dataframe = "pandas" From 4500592c8cd0a5acf0d84dab09e68c76cf87d107 Mon Sep 17 00:00:00 2001 From: Azory YData Bot Date: Tue, 7 May 2024 16:01:47 +0000 Subject: [PATCH 2/8] fix(linting): code formatting --- src/ydata_profiling/profile_report.py | 10 +++++----- src/ydata_profiling/utils/common.py | 5 ++--- src/ydata_profiling/utils/logger.py | 1 + 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/src/ydata_profiling/profile_report.py b/src/ydata_profiling/profile_report.py index d18834f52..ac8a73e2b 100644 --- a/src/ydata_profiling/profile_report.py +++ b/src/ydata_profiling/profile_report.py @@ -44,11 +44,10 @@ ) from ydata_profiling.serialize_report import SerializeReport from ydata_profiling.utils.dataframe import hash_dataframe -from ydata_profiling.utils.paths import get_config - from ydata_profiling.utils.logger import ProfilingLogger +from ydata_profiling.utils.paths import get_config -logger = ProfilingLogger(name='ReportLogger') +logger = ProfilingLogger(name="ReportLogger") @typechecked @@ -205,8 +204,9 @@ def __initialize_dataframe( df: Optional[Union[pd.DataFrame, sDataFrame]], report_config: Settings ) -> Optional[Union[pd.DataFrame, sDataFrame]]: - logger.info_def_report(dataframe=type(df), - timeseries=report_config.vars.timeseries.active) + logger.info_def_report( + dataframe=type(df), timeseries=report_config.vars.timeseries.active + ) if ( df is not None diff --git a/src/ydata_profiling/utils/common.py b/src/ydata_profiling/utils/common.py index 6d223e022..420a545b3 100644 --- a/src/ydata_profiling/utils/common.py +++ b/src/ydata_profiling/utils/common.py @@ -1,7 +1,6 @@ """Common util functions (e.g. missing in Python).""" -import contextlib - import collections.abc +import contextlib import os import platform import subprocess @@ -98,6 +97,7 @@ def convert_timestamp_to_datetime(timestamp: int) -> datetime: else: return datetime(1970, 1, 1) + timedelta(seconds=int(timestamp)) + def analytics_features(dataframe, datatype: str, report_type: str): endpoint = "https://packages.ydata.ai/ydata-profiling?" @@ -124,4 +124,3 @@ def analytics_features(dataframe, datatype: str, report_type: str): ) requests.get(request_message) - diff --git a/src/ydata_profiling/utils/logger.py b/src/ydata_profiling/utils/logger.py index ed90e7ab7..de0618f16 100644 --- a/src/ydata_profiling/utils/logger.py +++ b/src/ydata_profiling/utils/logger.py @@ -8,6 +8,7 @@ from ydata_profiling.utils.common import analytics_features + class ProfilingLogger(logging.Logger): def __init__(self, name, level=logging.INFO): super().__init__(name, level) From 43db959e7d17efdd4c3a037d1030f4d530e5f14a Mon Sep 17 00:00:00 2001 From: Fabiana Clemente Date: Tue, 7 May 2024 09:35:30 -0700 Subject: [PATCH 3/8] fix: linter recommendations update --- src/ydata_profiling/utils/common.py | 4 ++-- src/ydata_profiling/utils/logger.py | 4 ++-- src/ydata_profiling/visualisation/plot.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/src/ydata_profiling/utils/common.py b/src/ydata_profiling/utils/common.py index 420a545b3..7dc217084 100644 --- a/src/ydata_profiling/utils/common.py +++ b/src/ydata_profiling/utils/common.py @@ -98,10 +98,10 @@ def convert_timestamp_to_datetime(timestamp: int) -> datetime: return datetime(1970, 1, 1) + timedelta(seconds=int(timestamp)) -def analytics_features(dataframe, datatype: str, report_type: str): +def analytics_features(dataframe: str, datatype: str, report_type: str) -> None: endpoint = "https://packages.ydata.ai/ydata-profiling?" - if os.getenv("YDATA_PROFILING_NO_ANALYTICS") != True: + if bool(os.getenv("YDATA_PROFILING_NO_ANALYTICS")) is not True: package_version = __version__ try: diff --git a/src/ydata_profiling/utils/logger.py b/src/ydata_profiling/utils/logger.py index de0618f16..fc33f2297 100644 --- a/src/ydata_profiling/utils/logger.py +++ b/src/ydata_profiling/utils/logger.py @@ -14,10 +14,10 @@ def __init__(self, name, level=logging.INFO): super().__init__(name, level) def info_def_report(self, dataframe, timeseries: bool): - if dataframe == pd.DataFrame: + if dataframe is pd.DataFrame: dataframe = "pandas" report_type = "regular" - elif dataframe == type(None): + elif dataframe is type(None): dataframe = "pandas" report_type = "compare" else: diff --git a/src/ydata_profiling/visualisation/plot.py b/src/ydata_profiling/visualisation/plot.py index 88c38b98d..0a06e5937 100644 --- a/src/ydata_profiling/visualisation/plot.py +++ b/src/ydata_profiling/visualisation/plot.py @@ -743,7 +743,7 @@ def _plot_acf_pacf( for ax in axes: for item in ax.collections: - if type(item) == PolyCollection: + if type(item) is PolyCollection: item.set_facecolor(color) return plot_360_n0sc0pe(config) From e4e49f77d92ee22c1022a0aea275be2fefe4a82a Mon Sep 17 00:00:00 2001 From: Fabiana Clemente Date: Tue, 7 May 2024 10:03:10 -0700 Subject: [PATCH 4/8] chore: update readme --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 914cf6521..3c0d70051 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,7 @@ [![Release Version](https://img.shields.io/github/release/ydataai/pandas-profiling.svg)](https://github.com/ydataai/pandas-profiling/releases) [![Python Version](https://img.shields.io/pypi/pyversions/ydata-profiling)](https://pypi.org/project/ydata-profiling/) [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black) +

YData Profiling Logo

From bea0326018602abc24acb86f52966f0700c5144a Mon Sep 17 00:00:00 2001 From: Fabiana Clemente Date: Tue, 7 May 2024 10:08:50 -0700 Subject: [PATCH 5/8] chore: remove version --- src/ydata_profiling/utils/common.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/src/ydata_profiling/utils/common.py b/src/ydata_profiling/utils/common.py index 7dc217084..75ec2599c 100644 --- a/src/ydata_profiling/utils/common.py +++ b/src/ydata_profiling/utils/common.py @@ -100,10 +100,9 @@ def convert_timestamp_to_datetime(timestamp: int) -> datetime: def analytics_features(dataframe: str, datatype: str, report_type: str) -> None: endpoint = "https://packages.ydata.ai/ydata-profiling?" + package_version = __version__ - if bool(os.getenv("YDATA_PROFILING_NO_ANALYTICS")) is not True: - package_version = __version__ - + if bool(os.getenv("YDATA_PROFILING_NO_ANALYTICS")) is not True and package_version!='0.0.dev0': try: subprocess.check_output("nvidia-smi") gpu_present = True From a053f4becf6f901a99a692ee0c751e7dcdd9403c Mon Sep 17 00:00:00 2001 From: Azory YData Bot Date: Tue, 7 May 2024 17:15:41 +0000 Subject: [PATCH 6/8] fix(linting): code formatting --- src/ydata_profiling/utils/common.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/src/ydata_profiling/utils/common.py b/src/ydata_profiling/utils/common.py index 75ec2599c..0cd8d018d 100644 --- a/src/ydata_profiling/utils/common.py +++ b/src/ydata_profiling/utils/common.py @@ -102,7 +102,10 @@ def analytics_features(dataframe: str, datatype: str, report_type: str) -> None: endpoint = "https://packages.ydata.ai/ydata-profiling?" package_version = __version__ - if bool(os.getenv("YDATA_PROFILING_NO_ANALYTICS")) is not True and package_version!='0.0.dev0': + if ( + bool(os.getenv("YDATA_PROFILING_NO_ANALYTICS")) is not True + and package_version != "0.0.dev0" + ): try: subprocess.check_output("nvidia-smi") gpu_present = True From 004f2bf7f4617f4693d642807ab672427ea417f0 Mon Sep 17 00:00:00 2001 From: Fabiana Clemente Date: Tue, 7 May 2024 10:19:12 -0700 Subject: [PATCH 7/8] docs: add new link to docs --- docs/index.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/index.md b/docs/index.md index af0fa4271..344597293 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,5 +1,6 @@ # Welcome + Data quality profiling and exploratory data analysis are crucial steps in the process of Data Science and Machine Learning development. YData-profiling is a leading tool in the data understanding step of the data science workflow as a pioneering Python package. From 183925d26076b2cc5e501d0bc0ab2c1501c56dbb Mon Sep 17 00:00:00 2001 From: Fabiana Clemente Date: Tue, 7 May 2024 10:53:26 -0700 Subject: [PATCH 8/8] docs: update links in the documentation --- docs/advanced_settings/analytics.md | 2 +- docs/advanced_settings/available_settings.md | 2 ++ docs/advanced_settings/caching.md | 4 +++- docs/advanced_settings/changing_settings.md | 2 ++ docs/advanced_settings/collaborative_data_profiling.md | 2 ++ docs/features/big_data.md | 2 ++ docs/features/collaborative_data_profiling.md | 2 ++ docs/features/comparing_datasets.md | 1 + docs/features/custom_reports.md | 4 +++- docs/features/metadata.md | 2 ++ docs/features/pii_identification_management.md | 2 +- docs/features/sensitive_data.md | 4 +++- docs/features/time_series_datasets.md | 4 +++- docs/getting-started/concepts.md | 4 +++- docs/getting-started/examples.md | 2 ++ docs/getting-started/installation.md | 2 ++ docs/getting-started/quickstart.md | 2 ++ docs/integrations/bytewax.md | 4 +++- docs/integrations/great_expectations.md | 4 +++- docs/integrations/ides.md | 2 ++ docs/integrations/interactive_applications.md | 2 ++ docs/integrations/other_dataframe_libraries.md | 2 ++ docs/integrations/pipelines.md | 2 ++ docs/integrations/pyspark.md | 2 ++ docs/reference/history.md | 2 ++ docs/reference/resources.md | 2 ++ docs/support-contribution/common_issues.md | 2 ++ docs/support-contribution/contribution_guidelines.md | 2 ++ docs/support-contribution/help_troubleshoot.md | 2 ++ 29 files changed, 62 insertions(+), 9 deletions(-) diff --git a/docs/advanced_settings/analytics.md b/docs/advanced_settings/analytics.md index 39a7da16c..e21913b1d 100644 --- a/docs/advanced_settings/analytics.md +++ b/docs/advanced_settings/analytics.md @@ -39,4 +39,4 @@ Open your terminal or command prompt and set the YDATA_PROFILING_NO_ANALYTICS en os.environ['YDATA_PROFILING_NO_ANALYTICS'] = 'True' ```` - + diff --git a/docs/advanced_settings/available_settings.md b/docs/advanced_settings/available_settings.md index e03577032..ff9917958 100644 --- a/docs/advanced_settings/available_settings.md +++ b/docs/advanced_settings/available_settings.md @@ -121,3 +121,5 @@ Settings related with the interactions section. Settings related with the appearance and style of the report. {{ read_csv('./tables/config_html.csv') }} + + \ No newline at end of file diff --git a/docs/advanced_settings/caching.md b/docs/advanced_settings/caching.md index bb7547962..77d4adbbd 100644 --- a/docs/advanced_settings/caching.md +++ b/docs/advanced_settings/caching.md @@ -6,4 +6,6 @@ If you modify the configuration in-between runs, either a new ``ProfileReport`` - *rendering* to invalidate previously rendered reports (HTML, JSON or widgets) - *report* to remove the caching of the report's structure -- *None* (default) to invalidate all caches \ No newline at end of file +- *None* (default) to invalidate all caches + + \ No newline at end of file diff --git a/docs/advanced_settings/changing_settings.md b/docs/advanced_settings/changing_settings.md index 372dff383..30be08564 100644 --- a/docs/advanced_settings/changing_settings.md +++ b/docs/advanced_settings/changing_settings.md @@ -85,3 +85,5 @@ os.environ("PROFILE_TITLE")='My Custom Profiling Report' profile = ProfileReport(df) ``` + + diff --git a/docs/advanced_settings/collaborative_data_profiling.md b/docs/advanced_settings/collaborative_data_profiling.md index 44b1760c8..5c09e789e 100644 --- a/docs/advanced_settings/collaborative_data_profiling.md +++ b/docs/advanced_settings/collaborative_data_profiling.md @@ -57,3 +57,5 @@ regulatory compliance by identifying any sensitive data. Try today the Catalog experience in with [Fabric Community version](http://ydata.ai/register?utm_source=ydata-profiling&utm_medium=documentation&utm_campaign=YData%20Fabric%20Community)! + + \ No newline at end of file diff --git a/docs/features/big_data.md b/docs/features/big_data.md index ec52a7cf9..a95c2c083 100644 --- a/docs/features/big_data.md +++ b/docs/features/big_data.md @@ -1,5 +1,7 @@ # Profiling large datasets + + By default, `ydata-profiling` comprehensively summarizes the input dataset in a way that gives the most insights for data analysis. For small datasets, these computations can be performed in *quasi* diff --git a/docs/features/collaborative_data_profiling.md b/docs/features/collaborative_data_profiling.md index 2d6496493..90de5d61c 100644 --- a/docs/features/collaborative_data_profiling.md +++ b/docs/features/collaborative_data_profiling.md @@ -69,3 +69,5 @@ regulatory compliance by identifying any sensitive data. Try today the Catalog experience in with [Fabric Community version](http://ydata.ai/register?utm_source=ydata-profiling&utm_medium=documentation&utm_campaign=YData%20Fabric%20Community)! + + \ No newline at end of file diff --git a/docs/features/comparing_datasets.md b/docs/features/comparing_datasets.md index 25e9d7c2a..d55100d28 100644 --- a/docs/features/comparing_datasets.md +++ b/docs/features/comparing_datasets.md @@ -1,5 +1,6 @@ # Dataset Comparison + !!! note "Dataframes compare support" Profiling compare is supported from diff --git a/docs/features/custom_reports.md b/docs/features/custom_reports.md index 8ab4fdf64..916066dc0 100644 --- a/docs/features/custom_reports.md +++ b/docs/features/custom_reports.md @@ -89,4 +89,6 @@ Similarly, the palette for *Missing values* can be changed using ``missing`` arg ``ydata-profiling`` accepts all ``cmap`` values (colormaps) accepted by ``matplotlib``. The list of available colour maps can [be accessed here](https://matplotlib.org/stable/tutorials/colors/colormaps.html>). -Alternatively, it is possible to create [custom palettes](https://matplotlib.org/stable/gallery/color/custom_cmap.html>). \ No newline at end of file +Alternatively, it is possible to create [custom palettes](https://matplotlib.org/stable/gallery/color/custom_cmap.html>). + + \ No newline at end of file diff --git a/docs/features/metadata.md b/docs/features/metadata.md index badc4c9ae..d830d0d2d 100644 --- a/docs/features/metadata.md +++ b/docs/features/metadata.md @@ -112,3 +112,5 @@ report = ProfileReport(df, title="Titanic EDA", type_schema=type_schema) report.to_file("report.html") ``` + + diff --git a/docs/features/pii_identification_management.md b/docs/features/pii_identification_management.md index 6a630c645..b3cb55ed4 100644 --- a/docs/features/pii_identification_management.md +++ b/docs/features/pii_identification_management.md @@ -56,4 +56,4 @@ Data governance involves establishing policies and processes to ensure high data A PII management solution enhances data governance efforts by providing a centralized hub for overseeing PII classifications, metadata, and related policies. - + diff --git a/docs/features/sensitive_data.md b/docs/features/sensitive_data.md index 467ba691c..9ad80c7a6 100644 --- a/docs/features/sensitive_data.md +++ b/docs/features/sensitive_data.md @@ -59,4 +59,6 @@ help developers solve these cases, was developed. ## Automated PII classification & management -You can find more details about this feature [here](pii_identification_management.md). \ No newline at end of file +You can find more details about this feature [here](pii_identification_management.md). + + \ No newline at end of file diff --git a/docs/features/time_series_datasets.md b/docs/features/time_series_datasets.md index 213be1901..b06dc0cf6 100644 --- a/docs/features/time_series_datasets.md +++ b/docs/features/time_series_datasets.md @@ -151,4 +151,6 @@ profile = ProfileReport( profile.to_file("report_timeseries.html") ``` -For more questions and suggestions around time-series analysis reach us out at the [Data-Centric AI community](https://datacentricai.community/). \ No newline at end of file +For more questions and suggestions around time-series analysis reach us out at the [Data-Centric AI community](https://datacentricai.community/). + + \ No newline at end of file diff --git a/docs/getting-started/concepts.md b/docs/getting-started/concepts.md index 596eac2c8..aa38fcfba 100644 --- a/docs/getting-started/concepts.md +++ b/docs/getting-started/concepts.md @@ -1,4 +1,4 @@ -#Concepts +# Concepts !!! question "Text/corpus data - your input is needed!" @@ -106,3 +106,5 @@ For a quick overview of the data, ydata-profiling provides the following section - First n records of a given dataset - Last n records of a given dataset - A table containing observed duplicates (exact matches) + + \ No newline at end of file diff --git a/docs/getting-started/examples.md b/docs/getting-started/examples.md index 9aa8accc6..98ca106c1 100644 --- a/docs/getting-started/examples.md +++ b/docs/getting-started/examples.md @@ -46,3 +46,5 @@ across a wide range of dataset and data types: - [HCC](https://github.com/ydataai/ydata-profiling/tree/master/examples/hcc) (Open dataset from healthcare, showcasing compare between two sets of data, before and after preprocessing) + + diff --git a/docs/getting-started/installation.md b/docs/getting-started/installation.md index 886e89eab..9a6090518 100644 --- a/docs/getting-started/installation.md +++ b/docs/getting-started/installation.md @@ -78,3 +78,5 @@ Install these with e.g. ````console pip install -U ydata-profiling[notebook,unicode, pyspark] ```` + + \ No newline at end of file diff --git a/docs/getting-started/quickstart.md b/docs/getting-started/quickstart.md index 12afa654c..bd28fe9fd 100644 --- a/docs/getting-started/quickstart.md +++ b/docs/getting-started/quickstart.md @@ -99,3 +99,5 @@ profile = ProfileReport(df, title="Profiling Report", explorative=True) On the CLI utility `ydata_profiling`, this mode can be activated with the `-e` flag. Learn more about configuring `ydata-profiling` on the `../advanced_usage/available_settings`{.interpreted-text role="doc"}. + + \ No newline at end of file diff --git a/docs/integrations/bytewax.md b/docs/integrations/bytewax.md index 622584cf7..783e9dbae 100644 --- a/docs/integrations/bytewax.md +++ b/docs/integrations/bytewax.md @@ -185,4 +185,6 @@ comparison_report.to_file("comparison_report.html") Now you're all set to start exploring your data streams! Bytewax takes care of all the processes necessary to handle and structure data streams into snapshots, which can then be summarized and compared with -ydata-profiling through a comprehensive report of data characteristics. \ No newline at end of file +ydata-profiling through a comprehensive report of data characteristics. + + \ No newline at end of file diff --git a/docs/integrations/great_expectations.md b/docs/integrations/great_expectations.md index 6c76c19cc..8b0f0d07c 100644 --- a/docs/integrations/great_expectations.md +++ b/docs/integrations/great_expectations.md @@ -107,4 +107,6 @@ suite = profile.to_expectation_suite( See [the Great Expectations Examples](https://github.com/ydataai/ydata-profiling/blob/master/examples/features/great_expectations_example.py) -for complete examples. \ No newline at end of file +for complete examples. + + \ No newline at end of file diff --git a/docs/integrations/ides.md b/docs/integrations/ides.md index 9778a8611..e40ba6a9c 100644 --- a/docs/integrations/ides.md +++ b/docs/integrations/ides.md @@ -39,3 +39,5 @@ width="400px"} To use the PyCharm Integration, right click on any dataset file and *External Tools* \ *Data Profiling*. + + \ No newline at end of file diff --git a/docs/integrations/interactive_applications.md b/docs/integrations/interactive_applications.md index 0803a621f..53801a2e7 100644 --- a/docs/integrations/interactive_applications.md +++ b/docs/integrations/interactive_applications.md @@ -127,3 +127,5 @@ in Panel, see \`this GitHub issue \]{.title-ref}\_ and [this integration example](https://awesome-panel.org/pandas_profiling_app). + + \ No newline at end of file diff --git a/docs/integrations/other_dataframe_libraries.md b/docs/integrations/other_dataframe_libraries.md index cf79f68af..5dcf5373f 100644 --- a/docs/integrations/other_dataframe_libraries.md +++ b/docs/integrations/other_dataframe_libraries.md @@ -32,3 +32,5 @@ df = df.to_pandas_df() # Convert modin DataFrame to pandas DataFrame df = df._to_pandas() ``` + + \ No newline at end of file diff --git a/docs/integrations/pipelines.md b/docs/integrations/pipelines.md index c61b40ea0..721a54444 100644 --- a/docs/integrations/pipelines.md +++ b/docs/integrations/pipelines.md @@ -100,3 +100,5 @@ profiling_task2 = PythonOperator( There is a community created [Kedro plugin](https://github.com/BrickFrog/kedro-pandas-profiling) available. + + \ No newline at end of file diff --git a/docs/integrations/pyspark.md b/docs/integrations/pyspark.md index c2f8f3c61..1db3f4d53 100644 --- a/docs/integrations/pyspark.md +++ b/docs/integrations/pyspark.md @@ -128,3 +128,5 @@ The notebook example can be found [here](https://github.com/ydataai/ydata-profiling/tree/master/examples/integrations/databricks_example.ipynb). Stay tuned - we are going to update the documentation soon! + + \ No newline at end of file diff --git a/docs/reference/history.md b/docs/reference/history.md index 3c8b6e39d..da58ab94b 100644 --- a/docs/reference/history.md +++ b/docs/reference/history.md @@ -85,3 +85,5 @@ New features are expected, and it will be important to learn from you your needs and expectations so the future can be even brighter. Join the :fontawesome-brands-discord: [DCAI community](https://datacentricai.community/) and let us know your thoughts. + + \ No newline at end of file diff --git a/docs/reference/resources.md b/docs/reference/resources.md index bd9a73629..54169461f 100644 --- a/docs/reference/resources.md +++ b/docs/reference/resources.md @@ -112,3 +112,5 @@ Feel free to contribute it via a pull request on GitHub. (PMLB)](https://epistasislab.github.io/pmlb/) ([description](https://arxiv.org/ftp/arxiv/papers/2012/2012.00058.pdf)) - [dabl package](https://github.com/dabl/dabl) + + \ No newline at end of file diff --git a/docs/support-contribution/common_issues.md b/docs/support-contribution/common_issues.md index 77016dc91..e0235aaae 100644 --- a/docs/support-contribution/common_issues.md +++ b/docs/support-contribution/common_issues.md @@ -42,3 +42,5 @@ computation. Related StackOverflow questions: - [MemoryError when using ydata_profiling profile_report](https://stackoverflow.com/questions/67342168/memoryerror-when-using-pandas-profiling-profile-report) + + \ No newline at end of file diff --git a/docs/support-contribution/contribution_guidelines.md b/docs/support-contribution/contribution_guidelines.md index 86cab55da..4bf27e91d 100644 --- a/docs/support-contribution/contribution_guidelines.md +++ b/docs/support-contribution/contribution_guidelines.md @@ -85,3 +85,5 @@ community](https://discord.com/invite/mw7xjJ7b7s). Read more on getting involved in the [Contribution Guide available on GitHub](https://github.com/ydataai/ydata-profiling/blob/master/CONTRIBUTING.md). + + \ No newline at end of file diff --git a/docs/support-contribution/help_troubleshoot.md b/docs/support-contribution/help_troubleshoot.md index 209638f94..230927d93 100644 --- a/docs/support-contribution/help_troubleshoot.md +++ b/docs/support-contribution/help_troubleshoot.md @@ -83,3 +83,5 @@ for questions about `ydata-profiling` older versions. connect with both other users and developers that might be able to answer your questions. The **#ydata-profiling** and **#need-help** channels are recommended for questions and issues. + + \ No newline at end of file