diff --git a/pandas/tests/io/excel/test_openpyxl.py b/pandas/tests/io/excel/test_openpyxl.py index 79fc87a62ad08c..e9b4a5d4e430d0 100644 --- a/pandas/tests/io/excel/test_openpyxl.py +++ b/pandas/tests/io/excel/test_openpyxl.py @@ -1,7 +1,7 @@ import pytest from pandas import DataFrame -from pandas.util.testing import ensure_clean +import pandas.util.testing as tm from pandas.io.excel import ExcelWriter, _OpenpyxlWriter @@ -65,7 +65,7 @@ def test_write_cells_merge_styled(ext): ) ] - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: writer = _OpenpyxlWriter(path) writer.write_cells(initial_cells, sheet_name=sheet_name) writer.write_cells(merge_cells, sheet_name=sheet_name) @@ -83,7 +83,7 @@ def test_write_cells_merge_styled(ext): def test_write_append_mode(ext, mode, expected): df = DataFrame([1], columns=["baz"]) - with ensure_clean(ext) as f: + with tm.ensure_clean(ext) as f: wb = openpyxl.Workbook() wb.worksheets[0].title = "foo" wb.worksheets[0]["A1"].value = "foo" diff --git a/pandas/tests/io/excel/test_style.py b/pandas/tests/io/excel/test_style.py index 8862f85ae9ab4a..41363bf13ed4e9 100644 --- a/pandas/tests/io/excel/test_style.py +++ b/pandas/tests/io/excel/test_style.py @@ -2,7 +2,7 @@ import pytest from pandas import DataFrame -from pandas.util.testing import ensure_clean +import pandas.util.testing as tm from pandas.io.excel import ExcelWriter from pandas.io.formats.excel import ExcelFormatter @@ -70,7 +70,7 @@ def custom_converter(css): # Prepare spreadsheets df = DataFrame(np.random.randn(11, 3)) - with ensure_clean(".xlsx" if engine != "xlwt" else ".xls") as path: + with tm.ensure_clean(".xlsx" if engine != "xlwt" else ".xls") as path: writer = ExcelWriter(path, engine=engine) df.to_excel(writer, sheet_name="frame") df.style.to_excel(writer, sheet_name="unstyled") diff --git a/pandas/tests/io/excel/test_writers.py b/pandas/tests/io/excel/test_writers.py index 793f11c62f9f5f..1bc4ad3e7867ad 100644 --- a/pandas/tests/io/excel/test_writers.py +++ b/pandas/tests/io/excel/test_writers.py @@ -12,7 +12,6 @@ import pandas as pd from pandas import DataFrame, Index, MultiIndex, get_option, set_option import pandas.util.testing as tm -from pandas.util.testing import ensure_clean, makeCustomDataframe as mkdf from pandas.io.excel import ( ExcelFile, @@ -29,7 +28,7 @@ def path(ext): """ Fixture to open file for use in each test case. """ - with ensure_clean(ext) as file_path: + with tm.ensure_clean(ext) as file_path: yield file_path @@ -64,7 +63,7 @@ def test_read_one_empty_col_no_header(self, ext, header, expected): filename = "no_header" df = pd.DataFrame([["", 1, 100], ["", 2, 200], ["", 3, 300], ["", 4, 400]]) - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: df.to_excel(path, filename, index=False, header=False) result = pd.read_excel(path, filename, usecols=[0], header=header) @@ -80,7 +79,7 @@ def test_read_one_empty_col_with_header(self, ext, header, expected): filename = "with_header" df = pd.DataFrame([["", 1, 100], ["", 2, 200], ["", 3, 300], ["", 4, 400]]) - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: df.to_excel(path, "with_header", index=False, header=True) result = pd.read_excel(path, filename, usecols=[0], header=header) @@ -93,7 +92,7 @@ def test_set_column_names_in_parameter(self, ext): # keyword argument names refdf = pd.DataFrame([[1, "foo"], [2, "bar"], [3, "baz"]], columns=["a", "b"]) - with ensure_clean(ext) as pth: + with tm.ensure_clean(ext) as pth: with ExcelWriter(pth) as writer: refdf.to_excel(writer, "Data_no_head", header=False, index=False) refdf.to_excel(writer, "Data_with_head", index=False) @@ -127,7 +126,7 @@ def tdf(col_sheet_name): dfs = [tdf(s) for s in sheets] dfs = dict(zip(sheets, dfs)) - with ensure_clean(ext) as pth: + with tm.ensure_clean(ext) as pth: with ExcelWriter(pth) as ew: for sheetname, df in dfs.items(): df.to_excel(ew, sheetname) @@ -140,7 +139,7 @@ def tdf(col_sheet_name): @td.skip_if_no("xlsxwriter") def test_read_excel_multiindex_empty_level(self, ext): # see gh-12453 - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: df = DataFrame( { ("One", "x"): {0: 1}, @@ -194,7 +193,7 @@ def test_excel_multindex_roundtrip( self, ext, c_idx_names, r_idx_names, c_idx_levels, r_idx_levels ): # see gh-4679 - with ensure_clean(ext) as pth: + with tm.ensure_clean(ext) as pth: if c_idx_levels == 1 and c_idx_names: pytest.skip( "Column index name cannot be serialized unless it's a MultiIndex" @@ -204,7 +203,9 @@ def test_excel_multindex_roundtrip( # unnamed levels, not Nones. check_names = r_idx_names or r_idx_levels <= 1 - df = mkdf(5, 5, c_idx_names, r_idx_names, c_idx_levels, r_idx_levels) + df = tm.makeCustomDataframe( + 5, 5, c_idx_names, r_idx_names, c_idx_levels, r_idx_levels + ) df.to_excel(pth) act = pd.read_excel( @@ -243,7 +244,7 @@ def test_read_excel_parse_dates(self, ext): df2 = df.copy() df2["date_strings"] = df2["date_strings"].dt.strftime("%m/%d/%Y") - with ensure_clean(ext) as pth: + with tm.ensure_clean(ext) as pth: df2.to_excel(pth) res = pd.read_excel(pth, index_col=0) @@ -581,7 +582,7 @@ def test_excel_date_datetime_format(self, engine, ext, path): columns=["X", "Y"], ) - with ensure_clean(ext) as filename2: + with tm.ensure_clean(ext) as filename2: writer1 = ExcelWriter(path) writer2 = ExcelWriter( filename2, @@ -778,13 +779,13 @@ def test_to_excel_output_encoding(self, ext): columns=["X\u0193", "Y", "Z"], ) - with ensure_clean("__tmp_to_excel_float_format__." + ext) as filename: + with tm.ensure_clean("__tmp_to_excel_float_format__." + ext) as filename: df.to_excel(filename, sheet_name="TestSheet", encoding="utf8") result = pd.read_excel(filename, "TestSheet", encoding="utf8", index_col=0) tm.assert_frame_equal(result, df) def test_to_excel_unicode_filename(self, ext, path): - with ensure_clean("\u0192u." + ext) as filename: + with tm.ensure_clean("\u0192u." + ext) as filename: try: f = open(filename, "wb") except UnicodeEncodeError: @@ -932,12 +933,10 @@ def roundtrip(data, header=True, parser_hdr=0, index=True): nrows = 5 ncols = 3 - from pandas.util.testing import makeCustomDataframe as mkdf - # ensure limited functionality in 0.10 # override of gh-2370 until sorted out in 0.11 - df = mkdf( + df = tm.makeCustomDataframe( nrows, ncols, r_idx_nlevels=r_idx_nlevels, c_idx_nlevels=c_idx_nlevels ) @@ -1216,7 +1215,7 @@ class TestExcelWriterEngineTests: ], ) def test_ExcelWriter_dispatch(self, klass, ext): - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: writer = ExcelWriter(path) if ext == ".xlsx" and td.safe_import("xlsxwriter"): # xlsxwriter has preference over openpyxl if both installed diff --git a/pandas/tests/io/excel/test_xlrd.py b/pandas/tests/io/excel/test_xlrd.py index c4d99c827318de..fc36be9e1b7387 100644 --- a/pandas/tests/io/excel/test_xlrd.py +++ b/pandas/tests/io/excel/test_xlrd.py @@ -2,7 +2,6 @@ import pandas as pd import pandas.util.testing as tm -from pandas.util.testing import ensure_clean from pandas.io.excel import ExcelFile @@ -22,7 +21,7 @@ def test_read_xlrd_book(read_ext, frame): engine = "xlrd" sheet_name = "SheetA" - with ensure_clean(read_ext) as pth: + with tm.ensure_clean(read_ext) as pth: df.to_excel(pth, sheet_name) book = xlrd.open_workbook(pth) diff --git a/pandas/tests/io/excel/test_xlsxwriter.py b/pandas/tests/io/excel/test_xlsxwriter.py index 63e41c59ecb893..deb72cc2306696 100644 --- a/pandas/tests/io/excel/test_xlsxwriter.py +++ b/pandas/tests/io/excel/test_xlsxwriter.py @@ -3,7 +3,7 @@ import pytest from pandas import DataFrame -from pandas.util.testing import ensure_clean +import pandas.util.testing as tm from pandas.io.excel import ExcelWriter @@ -20,7 +20,7 @@ def test_column_format(ext): warnings.simplefilter("ignore") openpyxl = pytest.importorskip("openpyxl") - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: frame = DataFrame({"A": [123456, 123456], "B": [123456, 123456]}) writer = ExcelWriter(path) @@ -59,6 +59,6 @@ def test_column_format(ext): def test_write_append_mode_raises(ext): msg = "Append mode is not supported with xlsxwriter!" - with ensure_clean(ext) as f: + with tm.ensure_clean(ext) as f: with pytest.raises(ValueError, match=msg): ExcelWriter(f, engine="xlsxwriter", mode="a") diff --git a/pandas/tests/io/excel/test_xlwt.py b/pandas/tests/io/excel/test_xlwt.py index 51f94a2f01b849..c6af78c2704d8f 100644 --- a/pandas/tests/io/excel/test_xlwt.py +++ b/pandas/tests/io/excel/test_xlwt.py @@ -3,7 +3,7 @@ import pandas as pd from pandas import DataFrame, MultiIndex -from pandas.util.testing import ensure_clean +import pandas.util.testing as tm from pandas.io.excel import ExcelWriter, _XlwtWriter @@ -19,7 +19,7 @@ def test_excel_raise_error_on_multiindex_columns_and_no_index(ext): ) df = DataFrame(np.random.randn(10, 3), columns=cols) with pytest.raises(NotImplementedError): - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: df.to_excel(path, index=False) @@ -28,7 +28,7 @@ def test_excel_multiindex_columns_and_index_true(ext): [("site", ""), ("2014", "height"), ("2014", "weight")] ) df = pd.DataFrame(np.random.randn(10, 3), columns=cols) - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: df.to_excel(path, index=True) @@ -38,7 +38,7 @@ def test_excel_multiindex_index(ext): [("site", ""), ("2014", "height"), ("2014", "weight")] ) df = DataFrame(np.random.randn(3, 10), index=cols) - with ensure_clean(ext) as path: + with tm.ensure_clean(ext) as path: df.to_excel(path, index=False) @@ -62,6 +62,6 @@ def test_to_excel_styleconverter(ext): def test_write_append_mode_raises(ext): msg = "Append mode is not supported with xlwt!" - with ensure_clean(ext) as f: + with tm.ensure_clean(ext) as f: with pytest.raises(ValueError, match=msg): ExcelWriter(f, engine="xlwt", mode="a") diff --git a/pandas/tests/io/json/test_compression.py b/pandas/tests/io/json/test_compression.py index 56be84bccc51a0..adbb9dfbd2ddf7 100644 --- a/pandas/tests/io/json/test_compression.py +++ b/pandas/tests/io/json/test_compression.py @@ -4,7 +4,6 @@ import pandas as pd import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal def test_compression_roundtrip(compression): @@ -16,12 +15,12 @@ def test_compression_roundtrip(compression): with tm.ensure_clean() as path: df.to_json(path, compression=compression) - assert_frame_equal(df, pd.read_json(path, compression=compression)) + tm.assert_frame_equal(df, pd.read_json(path, compression=compression)) # explicitly ensure file was compressed. with tm.decompress_file(path, compression) as fh: result = fh.read().decode("utf8") - assert_frame_equal(df, pd.read_json(result)) + tm.assert_frame_equal(df, pd.read_json(result)) def test_read_zipped_json(datapath): @@ -31,7 +30,7 @@ def test_read_zipped_json(datapath): compressed_path = datapath("io", "json", "data", "tsframe_v012.json.zip") compressed_df = pd.read_json(compressed_path, compression="zip") - assert_frame_equal(uncompressed_df, compressed_df) + tm.assert_frame_equal(uncompressed_df, compressed_df) @td.skip_if_not_us_locale @@ -46,7 +45,7 @@ def test_with_s3_url(compression, s3_resource): s3_resource.Bucket("pandas-test").put_object(Key="test-1", Body=f) roundtripped_df = pd.read_json("s3://pandas-test/test-1", compression=compression) - assert_frame_equal(df, roundtripped_df) + tm.assert_frame_equal(df, roundtripped_df) def test_lines_with_compression(compression): @@ -55,7 +54,7 @@ def test_lines_with_compression(compression): df = pd.read_json('{"a": [1, 2, 3], "b": [4, 5, 6]}') df.to_json(path, orient="records", lines=True, compression=compression) roundtripped_df = pd.read_json(path, lines=True, compression=compression) - assert_frame_equal(df, roundtripped_df) + tm.assert_frame_equal(df, roundtripped_df) def test_chunksize_with_compression(compression): @@ -66,7 +65,7 @@ def test_chunksize_with_compression(compression): res = pd.read_json(path, lines=True, chunksize=1, compression=compression) roundtripped_df = pd.concat(res) - assert_frame_equal(df, roundtripped_df) + tm.assert_frame_equal(df, roundtripped_df) def test_write_unsupported_compression_type(): diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py index 8e28740c70bada..eaa46c4e9dc9b7 100644 --- a/pandas/tests/io/json/test_pandas.py +++ b/pandas/tests/io/json/test_pandas.py @@ -13,12 +13,6 @@ import pandas as pd from pandas import DataFrame, DatetimeIndex, Series, Timestamp, read_json import pandas.util.testing as tm -from pandas.util.testing import ( - assert_frame_equal, - assert_series_equal, - ensure_clean, - network, -) _seriesd = tm.getSeriesData() _tsd = tm.getTimeSeriesData() @@ -42,7 +36,7 @@ def assert_json_roundtrip_equal(result, expected, orient): expected = expected.reset_index(drop=True) if orient == "values": expected.columns = range(len(expected.columns)) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) class TestPandasContainer: @@ -142,7 +136,7 @@ def test_frame_non_unique_columns(self, orient, data): elif orient == "split": expected = df - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) @pytest.mark.parametrize("orient", ["index", "columns", "records"]) def test_frame_non_unique_columns_raises(self, orient): @@ -425,7 +419,7 @@ def test_frame_to_json_except(self): def test_frame_empty(self): df = DataFrame(columns=["jim", "joe"]) assert not df._is_mixed_type - assert_frame_equal( + tm.assert_frame_equal( read_json(df.to_json(), dtype=dict(df.dtypes)), df, check_index_type=False ) # GH 7445 @@ -438,7 +432,7 @@ def test_frame_empty_mixedtype(self): df = DataFrame(columns=["jim", "joe"]) df["joe"] = df["joe"].astype("i8") assert df._is_mixed_type - assert_frame_equal( + tm.assert_frame_equal( read_json(df.to_json(), dtype=dict(df.dtypes)), df, check_index_type=False ) @@ -460,17 +454,17 @@ def test_frame_mixedtype_orient(self): # GH10289 for orient in ["split", "index", "columns"]: inp = df.to_json(orient=orient) left = read_json(inp, orient=orient, convert_axes=False) - assert_frame_equal(left, right) + tm.assert_frame_equal(left, right) right.index = np.arange(len(df)) inp = df.to_json(orient="records") left = read_json(inp, orient="records", convert_axes=False) - assert_frame_equal(left, right) + tm.assert_frame_equal(left, right) right.columns = np.arange(df.shape[1]) inp = df.to_json(orient="values") left = read_json(inp, orient="values", convert_axes=False) - assert_frame_equal(left, right) + tm.assert_frame_equal(left, right) def test_v12_compat(self): df = DataFrame( @@ -491,12 +485,12 @@ def test_v12_compat(self): v12_json = os.path.join(self.dirpath, "tsframe_v012.json") df_unser = pd.read_json(v12_json) - assert_frame_equal(df, df_unser) + tm.assert_frame_equal(df, df_unser) df_iso = df.drop(["modified"], axis=1) v12_iso_json = os.path.join(self.dirpath, "tsframe_iso_v012.json") df_unser_iso = pd.read_json(v12_iso_json) - assert_frame_equal(df_iso, df_unser_iso) + tm.assert_frame_equal(df_iso, df_unser_iso) def test_blocks_compat_GH9037(self): index = pd.date_range("20000101", periods=10, freq="H") @@ -582,7 +576,7 @@ def test_blocks_compat_GH9037(self): df_mixed.columns = df_mixed.columns.astype("unicode") df_roundtrip = pd.read_json(df_mixed.to_json(orient="split"), orient="split") - assert_frame_equal( + tm.assert_frame_equal( df_mixed, df_roundtrip, check_index_type=True, @@ -643,7 +637,7 @@ def test_series_non_unique_index(self): with pytest.raises(ValueError, match=msg): s.to_json(orient="index") - assert_series_equal( + tm.assert_series_equal( s, read_json(s.to_json(orient="split"), orient="split", typ="series") ) unser = read_json(s.to_json(orient="records"), orient="records", typ="series") @@ -736,14 +730,14 @@ def test_series_to_json_except(self): def test_series_from_json_precise_float(self): s = Series([4.56, 4.56, 4.56]) result = read_json(s.to_json(), typ="series", precise_float=True) - assert_series_equal(result, s, check_index_type=False) + tm.assert_series_equal(result, s, check_index_type=False) def test_series_with_dtype(self): # GH 21986 s = Series([4.56, 4.56, 4.56]) result = read_json(s.to_json(), typ="series", dtype=np.int64) expected = Series([4] * 3) - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) @pytest.mark.parametrize( "dtype,expected", @@ -756,32 +750,34 @@ def test_series_with_dtype_datetime(self, dtype, expected): s = Series(["2000-01-01"], dtype="datetime64[ns]") data = s.to_json() result = pd.read_json(data, typ="series", dtype=dtype) - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) def test_frame_from_json_precise_float(self): df = DataFrame([[4.56, 4.56, 4.56], [4.56, 4.56, 4.56]]) result = read_json(df.to_json(), precise_float=True) - assert_frame_equal(result, df, check_index_type=False, check_column_type=False) + tm.assert_frame_equal( + result, df, check_index_type=False, check_column_type=False + ) def test_typ(self): s = Series(range(6), index=["a", "b", "c", "d", "e", "f"], dtype="int64") result = read_json(s.to_json(), typ=None) - assert_series_equal(result, s) + tm.assert_series_equal(result, s) def test_reconstruction_index(self): df = DataFrame([[1, 2, 3], [4, 5, 6]]) result = read_json(df.to_json()) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]}, index=["A", "B", "C"]) result = read_json(df.to_json()) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_path(self): - with ensure_clean("test.json") as path: + with tm.ensure_clean("test.json") as path: for df in [ self.frame, self.frame2, @@ -797,12 +793,12 @@ def test_axis_dates(self): # frame json = self.tsframe.to_json() result = read_json(json) - assert_frame_equal(result, self.tsframe) + tm.assert_frame_equal(result, self.tsframe) # series json = self.ts.to_json() result = read_json(json, typ="series") - assert_series_equal(result, self.ts, check_names=False) + tm.assert_series_equal(result, self.ts, check_names=False) assert result.name is None def test_convert_dates(self): @@ -813,7 +809,7 @@ def test_convert_dates(self): json = df.to_json() result = read_json(json) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) df["foo"] = 1.0 json = df.to_json(date_unit="ns") @@ -822,13 +818,13 @@ def test_convert_dates(self): expected = df.copy() expected["date"] = expected["date"].values.view("i8") expected["foo"] = expected["foo"].astype("int64") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # series ts = Series(Timestamp("20130101"), index=self.ts.index) json = ts.to_json() result = read_json(json, typ="series") - assert_series_equal(result, ts) + tm.assert_series_equal(result, ts) @pytest.mark.parametrize( "infer_word", @@ -851,7 +847,7 @@ def test_convert_dates_infer(self, infer_word): [[1, Timestamp("2002-11-08")], [2, pd.NaT]], columns=["id", infer_word] ) result = read_json(dumps(data))[["id", infer_word]] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) @pytest.mark.parametrize( "date,date_unit", @@ -877,7 +873,7 @@ def test_date_format_frame(self, date, date_unit): expected = df.copy() # expected.index = expected.index.tz_localize("UTC") expected["date"] = expected["date"].dt.tz_localize("UTC") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_date_format_frame_raises(self): df = self.tsframe.copy() @@ -907,7 +903,7 @@ def test_date_format_series(self, date, date_unit): expected = ts.copy() # expected.index = expected.index.tz_localize("UTC") expected = expected.dt.tz_localize("UTC") - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) def test_date_format_series_raises(self): ts = Series(Timestamp("20130101 20:43:42.123"), index=self.ts.index) @@ -928,11 +924,11 @@ def test_date_unit(self, unit): # force date unit result = read_json(json, date_unit=unit) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # detect date unit result = read_json(json, date_unit=None) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_weird_nested_json(self): # this used to core dump the parser @@ -965,7 +961,7 @@ def test_doc_example(self): json = dfj2.to_json() result = read_json(json, dtype={"ints": np.int64, "bools": np.bool_}) - assert_frame_equal(result, result) + tm.assert_frame_equal(result, result) def test_misc_example(self): @@ -979,13 +975,13 @@ def test_misc_example(self): \\[left\\]: Index\\(\\['a', 'b'\\], dtype='object'\\) \\[right\\]: RangeIndex\\(start=0, stop=2, step=1\\)""" with pytest.raises(AssertionError, match=error_msg): - assert_frame_equal(result, expected, check_index_type=False) + tm.assert_frame_equal(result, expected, check_index_type=False) result = read_json('[{"a": 1, "b": 2}, {"b":2, "a" :1}]') expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) - @network + @tm.network @pytest.mark.single def test_round_trip_exception_(self): # GH 3867 @@ -993,9 +989,9 @@ def test_round_trip_exception_(self): df = pd.read_csv(csv) s = df.to_json() result = pd.read_json(s) - assert_frame_equal(result.reindex(index=df.index, columns=df.columns), df) + tm.assert_frame_equal(result.reindex(index=df.index, columns=df.columns), df) - @network + @tm.network @pytest.mark.single @pytest.mark.parametrize( "field,dtype", @@ -1017,16 +1013,16 @@ def test_timedelta(self): assert s.dtype == "timedelta64[ns]" result = pd.read_json(s.to_json(), typ="series").apply(converter) - assert_series_equal(result, s) + tm.assert_series_equal(result, s) s = Series([timedelta(23), timedelta(seconds=5)], index=pd.Index([0, 1])) assert s.dtype == "timedelta64[ns]" result = pd.read_json(s.to_json(), typ="series").apply(converter) - assert_series_equal(result, s) + tm.assert_series_equal(result, s) frame = DataFrame([timedelta(23), timedelta(seconds=5)]) assert frame[0].dtype == "timedelta64[ns]" - assert_frame_equal(frame, pd.read_json(frame.to_json()).apply(converter)) + tm.assert_frame_equal(frame, pd.read_json(frame.to_json()).apply(converter)) frame = DataFrame( { @@ -1039,7 +1035,7 @@ def test_timedelta(self): result = pd.read_json(frame.to_json(date_unit="ns")) result["a"] = pd.to_timedelta(result.a, unit="ns") result["c"] = pd.to_datetime(result.c) - assert_frame_equal(frame, result) + tm.assert_frame_equal(frame, result) def test_mixed_timedelta_datetime(self): frame = DataFrame( @@ -1050,14 +1046,14 @@ def test_mixed_timedelta_datetime(self): {"a": [pd.Timedelta(frame.a[0]).value, pd.Timestamp(frame.a[1]).value]} ) result = pd.read_json(frame.to_json(date_unit="ns"), dtype={"a": "int64"}) - assert_frame_equal(result, expected, check_index_type=False) + tm.assert_frame_equal(result, expected, check_index_type=False) def test_default_handler(self): value = object() frame = DataFrame({"a": [7, value]}) expected = DataFrame({"a": [7, str(value)]}) result = pd.read_json(frame.to_json(default_handler=str)) - assert_frame_equal(expected, result, check_index_type=False) + tm.assert_frame_equal(expected, result, check_index_type=False) def test_default_handler_indirect(self): from pandas.io.json import dumps @@ -1199,7 +1195,7 @@ def test_read_inline_jsonl(self): # GH9180 result = read_json('{"a": 1, "b": 2}\n{"b":2, "a" :1}\n', lines=True) expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) @td.skip_if_not_us_locale def test_read_s3_jsonl(self, s3_resource): @@ -1207,16 +1203,16 @@ def test_read_s3_jsonl(self, s3_resource): result = read_json("s3n://pandas-test/items.jsonl", lines=True) expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_local_jsonl(self): # GH17200 - with ensure_clean("tmp_items.json") as path: + with tm.ensure_clean("tmp_items.json") as path: with open(path, "w") as infile: infile.write('{"a": 1, "b": 2}\n{"b":2, "a" :1}\n') result = read_json(path, lines=True) expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_jsonl_unicode_chars(self): # GH15132: non-ascii unicode characters @@ -1227,13 +1223,13 @@ def test_read_jsonl_unicode_chars(self): json = StringIO(json) result = read_json(json, lines=True) expected = DataFrame([["foo\u201d", "bar"], ["foo", "bar"]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # simulate string json = '{"a": "foo”", "b": "bar"}\n{"a": "foo", "b": "bar"}\n' result = read_json(json, lines=True) expected = DataFrame([["foo\u201d", "bar"], ["foo", "bar"]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_json_large_numbers(self): # GH18842 @@ -1241,13 +1237,13 @@ def test_read_json_large_numbers(self): json = StringIO(json) result = read_json(json, typ="series") expected = Series(1.404366e21, index=["articleId"]) - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) json = '{"0": {"articleId": "1404366058080022500245"}}' json = StringIO(json) result = read_json(json) expected = DataFrame(1.404366e21, index=["articleId"], columns=[0]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_to_jsonl(self): # GH9180 @@ -1260,14 +1256,14 @@ def test_to_jsonl(self): result = df.to_json(orient="records", lines=True) expected = '{"a":"foo}","b":"bar"}\n{"a":"foo\\"","b":"bar"}' assert result == expected - assert_frame_equal(pd.read_json(result, lines=True), df) + tm.assert_frame_equal(pd.read_json(result, lines=True), df) # GH15096: escaped characters in columns and data df = DataFrame([["foo\\", "bar"], ['foo"', "bar"]], columns=["a\\", "b"]) result = df.to_json(orient="records", lines=True) expected = '{"a\\\\":"foo\\\\","b":"bar"}\n' '{"a\\\\":"foo\\"","b":"bar"}' assert result == expected - assert_frame_equal(pd.read_json(result, lines=True), df) + tm.assert_frame_equal(pd.read_json(result, lines=True), df) # TODO: there is a near-identical test for pytables; can we share? def test_latin_encoding(self): @@ -1297,10 +1293,10 @@ def test_latin_encoding(self): examples.append(Series(val, dtype=dtype)) def roundtrip(s, encoding="latin-1"): - with ensure_clean("test.json") as path: + with tm.ensure_clean("test.json") as path: s.to_json(path, encoding=encoding) retr = read_json(path, encoding=encoding) - assert_series_equal(s, retr, check_categorical=False) + tm.assert_series_equal(s, retr, check_categorical=False) for s in examples: roundtrip(s) @@ -1324,14 +1320,14 @@ def test_from_json_to_json_table_index_and_columns(self, index, columns): expected = DataFrame([[1, 2], [3, 4]], index=index, columns=columns) dfjson = expected.to_json(orient="table") result = pd.read_json(dfjson, orient="table") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_from_json_to_json_table_dtypes(self): # GH21345 expected = pd.DataFrame({"a": [1, 2], "b": [3.0, 4.0], "c": ["5", "6"]}) dfjson = expected.to_json(orient="table") result = pd.read_json(dfjson, orient="table") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) @pytest.mark.parametrize("dtype", [True, {"b": int, "c": int}]) def test_read_json_table_dtype_raises(self, dtype): @@ -1435,7 +1431,7 @@ def test_index_false_from_json_to_json(self, orient, index): expected = DataFrame({"a": [1, 2], "b": [3, 4]}) dfjson = expected.to_json(orient=orient, index=index) result = read_json(dfjson, orient=orient) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_timezone_information(self): # GH 25546 @@ -1443,7 +1439,7 @@ def test_read_timezone_information(self): '{"2019-01-01T11:00:00.000Z":88}', typ="series", orient="index" ) expected = Series([88], index=DatetimeIndex(["2019-01-01 11:00:00"], tz="UTC")) - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) @pytest.mark.parametrize( "date_format,key", [("epoch", 86400000), ("iso", "P1DT0H0M0S")] diff --git a/pandas/tests/io/json/test_readlines.py b/pandas/tests/io/json/test_readlines.py index 821bf0287c6f12..05f97a17692052 100644 --- a/pandas/tests/io/json/test_readlines.py +++ b/pandas/tests/io/json/test_readlines.py @@ -5,7 +5,6 @@ import pandas as pd from pandas import DataFrame, read_json import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal, assert_series_equal, ensure_clean from pandas.io.json._json import JsonReader @@ -20,7 +19,7 @@ def test_read_jsonl(): # GH9180 result = read_json('{"a": 1, "b": 2}\n{"b":2, "a" :1}\n', lines=True) expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_jsonl_unicode_chars(): @@ -32,13 +31,13 @@ def test_read_jsonl_unicode_chars(): json = StringIO(json) result = read_json(json, lines=True) expected = DataFrame([["foo\u201d", "bar"], ["foo", "bar"]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # simulate string json = '{"a": "foo”", "b": "bar"}\n{"a": "foo", "b": "bar"}\n' result = read_json(json, lines=True) expected = DataFrame([["foo\u201d", "bar"], ["foo", "bar"]], columns=["a", "b"]) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_to_jsonl(): @@ -52,14 +51,14 @@ def test_to_jsonl(): result = df.to_json(orient="records", lines=True) expected = '{"a":"foo}","b":"bar"}\n{"a":"foo\\"","b":"bar"}' assert result == expected - assert_frame_equal(read_json(result, lines=True), df) + tm.assert_frame_equal(read_json(result, lines=True), df) # GH15096: escaped characters in columns and data df = DataFrame([["foo\\", "bar"], ['foo"', "bar"]], columns=["a\\", "b"]) result = df.to_json(orient="records", lines=True) expected = '{"a\\\\":"foo\\\\","b":"bar"}\n' '{"a\\\\":"foo\\"","b":"bar"}' assert result == expected - assert_frame_equal(read_json(result, lines=True), df) + tm.assert_frame_equal(read_json(result, lines=True), df) @pytest.mark.parametrize("chunksize", [1, 1.0]) @@ -72,7 +71,7 @@ def test_readjson_chunks(lines_json_df, chunksize): reader = read_json(StringIO(lines_json_df), lines=True, chunksize=chunksize) chunked = pd.concat(reader) - assert_frame_equal(chunked, unchunked) + tm.assert_frame_equal(chunked, unchunked) def test_readjson_chunksize_requires_lines(lines_json_df): @@ -91,7 +90,7 @@ def test_readjson_chunks_series(): strio = StringIO(s.to_json(lines=True, orient="records")) chunked = pd.concat(pd.read_json(strio, lines=True, typ="Series", chunksize=1)) - assert_series_equal(chunked, unchunked) + tm.assert_series_equal(chunked, unchunked) def test_readjson_each_chunk(lines_json_df): @@ -103,17 +102,17 @@ def test_readjson_each_chunk(lines_json_df): def test_readjson_chunks_from_file(): - with ensure_clean("test.json") as path: + with tm.ensure_clean("test.json") as path: df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}) df.to_json(path, lines=True, orient="records") chunked = pd.concat(pd.read_json(path, lines=True, chunksize=1)) unchunked = pd.read_json(path, lines=True) - assert_frame_equal(unchunked, chunked) + tm.assert_frame_equal(unchunked, chunked) @pytest.mark.parametrize("chunksize", [None, 1]) def test_readjson_chunks_closes(chunksize): - with ensure_clean("test.json") as path: + with tm.ensure_clean("test.json") as path: df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}) df.to_json(path, lines=True, orient="records") reader = JsonReader( diff --git a/pandas/tests/io/parser/test_textreader.py b/pandas/tests/io/parser/test_textreader.py index 9afeaf75f4da34..75a5b7cd53ddbc 100644 --- a/pandas/tests/io/parser/test_textreader.py +++ b/pandas/tests/io/parser/test_textreader.py @@ -13,7 +13,6 @@ from pandas import DataFrame import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal from pandas.io.parsers import TextFileReader, read_csv @@ -323,19 +322,19 @@ def test_empty_field_eof(self): for _ in range(100): df = read_csv(StringIO("a,b\nc\n"), skiprows=0, names=["a"], engine="c") - assert_frame_equal(df, a) + tm.assert_frame_equal(df, a) df = read_csv( StringIO("1,1,1,1,0\n" * 2 + "\n" * 2), names=list("abcd"), engine="c" ) - assert_frame_equal(df, b) + tm.assert_frame_equal(df, b) df = read_csv( StringIO("0,1,2,3,4\n5,6\n7,8,9,10,11\n12,13,14"), names=list("abcd"), engine="c", ) - assert_frame_equal(df, c) + tm.assert_frame_equal(df, c) def test_empty_csv_input(self): # GH14867 diff --git a/pandas/tests/io/pytables/test_compat.py b/pandas/tests/io/pytables/test_compat.py index fe8d8c56a4e82e..1e320e12a4a536 100644 --- a/pandas/tests/io/pytables/test_compat.py +++ b/pandas/tests/io/pytables/test_compat.py @@ -2,7 +2,7 @@ import pandas as pd from pandas.tests.io.pytables.common import ensure_clean_path -from pandas.util.testing import assert_frame_equal +import pandas.util.testing as tm tables = pytest.importorskip("tables") @@ -52,25 +52,25 @@ def test_read_complete(self, pytables_hdf5_file): path, objname, df = pytables_hdf5_file result = pd.read_hdf(path, key=objname) expected = df - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_with_start(self, pytables_hdf5_file): path, objname, df = pytables_hdf5_file # This is a regression test for pandas-dev/pandas/issues/11188 result = pd.read_hdf(path, key=objname, start=1) expected = df[1:].reset_index(drop=True) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_with_stop(self, pytables_hdf5_file): path, objname, df = pytables_hdf5_file # This is a regression test for pandas-dev/pandas/issues/11188 result = pd.read_hdf(path, key=objname, stop=1) expected = df[:1].reset_index(drop=True) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_with_startstop(self, pytables_hdf5_file): path, objname, df = pytables_hdf5_file # This is a regression test for pandas-dev/pandas/issues/11188 result = pd.read_hdf(path, key=objname, start=1, stop=2) expected = df[1:2].reset_index(drop=True) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) diff --git a/pandas/tests/io/pytables/test_complex.py b/pandas/tests/io/pytables/test_complex.py index e48cfb724ef1d3..91ee1061a5ef15 100644 --- a/pandas/tests/io/pytables/test_complex.py +++ b/pandas/tests/io/pytables/test_complex.py @@ -9,7 +9,6 @@ from pandas import DataFrame, Series from pandas.tests.io.pytables.common import ensure_clean_path, ensure_clean_store import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal from pandas.io.pytables import read_hdf @@ -26,7 +25,7 @@ def test_complex_fixed(setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df") reread = read_hdf(path, "df") - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) df = DataFrame( np.random.rand(4, 5).astype(np.complex128), @@ -36,7 +35,7 @@ def test_complex_fixed(setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df") reread = read_hdf(path, "df") - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) def test_complex_table(setup_path): @@ -49,7 +48,7 @@ def test_complex_table(setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df", format="table") reread = read_hdf(path, "df") - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) df = DataFrame( np.random.rand(4, 5).astype(np.complex128), @@ -60,7 +59,7 @@ def test_complex_table(setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df", format="table", mode="w") reread = read_hdf(path, "df") - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) @td.xfail_non_writeable @@ -84,7 +83,7 @@ def test_complex_mixed_fixed(setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df") reread = read_hdf(path, "df") - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) def test_complex_mixed_table(setup_path): @@ -108,12 +107,12 @@ def test_complex_mixed_table(setup_path): with ensure_clean_store(setup_path) as store: store.append("df", df, data_columns=["A", "B"]) result = store.select("df", where="A>2") - assert_frame_equal(df.loc[df.A > 2], result) + tm.assert_frame_equal(df.loc[df.A > 2], result) with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df", format="table") reread = read_hdf(path, "df") - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) def test_complex_across_dimensions_fixed(setup_path): @@ -183,4 +182,4 @@ def test_complex_append(setup_path): store.append("df", df, data_columns=["b"]) store.append("df", df) result = store.select("df") - assert_frame_equal(pd.concat([df, df], 0), result) + tm.assert_frame_equal(pd.concat([df, df], 0), result) diff --git a/pandas/tests/io/pytables/test_store.py b/pandas/tests/io/pytables/test_store.py index 956438f1afdf44..f9d525399bde3f 100644 --- a/pandas/tests/io/pytables/test_store.py +++ b/pandas/tests/io/pytables/test_store.py @@ -42,7 +42,6 @@ tables, ) import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal, assert_series_equal from pandas.io.pytables import ( ClosedFileError, @@ -99,19 +98,19 @@ def roundtrip(key, obj, **kwargs): return read_hdf(path, key) o = tm.makeTimeSeries() - assert_series_equal(o, roundtrip("series", o)) + tm.assert_series_equal(o, roundtrip("series", o)) o = tm.makeStringSeries() - assert_series_equal(o, roundtrip("string_series", o)) + tm.assert_series_equal(o, roundtrip("string_series", o)) o = tm.makeDataFrame() - assert_frame_equal(o, roundtrip("frame", o)) + tm.assert_frame_equal(o, roundtrip("frame", o)) # table df = DataFrame(dict(A=range(5), B=range(5))) df.to_hdf(path, "table", append=True) result = read_hdf(path, "table", where=["index>2"]) - assert_frame_equal(df[df.index > 2], result) + tm.assert_frame_equal(df[df.index > 2], result) finally: safe_remove(path) @@ -127,7 +126,7 @@ def test_long_strings(self, setup_path): store.append("df", df, data_columns=["a"]) result = store.select("df") - assert_frame_equal(df, result) + tm.assert_frame_equal(df, result) def test_api(self, setup_path): @@ -138,39 +137,39 @@ def test_api(self, setup_path): df = tm.makeDataFrame() df.iloc[:10].to_hdf(path, "df", append=True, format="table") df.iloc[10:].to_hdf(path, "df", append=True, format="table") - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) # append to False df.iloc[:10].to_hdf(path, "df", append=False, format="table") df.iloc[10:].to_hdf(path, "df", append=True, format="table") - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) with ensure_clean_path(setup_path) as path: df = tm.makeDataFrame() df.iloc[:10].to_hdf(path, "df", append=True) df.iloc[10:].to_hdf(path, "df", append=True, format="table") - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) # append to False df.iloc[:10].to_hdf(path, "df", append=False, format="table") df.iloc[10:].to_hdf(path, "df", append=True) - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) with ensure_clean_path(setup_path) as path: df = tm.makeDataFrame() df.to_hdf(path, "df", append=False, format="fixed") - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) df.to_hdf(path, "df", append=False, format="f") - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) df.to_hdf(path, "df", append=False) - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) df.to_hdf(path, "df") - assert_frame_equal(read_hdf(path, "df"), df) + tm.assert_frame_equal(read_hdf(path, "df"), df) with ensure_clean_store(setup_path) as store: @@ -180,24 +179,24 @@ def test_api(self, setup_path): _maybe_remove(store, "df") store.append("df", df.iloc[:10], append=True, format="table") store.append("df", df.iloc[10:], append=True, format="table") - assert_frame_equal(store.select("df"), df) + tm.assert_frame_equal(store.select("df"), df) # append to False _maybe_remove(store, "df") store.append("df", df.iloc[:10], append=False, format="table") store.append("df", df.iloc[10:], append=True, format="table") - assert_frame_equal(store.select("df"), df) + tm.assert_frame_equal(store.select("df"), df) # formats _maybe_remove(store, "df") store.append("df", df.iloc[:10], append=False, format="table") store.append("df", df.iloc[10:], append=True, format="table") - assert_frame_equal(store.select("df"), df) + tm.assert_frame_equal(store.select("df"), df) _maybe_remove(store, "df") store.append("df", df.iloc[:10], append=False, format="table") store.append("df", df.iloc[10:], append=True, format=None) - assert_frame_equal(store.select("df"), df) + tm.assert_frame_equal(store.select("df"), df) with ensure_clean_path(setup_path) as path: # Invalid. @@ -432,7 +431,7 @@ def check(mode): read_hdf(path, "df", mode=mode) else: result = read_hdf(path, "df", mode=mode) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def check_default_mode(): @@ -440,7 +439,7 @@ def check_default_mode(): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df", mode="w") result = read_hdf(path, "df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) check("r") check("r+") @@ -962,7 +961,7 @@ def check(format, index): _maybe_remove(store, "df") store.put("df", df, format=format) - assert_frame_equal(df, store["df"]) + tm.assert_frame_equal(df, store["df"]) for index in [ tm.makeFloatIndex, @@ -1032,9 +1031,11 @@ def test_latin_encoding(self, setup_path, dtype, val): if is_categorical_dtype(s_nan): assert is_categorical_dtype(retr) - assert_series_equal(s_nan, retr, check_dtype=False, check_categorical=False) + tm.assert_series_equal( + s_nan, retr, check_dtype=False, check_categorical=False + ) else: - assert_series_equal(s_nan, retr) + tm.assert_series_equal(s_nan, retr) # FIXME: don't leave commented-out # fails: @@ -1861,14 +1862,14 @@ def check(obj, comparator): # repeated append of 0/non-zero frames df = DataFrame(np.random.rand(10, 3), columns=list("ABC")) store.append("df", df) - assert_frame_equal(store.select("df"), df) + tm.assert_frame_equal(store.select("df"), df) store.append("df", df_empty) - assert_frame_equal(store.select("df"), df) + tm.assert_frame_equal(store.select("df"), df) # store df = DataFrame(columns=list("ABC")) store.put("df2", df) - assert_frame_equal(store.select("df2"), df) + tm.assert_frame_equal(store.select("df2"), df) def test_append_raise(self, setup_path): @@ -1929,11 +1930,11 @@ def test_table_values_dtypes_roundtrip(self, setup_path): with ensure_clean_store(setup_path) as store: df1 = DataFrame({"a": [1, 2, 3]}, dtype="f8") store.append("df_f8", df1) - assert_series_equal(df1.dtypes, store["df_f8"].dtypes) + tm.assert_series_equal(df1.dtypes, store["df_f8"].dtypes) df2 = DataFrame({"a": [1, 2, 3]}, dtype="i8") store.append("df_i8", df2) - assert_series_equal(df2.dtypes, store["df_i8"].dtypes) + tm.assert_series_equal(df2.dtypes, store["df_i8"].dtypes) # incompatible dtype with pytest.raises(ValueError): @@ -1943,7 +1944,7 @@ def test_table_values_dtypes_roundtrip(self, setup_path): # actually create them thought) df1 = DataFrame(np.array([[1], [2], [3]], dtype="f4"), columns=["A"]) store.append("df_f4", df1) - assert_series_equal(df1.dtypes, store["df_f4"].dtypes) + tm.assert_series_equal(df1.dtypes, store["df_f4"].dtypes) assert df1.dtypes[0] == "float32" # check with mixed dtypes @@ -2057,11 +2058,11 @@ def test_calendar_roundtrip_issue(self, setup_path): store.put("fixed", s) result = store.select("fixed") - assert_series_equal(result, s) + tm.assert_series_equal(result, s) store.append("table", s) result = store.select("table") - assert_series_equal(result, s) + tm.assert_series_equal(result, s) def test_roundtrip_tz_aware_index(self, setup_path): # GH 17618 @@ -2096,32 +2097,32 @@ def test_append_with_timedelta(self, setup_path): _maybe_remove(store, "df") store.append("df", df, data_columns=True) result = store.select("df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) result = store.select("df", where="C<100000") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) result = store.select("df", where="Cdatetime.datetime(2013,1,5)") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) from datetime import datetime # noqa # technically an error, but allow it result = store.select("df", "index>datetime.datetime(2013,1,5)") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = store.select("df", "index>datetime(2013,1,5)") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_series(self, setup_path): @@ -2459,7 +2460,7 @@ def test_store_index_name_numpy_str(self, table_format, setup_path): df.to_hdf(path, "df", format=table_format) df2 = read_hdf(path, "df") - assert_frame_equal(df, df2, check_names=True) + tm.assert_frame_equal(df, df2, check_names=True) assert type(df2.index.name) == str assert type(df2.columns.name) == str @@ -2534,15 +2535,15 @@ def test_select_with_dups(self, setup_path): result = store.select("df") expected = df - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) result = store.select("df", columns=df.columns) expected = df - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) result = store.select("df", columns=["A"]) expected = df.loc[:, ["A"]] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # dups across dtypes df = concat( @@ -2561,19 +2562,19 @@ def test_select_with_dups(self, setup_path): result = store.select("df") expected = df - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) result = store.select("df", columns=df.columns) expected = df - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) expected = df.loc[:, ["A"]] result = store.select("df", columns=["A"]) - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) expected = df.loc[:, ["B", "A"]] result = store.select("df", columns=["B", "A"]) - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) # duplicates on both index and columns with ensure_clean_store(setup_path) as store: @@ -2583,7 +2584,7 @@ def test_select_with_dups(self, setup_path): expected = df.loc[:, ["B", "A"]] expected = concat([expected, expected]) result = store.select("df", columns=["B", "A"]) - assert_frame_equal(result, expected, by_blocks=True) + tm.assert_frame_equal(result, expected, by_blocks=True) def test_overwrite_node(self, setup_path): @@ -3269,40 +3270,40 @@ def test_frame_select_complex2(self, setup_path): l = selection.index.tolist() # noqa store = HDFStore(hh) result = store.select("df", where="l1=l") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) store.close() result = read_hdf(hh, "df", where="l1=l") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # index index = selection.index # noqa result = read_hdf(hh, "df", where="l1=index") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = read_hdf(hh, "df", where="l1=selection.index") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = read_hdf(hh, "df", where="l1=selection.index.tolist()") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = read_hdf(hh, "df", where="l1=list(selection.index)") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # scope with index store = HDFStore(hh) result = store.select("df", where="l1=index") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = store.select("df", where="l1=selection.index") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = store.select("df", where="l1=selection.index.tolist()") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = store.select("df", where="l1=list(selection.index)") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) store.close() @@ -3337,11 +3338,11 @@ def test_string_select(self, setup_path): result = store.select("df", "x=none") expected = df[df.x == "none"] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = store.select("df", "x!=none") expected = df[df.x != "none"] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) df2 = df.copy() df2.loc[df2.x == "", "x"] = np.nan @@ -3349,7 +3350,7 @@ def test_string_select(self, setup_path): store.append("df2", df2, data_columns=["x"]) result = store.select("df2", "x!=none") expected = df2[isna(df2.x)] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # int ==/!= df["int"] = 1 @@ -3359,11 +3360,11 @@ def test_string_select(self, setup_path): result = store.select("df3", "int=2") expected = df[df.int == 2] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = store.select("df3", "int!=2") expected = df[df.int != 2] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_read_column(self, setup_path): @@ -3700,7 +3701,7 @@ def test_nan_selection_bug_4858(self, setup_path): # write w/o the index on that particular column store.append("df", df, data_columns=True, index=["cols"]) result = store.select("df", where="values>2.0") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_start_stop_table(self, setup_path): @@ -3816,7 +3817,7 @@ def test_contiguous_mixed_data_table(self, start, stop, setup_path): store.append("test_dataset", df) result = store.select("test_dataset", start=start, stop=stop) - assert_frame_equal(df[start:stop], result) + tm.assert_frame_equal(df[start:stop], result) def test_path_pathlib_hdfstore(self, setup_path): df = tm.makeDataFrame() @@ -4044,7 +4045,7 @@ def test_legacy_table_fixed_format_read_py2(self, datapath, setup_path): columns=["A", "B", "C", "D"], index=pd.Index(["ABC"], name="INDEX_NAME"), ) - assert_frame_equal(expected, result) + tm.assert_frame_equal(expected, result) def test_legacy_table_read_py2(self, datapath, setup_path): # issue: 24925 @@ -4055,7 +4056,7 @@ def test_legacy_table_read_py2(self, datapath, setup_path): result = store.select("table") expected = pd.DataFrame({"a": ["a", "b"], "b": [2, 3]}) - assert_frame_equal(expected, result) + tm.assert_frame_equal(expected, result) def test_copy(self, setup_path): @@ -4152,7 +4153,7 @@ def test_tseries_indices_frame(self, setup_path): store["a"] = df result = store["a"] - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) assert result.index.freq == df.index.freq tm.assert_class_equal(result.index, df.index, obj="dataframe index") @@ -4161,7 +4162,7 @@ def test_tseries_indices_frame(self, setup_path): store["a"] = df result = store["a"] - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) assert result.index.freq == df.index.freq tm.assert_class_equal(result.index, df.index, obj="dataframe index") @@ -4442,7 +4443,7 @@ def test_preserve_timedeltaindex_type(self, setup_path): with ensure_clean_store(setup_path) as store: store["df"] = df - assert_frame_equal(store["df"], df) + tm.assert_frame_equal(store["df"], df) def test_columns_multiindex_modified(self, setup_path): # BUG: 7212 @@ -4569,7 +4570,7 @@ def test_read_nokey(self, setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df", mode="a") reread = read_hdf(path) - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) df.to_hdf(path, "df2", mode="a") with pytest.raises(ValueError): @@ -4582,7 +4583,7 @@ def test_read_nokey_table(self, setup_path): with ensure_clean_path(setup_path) as path: df.to_hdf(path, "df", mode="a", format="table") reread = read_hdf(path) - assert_frame_equal(df, reread) + tm.assert_frame_equal(df, reread) df.to_hdf(path, "df2", mode="a", format="table") with pytest.raises(ValueError): @@ -4739,7 +4740,7 @@ def test_read_py2_hdf_file_in_py3(self, datapath): mode="r", ) as store: result = store["p"] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) @pytest.mark.parametrize("where", ["", (), (None,), [], [None]]) def test_select_empty_where(self, where): @@ -4754,7 +4755,7 @@ def test_select_empty_where(self, where): with pd.HDFStore(path) as store: store.put("df", df, "t") result = pd.read_hdf(store, "df", where=where) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) @pytest.mark.parametrize( "idx", diff --git a/pandas/tests/io/pytables/test_timezones.py b/pandas/tests/io/pytables/test_timezones.py index ba1df242248310..1acb0ac6e06d23 100644 --- a/pandas/tests/io/pytables/test_timezones.py +++ b/pandas/tests/io/pytables/test_timezones.py @@ -13,7 +13,6 @@ ensure_clean_store, ) import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal, set_timezone def _compare_with_tz(a, b): @@ -57,7 +56,7 @@ def test_append_with_timezones_dateutil(setup_path): store.append("df_tz", df, data_columns=["A"]) result = store["df_tz"] _compare_with_tz(result, df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # select with tz aware expected = df[df.A >= df.A[3]] @@ -76,7 +75,7 @@ def test_append_with_timezones_dateutil(setup_path): store.append("df_tz", df) result = store["df_tz"] _compare_with_tz(result, df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) df = DataFrame( dict( @@ -93,7 +92,7 @@ def test_append_with_timezones_dateutil(setup_path): store.append("df_tz", df, data_columns=["A", "B"]) result = store["df_tz"] _compare_with_tz(result, df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # can't append with diff timezone df = DataFrame( @@ -124,12 +123,12 @@ def test_append_with_timezones_dateutil(setup_path): _maybe_remove(store, "df") store.put("df", df) result = store.select("df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) _maybe_remove(store, "df") store.append("df", df) result = store.select("df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_append_with_timezones_pytz(setup_path): @@ -152,7 +151,7 @@ def test_append_with_timezones_pytz(setup_path): store.append("df_tz", df, data_columns=["A"]) result = store["df_tz"] _compare_with_tz(result, df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # select with tz aware _compare_with_tz(store.select("df_tz", where="A>=df.A[3]"), df[df.A >= df.A[3]]) @@ -169,7 +168,7 @@ def test_append_with_timezones_pytz(setup_path): store.append("df_tz", df) result = store["df_tz"] _compare_with_tz(result, df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) df = DataFrame( dict( @@ -186,7 +185,7 @@ def test_append_with_timezones_pytz(setup_path): store.append("df_tz", df, data_columns=["A", "B"]) result = store["df_tz"] _compare_with_tz(result, df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # can't append with diff timezone df = DataFrame( @@ -215,12 +214,12 @@ def test_append_with_timezones_pytz(setup_path): _maybe_remove(store, "df") store.put("df", df) result = store.select("df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) _maybe_remove(store, "df") store.append("df", df) result = store.select("df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_tseries_select_index_column(setup_path): @@ -264,7 +263,7 @@ def test_timezones_fixed(setup_path): df = DataFrame(np.random.randn(len(rng), 4), index=rng) store["df"] = df result = store["df"] - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # as data # GH11411 @@ -280,7 +279,7 @@ def test_timezones_fixed(setup_path): ) store["df"] = df result = store["df"] - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_fixed_offset_tz(setup_path): @@ -307,20 +306,20 @@ def test_store_timezone(setup_path): df = DataFrame([1, 2, 3], index=[today, today, today]) store["obj1"] = df result = store["obj1"] - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) # with tz setting with ensure_clean_store(setup_path) as store: - with set_timezone("EST5EDT"): + with tm.set_timezone("EST5EDT"): today = datetime.date(2013, 9, 10) df = DataFrame([1, 2, 3], index=[today, today, today]) store["obj1"] = df - with set_timezone("CST6CDT"): + with tm.set_timezone("CST6CDT"): result = store["obj1"] - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_legacy_datetimetz_object(datapath, setup_path): @@ -336,7 +335,7 @@ def test_legacy_datetimetz_object(datapath, setup_path): datapath("io", "data", "legacy_hdf", "datetimetz_object.h5"), mode="r" ) as store: result = store["df"] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_dst_transitions(setup_path): @@ -355,7 +354,7 @@ def test_dst_transitions(setup_path): df = DataFrame({"A": range(len(i)), "B": i}, index=i) store.append("df", df) result = store.select("df") - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_read_with_where_tz_aware_index(setup_path): @@ -370,7 +369,7 @@ def test_read_with_where_tz_aware_index(setup_path): with pd.HDFStore(path) as store: store.append(key, expected, format="table", append=True) result = pd.read_hdf(path, key, where="DATE > 20151130") - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_py2_created_with_datetimez(datapath, setup_path): @@ -384,4 +383,4 @@ def test_py2_created_with_datetimez(datapath, setup_path): datapath("io", "data", "legacy_hdf", "gh26443.h5"), mode="r" ) as store: result = store["key"] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py index fccd52f9916b84..33e6d3b05100e9 100644 --- a/pandas/tests/io/test_clipboard.py +++ b/pandas/tests/io/test_clipboard.py @@ -6,8 +6,7 @@ import pandas as pd from pandas import DataFrame, get_option, read_clipboard -from pandas.util import testing as tm -from pandas.util.testing import makeCustomDataframe as mkdf +import pandas.util.testing as tm from pandas.io.clipboard import clipboard_get, clipboard_set from pandas.io.clipboard.exceptions import PyperclipException @@ -54,12 +53,12 @@ def df(request): {"a": ["\U0001f44d\U0001f44d", "\U0001f44d\U0001f44d"], "b": ["abc", "def"]} ) elif data_type == "string": - return mkdf( + return tm.makeCustomDataframe( 5, 3, c_idx_type="s", r_idx_type="i", c_idx_names=[None], r_idx_names=[None] ) elif data_type == "long": max_rows = get_option("display.max_rows") - return mkdf( + return tm.makeCustomDataframe( max_rows + 1, 3, data_gen_f=lambda *args: randint(2), @@ -72,7 +71,7 @@ def df(request): return pd.DataFrame({"en": "in English".split(), "es": "en español".split()}) elif data_type == "colwidth": _cw = get_option("display.max_colwidth") + 1 - return mkdf( + return tm.makeCustomDataframe( 5, 3, data_gen_f=lambda *args: "x" * _cw, @@ -86,7 +85,7 @@ def df(request): {"a": np.arange(1.0, 6.0) + 0.01, "b": np.arange(1, 6), "c": list("abcde")} ) elif data_type == "float": - return mkdf( + return tm.makeCustomDataframe( 5, 3, data_gen_f=lambda r, c: float(r) + 0.01, @@ -96,7 +95,7 @@ def df(request): r_idx_names=[None], ) elif data_type == "int": - return mkdf( + return tm.makeCustomDataframe( 5, 3, data_gen_f=lambda *args: randint(2), diff --git a/pandas/tests/io/test_feather.py b/pandas/tests/io/test_feather.py index ea69245924b0ca..0f68a6534dad1a 100644 --- a/pandas/tests/io/test_feather.py +++ b/pandas/tests/io/test_feather.py @@ -6,7 +6,6 @@ import pandas as pd import pandas.util.testing as tm -from pandas.util.testing import assert_frame_equal, ensure_clean from pandas.io.feather_format import read_feather, to_feather # noqa: E402 isort:skip @@ -25,7 +24,7 @@ def check_error_on_write(self, df, exc): # on writing with pytest.raises(exc): - with ensure_clean() as path: + with tm.ensure_clean() as path: to_feather(df, path) def check_round_trip(self, df, expected=None, **kwargs): @@ -33,11 +32,11 @@ def check_round_trip(self, df, expected=None, **kwargs): if expected is None: expected = df - with ensure_clean() as path: + with tm.ensure_clean() as path: to_feather(df, path) result = read_feather(path, **kwargs) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_error(self): diff --git a/pandas/tests/io/test_gcs.py b/pandas/tests/io/test_gcs.py index 8313b85d75ca7a..85ac56c8193a6d 100644 --- a/pandas/tests/io/test_gcs.py +++ b/pandas/tests/io/test_gcs.py @@ -6,7 +6,7 @@ from pandas import DataFrame, date_range, read_csv from pandas.util import _test_decorators as td -from pandas.util.testing import assert_frame_equal +import pandas.util.testing as tm from pandas.io.common import is_gcs_url @@ -35,7 +35,7 @@ def open(*args): monkeypatch.setattr("gcsfs.GCSFileSystem", MockGCSFileSystem) df2 = read_csv("gs://test/test.csv", parse_dates=["dt"]) - assert_frame_equal(df1, df2) + tm.assert_frame_equal(df1, df2) @td.skip_if_no("gcsfs") @@ -58,7 +58,7 @@ def open(*args): df1.to_csv("gs://test/test.csv", index=True) df2 = read_csv(StringIO(s.getvalue()), parse_dates=["dt"], index_col=0) - assert_frame_equal(df1, df2) + tm.assert_frame_equal(df1, df2) @td.skip_if_no("fastparquet") @@ -105,7 +105,7 @@ def mock_get_filepath_or_buffer(*args, **kwargs): ) df2 = read_csv("gs://test/test.csv", parse_dates=["dt"]) - assert_frame_equal(df1, df2) + tm.assert_frame_equal(df1, df2) @td.skip_if_installed("gcsfs") diff --git a/pandas/tests/io/test_html.py b/pandas/tests/io/test_html.py index f35707de189dc9..3d855a12d5481b 100644 --- a/pandas/tests/io/test_html.py +++ b/pandas/tests/io/test_html.py @@ -16,7 +16,6 @@ from pandas import DataFrame, Index, MultiIndex, Series, Timestamp, date_range, read_csv import pandas.util.testing as tm -from pandas.util.testing import makeCustomDataframe as mkdf, network from pandas.io.common import file_path_to_url import pandas.io.html @@ -108,7 +107,7 @@ def set_defaults(self, flavor, request): def test_to_html_compat(self): df = ( - mkdf( + tm.makeCustomDataframe( 4, 3, data_gen_f=lambda *args: rand(), @@ -122,7 +121,7 @@ def test_to_html_compat(self): res = self.read_html(out, attrs={"class": "dataframe"}, index_col=0)[0] tm.assert_frame_equal(res, df) - @network + @tm.network def test_banklist_url(self): url = "http://www.fdic.gov/bank/individual/failed/banklist.html" df1 = self.read_html( @@ -132,7 +131,7 @@ def test_banklist_url(self): assert_framelist_equal(df1, df2) - @network + @tm.network def test_spam_url(self): url = ( "https://raw.githubusercontent.com/pandas-dev/pandas/master/" @@ -275,12 +274,12 @@ def test_file_like(self): assert_framelist_equal(df1, df2) - @network + @tm.network def test_bad_url_protocol(self): with pytest.raises(URLError): self.read_html("git://github.com", match=".*Water.*") - @network + @tm.network @pytest.mark.slow def test_invalid_url(self): try: @@ -361,13 +360,13 @@ def test_negative_skiprows(self): with pytest.raises(ValueError, match=msg): self.read_html(self.spam_data, "Water", skiprows=-1) - @network + @tm.network def test_multiple_matches(self): url = "https://docs.python.org/2/" dfs = self.read_html(url, match="Python") assert len(dfs) > 1 - @network + @tm.network def test_python_docs_table(self): url = "https://docs.python.org/2/" dfs = self.read_html(url, match="Python") diff --git a/pandas/tests/io/test_packers.py b/pandas/tests/io/test_packers.py index 0bafbab069dd4b..f8005273319e02 100644 --- a/pandas/tests/io/test_packers.py +++ b/pandas/tests/io/test_packers.py @@ -26,13 +26,6 @@ period_range, ) import pandas.util.testing as tm -from pandas.util.testing import ( - assert_categorical_equal, - assert_frame_equal, - assert_index_equal, - assert_series_equal, - ensure_clean, -) from pandas.io.packers import read_msgpack, to_msgpack @@ -76,11 +69,11 @@ def check_arbitrary(a, b): for a_, b_ in zip(a, b): check_arbitrary(a_, b_) elif isinstance(a, DataFrame): - assert_frame_equal(a, b) + tm.assert_frame_equal(a, b) elif isinstance(a, Series): - assert_series_equal(a, b) + tm.assert_series_equal(a, b) elif isinstance(a, Index): - assert_index_equal(a, b) + tm.assert_index_equal(a, b) elif isinstance(a, Categorical): # Temp, # Categorical.categories is changed from str to bytes in PY3 @@ -107,7 +100,7 @@ def teardown_method(self, method): pass def encode_decode(self, x, compress=None, **kwargs): - with ensure_clean(self.path) as p: + with tm.ensure_clean(self.path) as p: to_msgpack(p, x, compress=compress, **kwargs) return read_msgpack(p, **kwargs) @@ -133,7 +126,7 @@ def test_string_io(self): result = read_msgpack(s) tm.assert_frame_equal(result, df) - with ensure_clean(self.path) as p: + with tm.ensure_clean(self.path) as p: s = df.to_msgpack() with open(p, "wb") as fh: @@ -462,7 +455,7 @@ def test_basic(self): for n in range(10): for s, i in self.d.items(): i_rec = self.encode_decode(i) - assert_series_equal(i, i_rec) + tm.assert_series_equal(i, i_rec) @pytest.mark.filterwarnings("ignore:.*msgpack:FutureWarning") @@ -486,7 +479,7 @@ def test_basic(self): for n in range(10): for s, i in self.d.items(): i_rec = self.encode_decode(i) - assert_categorical_equal(i, i_rec) + tm.assert_categorical_equal(i, i_rec) @pytest.mark.filterwarnings("ignore:msgpack:FutureWarning") @@ -516,13 +509,13 @@ def test_basic_frame(self): for s, i in self.frame.items(): i_rec = self.encode_decode(i) - assert_frame_equal(i, i_rec) + tm.assert_frame_equal(i, i_rec) def test_multi(self): i_rec = self.encode_decode(self.frame) for k in self.frame.keys(): - assert_frame_equal(self.frame[k], i_rec[k]) + tm.assert_frame_equal(self.frame[k], i_rec[k]) packed_items = tuple( [self.frame["float"], self.frame["float"].A, self.frame["float"].B, None] @@ -550,7 +543,7 @@ def test_iterator(self): None, ] - with ensure_clean(self.path) as path: + with tm.ensure_clean(self.path) as path: to_msgpack(path, *packed_items) for i, packed in enumerate(read_msgpack(path, iterator=True)): check_arbitrary(packed, packed_items[i]) @@ -561,11 +554,11 @@ def tests_datetimeindex_freq_issue(self): # inferring freq on the datetimeindex df = DataFrame([1, 2, 3], index=date_range("1/1/2013", "1/3/2013")) result = self.encode_decode(df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) df = DataFrame([1, 2], index=date_range("1/1/2013", "1/2/2013")) result = self.encode_decode(df) - assert_frame_equal(result, df) + tm.assert_frame_equal(result, df) def test_dataframe_duplicate_column_names(self): @@ -580,9 +573,9 @@ def test_dataframe_duplicate_column_names(self): result_2 = self.encode_decode(expected_2) result_3 = self.encode_decode(expected_3) - assert_frame_equal(result_1, expected_1) - assert_frame_equal(result_2, expected_2) - assert_frame_equal(result_3, expected_3) + tm.assert_frame_equal(result_1, expected_1) + tm.assert_frame_equal(result_2, expected_2) + tm.assert_frame_equal(result_3, expected_3) @pytest.mark.filterwarnings("ignore:.*msgpack:FutureWarning") @@ -617,14 +610,14 @@ def setup_method(self, method): def test_plain(self): i_rec = self.encode_decode(self.frame) for k in self.frame.keys(): - assert_frame_equal(self.frame[k], i_rec[k]) + tm.assert_frame_equal(self.frame[k], i_rec[k]) def _test_compression(self, compress): i_rec = self.encode_decode(self.frame, compress=compress) for k in self.frame.keys(): value = i_rec[k] expected = self.frame[k] - assert_frame_equal(value, expected) + tm.assert_frame_equal(value, expected) # make sure that we can write to the new frames for block in value._data.blocks: assert block.values.flags.writeable @@ -676,7 +669,7 @@ def decompress(ob): value = i_rec[k] expected = self.frame[k] - assert_frame_equal(value, expected) + tm.assert_frame_equal(value, expected) # make sure that we can write to the new frames even though # we needed to copy the data for block in value._data.blocks: @@ -773,7 +766,7 @@ def test_readonly_axis_blosc_to_sql(self): df.to_sql("test", eng, if_exists="append") result = pandas.read_sql_table("test", eng, index_col="index") result.index.names = [None] - assert_frame_equal(expected, result) + tm.assert_frame_equal(expected, result) def test_readonly_axis_zlib_to_sql(self): # GH11880 @@ -787,7 +780,7 @@ def test_readonly_axis_zlib_to_sql(self): df.to_sql("test", eng, if_exists="append") result = pandas.read_sql_table("test", eng, index_col="index") result.index.names = [None] - assert_frame_equal(expected, result) + tm.assert_frame_equal(expected, result) @pytest.mark.filterwarnings("ignore:.*msgpack:FutureWarning") @@ -814,7 +807,7 @@ def test_utf(self): for encoding in self.utf_encodings: for frame in self.frame.values(): result = self.encode_decode(frame, encoding=encoding) - assert_frame_equal(result, frame) + tm.assert_frame_equal(result, frame) def test_default_encoding(self): for frame in self.frame.values(): @@ -822,7 +815,7 @@ def test_default_encoding(self): expected = frame.to_msgpack(encoding="utf8") assert result == expected result = self.encode_decode(frame) - assert_frame_equal(result, frame) + tm.assert_frame_equal(result, frame) files = glob.glob(