From d3577aa6716f579141b7fa717e3fb2fd6f9db543 Mon Sep 17 00:00:00 2001 From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com> Date: Sun, 26 Nov 2023 19:41:17 -0800 Subject: [PATCH] Remmove makeMixedDataFrame and makeMixedData --- pandas/_testing/__init__.py | 19 ------------------- pandas/tests/frame/methods/test_transpose.py | 14 ++++++++++++-- pandas/tests/io/pytables/test_append.py | 9 ++++++++- pandas/tests/io/pytables/test_store.py | 9 ++++++++- pandas/tests/reshape/merge/test_join.py | 10 ++++++++-- pandas/tests/series/methods/test_map.py | 18 ++++++++++++++++-- pandas/tests/util/test_hashing.py | 18 ++++++++++++++++-- 7 files changed, 68 insertions(+), 29 deletions(-) diff --git a/pandas/_testing/__init__.py b/pandas/_testing/__init__.py index c73d869b6c39c..14ee29d24800e 100644 --- a/pandas/_testing/__init__.py +++ b/pandas/_testing/__init__.py @@ -482,23 +482,6 @@ def makeDataFrame() -> DataFrame: return DataFrame(data) -def getMixedTypeDict(): - index = Index(["a", "b", "c", "d", "e"]) - - data = { - "A": [0.0, 1.0, 2.0, 3.0, 4.0], - "B": [0.0, 1.0, 0.0, 1.0, 0.0], - "C": ["foo1", "foo2", "foo3", "foo4", "foo5"], - "D": bdate_range("1/1/2009", periods=5), - } - - return index, data - - -def makeMixedDataFrame() -> DataFrame: - return DataFrame(getMixedTypeDict()[1]) - - def makeCustomIndex( nentries, nlevels, @@ -1026,7 +1009,6 @@ def shares_memory(left, right) -> bool: "get_dtype", "getitem", "get_locales", - "getMixedTypeDict", "get_finest_unit", "get_obj", "get_op_from_name", @@ -1042,7 +1024,6 @@ def shares_memory(left, right) -> bool: "makeDateIndex", "makeFloatIndex", "makeIntIndex", - "makeMixedDataFrame", "makeNumericIndex", "makeObjectSeries", "makePeriodIndex", diff --git a/pandas/tests/frame/methods/test_transpose.py b/pandas/tests/frame/methods/test_transpose.py index 93a2f8d80019c..d0caa071fae1c 100644 --- a/pandas/tests/frame/methods/test_transpose.py +++ b/pandas/tests/frame/methods/test_transpose.py @@ -6,9 +6,11 @@ from pandas import ( DataFrame, DatetimeIndex, + Index, IntervalIndex, Series, Timestamp, + bdate_range, date_range, timedelta_range, ) @@ -108,9 +110,17 @@ def test_transpose_float(self, float_frame): else: assert value == frame[col][idx] + def test_transpose_mixed(self): # mixed type - index, data = tm.getMixedTypeDict() - mixed = DataFrame(data, index=index) + mixed = DataFrame( + { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": ["foo1", "foo2", "foo3", "foo4", "foo5"], + "D": bdate_range("1/1/2009", periods=5), + }, + index=Index(["a", "b", "c", "d", "e"], dtype=object), + ) mixed_T = mixed.T for col, s in mixed_T.items(): diff --git a/pandas/tests/io/pytables/test_append.py b/pandas/tests/io/pytables/test_append.py index 50cf7d737eb99..89a0162af1c54 100644 --- a/pandas/tests/io/pytables/test_append.py +++ b/pandas/tests/io/pytables/test_append.py @@ -397,7 +397,14 @@ def check_col(key, name, size): store.append("df_new", df_new) # min_itemsize on Series index (GH 11412) - df = tm.makeMixedDataFrame().set_index("C") + df = DataFrame( + { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": pd.Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object), + "D": date_range("20130101", periods=5), + } + ).set_index("C") store.append("ss", df["B"], min_itemsize={"index": 4}) tm.assert_series_equal(store.select("ss"), df["B"]) diff --git a/pandas/tests/io/pytables/test_store.py b/pandas/tests/io/pytables/test_store.py index df8a1e3cb7470..5b16ea9ee6b09 100644 --- a/pandas/tests/io/pytables/test_store.py +++ b/pandas/tests/io/pytables/test_store.py @@ -323,7 +323,14 @@ def test_to_hdf_with_min_itemsize(tmp_path, setup_path): path = tmp_path / setup_path # min_itemsize in index with to_hdf (GH 10381) - df = tm.makeMixedDataFrame().set_index("C") + df = DataFrame( + { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object), + "D": date_range("20130101", periods=5), + } + ).set_index("C") df.to_hdf(path, key="ss3", format="table", min_itemsize={"index": 6}) # just make sure there is a longer string: df2 = df.copy().reset_index().assign(C="longer").set_index("C") diff --git a/pandas/tests/reshape/merge/test_join.py b/pandas/tests/reshape/merge/test_join.py index c4c83e2046b76..f07c223bf0de2 100644 --- a/pandas/tests/reshape/merge/test_join.py +++ b/pandas/tests/reshape/merge/test_join.py @@ -11,6 +11,7 @@ MultiIndex, Series, Timestamp, + bdate_range, concat, merge, ) @@ -57,8 +58,13 @@ def df2(self): @pytest.fixture def target_source(self): - index, data = tm.getMixedTypeDict() - target = DataFrame(data, index=index) + data = { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": ["foo1", "foo2", "foo3", "foo4", "foo5"], + "D": bdate_range("1/1/2009", periods=5), + } + target = DataFrame(data, index=Index(["a", "b", "c", "d", "e"], dtype=object)) # Join on string value diff --git a/pandas/tests/series/methods/test_map.py b/pandas/tests/series/methods/test_map.py index f86f6069a2ef3..7b14e1289abf0 100644 --- a/pandas/tests/series/methods/test_map.py +++ b/pandas/tests/series/methods/test_map.py @@ -14,6 +14,7 @@ Index, MultiIndex, Series, + bdate_range, isna, timedelta_range, ) @@ -154,8 +155,13 @@ def test_list_raises(string_series): string_series.map([lambda x: x]) -def test_map(datetime_series): - index, data = tm.getMixedTypeDict() +def test_map(): + data = { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": ["foo1", "foo2", "foo3", "foo4", "foo5"], + "D": bdate_range("1/1/2009", periods=5), + } source = Series(data["B"], index=data["C"]) target = Series(data["C"][:4], index=data["D"][:4]) @@ -171,10 +177,14 @@ def test_map(datetime_series): for k, v in merged.items(): assert v == source[target[k]] + +def test_map_datetime(datetime_series): # function result = datetime_series.map(lambda x: x * 2) tm.assert_series_equal(result, datetime_series * 2) + +def test_map_category(): # GH 10324 a = Series([1, 2, 3, 4]) b = Series(["even", "odd", "even", "odd"], dtype="category") @@ -185,6 +195,8 @@ def test_map(datetime_series): exp = Series(["odd", "even", "odd", np.nan]) tm.assert_series_equal(a.map(c), exp) + +def test_map_category_numeric(): a = Series(["a", "b", "c", "d"]) b = Series([1, 2, 3, 4], index=pd.CategoricalIndex(["b", "c", "d", "e"])) c = Series([1, 2, 3, 4], index=Index(["b", "c", "d", "e"])) @@ -194,6 +206,8 @@ def test_map(datetime_series): exp = Series([np.nan, 1, 2, 3]) tm.assert_series_equal(a.map(c), exp) + +def test_map_category_string(): a = Series(["a", "b", "c", "d"]) b = Series( ["B", "C", "D", "E"], diff --git a/pandas/tests/util/test_hashing.py b/pandas/tests/util/test_hashing.py index e7c4c27714d5f..5f1d905aa4a46 100644 --- a/pandas/tests/util/test_hashing.py +++ b/pandas/tests/util/test_hashing.py @@ -136,7 +136,14 @@ def test_multiindex_objects(): DataFrame({"x": ["a", "b", "c"], "y": [1, 2, 3]}), DataFrame(), DataFrame(np.full((10, 4), np.nan)), - tm.makeMixedDataFrame(), + DataFrame( + { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object), + "D": pd.date_range("20130101", periods=5), + } + ), tm.makeTimeDataFrame(), tm.makeTimeSeries(), Series(tm.makePeriodIndex()), @@ -162,7 +169,14 @@ def test_hash_pandas_object(obj, index): Series([True, False, True]), DataFrame({"x": ["a", "b", "c"], "y": [1, 2, 3]}), DataFrame(np.full((10, 4), np.nan)), - tm.makeMixedDataFrame(), + DataFrame( + { + "A": [0.0, 1.0, 2.0, 3.0, 4.0], + "B": [0.0, 1.0, 0.0, 1.0, 0.0], + "C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object), + "D": pd.date_range("20130101", periods=5), + } + ), tm.makeTimeDataFrame(), tm.makeTimeSeries(), Series(tm.makePeriodIndex()),