FM / methods

/usr/local/lib64/python3.6/site-packages/pandas/tests/series/methods/

/usr/local/lib64/python3.6/site-packages/pandas/tests/series/methods

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
test_align.py	5359	0644	edit dl rm
test_append.py	9600	0644	edit dl rm
test_argsort.py	2249	0644	edit dl rm
test_asfreq.py	3616	0644	edit dl rm
test_asof.py	5515	0644	edit dl rm
test_astype.py	2628	0644	edit dl rm
test_at_time.py	2629	0644	edit dl rm
test_autocorr.py	999	0644	edit dl rm
test_between.py	1197	0644	edit dl rm
test_between_time.py	5086	0644	edit dl rm
test_clip.py	3384	0644	edit dl rm
test_combine.py	627	0644	edit dl rm
test_combine_first.py	3411	0644	edit dl rm
test_compare.py	3734	0644	edit dl rm
test_convert_dtypes.py	9914	0644	edit dl rm
test_count.py	1123	0644	edit dl rm
test_cov_corr.py	5215	0644	edit dl rm
test_describe.py	4640	0644	edit dl rm
test_diff.py	2331	0644	edit dl rm
test_drop.py	2986	0644	edit dl rm
test_droplevel.py	629	0644	edit dl rm
test_drop_duplicates.py	6850	0644	edit dl rm
test_duplicated.py	996	0644	edit dl rm
test_equals.py	1295	0644	edit dl rm
test_explode.py	3538	0644	edit dl rm
test_fillna.py	6513	0644	edit dl rm
test_first_and_last.py	2042	0644	edit dl rm
test_head_tail.py	343	0644	edit dl rm
test_interpolate.py	27757	0644	edit dl rm
test_isin.py	3445	0644	edit dl rm
test_nlargest.py	7121	0644	edit dl rm
test_pct_change.py	2968	0644	edit dl rm
test_quantile.py	6810	0644	edit dl rm
test_rank.py	20287	0644	edit dl rm
test_reindex_like.py	1245	0644	edit dl rm
test_rename.py	3378	0644	edit dl rm
test_rename_axis.py	1503	0644	edit dl rm
test_replace.py	15559	0644	edit dl rm
test_reset_index.py	4636	0644	edit dl rm
test_round.py	1970	0644	edit dl rm
test_searchsorted.py	2121	0644	edit dl rm
test_shift.py	12595	0644	edit dl rm
test_sort_index.py	12277	0644	edit dl rm
test_sort_values.py	7981	0644	edit dl rm
test_to_dict.py	742	0644	edit dl rm
test_to_period.py	1755	0644	edit dl rm
test_to_timestamp.py	2616	0644	edit dl rm
test_truncate.py	5557	0644	edit dl rm
test_tz_convert.py	1008	0644	edit dl rm
test_tz_localize.py	3108	0644	edit dl rm
test_unstack.py	4208	0644	edit dl rm
test_update.py	4213	0644	edit dl rm
test_value_counts.py	8136	0644	edit dl rm
__init__.py	225	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/pandas/tests/series/methods/test_drop_duplicates.py (6850B)

import numpy as np
import pytest

from pandas import Categorical, Series
import pandas._testing as tm

@pytest.mark.parametrize(
    "keep, expected",
    [
        ("first", Series([False, False, False, False, True, True, False])),
        ("last", Series([False, True, True, False, False, False, False])),
        (False, Series([False, True, True, False, True, True, False])),
    ],
)
def test_drop_duplicates(any_numpy_dtype, keep, expected):
    tc = Series([1, 0, 3, 5, 3, 0, 4], dtype=np.dtype(any_numpy_dtype))

if tc.dtype == "bool":
        pytest.skip("tested separately in test_drop_duplicates_bool")

tm.assert_series_equal(tc.duplicated(keep=keep), expected)
    tm.assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected])
    sc = tc.copy()
    return_value = sc.drop_duplicates(keep=keep, inplace=True)
    assert return_value is None
    tm.assert_series_equal(sc, tc[~expected])

@pytest.mark.parametrize(
    "keep, expected",
    [
        ("first", Series([False, False, True, True])),
        ("last", Series([True, True, False, False])),
        (False, Series([True, True, True, True])),
    ],
)
def test_drop_duplicates_bool(keep, expected):
    tc = Series([True, False, True, False])

tm.assert_series_equal(tc.duplicated(keep=keep), expected)
    tm.assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected])
    sc = tc.copy()
    return_value = sc.drop_duplicates(keep=keep, inplace=True)
    tm.assert_series_equal(sc, tc[~expected])
    assert return_value is None

@pytest.mark.parametrize("values", [[], list(range(5))])
def test_drop_duplicates_no_duplicates(any_numpy_dtype, keep, values):
    tc = Series(values, dtype=np.dtype(any_numpy_dtype))
    expected = Series([False] * len(tc), dtype="bool")

if tc.dtype == "bool":
        # 0 -> False and 1-> True
        # any other value would be duplicated
        tc = tc[:2]
        expected = expected[:2]

tm.assert_series_equal(tc.duplicated(keep=keep), expected)

result_dropped = tc.drop_duplicates(keep=keep)
    tm.assert_series_equal(result_dropped, tc)

# validate shallow copy
    assert result_dropped is not tc

class TestSeriesDropDuplicates:
    @pytest.mark.parametrize(
        "dtype",
        ["int_", "uint", "float_", "unicode_", "timedelta64[h]", "datetime64[D]"],
    )
    def test_drop_duplicates_categorical_non_bool(self, dtype, ordered):
        cat_array = np.array([1, 2, 3, 4, 5], dtype=np.dtype(dtype))

# Test case 1
        input1 = np.array([1, 2, 3, 3], dtype=np.dtype(dtype))
        tc1 = Series(Categorical(input1, categories=cat_array, ordered=ordered))
        if dtype == "datetime64[D]":
            # pre-empty flaky xfail, tc1 values are seemingly-random
            if not (np.array(tc1) == input1).all():
                pytest.xfail(reason="GH#7996")

expected = Series([False, False, False, True])
        tm.assert_series_equal(tc1.duplicated(), expected)
        tm.assert_series_equal(tc1.drop_duplicates(), tc1[~expected])
        sc = tc1.copy()
        return_value = sc.drop_duplicates(inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc1[~expected])

expected = Series([False, False, True, False])
        tm.assert_series_equal(tc1.duplicated(keep="last"), expected)
        tm.assert_series_equal(tc1.drop_duplicates(keep="last"), tc1[~expected])
        sc = tc1.copy()
        return_value = sc.drop_duplicates(keep="last", inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc1[~expected])

expected = Series([False, False, True, True])
        tm.assert_series_equal(tc1.duplicated(keep=False), expected)
        tm.assert_series_equal(tc1.drop_duplicates(keep=False), tc1[~expected])
        sc = tc1.copy()
        return_value = sc.drop_duplicates(keep=False, inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc1[~expected])

# Test case 2
        input2 = np.array([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(dtype))
        tc2 = Series(Categorical(input2, categories=cat_array, ordered=ordered))
        if dtype == "datetime64[D]":
            # pre-empty flaky xfail, tc2 values are seemingly-random
            if not (np.array(tc2) == input2).all():
                pytest.xfail(reason="GH#7996")

expected = Series([False, False, False, False, True, True, False])
        tm.assert_series_equal(tc2.duplicated(), expected)
        tm.assert_series_equal(tc2.drop_duplicates(), tc2[~expected])
        sc = tc2.copy()
        return_value = sc.drop_duplicates(inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc2[~expected])

expected = Series([False, True, True, False, False, False, False])
        tm.assert_series_equal(tc2.duplicated(keep="last"), expected)
        tm.assert_series_equal(tc2.drop_duplicates(keep="last"), tc2[~expected])
        sc = tc2.copy()
        return_value = sc.drop_duplicates(keep="last", inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc2[~expected])

expected = Series([False, True, True, False, True, True, False])
        tm.assert_series_equal(tc2.duplicated(keep=False), expected)
        tm.assert_series_equal(tc2.drop_duplicates(keep=False), tc2[~expected])
        sc = tc2.copy()
        return_value = sc.drop_duplicates(keep=False, inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc2[~expected])

def test_drop_duplicates_categorical_bool(self, ordered):
        tc = Series(
            Categorical(
                [True, False, True, False], categories=[True, False], ordered=ordered,
            )
        )

expected = Series([False, False, True, True])
        tm.assert_series_equal(tc.duplicated(), expected)
        tm.assert_series_equal(tc.drop_duplicates(), tc[~expected])
        sc = tc.copy()
        return_value = sc.drop_duplicates(inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc[~expected])

expected = Series([True, True, False, False])
        tm.assert_series_equal(tc.duplicated(keep="last"), expected)
        tm.assert_series_equal(tc.drop_duplicates(keep="last"), tc[~expected])
        sc = tc.copy()
        return_value = sc.drop_duplicates(keep="last", inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc[~expected])

expected = Series([True, True, True, True])
        tm.assert_series_equal(tc.duplicated(keep=False), expected)
        tm.assert_series_equal(tc.drop_duplicates(keep=False), tc[~expected])
        sc = tc.copy()
        return_value = sc.drop_duplicates(keep=False, inplace=True)
        assert return_value is None
        tm.assert_series_equal(sc, tc[~expected])

import numpy as np import pytest from pandas import Categorical, Series import pandas._testing as tm @pytest.mark.parametrize( "keep, expected", [ ("first", Series([False, False, False, False, True, True, False])), ("last", Series([False, True, True, False, False, False, False])), (False, Series([False, True, True, False, True, True, False])), ], ) def test_drop_duplicates(any_numpy_dtype, keep, expected): tc = Series([1, 0, 3, 5, 3, 0, 4], dtype=np.dtype(any_numpy_dtype)) if tc.dtype == "bool": pytest.skip("tested separately in test_drop_duplicates_bool") tm.assert_series_equal(tc.duplicated(keep=keep), expected) tm.assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected]) sc = tc.copy() return_value = sc.drop_duplicates(keep=keep, inplace=True) assert return_value is None tm.assert_series_equal(sc, tc[~expected]) @pytest.mark.parametrize( "keep, expected", [ ("first", Series([False, False, True, True])), ("last", Series([True, True, False, False])), (False, Series([True, True, True, True])), ], ) def test_drop_duplicates_bool(keep, expected): tc = Series([True, False, True, False]) tm.assert_series_equal(tc.duplicated(keep=keep), expected) tm.assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected]) sc = tc.copy() return_value = sc.drop_duplicates(keep=keep, inplace=True) tm.assert_series_equal(sc, tc[~expected]) assert return_value is None @pytest.mark.parametrize("values", [[], list(range(5))]) def test_drop_duplicates_no_duplicates(any_numpy_dtype, keep, values): tc = Series(values, dtype=np.dtype(any_numpy_dtype)) expected = Series([False] * len(tc), dtype="bool") if tc.dtype == "bool": # 0 -> False and 1-> True # any other value would be duplicated tc = tc[:2] expected = expected[:2] tm.assert_series_equal(tc.duplicated(keep=keep), expected) result_dropped = tc.drop_duplicates(keep=keep) tm.assert_series_equal(result_dropped, tc) # validate shallow copy assert result_dropped is not tc class TestSeriesDropDuplicates: @pytest.mark.parametrize( "dtype", ["int_", "uint", "float_", "unicode_", "timedelta64[h]", "datetime64[D]"], ) def test_drop_duplicates_categorical_non_bool(self, dtype, ordered): cat_array = np.array([1, 2, 3, 4, 5], dtype=np.dtype(dtype)) # Test case 1 input1 = np.array([1, 2, 3, 3], dtype=np.dtype(dtype)) tc1 = Series(Categorical(input1, categories=cat_array, ordered=ordered)) if dtype == "datetime64[D]": # pre-empty flaky xfail, tc1 values are seemingly-random if not (np.array(tc1) == input1).all(): pytest.xfail(reason="GH#7996") expected = Series([False, False, False, True]) tm.assert_series_equal(tc1.duplicated(), expected) tm.assert_series_equal(tc1.drop_duplicates(), tc1[~expected]) sc = tc1.copy() return_value = sc.drop_duplicates(inplace=True) assert return_value is None tm.assert_series_equal(sc, tc1[~expected]) expected = Series([False, False, True, False]) tm.assert_series_equal(tc1.duplicated(keep="last"), expected) tm.assert_series_equal(tc1.drop_duplicates(keep="last"), tc1[~expected]) sc = tc1.copy() return_value = sc.drop_duplicates(keep="last", inplace=True) assert return_value is None tm.assert_series_equal(sc, tc1[~expected]) expected = Series([False, False, True, True]) tm.assert_series_equal(tc1.duplicated(keep=False), expected) tm.assert_series_equal(tc1.drop_duplicates(keep=False), tc1[~expected]) sc = tc1.copy() return_value = sc.drop_duplicates(keep=False, inplace=True) assert return_value is None tm.assert_series_equal(sc, tc1[~expected]) # Test case 2 input2 = np.array([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(dtype)) tc2 = Series(Categorical(input2, categories=cat_array, ordered=ordered)) if dtype == "datetime64[D]": # pre-empty flaky xfail, tc2 values are seemingly-random if not (np.array(tc2) == input2).all(): pytest.xfail(reason="GH#7996") expected = Series([False, False, False, False, True, True, False]) tm.assert_series_equal(tc2.duplicated(), expected) tm.assert_series_equal(tc2.drop_duplicates(), tc2[~expected]) sc = tc2.copy() return_value = sc.drop_duplicates(inplace=True) assert return_value is None tm.assert_series_equal(sc, tc2[~expected]) expected = Series([False, True, True, False, False, False, False]) tm.assert_series_equal(tc2.duplicated(keep="last"), expected) tm.assert_series_equal(tc2.drop_duplicates(keep="last"), tc2[~expected]) sc = tc2.copy() return_value = sc.drop_duplicates(keep="last", inplace=True) assert return_value is None tm.assert_series_equal(sc, tc2[~expected]) expected = Series([False, True, True, False, True, True, False]) tm.assert_series_equal(tc2.duplicated(keep=False), expected) tm.assert_series_equal(tc2.drop_duplicates(keep=False), tc2[~expected]) sc = tc2.copy() return_value = sc.drop_duplicates(keep=False, inplace=True) assert return_value is None tm.assert_series_equal(sc, tc2[~expected]) def test_drop_duplicates_categorical_bool(self, ordered): tc = Series( Categorical( [True, False, True, False], categories=[True, False], ordered=ordered, ) ) expected = Series([False, False, True, True]) tm.assert_series_equal(tc.duplicated(), expected) tm.assert_series_equal(tc.drop_duplicates(), tc[~expected]) sc = tc.copy() return_value = sc.drop_duplicates(inplace=True) assert return_value is None tm.assert_series_equal(sc, tc[~expected]) expected = Series([True, True, False, False]) tm.assert_series_equal(tc.duplicated(keep="last"), expected) tm.assert_series_equal(tc.drop_duplicates(keep="last"), tc[~expected]) sc = tc.copy() return_value = sc.drop_duplicates(keep="last", inplace=True) assert return_value is None tm.assert_series_equal(sc, tc[~expected]) expected = Series([True, True, True, True]) tm.assert_series_equal(tc.duplicated(keep=False), expected) tm.assert_series_equal(tc.drop_duplicates(keep=False), tc[~expected]) sc = tc.copy() return_value = sc.drop_duplicates(keep=False, inplace=True) assert return_value is None tm.assert_series_equal(sc, tc[~expected])