FM / methods

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

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

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
test_align.py	10339	0644	edit dl rm
test_append.py	7399	0644	edit dl rm
test_asfreq.py	1970	0644	edit dl rm
test_asof.py	5767	0644	edit dl rm
test_assign.py	2982	0644	edit dl rm
test_astype.py	21027	0644	edit dl rm
test_at_time.py	3205	0644	edit dl rm
test_between_time.py	3675	0644	edit dl rm
test_clip.py	6028	0644	edit dl rm
test_combine.py	1359	0644	edit dl rm
test_combine_first.py	12748	0644	edit dl rm
test_compare.py	6158	0644	edit dl rm
test_count.py	1068	0644	edit dl rm
test_cov_corr.py	11888	0644	edit dl rm
test_describe.py	12492	0644	edit dl rm
test_diff.py	7374	0644	edit dl rm
test_drop.py	15662	0644	edit dl rm
test_droplevel.py	855	0644	edit dl rm
test_drop_duplicates.py	13387	0644	edit dl rm
test_duplicated.py	3191	0644	edit dl rm
test_explode.py	5294	0644	edit dl rm
test_filter.py	4933	0644	edit dl rm
test_first_and_last.py	1803	0644	edit dl rm
test_head_tail.py	1194	0644	edit dl rm
test_interpolate.py	11816	0644	edit dl rm
test_isin.py	7324	0644	edit dl rm
test_nlargest.py	6731	0644	edit dl rm
test_pct_change.py	3436	0644	edit dl rm
test_pop.py	1226	0644	edit dl rm
test_quantile.py	18028	0644	edit dl rm
test_rank.py	11377	0644	edit dl rm
test_reindex_like.py	1187	0644	edit dl rm
test_rename.py	12543	0644	edit dl rm
test_rename_axis.py	4074	0644	edit dl rm
test_replace.py	59230	0644	edit dl rm
test_reset_index.py	12506	0644	edit dl rm
test_round.py	7916	0644	edit dl rm
test_select_dtypes.py	12104	0644	edit dl rm
test_set_index.py	19571	0644	edit dl rm
test_shift.py	10324	0644	edit dl rm
test_sort_index.py	25678	0644	edit dl rm
test_sort_values.py	25358	0644	edit dl rm
test_to_dict.py	9989	0644	edit dl rm
test_to_period.py	984	0644	edit dl rm
test_to_records.py	13981	0644	edit dl rm
test_to_timestamp.py	4020	0644	edit dl rm
test_transpose.py	2426	0644	edit dl rm
test_truncate.py	4180	0644	edit dl rm
test_tz_convert.py	3415	0644	edit dl rm
test_tz_localize.py	666	0644	edit dl rm
test_update.py	4259	0644	edit dl rm
test_value_counts.py	2631	0644	edit dl rm
__init__.py	229	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/pandas/tests/frame/methods/test_duplicated.py (3191B)

import re

import numpy as np
import pytest

from pandas import DataFrame, Series, date_range
import pandas._testing as tm

@pytest.mark.parametrize("subset", ["a", ["a"], ["a", "B"]])
def test_duplicated_with_misspelled_column_name(subset):
    # GH 19730
    df = DataFrame({"A": [0, 0, 1], "B": [0, 0, 1], "C": [0, 0, 1]})
    msg = re.escape("Index(['a'], dtype='object')")

with pytest.raises(KeyError, match=msg):
        df.duplicated(subset)

@pytest.mark.slow
def test_duplicated_do_not_fail_on_wide_dataframes():
    # gh-21524
    # Given the wide dataframe with a lot of columns
    # with different (important!) values
    data = {f"col_{i:02d}": np.random.randint(0, 1000, 30000) for i in range(100)}
    df = DataFrame(data).T
    result = df.duplicated()

# Then duplicates produce the bool Series as a result and don't fail during
    # calculation. Actual values doesn't matter here, though usually it's all
    # False in this case
    assert isinstance(result, Series)
    assert result.dtype == np.bool_

@pytest.mark.parametrize(
    "keep, expected",
    [
        ("first", Series([False, False, True, False, True])),
        ("last", Series([True, True, False, False, False])),
        (False, Series([True, True, True, False, True])),
    ],
)
def test_duplicated_keep(keep, expected):
    df = DataFrame({"A": [0, 1, 1, 2, 0], "B": ["a", "b", "b", "c", "a"]})

result = df.duplicated(keep=keep)
    tm.assert_series_equal(result, expected)

@pytest.mark.xfail(reason="GH#21720; nan/None falsely considered equal")
@pytest.mark.parametrize(
    "keep, expected",
    [
        ("first", Series([False, False, True, False, True])),
        ("last", Series([True, True, False, False, False])),
        (False, Series([True, True, True, False, True])),
    ],
)
def test_duplicated_nan_none(keep, expected):
    df = DataFrame({"C": [np.nan, 3, 3, None, np.nan]}, dtype=object)

result = df.duplicated(keep=keep)
    tm.assert_series_equal(result, expected)

@pytest.mark.parametrize("subset", [None, ["A", "B"], "A"])
def test_duplicated_subset(subset, keep):
    df = DataFrame(
        {
            "A": [0, 1, 1, 2, 0],
            "B": ["a", "b", "b", "c", "a"],
            "C": [np.nan, 3, 3, None, np.nan],
        }
    )

if subset is None:
        subset = list(df.columns)
    elif isinstance(subset, str):
        # need to have a DataFrame, not a Series
        # -> select columns with singleton list, not string
        subset = [subset]

expected = df[subset].duplicated(keep=keep)
    result = df.duplicated(keep=keep, subset=subset)
    tm.assert_series_equal(result, expected)

def test_duplicated_on_empty_frame():
    # GH 25184

df = DataFrame(columns=["a", "b"])
    dupes = df.duplicated("a")

result = df[dupes]
    expected = df.copy()
    tm.assert_frame_equal(result, expected)

def test_frame_datetime64_duplicated():
    dates = date_range("2010-07-01", end="2010-08-05")

tst = DataFrame({"symbol": "AAA", "date": dates})
    result = tst.duplicated(["date", "symbol"])
    assert (-result).all()

tst = DataFrame({"date": dates})
    result = tst.duplicated()
    assert (-result).all()

import re import numpy as np import pytest from pandas import DataFrame, Series, date_range import pandas._testing as tm @pytest.mark.parametrize("subset", ["a", ["a"], ["a", "B"]]) def test_duplicated_with_misspelled_column_name(subset): # GH 19730 df = DataFrame({"A": [0, 0, 1], "B": [0, 0, 1], "C": [0, 0, 1]}) msg = re.escape("Index(['a'], dtype='object')") with pytest.raises(KeyError, match=msg): df.duplicated(subset) @pytest.mark.slow def test_duplicated_do_not_fail_on_wide_dataframes(): # gh-21524 # Given the wide dataframe with a lot of columns # with different (important!) values data = {f"col_{i:02d}": np.random.randint(0, 1000, 30000) for i in range(100)} df = DataFrame(data).T result = df.duplicated() # Then duplicates produce the bool Series as a result and don't fail during # calculation. Actual values doesn't matter here, though usually it's all # False in this case assert isinstance(result, Series) assert result.dtype == np.bool_ @pytest.mark.parametrize( "keep, expected", [ ("first", Series([False, False, True, False, True])), ("last", Series([True, True, False, False, False])), (False, Series([True, True, True, False, True])), ], ) def test_duplicated_keep(keep, expected): df = DataFrame({"A": [0, 1, 1, 2, 0], "B": ["a", "b", "b", "c", "a"]}) result = df.duplicated(keep=keep) tm.assert_series_equal(result, expected) @pytest.mark.xfail(reason="GH#21720; nan/None falsely considered equal") @pytest.mark.parametrize( "keep, expected", [ ("first", Series([False, False, True, False, True])), ("last", Series([True, True, False, False, False])), (False, Series([True, True, True, False, True])), ], ) def test_duplicated_nan_none(keep, expected): df = DataFrame({"C": [np.nan, 3, 3, None, np.nan]}, dtype=object) result = df.duplicated(keep=keep) tm.assert_series_equal(result, expected) @pytest.mark.parametrize("subset", [None, ["A", "B"], "A"]) def test_duplicated_subset(subset, keep): df = DataFrame( { "A": [0, 1, 1, 2, 0], "B": ["a", "b", "b", "c", "a"], "C": [np.nan, 3, 3, None, np.nan], } ) if subset is None: subset = list(df.columns) elif isinstance(subset, str): # need to have a DataFrame, not a Series # -> select columns with singleton list, not string subset = [subset] expected = df[subset].duplicated(keep=keep) result = df.duplicated(keep=keep, subset=subset) tm.assert_series_equal(result, expected) def test_duplicated_on_empty_frame(): # GH 25184 df = DataFrame(columns=["a", "b"]) dupes = df.duplicated("a") result = df[dupes] expected = df.copy() tm.assert_frame_equal(result, expected) def test_frame_datetime64_duplicated(): dates = date_range("2010-07-01", end="2010-08-05") tst = DataFrame({"symbol": "AAA", "date": dates}) result = tst.duplicated(["date", "symbol"]) assert (-result).all() tst = DataFrame({"date": dates}) result = tst.duplicated() assert (-result).all()