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_explode.py (5294B)

import numpy as np
import pytest

import pandas as pd
import pandas._testing as tm

def test_error():
    df = pd.DataFrame(
        {"A": pd.Series([[0, 1, 2], np.nan, [], (3, 4)], index=list("abcd")), "B": 1}
    )
    with pytest.raises(ValueError, match="column must be a scalar"):
        df.explode(list("AA"))

df.columns = list("AA")
    with pytest.raises(ValueError, match="columns must be unique"):
        df.explode("A")

def test_basic():
    df = pd.DataFrame(
        {"A": pd.Series([[0, 1, 2], np.nan, [], (3, 4)], index=list("abcd")), "B": 1}
    )
    result = df.explode("A")
    expected = pd.DataFrame(
        {
            "A": pd.Series(
                [0, 1, 2, np.nan, np.nan, 3, 4], index=list("aaabcdd"), dtype=object
            ),
            "B": 1,
        }
    )
    tm.assert_frame_equal(result, expected)

def test_multi_index_rows():
    df = pd.DataFrame(
        {"A": np.array([[0, 1, 2], np.nan, [], (3, 4)], dtype=object), "B": 1},
        index=pd.MultiIndex.from_tuples([("a", 1), ("a", 2), ("b", 1), ("b", 2)]),
    )

result = df.explode("A")
    expected = pd.DataFrame(
        {
            "A": pd.Series(
                [0, 1, 2, np.nan, np.nan, 3, 4],
                index=pd.MultiIndex.from_tuples(
                    [
                        ("a", 1),
                        ("a", 1),
                        ("a", 1),
                        ("a", 2),
                        ("b", 1),
                        ("b", 2),
                        ("b", 2),
                    ]
                ),
                dtype=object,
            ),
            "B": 1,
        }
    )
    tm.assert_frame_equal(result, expected)

def test_multi_index_columns():
    df = pd.DataFrame(
        {("A", 1): np.array([[0, 1, 2], np.nan, [], (3, 4)], dtype=object), ("A", 2): 1}
    )

result = df.explode(("A", 1))
    expected = pd.DataFrame(
        {
            ("A", 1): pd.Series(
                [0, 1, 2, np.nan, np.nan, 3, 4],
                index=pd.Index([0, 0, 0, 1, 2, 3, 3]),
                dtype=object,
            ),
            ("A", 2): 1,
        }
    )
    tm.assert_frame_equal(result, expected)

def test_usecase():
    # explode a single column
    # gh-10511
    df = pd.DataFrame(
        [[11, range(5), 10], [22, range(3), 20]], columns=list("ABC")
    ).set_index("C")
    result = df.explode("B")

expected = pd.DataFrame(
        {
            "A": [11, 11, 11, 11, 11, 22, 22, 22],
            "B": np.array([0, 1, 2, 3, 4, 0, 1, 2], dtype=object),
            "C": [10, 10, 10, 10, 10, 20, 20, 20],
        },
        columns=list("ABC"),
    ).set_index("C")

tm.assert_frame_equal(result, expected)

# gh-8517
    df = pd.DataFrame(
        [["2014-01-01", "Alice", "A B"], ["2014-01-02", "Bob", "C D"]],
        columns=["dt", "name", "text"],
    )
    result = df.assign(text=df.text.str.split(" ")).explode("text")
    expected = pd.DataFrame(
        [
            ["2014-01-01", "Alice", "A"],
            ["2014-01-01", "Alice", "B"],
            ["2014-01-02", "Bob", "C"],
            ["2014-01-02", "Bob", "D"],
        ],
        columns=["dt", "name", "text"],
        index=[0, 0, 1, 1],
    )
    tm.assert_frame_equal(result, expected)

@pytest.mark.parametrize(
    "input_dict, input_index, expected_dict, expected_index",
    [
        (
            {"col1": [[1, 2], [3, 4]], "col2": ["foo", "bar"]},
            [0, 0],
            {"col1": [1, 2, 3, 4], "col2": ["foo", "foo", "bar", "bar"]},
            [0, 0, 0, 0],
        ),
        (
            {"col1": [[1, 2], [3, 4]], "col2": ["foo", "bar"]},
            pd.Index([0, 0], name="my_index"),
            {"col1": [1, 2, 3, 4], "col2": ["foo", "foo", "bar", "bar"]},
            pd.Index([0, 0, 0, 0], name="my_index"),
        ),
        (
            {"col1": [[1, 2], [3, 4]], "col2": ["foo", "bar"]},
            pd.MultiIndex.from_arrays(
                [[0, 0], [1, 1]], names=["my_first_index", "my_second_index"]
            ),
            {"col1": [1, 2, 3, 4], "col2": ["foo", "foo", "bar", "bar"]},
            pd.MultiIndex.from_arrays(
                [[0, 0, 0, 0], [1, 1, 1, 1]],
                names=["my_first_index", "my_second_index"],
            ),
        ),
        (
            {"col1": [[1, 2], [3, 4]], "col2": ["foo", "bar"]},
            pd.MultiIndex.from_arrays([[0, 0], [1, 1]], names=["my_index", None]),
            {"col1": [1, 2, 3, 4], "col2": ["foo", "foo", "bar", "bar"]},
            pd.MultiIndex.from_arrays(
                [[0, 0, 0, 0], [1, 1, 1, 1]], names=["my_index", None]
            ),
        ),
    ],
)
def test_duplicate_index(input_dict, input_index, expected_dict, expected_index):
    # GH 28005
    df = pd.DataFrame(input_dict, index=input_index)
    result = df.explode("col1")
    expected = pd.DataFrame(expected_dict, index=expected_index, dtype=object)
    tm.assert_frame_equal(result, expected)

def test_ignore_index():
    # GH 34932
    df = pd.DataFrame({"id": range(0, 20, 10), "values": [list("ab"), list("cd")]})
    result = df.explode("values", ignore_index=True)
    expected = pd.DataFrame(
        {"id": [0, 0, 10, 10], "values": list("abcd")}, index=[0, 1, 2, 3]
    )
    tm.assert_frame_equal(result, expected)

cmd: