FM / groupby

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

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

Name	Size	Mode	Actions
aggregate/	-	0755	rm
transform/	-	0755	rm
__pycache__/	-	0755	rm
conftest.py	3425	0644	edit dl rm
test_allowlist.py	10410	0644	edit dl rm
test_apply.py	31700	0644	edit dl rm
test_apply_mutate.py	1849	0644	edit dl rm
test_bin_groupby.py	4083	0644	edit dl rm
test_categorical.py	56137	0644	edit dl rm
test_counting.py	12289	0644	edit dl rm
test_filters.py	20402	0644	edit dl rm
test_function.py	32913	0644	edit dl rm
test_groupby.py	62594	0644	edit dl rm
test_groupby_dropna.py	7193	0644	edit dl rm
test_groupby_subclass.py	2676	0644	edit dl rm
test_grouping.py	35091	0644	edit dl rm
test_index_as_string.py	2069	0644	edit dl rm
test_nth.py	21112	0644	edit dl rm
test_nunique.py	5803	0644	edit dl rm
test_pipe.py	2075	0644	edit dl rm
test_quantile.py	8236	0644	edit dl rm
test_rank.py	15447	0644	edit dl rm
test_sample.py	4358	0644	edit dl rm
test_size.py	2149	0644	edit dl rm
test_timegrouper.py	28453	0644	edit dl rm
test_value_counts.py	3470	0644	edit dl rm
__init__.py	0	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/pandas/tests/groupby/test_value_counts.py (3470B)

"""
these are systematically testing all of the args to value_counts
with different size combinations. This is to ensure stability of the sorting
and proper parameter handling
"""

from itertools import product

import numpy as np
import pytest

from pandas import DataFrame, Grouper, MultiIndex, Series, date_range, to_datetime
import pandas._testing as tm

# our starting frame
def seed_df(seed_nans, n, m):
    np.random.seed(1234)
    days = date_range("2015-08-24", periods=10)

frame = DataFrame(
        {
            "1st": np.random.choice(list("abcd"), n),
            "2nd": np.random.choice(days, n),
            "3rd": np.random.randint(1, m + 1, n),
        }
    )

if seed_nans:
        frame.loc[1::11, "1st"] = np.nan
        frame.loc[3::17, "2nd"] = np.nan
        frame.loc[7::19, "3rd"] = np.nan
        frame.loc[8::19, "3rd"] = np.nan
        frame.loc[9::19, "3rd"] = np.nan

return frame

# create input df, keys, and the bins
binned = []
ids = []
for seed_nans in [True, False]:
    for n, m in product((100, 1000), (5, 20)):

df = seed_df(seed_nans, n, m)
        bins = None, np.arange(0, max(5, df["3rd"].max()) + 1, 2)
        keys = "1st", "2nd", ["1st", "2nd"]
        for k, b in product(keys, bins):
            binned.append((df, k, b, n, m))
            ids.append(f"{k}-{n}-{m}")

@pytest.mark.slow
@pytest.mark.parametrize("df, keys, bins, n, m", binned, ids=ids)
@pytest.mark.parametrize("isort", [True, False])
@pytest.mark.parametrize("normalize", [True, False])
@pytest.mark.parametrize("sort", [True, False])
@pytest.mark.parametrize("ascending", [True, False])
@pytest.mark.parametrize("dropna", [True, False])
def test_series_groupby_value_counts(
    df, keys, bins, n, m, isort, normalize, sort, ascending, dropna
):
    def rebuild_index(df):
        arr = list(map(df.index.get_level_values, range(df.index.nlevels)))
        df.index = MultiIndex.from_arrays(arr, names=df.index.names)
        return df

kwargs = dict(
        normalize=normalize, sort=sort, ascending=ascending, dropna=dropna, bins=bins
    )

gr = df.groupby(keys, sort=isort)
    left = gr["3rd"].value_counts(**kwargs)

gr = df.groupby(keys, sort=isort)
    right = gr["3rd"].apply(Series.value_counts, **kwargs)
    right.index.names = right.index.names[:-1] + ["3rd"]

# have to sort on index because of unstable sort on values
    left, right = map(rebuild_index, (left, right))  # xref GH9212
    tm.assert_series_equal(left.sort_index(), right.sort_index())

def test_series_groupby_value_counts_with_grouper():
    # GH28479
    df = DataFrame(
        {
            "Timestamp": [
                1565083561,
                1565083561 + 86400,
                1565083561 + 86500,
                1565083561 + 86400 * 2,
                1565083561 + 86400 * 3,
                1565083561 + 86500 * 3,
                1565083561 + 86400 * 4,
            ],
            "Food": ["apple", "apple", "banana", "banana", "orange", "orange", "pear"],
        }
    ).drop([3])

df["Datetime"] = to_datetime(df["Timestamp"].apply(lambda t: str(t)), unit="s")
    dfg = df.groupby(Grouper(freq="1D", key="Datetime"))

# have to sort on index because of unstable sort on values xref GH9212
    result = dfg["Food"].value_counts().sort_index()
    expected = dfg["Food"].apply(Series.value_counts).sort_index()
    expected.index.names = result.index.names

tm.assert_series_equal(result, expected)

""" these are systematically testing all of the args to value_counts with different size combinations. This is to ensure stability of the sorting and proper parameter handling """ from itertools import product import numpy as np import pytest from pandas import DataFrame, Grouper, MultiIndex, Series, date_range, to_datetime import pandas._testing as tm # our starting frame def seed_df(seed_nans, n, m): np.random.seed(1234) days = date_range("2015-08-24", periods=10) frame = DataFrame( { "1st": np.random.choice(list("abcd"), n), "2nd": np.random.choice(days, n), "3rd": np.random.randint(1, m + 1, n), } ) if seed_nans: frame.loc[1::11, "1st"] = np.nan frame.loc[3::17, "2nd"] = np.nan frame.loc[7::19, "3rd"] = np.nan frame.loc[8::19, "3rd"] = np.nan frame.loc[9::19, "3rd"] = np.nan return frame # create input df, keys, and the bins binned = [] ids = [] for seed_nans in [True, False]: for n, m in product((100, 1000), (5, 20)): df = seed_df(seed_nans, n, m) bins = None, np.arange(0, max(5, df["3rd"].max()) + 1, 2) keys = "1st", "2nd", ["1st", "2nd"] for k, b in product(keys, bins): binned.append((df, k, b, n, m)) ids.append(f"{k}-{n}-{m}") @pytest.mark.slow @pytest.mark.parametrize("df, keys, bins, n, m", binned, ids=ids) @pytest.mark.parametrize("isort", [True, False]) @pytest.mark.parametrize("normalize", [True, False]) @pytest.mark.parametrize("sort", [True, False]) @pytest.mark.parametrize("ascending", [True, False]) @pytest.mark.parametrize("dropna", [True, False]) def test_series_groupby_value_counts( df, keys, bins, n, m, isort, normalize, sort, ascending, dropna ): def rebuild_index(df): arr = list(map(df.index.get_level_values, range(df.index.nlevels))) df.index = MultiIndex.from_arrays(arr, names=df.index.names) return df kwargs = dict( normalize=normalize, sort=sort, ascending=ascending, dropna=dropna, bins=bins ) gr = df.groupby(keys, sort=isort) left = gr["3rd"].value_counts(**kwargs) gr = df.groupby(keys, sort=isort) right = gr["3rd"].apply(Series.value_counts, **kwargs) right.index.names = right.index.names[:-1] + ["3rd"] # have to sort on index because of unstable sort on values left, right = map(rebuild_index, (left, right)) # xref GH9212 tm.assert_series_equal(left.sort_index(), right.sort_index()) def test_series_groupby_value_counts_with_grouper(): # GH28479 df = DataFrame( { "Timestamp": [ 1565083561, 1565083561 + 86400, 1565083561 + 86500, 1565083561 + 86400 * 2, 1565083561 + 86400 * 3, 1565083561 + 86500 * 3, 1565083561 + 86400 * 4, ], "Food": ["apple", "apple", "banana", "banana", "orange", "orange", "pear"], } ).drop([3]) df["Datetime"] = to_datetime(df["Timestamp"].apply(lambda t: str(t)), unit="s") dfg = df.groupby(Grouper(freq="1D", key="Datetime")) # have to sort on index because of unstable sort on values xref GH9212 result = dfg["Food"].value_counts().sort_index() expected = dfg["Food"].apply(Series.value_counts).sort_index() expected.index.names = result.index.names tm.assert_series_equal(result, expected)