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_apply_mutate.py (1849B)

import numpy as np

import pandas as pd
import pandas._testing as tm

def test_mutate_groups():

# GH3380

df = pd.DataFrame(
        {
            "cat1": ["a"] * 8 + ["b"] * 6,
            "cat2": ["c"] * 2
            + ["d"] * 2
            + ["e"] * 2
            + ["f"] * 2
            + ["c"] * 2
            + ["d"] * 2
            + ["e"] * 2,
            "cat3": [f"g{x}" for x in range(1, 15)],
            "val": np.random.randint(100, size=14),
        }
    )

def f_copy(x):
        x = x.copy()
        x["rank"] = x.val.rank(method="min")
        return x.groupby("cat2")["rank"].min()

def f_no_copy(x):
        x["rank"] = x.val.rank(method="min")
        return x.groupby("cat2")["rank"].min()

grpby_copy = df.groupby("cat1").apply(f_copy)
    grpby_no_copy = df.groupby("cat1").apply(f_no_copy)
    tm.assert_series_equal(grpby_copy, grpby_no_copy)

def test_no_mutate_but_looks_like():

# GH 8467
    # first show's mutation indicator
    # second does not, but should yield the same results
    df = pd.DataFrame({"key": [1, 1, 1, 2, 2, 2, 3, 3, 3], "value": range(9)})

result1 = df.groupby("key", group_keys=True).apply(lambda x: x[:].key)
    result2 = df.groupby("key", group_keys=True).apply(lambda x: x.key)
    tm.assert_series_equal(result1, result2)

def test_apply_function_with_indexing():
    # GH: 33058
    df = pd.DataFrame(
        {"col1": ["A", "A", "A", "B", "B", "B"], "col2": [1, 2, 3, 4, 5, 6]}
    )

def fn(x):
        x.col2[x.index[-1]] = 0
        return x.col2

result = df.groupby(["col1"], as_index=False).apply(fn)
    expected = pd.Series(
        [1, 2, 0, 4, 5, 0],
        index=pd.MultiIndex.from_tuples(
            [(0, 0), (0, 1), (0, 2), (1, 3), (1, 4), (1, 5)]
        ),
        name="col2",
    )
    tm.assert_series_equal(result, expected)

import numpy as np import pandas as pd import pandas._testing as tm def test_mutate_groups(): # GH3380 df = pd.DataFrame( { "cat1": ["a"] * 8 + ["b"] * 6, "cat2": ["c"] * 2 + ["d"] * 2 + ["e"] * 2 + ["f"] * 2 + ["c"] * 2 + ["d"] * 2 + ["e"] * 2, "cat3": [f"g{x}" for x in range(1, 15)], "val": np.random.randint(100, size=14), } ) def f_copy(x): x = x.copy() x["rank"] = x.val.rank(method="min") return x.groupby("cat2")["rank"].min() def f_no_copy(x): x["rank"] = x.val.rank(method="min") return x.groupby("cat2")["rank"].min() grpby_copy = df.groupby("cat1").apply(f_copy) grpby_no_copy = df.groupby("cat1").apply(f_no_copy) tm.assert_series_equal(grpby_copy, grpby_no_copy) def test_no_mutate_but_looks_like(): # GH 8467 # first show's mutation indicator # second does not, but should yield the same results df = pd.DataFrame({"key": [1, 1, 1, 2, 2, 2, 3, 3, 3], "value": range(9)}) result1 = df.groupby("key", group_keys=True).apply(lambda x: x[:].key) result2 = df.groupby("key", group_keys=True).apply(lambda x: x.key) tm.assert_series_equal(result1, result2) def test_apply_function_with_indexing(): # GH: 33058 df = pd.DataFrame( {"col1": ["A", "A", "A", "B", "B", "B"], "col2": [1, 2, 3, 4, 5, 6]} ) def fn(x): x.col2[x.index[-1]] = 0 return x.col2 result = df.groupby(["col1"], as_index=False).apply(fn) expected = pd.Series( [1, 2, 0, 4, 5, 0], index=pd.MultiIndex.from_tuples( [(0, 0), (0, 1), (0, 2), (1, 3), (1, 4), (1, 5)] ), name="col2", ) tm.assert_series_equal(result, expected)