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_nlargest.py (6731B)

"""
Note: for naming purposes, most tests are title with as e.g. "test_nlargest_foo"
but are implicitly also testing nsmallest_foo.
"""
from string import ascii_lowercase

import numpy as np
import pytest

import pandas as pd
import pandas._testing as tm

@pytest.fixture
def df_duplicates():
    return pd.DataFrame(
        {"a": [1, 2, 3, 4, 4], "b": [1, 1, 1, 1, 1], "c": [0, 1, 2, 5, 4]},
        index=[0, 0, 1, 1, 1],
    )

@pytest.fixture
def df_strings():
    return pd.DataFrame(
        {
            "a": np.random.permutation(10),
            "b": list(ascii_lowercase[:10]),
            "c": np.random.permutation(10).astype("float64"),
        }
    )

@pytest.fixture
def df_main_dtypes():
    return pd.DataFrame(
        {
            "group": [1, 1, 2],
            "int": [1, 2, 3],
            "float": [4.0, 5.0, 6.0],
            "string": list("abc"),
            "category_string": pd.Series(list("abc")).astype("category"),
            "category_int": [7, 8, 9],
            "datetime": pd.date_range("20130101", periods=3),
            "datetimetz": pd.date_range("20130101", periods=3, tz="US/Eastern"),
            "timedelta": pd.timedelta_range("1 s", periods=3, freq="s"),
        },
        columns=[
            "group",
            "int",
            "float",
            "string",
            "category_string",
            "category_int",
            "datetime",
            "datetimetz",
            "timedelta",
        ],
    )

class TestNLargestNSmallest:

# ----------------------------------------------------------------------
    # Top / bottom
    @pytest.mark.parametrize(
        "order",
        [
            ["a"],
            ["c"],
            ["a", "b"],
            ["a", "c"],
            ["b", "a"],
            ["b", "c"],
            ["a", "b", "c"],
            ["c", "a", "b"],
            ["c", "b", "a"],
            ["b", "c", "a"],
            ["b", "a", "c"],
            # dups!
            ["b", "c", "c"],
        ],
    )
    @pytest.mark.parametrize("n", range(1, 11))
    def test_nlargest_n(self, df_strings, nselect_method, n, order):
        # GH#10393
        df = df_strings
        if "b" in order:

error_msg = (
                f"Column 'b' has dtype object, "
                f"cannot use method '{nselect_method}' with this dtype"
            )
            with pytest.raises(TypeError, match=error_msg):
                getattr(df, nselect_method)(n, order)
        else:
            ascending = nselect_method == "nsmallest"
            result = getattr(df, nselect_method)(n, order)
            expected = df.sort_values(order, ascending=ascending).head(n)
            tm.assert_frame_equal(result, expected)

@pytest.mark.parametrize(
        "columns", [["group", "category_string"], ["group", "string"]]
    )
    def test_nlargest_error(self, df_main_dtypes, nselect_method, columns):
        df = df_main_dtypes
        col = columns[1]
        error_msg = (
            f"Column '{col}' has dtype {df[col].dtype}, "
            f"cannot use method '{nselect_method}' with this dtype"
        )
        # escape some characters that may be in the repr
        error_msg = (
            error_msg.replace("(", "\\(")
            .replace(")", "\\)")
            .replace("[", "\\[")
            .replace("]", "\\]")
        )
        with pytest.raises(TypeError, match=error_msg):
            getattr(df, nselect_method)(2, columns)

def test_nlargest_all_dtypes(self, df_main_dtypes):
        df = df_main_dtypes
        df.nsmallest(2, list(set(df) - {"category_string", "string"}))
        df.nlargest(2, list(set(df) - {"category_string", "string"}))

def test_nlargest_duplicates_on_starter_columns(self):
        # regression test for GH#22752

df = pd.DataFrame({"a": [2, 2, 2, 1, 1, 1], "b": [1, 2, 3, 3, 2, 1]})

result = df.nlargest(4, columns=["a", "b"])
        expected = pd.DataFrame(
            {"a": [2, 2, 2, 1], "b": [3, 2, 1, 3]}, index=[2, 1, 0, 3]
        )
        tm.assert_frame_equal(result, expected)

result = df.nsmallest(4, columns=["a", "b"])
        expected = pd.DataFrame(
            {"a": [1, 1, 1, 2], "b": [1, 2, 3, 1]}, index=[5, 4, 3, 0]
        )
        tm.assert_frame_equal(result, expected)

def test_nlargest_n_identical_values(self):
        # GH#15297
        df = pd.DataFrame({"a": [1] * 5, "b": [1, 2, 3, 4, 5]})

result = df.nlargest(3, "a")
        expected = pd.DataFrame({"a": [1] * 3, "b": [1, 2, 3]}, index=[0, 1, 2])
        tm.assert_frame_equal(result, expected)

result = df.nsmallest(3, "a")
        expected = pd.DataFrame({"a": [1] * 3, "b": [1, 2, 3]})
        tm.assert_frame_equal(result, expected)

@pytest.mark.parametrize(
        "order",
        [["a", "b", "c"], ["c", "b", "a"], ["a"], ["b"], ["a", "b"], ["c", "b"]],
    )
    @pytest.mark.parametrize("n", range(1, 6))
    def test_nlargest_n_duplicate_index(self, df_duplicates, n, order):
        # GH#13412

df = df_duplicates
        result = df.nsmallest(n, order)
        expected = df.sort_values(order).head(n)
        tm.assert_frame_equal(result, expected)

result = df.nlargest(n, order)
        expected = df.sort_values(order, ascending=False).head(n)
        tm.assert_frame_equal(result, expected)

def test_nlargest_duplicate_keep_all_ties(self):
        # GH#16818
        df = pd.DataFrame(
            {"a": [5, 4, 4, 2, 3, 3, 3, 3], "b": [10, 9, 8, 7, 5, 50, 10, 20]}
        )
        result = df.nlargest(4, "a", keep="all")
        expected = pd.DataFrame(
            {
                "a": {0: 5, 1: 4, 2: 4, 4: 3, 5: 3, 6: 3, 7: 3},
                "b": {0: 10, 1: 9, 2: 8, 4: 5, 5: 50, 6: 10, 7: 20},
            }
        )
        tm.assert_frame_equal(result, expected)

result = df.nsmallest(2, "a", keep="all")
        expected = pd.DataFrame(
            {
                "a": {3: 2, 4: 3, 5: 3, 6: 3, 7: 3},
                "b": {3: 7, 4: 5, 5: 50, 6: 10, 7: 20},
            }
        )
        tm.assert_frame_equal(result, expected)

def test_nlargest_multiindex_column_lookup(self):
        # Check whether tuples are correctly treated as multi-level lookups.
        # GH#23033
        df = pd.DataFrame(
            columns=pd.MultiIndex.from_product([["x"], ["a", "b"]]),
            data=[[0.33, 0.13], [0.86, 0.25], [0.25, 0.70], [0.85, 0.91]],
        )

# nsmallest
        result = df.nsmallest(3, ("x", "a"))
        expected = df.iloc[[2, 0, 3]]
        tm.assert_frame_equal(result, expected)

# nlargest
        result = df.nlargest(3, ("x", "b"))
        expected = df.iloc[[3, 2, 1]]
        tm.assert_frame_equal(result, expected)

cmd: