Merge branch 'issue37053-unify-numpy-related-imports-in-pandas/tests/plotting' of https://github.com/onshek/pandas into issue37053-unify-numpy-related-imports-in-pandas/tests/plotting

Author: onshek

pandas/tests/computation/test_eval.py

@@ -7,47 +7,17 @@
 from pandas import DataFrame, Series
 import pandas._testing as tm
 
-m = 50
-n = 1000
-cols = ["jim", "joe", "jolie", "joline", "jolia"]
-
-vals = [
-    np.random.randint(0, 10, n),
-    np.random.choice(list("abcdefghij"), n),
-    np.random.choice(pd.date_range("20141009", periods=10).tolist(), n),
-    np.random.choice(list("ZYXWVUTSRQ"), n),
-    np.random.randn(n),
-]
-vals = list(map(tuple, zip(*vals)))
-
-# bunch of keys for testing
-keys = [
-    np.random.randint(0, 11, m),
-    np.random.choice(list("abcdefghijk"), m),
-    np.random.choice(pd.date_range("20141009", periods=11).tolist(), m),
-    np.random.choice(list("ZYXWVUTSRQP"), m),
-]
-keys = list(map(tuple, zip(*keys)))
-keys += list(map(lambda t: t[:-1], vals[:: n // m]))
-
-
-# covers both unique index and non-unique index
-df = DataFrame(vals, columns=cols)
-a = pd.concat([df, df])
-b = df.drop_duplicates(subset=cols[:-1])
-
 
+@pytest.mark.slow
 @pytest.mark.filterwarnings("ignore::pandas.errors.PerformanceWarning")
-@pytest.mark.parametrize("lexsort_depth", list(range(5)))
-@pytest.mark.parametrize("key", keys)
-@pytest.mark.parametrize("frame", [a, b])
-def test_multiindex_get_loc(lexsort_depth, key, frame):
-    # GH7724, GH2646
+def test_multiindex_get_loc():  # GH7724, GH2646
 
     with warnings.catch_warnings(record=True):
 
         # test indexing into a multi-index before & past the lexsort depth
 
+        cols = ["jim", "joe", "jolie", "joline", "jolia"]
+
         def validate(mi, df, key):
             mask = np.ones(len(df)).astype("bool")
 
@@ -80,11 +50,38 @@ def validate(mi, df, key):
                     else:  # multi hit
                         tm.assert_frame_equal(mi.loc[key[: i + 1]], right)
 
-        if lexsort_depth == 0:
-            df = frame.copy()
-        else:
-            df = frame.sort_values(by=cols[:lexsort_depth])
-
-        mi = df.set_index(cols[:-1])
-        assert not mi.index.lexsort_depth < lexsort_depth
-        validate(mi, df, key)
+        def loop(mi, df, keys):
+            for key in keys:
+                validate(mi, df, key)
+
+        n, m = 1000, 50
+
+        vals = [
+            np.random.randint(0, 10, n),
+            np.random.choice(list("abcdefghij"), n),
+            np.random.choice(pd.date_range("20141009", periods=10).tolist(), n),
+            np.random.choice(list("ZYXWVUTSRQ"), n),
+            np.random.randn(n),
+        ]
+        vals = list(map(tuple, zip(*vals)))
+
+        # bunch of keys for testing
+        keys = [
+            np.random.randint(0, 11, m),
+            np.random.choice(list("abcdefghijk"), m),
+            np.random.choice(pd.date_range("20141009", periods=11).tolist(), m),
+            np.random.choice(list("ZYXWVUTSRQP"), m),
+        ]
+        keys = list(map(tuple, zip(*keys)))
+        keys += list(map(lambda t: t[:-1], vals[:: n // m]))
+
+        # covers both unique index and non-unique index
+        df = DataFrame(vals, columns=cols)
+        a, b = pd.concat([df, df]), df.drop_duplicates(subset=cols[:-1])
+
+        for frame in a, b:
+            for i in range(5):  # lexsort depth
+                df = frame.copy() if i == 0 else frame.sort_values(by=cols[:i])
+                mi = df.set_index(cols[:-1])
+                assert not mi.index.lexsort_depth < i
+                loop(mi, df, keys)

pandas/tests/indexing/multiindex/test_indexing_slow.py

@@ -1,4 +1,4 @@
-from numpy.random import randn
+import numpy as np
 
 from pandas import DataFrame, MultiIndex, Series
 import pandas._testing as tm
@@ -14,7 +14,7 @@ def test_setitem_mixed_depth(self):
 
         tuples = sorted(zip(*arrays))
         index = MultiIndex.from_tuples(tuples)
-        df = DataFrame(randn(4, 6), columns=index)
+        df = DataFrame(np.random.randn(4, 6), columns=index)
 
         result = df.copy()
         expected = df.copy()

pandas/tests/indexing/multiindex/test_insert.py

@@ -1,5 +1,4 @@
 import numpy as np
-from numpy.random import randn
 import pytest
 
 import pandas as pd
@@ -311,7 +310,9 @@ def test_frame_getitem_setitem_multislice(self):
         tm.assert_frame_equal(df, result)
 
     def test_frame_setitem_multi_column(self):
-        df = DataFrame(randn(10, 4), columns=[["a", "a", "b", "b"], [0, 1, 0, 1]])
+        df = DataFrame(
+            np.random.randn(10, 4), columns=[["a", "a", "b", "b"], [0, 1, 0, 1]]
+        )
 
         cp = df.copy()
         cp["a"] = cp["b"]

pandas/tests/indexing/multiindex/test_setitem.py

@@ -1,5 +1,4 @@
 import numpy as np
-from numpy.random import randn
 import pytest
 
 from pandas import DataFrame, MultiIndex, Series
@@ -115,7 +114,7 @@ def test_series_getitem_not_sorted(self):
         ]
         tuples = zip(*arrays)
         index = MultiIndex.from_tuples(tuples)
-        s = Series(randn(8), index=index)
+        s = Series(np.random.randn(8), index=index)
 
         arrays = [np.array(x) for x in zip(*index.values)]
 

pandas/tests/indexing/multiindex/test_sorted.py

@@ -1,7 +1,6 @@
 from textwrap import dedent
 
 import numpy as np
-from numpy.random import randint
 import pytest
 
 import pandas as pd
@@ -54,7 +53,7 @@ def df(request):
         return tm.makeCustomDataframe(
             max_rows + 1,
             3,
-            data_gen_f=lambda *args: randint(2),
+            data_gen_f=lambda *args: np.random.randint(2),
             c_idx_type="s",
             r_idx_type="i",
             c_idx_names=[None],
@@ -95,7 +94,7 @@ def df(request):
         return tm.makeCustomDataframe(
             5,
             3,
-            data_gen_f=lambda *args: randint(2),
+            data_gen_f=lambda *args: np.random.randint(2),
             c_idx_type="s",
             r_idx_type="i",
             c_idx_names=[None],

pandas/tests/io/test_clipboard.py

@@ -7,7 +7,6 @@
 from urllib.error import URLError
 
 import numpy as np
-from numpy.random import rand
 import pytest
 
 from pandas.compat import is_platform_windows
@@ -110,7 +109,7 @@ def test_to_html_compat(self):
             tm.makeCustomDataframe(
                 4,
                 3,
-                data_gen_f=lambda *args: rand(),
+                data_gen_f=lambda *args: np.random.rand(),
                 c_idx_names=False,
                 r_idx_names=False,
             )

pandas/tests/io/test_html.py

@@ -2,7 +2,6 @@
 import warnings
 
 import numpy as np
-from numpy import random
 
 from pandas.util._decorators import cache_readonly
 import pandas.util._test_decorators as td
@@ -50,11 +49,11 @@ def setup_method(self, method):
                 {
                     "gender": gender,
                     "classroom": classroom,
-                    "height": random.normal(66, 4, size=n),
-                    "weight": random.normal(161, 32, size=n),
-                    "category": random.randint(4, size=n),
+                    "height": np.random.normal(66, 4, size=n),
+                    "weight": np.random.normal(161, 32, size=n),
+                    "category": np.random.randint(4, size=n),
                     "datetime": to_datetime(
-                        random.randint(
+                        np.random.randint(
                             self.start_date_to_int64,
                             self.end_date_to_int64,
                             size=n,

pandas/tests/plotting/common.py

@@ -2,7 +2,6 @@
 import string
 
 import numpy as np
-from numpy import random
 import pytest
 
 import pandas.util._test_decorators as td
@@ -186,7 +185,7 @@ def test_boxplot_numeric_data(self):
     )
     def test_color_kwd(self, colors_kwd, expected):
         # GH: 26214
-        df = DataFrame(random.rand(10, 2))
+        df = DataFrame(np.random.rand(10, 2))
         result = df.boxplot(color=colors_kwd, return_type="dict")
         for k, v in expected.items():
             assert result[k][0].get_color() == v
@@ -197,7 +196,7 @@ def test_color_kwd(self, colors_kwd, expected):
     )
     def test_color_kwd_errors(self, dict_colors, msg):
         # GH: 26214
-        df = DataFrame(random.rand(10, 2))
+        df = DataFrame(np.random.rand(10, 2))
         with pytest.raises(ValueError, match=msg):
             df.boxplot(color=dict_colors, return_type="dict")
 
@@ -293,7 +292,7 @@ def test_grouped_box_return_type(self):
         self._check_box_return_type(result, "dict", expected_keys=["Male", "Female"])
 
         columns2 = "X B C D A G Y N Q O".split()
-        df2 = DataFrame(random.randn(50, 10), columns=columns2)
+        df2 = DataFrame(np.random.randn(50, 10), columns=columns2)
         categories2 = "A B C D E F G H I J".split()
         df2["category"] = categories2 * 5