avoid non-standard imports (pandas-dev#24822)

ci/code_checks.sh

@@ -112,6 +112,7 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     # Check for imports from pandas.core.common instead of `import pandas.core.common as com`
     MSG='Check for non-standard imports' ; echo $MSG
     invgrep -R --include="*.py*" -E "from pandas.core.common import " pandas
+    # invgrep -R --include="*.py*" -E "from numpy import nan " pandas  # GH#24822 not yet implemented since the offending imports have not all been removed
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for pytest warns' ; echo $MSG

pandas/tests/frame/test_analytics.py

@@ -6,8 +6,6 @@
 import warnings
 
 import numpy as np
-from numpy import nan
-from numpy.random import randn
 import pytest
 
 from pandas.compat import PY35, lrange
@@ -240,22 +238,22 @@ class TestDataFrameAnalytics():
 
     @td.skip_if_no_scipy
     def test_corr_pearson(self, float_frame):
-        float_frame['A'][:5] = nan
-        float_frame['B'][5:10] = nan
+        float_frame['A'][:5] = np.nan
+        float_frame['B'][5:10] = np.nan
 
         self._check_method(float_frame, 'pearson')
 
     @td.skip_if_no_scipy
     def test_corr_kendall(self, float_frame):
-        float_frame['A'][:5] = nan
-        float_frame['B'][5:10] = nan
+        float_frame['A'][:5] = np.nan
+        float_frame['B'][5:10] = np.nan
 
         self._check_method(float_frame, 'kendall')
 
     @td.skip_if_no_scipy
     def test_corr_spearman(self, float_frame):
-        float_frame['A'][:5] = nan
-        float_frame['B'][5:10] = nan
+        float_frame['A'][:5] = np.nan
+        float_frame['B'][5:10] = np.nan
 
         self._check_method(float_frame, 'spearman')
 
@@ -266,8 +264,8 @@ def _check_method(self, frame, method='pearson'):
 
     @td.skip_if_no_scipy
     def test_corr_non_numeric(self, float_frame, float_string_frame):
-        float_frame['A'][:5] = nan
-        float_frame['B'][5:10] = nan
+        float_frame['A'][:5] = np.nan
+        float_frame['B'][5:10] = np.nan
 
         # exclude non-numeric types
         result = float_string_frame.corr()
@@ -351,16 +349,16 @@ def test_cov(self, float_frame, float_string_frame):
 
         # with NAs
         frame = float_frame.copy()
-        frame['A'][:5] = nan
-        frame['B'][5:10] = nan
+        frame['A'][:5] = np.nan
+        frame['B'][5:10] = np.nan
         result = float_frame.cov(min_periods=len(float_frame) - 8)
         expected = float_frame.cov()
         expected.loc['A', 'B'] = np.nan
         expected.loc['B', 'A'] = np.nan
 
         # regular
-        float_frame['A'][:5] = nan
-        float_frame['B'][:10] = nan
+        float_frame['A'][:5] = np.nan
+        float_frame['B'][:10] = np.nan
         cov = float_frame.cov()
 
         tm.assert_almost_equal(cov['A']['C'],
@@ -385,7 +383,7 @@ def test_cov(self, float_frame, float_string_frame):
 
     def test_corrwith(self, datetime_frame):
         a = datetime_frame
-        noise = Series(randn(len(a)), index=a.index)
+        noise = Series(np.random.randn(len(a)), index=a.index)
 
         b = datetime_frame.add(noise, axis=0)
 
@@ -409,8 +407,9 @@ def test_corrwith(self, datetime_frame):
         # non time-series data
         index = ['a', 'b', 'c', 'd', 'e']
         columns = ['one', 'two', 'three', 'four']
-        df1 = DataFrame(randn(5, 4), index=index, columns=columns)
-        df2 = DataFrame(randn(4, 4), index=index[:4], columns=columns)
+        df1 = DataFrame(np.random.randn(5, 4), index=index, columns=columns)
+        df2 = DataFrame(np.random.randn(4, 4),
+                        index=index[:4], columns=columns)
         correls = df1.corrwith(df2, axis=1)
         for row in index[:4]:
             tm.assert_almost_equal(correls[row],
@@ -823,9 +822,9 @@ def test_min(self, float_frame_with_na, int_frame,
         assert_stat_op_api('min', float_frame, float_string_frame)
 
     def test_cummin(self, datetime_frame):
-        datetime_frame.loc[5:10, 0] = nan
-        datetime_frame.loc[10:15, 1] = nan
-        datetime_frame.loc[15:, 2] = nan
+        datetime_frame.loc[5:10, 0] = np.nan
+        datetime_frame.loc[10:15, 1] = np.nan
+        datetime_frame.loc[15:, 2] = np.nan
 
         # axis = 0
         cummin = datetime_frame.cummin()
@@ -846,9 +845,9 @@ def test_cummin(self, datetime_frame):
         assert np.shape(cummin_xs) == np.shape(datetime_frame)
 
     def test_cummax(self, datetime_frame):
-        datetime_frame.loc[5:10, 0] = nan
-        datetime_frame.loc[10:15, 1] = nan
-        datetime_frame.loc[15:, 2] = nan
+        datetime_frame.loc[5:10, 0] = np.nan
+        datetime_frame.loc[10:15, 1] = np.nan
+        datetime_frame.loc[15:, 2] = np.nan
 
         # axis = 0
         cummax = datetime_frame.cummax()
@@ -950,9 +949,9 @@ def test_mixed_ops(self, op):
             assert len(result) == 2
 
     def test_cumsum(self, datetime_frame):
-        datetime_frame.loc[5:10, 0] = nan
-        datetime_frame.loc[10:15, 1] = nan
-        datetime_frame.loc[15:, 2] = nan
+        datetime_frame.loc[5:10, 0] = np.nan
+        datetime_frame.loc[10:15, 1] = np.nan
+        datetime_frame.loc[15:, 2] = np.nan
 
         # axis = 0
         cumsum = datetime_frame.cumsum()
@@ -973,9 +972,9 @@ def test_cumsum(self, datetime_frame):
         assert np.shape(cumsum_xs) == np.shape(datetime_frame)
 
     def test_cumprod(self, datetime_frame):
-        datetime_frame.loc[5:10, 0] = nan
-        datetime_frame.loc[10:15, 1] = nan
-        datetime_frame.loc[15:, 2] = nan
+        datetime_frame.loc[5:10, 0] = np.nan
+        datetime_frame.loc[10:15, 1] = np.nan
+        datetime_frame.loc[15:, 2] = np.nan
 
         # axis = 0
         cumprod = datetime_frame.cumprod()
@@ -1753,7 +1752,7 @@ def test_round(self):
                               expected_neg_rounded)
 
         # nan in Series round
-        nan_round_Series = Series({'col1': nan, 'col2': 1})
+        nan_round_Series = Series({'col1': np.nan, 'col2': 1})
 
         # TODO(wesm): unused?
         expected_nan_round = DataFrame({  # noqa
@@ -2084,8 +2083,10 @@ def test_dot(self):
         result = A.dot(b)
 
         # unaligned
-        df = DataFrame(randn(3, 4), index=[1, 2, 3], columns=lrange(4))
-        df2 = DataFrame(randn(5, 3), index=lrange(5), columns=[1, 2, 3])
+        df = DataFrame(np.random.randn(3, 4),
+                       index=[1, 2, 3], columns=lrange(4))
+        df2 = DataFrame(np.random.randn(5, 3),
+                        index=lrange(5), columns=[1, 2, 3])
 
         with pytest.raises(ValueError, match='aligned'):
             df.dot(df2)
@@ -2144,8 +2145,10 @@ def test_matmul(self):
         tm.assert_frame_equal(result, expected)
 
         # unaligned
-        df = DataFrame(randn(3, 4), index=[1, 2, 3], columns=lrange(4))
-        df2 = DataFrame(randn(5, 3), index=lrange(5), columns=[1, 2, 3])
+        df = DataFrame(np.random.randn(3, 4),
+                       index=[1, 2, 3], columns=lrange(4))
+        df2 = DataFrame(np.random.randn(5, 3),
+                        index=lrange(5), columns=[1, 2, 3])
 
         with pytest.raises(ValueError, match='aligned'):
             operator.matmul(df, df2)

pandas/tests/frame/test_api.py

@@ -7,7 +7,6 @@
 import pydoc
 
 import numpy as np
-from numpy.random import randn
 import pytest
 
 from pandas.compat import long, lrange, range
@@ -149,8 +148,8 @@ def test_not_hashable(self, empty_frame):
         pytest.raises(TypeError, hash, empty_frame)
 
     def test_new_empty_index(self):
-        df1 = self.klass(randn(0, 3))
-        df2 = self.klass(randn(0, 3))
+        df1 = self.klass(np.random.randn(0, 3))
+        df2 = self.klass(np.random.randn(0, 3))
         df1.index.name = 'foo'
         assert df2.index.name is None
 

pandas/tests/frame/test_axis_select_reindex.py

@@ -5,7 +5,6 @@
 from datetime import datetime
 
 import numpy as np
-from numpy import random
 import pytest
 
 from pandas.compat import lrange, lzip, u
@@ -289,7 +288,7 @@ def test_reindex_nan(self):
         assert_frame_equal(left, right)
 
     def test_reindex_name_remains(self):
-        s = Series(random.rand(10))
+        s = Series(np.random.rand(10))
         df = DataFrame(s, index=np.arange(len(s)))
         i = Series(np.arange(10), name='iname')
 
@@ -299,7 +298,7 @@ def test_reindex_name_remains(self):
         df = df.reindex(Index(np.arange(10), name='tmpname'))
         assert df.index.name == 'tmpname'
 
-        s = Series(random.rand(10))
+        s = Series(np.random.rand(10))
         df = DataFrame(s.T, index=np.arange(len(s)))
         i = Series(np.arange(10), name='iname')
         df = df.reindex(columns=i)

pandas/tests/frame/test_block_internals.py

@@ -6,7 +6,6 @@
 import itertools
 
 import numpy as np
-from numpy import nan
 import pytest
 
 from pandas.compat import StringIO
@@ -216,7 +215,7 @@ def test_construction_with_mixed(self, float_string_frame):
         # test construction edge cases with mixed types
 
         # f7u12, this does not work without extensive workaround
-        data = [[datetime(2001, 1, 5), nan, datetime(2001, 1, 2)],
+        data = [[datetime(2001, 1, 5), np.nan, datetime(2001, 1, 2)],
                 [datetime(2000, 1, 2), datetime(2000, 1, 3),
                  datetime(2000, 1, 1)]]
         df = DataFrame(data)
@@ -558,18 +557,18 @@ def test_get_X_columns(self):
     def test_strange_column_corruption_issue(self):
         # (wesm) Unclear how exactly this is related to internal matters
         df = DataFrame(index=[0, 1])
-        df[0] = nan
+        df[0] = np.nan
         wasCol = {}
         # uncommenting these makes the results match
         # for col in xrange(100, 200):
         #    wasCol[col] = 1
-        #    df[col] = nan
+        #    df[col] = np.nan
 
         for i, dt in enumerate(df.index):
             for col in range(100, 200):
                 if col not in wasCol:
                     wasCol[col] = 1
-                    df[col] = nan
+                    df[col] = np.nan
                 df[col][dt] = i
 
         myid = 100

pandas/tests/frame/test_combine_concat.py

@@ -5,7 +5,6 @@
 from datetime import datetime
 
 import numpy as np
-from numpy import nan
 import pytest
 
 from pandas.compat import lrange
@@ -247,20 +246,20 @@ def test_append_dtypes(self):
         assert_frame_equal(result, expected)
 
     def test_update(self):
-        df = DataFrame([[1.5, nan, 3.],
-                        [1.5, nan, 3.],
-                        [1.5, nan, 3],
-                        [1.5, nan, 3]])
+        df = DataFrame([[1.5, np.nan, 3.],
+                        [1.5, np.nan, 3.],
+                        [1.5, np.nan, 3],
+                        [1.5, np.nan, 3]])
 
         other = DataFrame([[3.6, 2., np.nan],
                            [np.nan, np.nan, 7]], index=[1, 3])
 
         df.update(other)
 
-        expected = DataFrame([[1.5, nan, 3],
+        expected = DataFrame([[1.5, np.nan, 3],
                               [3.6, 2, 3],
-                              [1.5, nan, 3],
-                              [1.5, nan, 7.]])
+                              [1.5, np.nan, 3],
+                              [1.5, np.nan, 7.]])
         assert_frame_equal(df, expected)
 
     def test_update_dtypes(self):
@@ -277,37 +276,37 @@ def test_update_dtypes(self):
         assert_frame_equal(df, expected)
 
     def test_update_nooverwrite(self):
-        df = DataFrame([[1.5, nan, 3.],
-                        [1.5, nan, 3.],
-                        [1.5, nan, 3],
-                        [1.5, nan, 3]])
+        df = DataFrame([[1.5, np.nan, 3.],
+                        [1.5, np.nan, 3.],
+                        [1.5, np.nan, 3],
+                        [1.5, np.nan, 3]])
 
         other = DataFrame([[3.6, 2., np.nan],
                            [np.nan, np.nan, 7]], index=[1, 3])
 
         df.update(other, overwrite=False)
 
-        expected = DataFrame([[1.5, nan, 3],
+        expected = DataFrame([[1.5, np.nan, 3],
                               [1.5, 2, 3],
-                              [1.5, nan, 3],
-                              [1.5, nan, 3.]])
+                              [1.5, np.nan, 3],
+                              [1.5, np.nan, 3.]])
         assert_frame_equal(df, expected)
 
     def test_update_filtered(self):
-        df = DataFrame([[1.5, nan, 3.],
-                        [1.5, nan, 3.],
-                        [1.5, nan, 3],
-                        [1.5, nan, 3]])
+        df = DataFrame([[1.5, np.nan, 3.],
+                        [1.5, np.nan, 3.],
+                        [1.5, np.nan, 3],
+                        [1.5, np.nan, 3]])
 
         other = DataFrame([[3.6, 2., np.nan],
                            [np.nan, np.nan, 7]], index=[1, 3])
 
         df.update(other, filter_func=lambda x: x > 2)
 
-        expected = DataFrame([[1.5, nan, 3],
-                              [1.5, nan, 3],
-                              [1.5, nan, 3],
-                              [1.5, nan, 7.]])
+        expected = DataFrame([[1.5, np.nan, 3],
+                              [1.5, np.nan, 3],
+                              [1.5, np.nan, 3],
+                              [1.5, np.nan, 7.]])
         assert_frame_equal(df, expected)
 
     @pytest.mark.parametrize('bad_kwarg, exception, msg', [
@@ -322,12 +321,12 @@ def test_update_raise_bad_parameter(self, bad_kwarg, exception, msg):
 
     def test_update_raise_on_overlap(self):
         df = DataFrame([[1.5, 1, 3.],
-                        [1.5, nan, 3.],
-                        [1.5, nan, 3],
-                        [1.5, nan, 3]])
+                        [1.5, np.nan, 3.],
+                        [1.5, np.nan, 3],
+                        [1.5, np.nan, 3]])
 
-        other = DataFrame([[2., nan],
-                           [nan, 7]], index=[1, 3], columns=[1, 2])
+        other = DataFrame([[2., np.nan],
+                           [np.nan, 7]], index=[1, 3], columns=[1, 2])
         with pytest.raises(ValueError, match="Data overlaps"):
             df.update(other, errors='raise')