Merge pull request #11391 from jreback/slow

TST: make a couple of tests slow / remove some warnings

Author: jreback

ci/requirements-2.7_SLOW.pip

@@ -4,13 +4,6 @@
 3. Goto APIs and register for OAuth2.0 for installed applications
 4. Download JSON secret file and move into same directory as this file
 """
-
-# GH11038
-import warnings
-warnings.warn("The pandas.io.ga module is deprecated and will be "
-              "removed in a future version.",
-              FutureWarning, stacklevel=2)
-
 from datetime import datetime
 import re
 from pandas import compat
@@ -27,6 +20,12 @@
 from oauth2client.client import AccessTokenRefreshError
 from pandas.compat import zip, u
 
+# GH11038
+import warnings
+warnings.warn("The pandas.io.ga module is deprecated and will be "
+              "removed in a future version.",
+              FutureWarning, stacklevel=2)
+
 TYPE_MAP = {u('INTEGER'): int, u('FLOAT'): float, u('TIME'): int}
 
 NO_CALLBACK = auth.OOB_CALLBACK_URN

pandas/io/ga.py

@@ -9,12 +9,15 @@
 import numpy as np
 import pandas as pd
 from pandas import DataFrame, Timestamp
-from pandas.io import data as web
-from pandas.io.data import DataReader, SymbolWarning, RemoteDataError, _yahoo_codes
 from pandas.util.testing import (assert_series_equal, assert_produces_warning,
                                  network, assert_frame_equal)
 import pandas.util.testing as tm
 
+with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+    from pandas.io import data as web
+
+from pandas.io.data import DataReader, SymbolWarning, RemoteDataError, _yahoo_codes
+
 if compat.PY3:
     from urllib.error import HTTPError
 else:
@@ -293,6 +296,7 @@ def test_get_date_ret_index(self):
 
 
 class TestYahooOptions(tm.TestCase):
+
     @classmethod
     def setUpClass(cls):
         super(TestYahooOptions, cls).setUpClass()

pandas/io/tests/test_data.py

@@ -6,6 +6,7 @@
 import os
 from distutils.version import LooseVersion
 
+import warnings
 import operator
 import functools
 import nose
@@ -1829,7 +1830,6 @@ def test_column_format(self):
         # Applicable to xlsxwriter only.
         _skip_if_no_xlsxwriter()
 
-        import warnings
         with warnings.catch_warnings():
             # Ignore the openpyxl lxml warning.
             warnings.simplefilter("ignore")

pandas/io/tests/test_excel.py

@@ -1,6 +1,7 @@
 import os
 from datetime import datetime
 
+import warnings
 import nose
 import pandas as pd
 from pandas import compat
@@ -13,7 +14,12 @@
 
 try:
     import httplib2
-    import pandas.io.ga as ga
+    import apiclient
+
+    # deprecated
+    with warnings.catch_warnings(record=True):
+        import pandas.io.ga as ga
+
     from pandas.io.ga import GAnalytics, read_ga
     from pandas.io.auth import AuthenticationConfigError, reset_default_token_store
     from pandas.io import auth

pandas/io/tests/test_ga.py

@@ -461,20 +461,21 @@ def test_sparse_frame(self):
 
     def test_sparse_panel(self):
 
-        items = ['x', 'y', 'z']
-        p = Panel(dict((i, tm.makeDataFrame().ix[:2, :2]) for i in items))
-        sp = p.to_sparse()
+        with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+            items = ['x', 'y', 'z']
+            p = Panel(dict((i, tm.makeDataFrame().ix[:2, :2]) for i in items))
+            sp = p.to_sparse()
 
-        self._check_roundtrip(sp, tm.assert_panel_equal,
-                              check_panel_type=True)
+            self._check_roundtrip(sp, tm.assert_panel_equal,
+                                  check_panel_type=True)
 
-        sp2 = p.to_sparse(kind='integer')
-        self._check_roundtrip(sp2, tm.assert_panel_equal,
-                              check_panel_type=True)
+            sp2 = p.to_sparse(kind='integer')
+            self._check_roundtrip(sp2, tm.assert_panel_equal,
+                                  check_panel_type=True)
 
-        sp3 = p.to_sparse(fill_value=0)
-        self._check_roundtrip(sp3, tm.assert_panel_equal,
-                              check_panel_type=True)
+            sp3 = p.to_sparse(fill_value=0)
+            self._check_roundtrip(sp3, tm.assert_panel_equal,
+                                  check_panel_type=True)
 
 
 class TestCompression(TestPackers):

pandas/io/tests/test_packers.py

@@ -5,9 +5,11 @@
 from pandas.util.testing import network
 from pandas.util.testing import assert_frame_equal
 from numpy.testing.decorators import slow
-from pandas.io.wb import search, download, get_countries
 import pandas.util.testing as tm
 
+# deprecated
+with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+    from pandas.io.wb import search, download, get_countries
 
 class TestWB(tm.TestCase):
 

pandas/io/tests/test_wb.py

@@ -6,6 +6,7 @@
 import numpy as np
 import unittest
 import nose
+import warnings
 import pandas.util.testing as tm
 
 try:

pandas/rpy/tests/test_common.py

@@ -283,7 +283,15 @@ def __getitem__(self, key):
         if com.is_integer(key):
             return self._get_val_at(key)
         else:
-            data_slice = self.values[key]
+            if isinstance(key, SparseArray):
+                key = np.asarray(key)
+            if hasattr(key,'__len__') and len(self) != len(key):
+                indices = self.sp_index
+                if hasattr(indices,'to_int_index'):
+                    indices = indices.to_int_index()
+                data_slice = self.values.take(indices.indices)[key]
+            else:
+                data_slice = self.values[key]
             return self._constructor(data_slice)
 
     def __getslice__(self, i, j):
@@ -513,7 +521,12 @@ def make_sparse(arr, kind='block', fill_value=nan):
     else:
         mask = arr != fill_value
 
-    indices = np.arange(length, dtype=np.int32)[mask]
+    length = len(arr)
+    if length != mask.size:
+        # the arr is a SparseArray
+        indices = mask.sp_index.indices
+    else:
+        indices = np.arange(length, dtype=np.int32)[mask]
 
     if kind == 'block':
         locs, lens = splib.get_blocks(indices)

pandas/sparse/array.py

@@ -43,10 +43,6 @@ class TestMoments(Base):
 
     def setUp(self):
         self._create_data()
-        warnings.simplefilter("ignore", category=FutureWarning)
-
-    def tearDown(self):
-        warnings.simplefilter("default", category=FutureWarning)
 
     def test_centered_axis_validation(self):
         # ok
@@ -890,7 +886,6 @@ def _create_data(self):
 
     def setUp(self):
         self._create_data()
-        warnings.simplefilter("ignore", category=FutureWarning)
 
     def _test_moments_consistency(self,
                                   min_periods,
@@ -1516,9 +1511,6 @@ def test_rolling_functions_window_non_shrinkage(self):
 
         functions = [lambda x: mom.rolling_cov(x, x, pairwise=True, window=10, min_periods=5),
                      lambda x: mom.rolling_corr(x, x, pairwise=True, window=10, min_periods=5),
-                     # rolling_corr_pairwise is depracated, so the following line should be deleted
-                     # when rolling_corr_pairwise is removed.
-                     lambda x: mom.rolling_corr_pairwise(x, x, window=10, min_periods=5),
                     ]
         for f in functions:
             df_result_panel = f(df)
@@ -1585,9 +1577,6 @@ def test_moment_functions_zero_length(self):
                      lambda x: mom.expanding_corr(x, x, pairwise=True, min_periods=5),
                      lambda x: mom.rolling_cov(x, x, pairwise=True, window=10, min_periods=5),
                      lambda x: mom.rolling_corr(x, x, pairwise=True, window=10, min_periods=5),
-                     # rolling_corr_pairwise is depracated, so the following line should be deleted
-                     # when rolling_corr_pairwise is removed.
-                     lambda x: mom.rolling_corr_pairwise(x, x, window=10, min_periods=5),
                     ]
         for f in functions:
             df1_result_panel = f(df1)

pandas/stats/tests/test_moments.py

@@ -3169,6 +3169,7 @@ def test_pie_df_nan(self):
                               ax.get_legend().get_texts()],
                              base_expected[:i] + base_expected[i+1:])
 
+    @slow
     def test_errorbar_plot(self):
         d = {'x': np.arange(12), 'y': np.arange(12, 0, -1)}
         df = DataFrame(d)

pandas/tests/test_graphics.py

@@ -1655,6 +1655,7 @@ def check_nunique(df, keys):
             check_nunique(frame, ['jim'])
             check_nunique(frame, ['jim', 'joe'])
 
+    @slow
     def test_series_groupby_value_counts(self):
         from itertools import product
 

pandas/tests/test_groupby.py

@@ -25,6 +25,7 @@
 
 import pandas.util.testing as tm
 from pandas import date_range
+from numpy.testing.decorators import slow
 
 _verbose = False
 
@@ -1689,74 +1690,71 @@ def test_multiindex_perf_warn(self):
         with tm.assert_produces_warning(PerformanceWarning):
             _ = df.loc[(0,)]
 
+    @slow
     def test_multiindex_get_loc(self):  # GH7724, GH2646
 
-        # ignore the warning here
-        warnings.simplefilter('ignore', PerformanceWarning)
+        with warnings.catch_warnings(record=True):
 
-        # test indexing into a multi-index before & past the lexsort depth
-        from numpy.random import randint, choice, randn
-        cols = ['jim', 'joe', 'jolie', 'joline', 'jolia']
+            # test indexing into a multi-index before & past the lexsort depth
+            from numpy.random import randint, choice, randn
+            cols = ['jim', 'joe', 'jolie', 'joline', 'jolia']
 
-        def validate(mi, df, key):
-            mask = np.ones(len(df)).astype('bool')
+            def validate(mi, df, key):
+                mask = np.ones(len(df)).astype('bool')
 
-            # test for all partials of this key
-            for i, k in enumerate(key):
-                mask &= df.iloc[:, i] == k
+                # test for all partials of this key
+                for i, k in enumerate(key):
+                    mask &= df.iloc[:, i] == k
 
-                if not mask.any():
-                    self.assertNotIn(key[:i+1], mi.index)
-                    continue
-
-                self.assertIn(key[:i+1], mi.index)
-                right = df[mask].copy()
+                    if not mask.any():
+                        self.assertNotIn(key[:i+1], mi.index)
+                        continue
 
-                if i + 1 != len(key):  # partial key
-                    right.drop(cols[:i+1], axis=1, inplace=True)
-                    right.set_index(cols[i+1:-1], inplace=True)
-                    assert_frame_equal(mi.loc[key[:i+1]], right)
+                    self.assertIn(key[:i+1], mi.index)
+                    right = df[mask].copy()
 
-                else:  # full key
-                    right.set_index(cols[:-1], inplace=True)
-                    if len(right) == 1:  # single hit
-                        right = Series(right['jolia'].values,
-                                name=right.index[0], index=['jolia'])
-                        assert_series_equal(mi.loc[key[:i+1]], right)
-                    else:  # multi hit
+                    if i + 1 != len(key):  # partial key
+                        right.drop(cols[:i+1], axis=1, inplace=True)
+                        right.set_index(cols[i+1:-1], inplace=True)
                         assert_frame_equal(mi.loc[key[:i+1]], right)
 
-        def loop(mi, df, keys):
-            for key in keys:
-                validate(mi, df, key)
-
-        n, m = 1000, 50
-
-        vals = [randint(0, 10, n), choice(list('abcdefghij'), n),
-                choice(pd.date_range('20141009', periods=10).tolist(), n),
-                choice(list('ZYXWVUTSRQ'), n), randn(n)]
-        vals = list(map(tuple, zip(*vals)))
-
-        # bunch of keys for testing
-        keys = [randint(0, 11, m), choice(list('abcdefghijk'), m),
-                choice(pd.date_range('20141009', periods=11).tolist(), m),
-                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 = pd.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)
-
-        # restore
-        warnings.simplefilter('always', PerformanceWarning)
+                    else:  # full key
+                        right.set_index(cols[:-1], inplace=True)
+                        if len(right) == 1:  # single hit
+                            right = Series(right['jolia'].values,
+                                           name=right.index[0], index=['jolia'])
+                            assert_series_equal(mi.loc[key[:i+1]], right)
+                        else:  # multi hit
+                            assert_frame_equal(mi.loc[key[:i+1]], right)
+
+            def loop(mi, df, keys):
+                for key in keys:
+                    validate(mi, df, key)
+
+            n, m = 1000, 50
+
+            vals = [randint(0, 10, n), choice(list('abcdefghij'), n),
+                    choice(pd.date_range('20141009', periods=10).tolist(), n),
+                    choice(list('ZYXWVUTSRQ'), n), randn(n)]
+            vals = list(map(tuple, zip(*vals)))
+
+            # bunch of keys for testing
+            keys = [randint(0, 11, m), choice(list('abcdefghijk'), m),
+                    choice(pd.date_range('20141009', periods=11).tolist(), m),
+                    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 = pd.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)
 
     def test_series_getitem_multiindex(self):
 
@@ -4653,13 +4651,15 @@ def test_indexing_dtypes_on_empty(self):
         assert_series_equal(df2.loc[:,'a'], df2.iloc[:,0])
         assert_series_equal(df2.loc[:,'a'], df2.ix[:,0])
 
+    @slow
     def test_large_dataframe_indexing(self):
         #GH10692
         result = DataFrame({'x': range(10**6)},dtype='int64')
         result.loc[len(result)] = len(result) + 1
         expected = DataFrame({'x': range(10**6 + 1)},dtype='int64')
         assert_frame_equal(result, expected)
 
+    @slow
     def test_large_mi_dataframe_indexing(self):
         #GH10645
         result = MultiIndex.from_arrays([range(10**6), range(10**6)])