diff --git a/pandas/tests/groupby/aggregate/test_aggregate.py b/pandas/tests/groupby/aggregate/test_aggregate.py index 5c38d8ebcb512d..6a598c3de55c9d 100644 --- a/pandas/tests/groupby/aggregate/test_aggregate.py +++ b/pandas/tests/groupby/aggregate/test_aggregate.py @@ -9,7 +9,6 @@ import pandas as pd from pandas import concat, DataFrame, Index, MultiIndex, Series -from pandas.util.testing import assert_frame_equal, assert_series_equal from pandas.core.groupby import SpecificationError from pandas.compat import OrderedDict import pandas.util.testing as tm @@ -61,7 +60,7 @@ def test_agg_regression1(self): grouped = self.tsframe.groupby([lambda x: x.year, lambda x: x.month]) result = grouped.agg(np.mean) expected = grouped.mean() - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_must_agg(self): grouped = self.df.groupby('A')['C'] @@ -79,7 +78,7 @@ def test_agg_ser_multi_key(self): f = lambda x: x.sum() results = self.df.C.groupby([self.df.A, self.df.B]).aggregate(f) expected = self.df.groupby(['A', 'B']).sum()['C'] - assert_series_equal(results, expected) + tm.assert_series_equal(results, expected) def test_agg_apply_corner(self): # nothing to group, all NA @@ -90,18 +89,18 @@ def test_agg_apply_corner(self): exp = Series([], dtype=np.float64, index=pd.Index([], dtype=np.float64)) - assert_series_equal(grouped.sum(), exp) - assert_series_equal(grouped.agg(np.sum), exp) - assert_series_equal(grouped.apply(np.sum), exp, check_index_type=False) + tm.assert_series_equal(grouped.sum(), exp) + tm.assert_series_equal(grouped.agg(np.sum), exp) + tm.assert_series_equal(grouped.apply(np.sum), exp, check_index_type=False) # DataFrame grouped = self.tsframe.groupby(self.tsframe['A'] * np.nan) exp_df = DataFrame(columns=self.tsframe.columns, dtype=float, index=pd.Index([], dtype=np.float64)) - assert_frame_equal(grouped.sum(), exp_df, check_names=False) - assert_frame_equal(grouped.agg(np.sum), exp_df, check_names=False) - assert_frame_equal(grouped.apply(np.sum), exp_df.iloc[:, :0], + tm.assert_frame_equal(grouped.sum(), exp_df, check_names=False) + tm.assert_frame_equal(grouped.agg(np.sum), exp_df, check_names=False) + tm.assert_frame_equal(grouped.apply(np.sum), exp_df.iloc[:, :0], check_names=False) def test_agg_grouping_is_list_tuple(self): @@ -135,12 +134,12 @@ def _check_results(grouped): # single series result = grouped['A'].agg('std') expected = grouped['A'].std() - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) # group frame by function name result = grouped.aggregate('var') expected = grouped.var() - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # group frame by function dict result = grouped.agg(OrderedDict([['A', 'var'], ['B', 'std'], @@ -148,7 +147,7 @@ def _check_results(grouped): expected = DataFrame(OrderedDict([['A', grouped['A'].var( )], ['B', grouped['B'].std()], ['C', grouped['C'].mean()], ['D', grouped['D'].sem()]])) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) by_weekday = self.tsframe.groupby(lambda x: x.weekday()) _check_results(by_weekday) @@ -204,7 +203,7 @@ def func(ser): result = grouped.aggregate(func) exp_grouped = self.three_group.loc[:, self.three_group.columns != 'C'] expected = exp_grouped.groupby(['A', 'B']).aggregate(func) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_multiple_functions_maintain_order(self): # GH #610 @@ -222,11 +221,11 @@ def test_multiple_functions_tuples_and_non_tuples(self): result = self.df.groupby('A')['C'].agg(funcs) expected = self.df.groupby('A')['C'].agg(ex_funcs) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) result = self.df.groupby('A').agg(funcs) expected = self.df.groupby('A').agg(ex_funcs) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_multiple_functions_too_many_lambdas(self): grouped = self.df.groupby('A') @@ -249,14 +248,14 @@ def test_more_flexible_frame_multi_function(self): d = OrderedDict([['C', [np.mean, np.std]], ['D', [np.mean, np.std]]]) result = grouped.aggregate(d) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) # be careful result = grouped.aggregate(OrderedDict([['C', np.mean], ['D', [np.mean, np.std]]])) expected = grouped.aggregate(OrderedDict([['C', np.mean], ['D', [np.mean, np.std]]])) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def foo(x): return np.mean(x) @@ -274,7 +273,7 @@ def bar(x): d = OrderedDict([['C', [np.mean]], ['D', [foo, bar]]]) expected = grouped.aggregate(d) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_multi_function_flexible_mix(self): # GH #1268 @@ -306,5 +305,5 @@ def test_multi_function_flexible_mix(self): check_stacklevel=False): expected = grouped.aggregate(d3) - assert_frame_equal(result, expected) - assert_frame_equal(result2, expected) + tm.assert_frame_equal(result, expected) + tm.assert_frame_equal(result2, expected) diff --git a/pandas/tests/groupby/aggregate/test_cython.py b/pandas/tests/groupby/aggregate/test_cython.py index 77741a04a711fd..909346c342047a 100644 --- a/pandas/tests/groupby/aggregate/test_cython.py +++ b/pandas/tests/groupby/aggregate/test_cython.py @@ -12,7 +12,6 @@ import pandas as pd from pandas import bdate_range, DataFrame, Index, Series -from pandas.util.testing import assert_frame_equal, assert_series_equal from pandas.core.groupby import DataError import pandas.util.testing as tm @@ -38,7 +37,7 @@ def _testit(name): exp = DataFrame({'C': exp}) exp.index.name = 'A' result = op(grouped) - assert_frame_equal(result, exp) + tm.assert_frame_equal(result, exp) # multiple columns grouped = df.groupby(['A', 'B']) @@ -51,7 +50,7 @@ def _testit(name): result = op(grouped)['C'] if name in ['sum', 'prod']: - assert_series_equal(result, exp) + tm.assert_series_equal(result, exp) _testit('count') _testit('sum') @@ -70,7 +69,7 @@ def test_cython_agg_boolean(self): result = frame.groupby('a')['b'].mean() expected = frame.groupby('a')['b'].agg(np.mean) - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) def test_cython_agg_nothing_to_agg(self): frame = DataFrame({'a': np.random.randint(0, 5, 50), @@ -117,7 +116,7 @@ def test_cython_agg_return_dict(self): {'two': 2, 'one': 2, 'three': 1}], index=Index(['bar', 'foo'], name='A'), name='B') - assert_series_equal(ts, expected) + tm.assert_series_equal(ts, expected) def test_cython_fail_agg(self): dr = bdate_range('1/1/2000', periods=50) @@ -126,7 +125,7 @@ def test_cython_fail_agg(self): grouped = ts.groupby(lambda x: x.month) summed = grouped.sum() expected = grouped.agg(np.sum) - assert_series_equal(summed, expected) + tm.assert_series_equal(summed, expected) def test__cython_agg_general(self): ops = [('mean', np.mean), diff --git a/pandas/tests/groupby/aggregate/test_other.py b/pandas/tests/groupby/aggregate/test_other.py index 58494a51ab66c4..23c3e9fbc4cd81 100644 --- a/pandas/tests/groupby/aggregate/test_other.py +++ b/pandas/tests/groupby/aggregate/test_other.py @@ -16,7 +16,6 @@ import pandas as pd from pandas import date_range, DataFrame, Index, MultiIndex, Series -from pandas.util.testing import assert_frame_equal, assert_series_equal from pandas.core.groupby import SpecificationError from pandas.io.formats.printing import pprint_thing import pandas.util.testing as tm @@ -39,7 +38,7 @@ def peak_to_peak(arr): expected = grouped.agg([peak_to_peak]) expected.columns = ['data1', 'data2'] result = grouped.agg(peak_to_peak) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_datetimes_mixed(): @@ -93,32 +92,32 @@ def test_agg_dict_parameter_cast_result_dtypes(): # test for `first` function exp = df.loc[[0, 3, 4, 6]].set_index('class') grouped = df.groupby('class') - assert_frame_equal(grouped.first(), exp) - assert_frame_equal(grouped.agg('first'), exp) - assert_frame_equal(grouped.agg({'time': 'first'}), exp) - assert_series_equal(grouped.time.first(), exp['time']) - assert_series_equal(grouped.time.agg('first'), exp['time']) + tm.assert_frame_equal(grouped.first(), exp) + tm.assert_frame_equal(grouped.agg('first'), exp) + tm.assert_frame_equal(grouped.agg({'time': 'first'}), exp) + tm.assert_series_equal(grouped.time.first(), exp['time']) + tm.assert_series_equal(grouped.time.agg('first'), exp['time']) # test for `last` function exp = df.loc[[0, 3, 4, 7]].set_index('class') grouped = df.groupby('class') - assert_frame_equal(grouped.last(), exp) - assert_frame_equal(grouped.agg('last'), exp) - assert_frame_equal(grouped.agg({'time': 'last'}), exp) - assert_series_equal(grouped.time.last(), exp['time']) - assert_series_equal(grouped.time.agg('last'), exp['time']) + tm.assert_frame_equal(grouped.last(), exp) + tm.assert_frame_equal(grouped.agg('last'), exp) + tm.assert_frame_equal(grouped.agg({'time': 'last'}), exp) + tm.assert_series_equal(grouped.time.last(), exp['time']) + tm.assert_series_equal(grouped.time.agg('last'), exp['time']) # count exp = pd.Series([2, 2, 2, 2], index=Index(list('ABCD'), name='class'), name='time') - assert_series_equal(grouped.time.agg(len), exp) - assert_series_equal(grouped.time.size(), exp) + tm.assert_series_equal(grouped.time.agg(len), exp) + tm.assert_series_equal(grouped.time.size(), exp) exp = pd.Series([0, 1, 1, 2], index=Index(list('ABCD'), name='class'), name='time') - assert_series_equal(grouped.time.count(), exp) + tm.assert_series_equal(grouped.time.count(), exp) def test_agg_cast_results_dtypes(): @@ -130,7 +129,7 @@ def test_agg_cast_results_dtypes(): result = df.groupby('X')['Y'].agg(len) expected = df.groupby('X')['Y'].count() - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) def test_aggregate_float64_no_int64(): @@ -177,7 +176,7 @@ def test_aggregate_api_consistency(): expected = pd.concat([d_sum, d_mean], axis=1) expected.columns = ['sum', 'mean'] - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) result = grouped.agg([np.sum, np.mean]) expected = pd.concat([c_sum, @@ -187,7 +186,7 @@ def test_aggregate_api_consistency(): axis=1) expected.columns = MultiIndex.from_product([['C', 'D'], ['sum', 'mean']]) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) result = grouped[['D', 'C']].agg([np.sum, np.mean]) expected = pd.concat([d_sum, @@ -197,13 +196,13 @@ def test_aggregate_api_consistency(): axis=1) expected.columns = MultiIndex.from_product([['D', 'C'], ['sum', 'mean']]) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) result = grouped.agg({'C': 'mean', 'D': 'sum'}) expected = pd.concat([d_sum, c_mean], axis=1) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) result = grouped.agg({'C': ['mean', 'sum'], 'D': ['mean', 'sum']}) @@ -226,7 +225,7 @@ def test_aggregate_api_consistency(): axis=1) expected.columns = MultiIndex.from_product([['r', 'r2'], ['D', 'C']]) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) def test_agg_dict_renaming_deprecation(): @@ -270,7 +269,7 @@ def test_agg_compat(): with tm.assert_produces_warning(FutureWarning, check_stacklevel=False): result = g['D'].agg({'C': ['sum', 'std']}) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) expected = pd.concat([g['D'].sum(), g['D'].std()], @@ -280,7 +279,7 @@ def test_agg_compat(): with tm.assert_produces_warning(FutureWarning, check_stacklevel=False): result = g['D'].agg({'C': 'sum', 'D': 'std'}) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) def test_agg_nested_dicts(): @@ -310,7 +309,7 @@ def test_agg_nested_dicts(): expected.columns = pd.MultiIndex.from_tuples( [('ra', 'mean'), ('ra', 'std'), ('rb', 'mean'), ('rb', 'std')]) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) # same name as the original column # GH9052 @@ -322,7 +321,7 @@ def test_agg_nested_dicts(): with tm.assert_produces_warning(FutureWarning, check_stacklevel=False): result = g['D'].agg({'D': np.sum, 'result2': np.mean}) - assert_frame_equal(result, expected, check_like=True) + tm.assert_frame_equal(result, expected, check_like=True) def test_agg_item_by_item_raise_typeerror(): @@ -345,7 +344,7 @@ def test_series_agg_multikey(): result = grouped.agg(np.sum) expected = grouped.sum() - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected) def test_series_agg_multi_pure_python(): @@ -366,7 +365,7 @@ def bad(x): result = data.groupby(['A', 'B']).agg(bad) expected = data.groupby(['A', 'B']).agg(lambda x: 'foo') - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_consistency(): @@ -391,7 +390,7 @@ def P1(a): expected.columns = expected.columns.levels[0] result = g.agg(P1) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_callables(): @@ -409,7 +408,7 @@ def __call__(self, x): expected = df.groupby("foo").agg(sum) for ecall in equiv_callables: result = df.groupby('foo').agg(ecall) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_over_numpy_arrays(): @@ -427,7 +426,7 @@ def test_agg_over_numpy_arrays(): index=expected_index, columns=expected_column) - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) def test_agg_timezone_round_trip(): @@ -493,7 +492,7 @@ def test_agg_structs_dataframe(structure, expected): result = df.groupby(['A', 'B']).aggregate(structure) expected.index.names = ['A', 'B'] - assert_frame_equal(result, expected) + tm.assert_frame_equal(result, expected) @pytest.mark.parametrize("structure, expected", [ @@ -512,4 +511,4 @@ def test_agg_structs_series(structure, expected): result = df.groupby('A')['C'].aggregate(structure) expected.index.name = 'A' - assert_series_equal(result, expected) + tm.assert_series_equal(result, expected)