def test_merge_unicode_col():
bad_df = DDF(DATA)
bad_str = u'hurac\xe1n'
bad_df['name'] = np.array([bad_str]*N_EXAMPLES).astype(unicode)
good_df = DDF(DATA)
good_str = u'namey_mc_name'
good_df['name'] = np.array([good_str]*N_EXAMPLES).astype(str)
bad_df.merge(good_df, on=['group_id', 'name'], how='left')
def test_can_merge_two_ddfs():
d1 = DDF({'col1': np.arange(4), 'col2': np.arange(4)})
d2 = DDF({'col1': np.arange(2), 'col3': np.arange(2)})
d3 = d2.merge(d1, on='col1', how='outer')
assert np.allclose(d3['col2'], d1['col2'])
assert utils.nan_allclose(d3['col3'], np.array([0, 1, np.nan, np.nan]))
def test_merge_preservers_strings():
d1 = DDF({'a': np.arange(4), 'b': np.repeat('b', 4), 'd': np.repeat('r', 4)})
d2 = DDF({'a': np.arange(4), 'c': np.repeat('c', 4), 'd': np.repeat('2r', 4)})
merged = d1.merge(d2, on='a')
assert merged['b'].dtype.type is np.str_
assert merged['c'].dtype.type is np.str_
