Skip to content

Commit

Permalink
STY: use pytest.raises context syntax (reshape) (#24838)
Browse files Browse the repository at this point in the history
  • Loading branch information
@simonjayhawkins @jreback
simonjayhawkins authored and jreback committed Jan 19, 2019
1 parent 1dcfc5f commit f78790f
Show file tree
Hide file tree
Showing 6 changed files with 204 additions and 114 deletions.
2 changes: 1 addition & 1 deletion pandas/core/reshape/merge.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1087,7 +1087,7 @@ def _validate(self, validate):
elif validate in ["one_to_many", "1:m"]:
if not left_unique:
raise MergeError("Merge keys are not unique in left dataset;"
"not a one-to-many merge")
" not a one-to-many merge")

elif validate in ["many_to_one", "m:1"]:
if not right_unique:
Expand Down
76 changes: 47 additions & 29 deletions pandas/tests/reshape/merge/test_join.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -195,38 +195,47 @@ def test_join_on(self):
assert np.isnan(joined['three']['c'])

# merge column not p resent
pytest.raises(KeyError, target.join, source, on='E')
with pytest.raises(KeyError, match="^'E'$"):
target.join(source, on='E')

# overlap
source_copy = source.copy()
source_copy['A'] = 0
pytest.raises(ValueError, target.join, source_copy, on='A')
msg = ("You are trying to merge on float64 and object columns. If"
" you wish to proceed you should use pd.concat")
with pytest.raises(ValueError, match=msg):
target.join(source_copy, on='A')

def test_join_on_fails_with_different_right_index(self):
with pytest.raises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
msg = (r'len\(left_on\) must equal the number of levels in the index'
' of "right"')
with pytest.raises(ValueError, match=msg):
merge(df, df2, left_on='a', right_index=True)

def test_join_on_fails_with_different_left_index(self):
with pytest.raises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)},
index=tm.makeCustomIndex(10, 2))
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)})
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)},
index=tm.makeCustomIndex(3, 2))
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)})
msg = (r'len\(right_on\) must equal the number of levels in the index'
' of "left"')
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on='b', left_index=True)

def test_join_on_fails_with_different_column_counts(self):
with pytest.raises(ValueError):
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
df = DataFrame({'a': np.random.choice(['m', 'f'], size=3),
'b': np.random.randn(3)})
df2 = DataFrame({'a': np.random.choice(['m', 'f'], size=10),
'b': np.random.randn(10)},
index=tm.makeCustomIndex(10, 2))
msg = r"len\(right_on\) must equal len\(left_on\)"
with pytest.raises(ValueError, match=msg):
merge(df, df2, right_on='a', left_on=['a', 'b'])

@pytest.mark.parametrize("wrong_type", [2, 'str', None, np.array([0, 1])])
Expand All @@ -237,9 +246,11 @@ def test_join_on_fails_with_wrong_object_type(self, wrong_type):
# Edited test to remove the Series object from test parameters

df = DataFrame({'a': [1, 1]})
with pytest.raises(TypeError, match=str(type(wrong_type))):
msg = ("Can only merge Series or DataFrame objects, a {} was passed"
.format(str(type(wrong_type))))
with pytest.raises(TypeError, match=msg):
merge(wrong_type, df, left_on='a', right_on='a')
with pytest.raises(TypeError, match=str(type(wrong_type))):
with pytest.raises(TypeError, match=msg):
merge(df, wrong_type, left_on='a', right_on='a')

def test_join_on_pass_vector(self):
Expand Down Expand Up @@ -603,7 +614,9 @@ def _check_diff_index(df_list, result, exp_index):
joined = df_list[0].join(df_list[1:], how='inner')
_check_diff_index(df_list, joined, df.index[2:8])

pytest.raises(ValueError, df_list[0].join, df_list[1:], on='a')
msg = "Joining multiple DataFrames only supported for joining on index"
with pytest.raises(ValueError, match=msg):
df_list[0].join(df_list[1:], on='a')

def test_join_many_mixed(self):
df = DataFrame(np.random.randn(8, 4), columns=['A', 'B', 'C', 'D'])
Expand Down Expand Up @@ -725,10 +738,13 @@ def test_panel_join_many(self):
tm.assert_panel_equal(joined, expected)

# edge cases
pytest.raises(ValueError, panels[0].join, panels[1:],
how='outer', lsuffix='foo', rsuffix='bar')
pytest.raises(ValueError, panels[0].join, panels[1:],
how='right')
msg = "Suffixes not supported when passing multiple panels"
with pytest.raises(ValueError, match=msg):
panels[0].join(panels[1:], how='outer', lsuffix='foo',
rsuffix='bar')
msg = "Right join not supported with multiple panels"
with pytest.raises(ValueError, match=msg):
panels[0].join(panels[1:], how='right')

def test_join_multi_to_multi(self, join_type):
# GH 20475
Expand All @@ -749,10 +765,12 @@ def test_join_multi_to_multi(self, join_type):
)
assert_frame_equal(expected, result)

with pytest.raises(ValueError):
msg = (r'len\(left_on\) must equal the number of levels in the index'
' of "right"')
with pytest.raises(ValueError, match=msg):
left.join(right, on='xy', how=join_type)

with pytest.raises(ValueError):
with pytest.raises(ValueError, match=msg):
right.join(left, on=['abc', 'xy'], how=join_type)


Expand Down
100 changes: 66 additions & 34 deletions pandas/tests/reshape/merge/test_merge.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -119,25 +119,37 @@ def test_merge_index_singlekey_inner(self):
assert_frame_equal(result, expected.loc[:, result.columns])

def test_merge_misspecified(self):
pytest.raises(ValueError, merge, self.left, self.right,
left_index=True)
pytest.raises(ValueError, merge, self.left, self.right,
right_index=True)

pytest.raises(ValueError, merge, self.left, self.left,
left_on='key', on='key')

pytest.raises(ValueError, merge, self.df, self.df2,
left_on=['key1'], right_on=['key1', 'key2'])
msg = "Must pass right_on or right_index=True"
with pytest.raises(pd.errors.MergeError, match=msg):
merge(self.left, self.right, left_index=True)
msg = "Must pass left_on or left_index=True"
with pytest.raises(pd.errors.MergeError, match=msg):
merge(self.left, self.right, right_index=True)

msg = ('Can only pass argument "on" OR "left_on" and "right_on", not'
' a combination of both')
with pytest.raises(pd.errors.MergeError, match=msg):
merge(self.left, self.left, left_on='key', on='key')

msg = r"len\(right_on\) must equal len\(left_on\)"
with pytest.raises(ValueError, match=msg):
merge(self.df, self.df2, left_on=['key1'],
right_on=['key1', 'key2'])

def test_index_and_on_parameters_confusion(self):
pytest.raises(ValueError, merge, self.df, self.df2, how='left',
left_index=False, right_index=['key1', 'key2'])
pytest.raises(ValueError, merge, self.df, self.df2, how='left',
left_index=['key1', 'key2'], right_index=False)
pytest.raises(ValueError, merge, self.df, self.df2, how='left',
left_index=['key1', 'key2'],
right_index=['key1', 'key2'])
msg = ("right_index parameter must be of type bool, not"
r" <(class|type) 'list'>")
with pytest.raises(ValueError, match=msg):
merge(self.df, self.df2, how='left',
left_index=False, right_index=['key1', 'key2'])
msg = ("left_index parameter must be of type bool, not "
r"<(class|type) 'list'>")
with pytest.raises(ValueError, match=msg):
merge(self.df, self.df2, how='left',
left_index=['key1', 'key2'], right_index=False)
with pytest.raises(ValueError, match=msg):
merge(self.df, self.df2, how='left',
left_index=['key1', 'key2'], right_index=['key1', 'key2'])

def test_merge_overlap(self):
merged = merge(self.left, self.left, on='key')
Expand Down Expand Up @@ -269,7 +281,6 @@ def test_no_overlap_more_informative_error(self):
df1 = DataFrame({'x': ['a']}, index=[dt])

df2 = DataFrame({'y': ['b', 'c']}, index=[dt, dt])
pytest.raises(MergeError, merge, df1, df2)

msg = ('No common columns to perform merge on. '
'Merge options: left_on={lon}, right_on={ron}, '
Expand Down Expand Up @@ -566,7 +577,10 @@ def test_overlapping_columns_error_message(self):

# #2649, #10639
df2.columns = ['key1', 'foo', 'foo']
pytest.raises(ValueError, merge, df, df2)
msg = (r"Data columns not unique: Index\(\[u?'foo', u?'foo'\],"
r" dtype='object'\)")
with pytest.raises(MergeError, match=msg):
merge(df, df2)

def test_merge_on_datetime64tz(self):

Expand Down Expand Up @@ -717,9 +731,10 @@ def test_indicator(self):
assert_frame_equal(test_custom_name, df_result_custom_name)

# Check only accepts strings and booleans
with pytest.raises(ValueError):
msg = "indicator option can only accept boolean or string arguments"
with pytest.raises(ValueError, match=msg):
merge(df1, df2, on='col1', how='outer', indicator=5)
with pytest.raises(ValueError):
with pytest.raises(ValueError, match=msg):
df1.merge(df2, on='col1', how='outer', indicator=5)

# Check result integrity
Expand All @@ -743,20 +758,25 @@ def test_indicator(self):
for i in ['_right_indicator', '_left_indicator', '_merge']:
df_badcolumn = DataFrame({'col1': [1, 2], i: [2, 2]})

with pytest.raises(ValueError):
msg = ("Cannot use `indicator=True` option when data contains a"
" column named {}|"
"Cannot use name of an existing column for indicator"
" column").format(i)
with pytest.raises(ValueError, match=msg):
merge(df1, df_badcolumn, on='col1',
how='outer', indicator=True)
with pytest.raises(ValueError):
with pytest.raises(ValueError, match=msg):
df1.merge(df_badcolumn, on='col1', how='outer', indicator=True)

# Check for name conflict with custom name
df_badcolumn = DataFrame(
{'col1': [1, 2], 'custom_column_name': [2, 2]})

with pytest.raises(ValueError):
msg = "Cannot use name of an existing column for indicator column"
with pytest.raises(ValueError, match=msg):
merge(df1, df_badcolumn, on='col1', how='outer',
indicator='custom_column_name')
with pytest.raises(ValueError):
with pytest.raises(ValueError, match=msg):
df1.merge(df_badcolumn, on='col1', how='outer',
indicator='custom_column_name')

Expand Down Expand Up @@ -843,11 +863,13 @@ def test_validation(self):
merge(left, right_w_dups, left_index=True, right_index=True,
validate='one_to_many')

with pytest.raises(MergeError):
msg = ("Merge keys are not unique in right dataset; not a one-to-one"
" merge")
with pytest.raises(MergeError, match=msg):
merge(left, right_w_dups, left_index=True, right_index=True,
validate='one_to_one')

with pytest.raises(MergeError):
with pytest.raises(MergeError, match=msg):
merge(left, right_w_dups, on='a', validate='one_to_one')

# Dups on left
Expand All @@ -856,26 +878,33 @@ def test_validation(self):
merge(left_w_dups, right, left_index=True, right_index=True,
validate='many_to_one')

with pytest.raises(MergeError):
msg = ("Merge keys are not unique in left dataset; not a one-to-one"
" merge")
with pytest.raises(MergeError, match=msg):
merge(left_w_dups, right, left_index=True, right_index=True,
validate='one_to_one')

with pytest.raises(MergeError):
with pytest.raises(MergeError, match=msg):
merge(left_w_dups, right, on='a', validate='one_to_one')

# Dups on both
merge(left_w_dups, right_w_dups, on='a', validate='many_to_many')

with pytest.raises(MergeError):
msg = ("Merge keys are not unique in right dataset; not a many-to-one"
" merge")
with pytest.raises(MergeError, match=msg):
merge(left_w_dups, right_w_dups, left_index=True,
right_index=True, validate='many_to_one')

with pytest.raises(MergeError):
msg = ("Merge keys are not unique in left dataset; not a one-to-many"
" merge")
with pytest.raises(MergeError, match=msg):
merge(left_w_dups, right_w_dups, on='a',
validate='one_to_many')

# Check invalid arguments
with pytest.raises(ValueError):
msg = "Not a valid argument for validate"
with pytest.raises(ValueError, match=msg):
merge(left, right, on='a', validate='jibberish')

# Two column merge, dups in both, but jointly no dups.
Expand All @@ -896,7 +925,9 @@ def test_validation(self):
'um... weasel noise?']},
index=range(3))

with pytest.raises(MergeError):
msg = ("Merge keys are not unique in either left or right dataset;"
" not a one-to-one merge")
with pytest.raises(MergeError, match=msg):
merge(left, right, on='a', validate='1:1')

result = merge(left, right, on=['a', 'b'], validate='1:1')
Expand Down Expand Up @@ -1439,6 +1470,7 @@ def test_merge_series(on, left_on, right_on, left_index, right_index, nm):
left_index=left_index, right_index=right_index)
tm.assert_frame_equal(result, expected)
else:
with pytest.raises(ValueError, match='a Series without a name'):
msg = "Cannot merge a Series without a name"
with pytest.raises(ValueError, match=msg):
result = pd.merge(a, b, on=on, left_on=left_on, right_on=right_on,
left_index=left_index, right_index=right_index)
Loading

0 comments on commit f78790f

Please sign in to comment.