def none_missing(df, columns=None):
"""
Asserts that there are no missing values (NaNs) in the DataFrame.
Parameters
----------
df : DataFrame
columns : list
list of columns to restrict the check to
Returns
-------
df : DataFrame
same as the original
"""
if columns is None:
columns = df.columns
try:
assert not df[columns].isnull().any().any()
except AssertionError as e:
missing = df[columns].isnull()
msg = generic.bad_locations(missing)
e.args = msg
raise
return df
def none_missing(df, columns=None):
"""
Asserts that there are no missing values (NaNs) in the DataFrame.
Parameters
----------
df : DataFrame
columns : list
list of columns to restrict the check to
Returns
-------
df : DataFrame
same as the original
"""
if columns is None:
columns = df.columns
try:
assert not df[columns].isnull().any().any()
except AssertionError as e:
missing = df[columns].isnull()
msg = generic.bad_locations(missing)
e.args = msg
raise
return df
def within_n_std(df, n=3):
"""
Assert that every value is within ``n`` standard
deviations of its column's mean.
Parameters
==========
df : DataFame
n : int
number of standard devations from the mean
Returns
=======
df : DatFrame
"""
means = df.mean()
stds = df.std()
inliers = (np.abs(df - means) < n * stds)
if not np.all(inliers):
msg = generic.bad_locations(~inliers)
raise AssertionError(msg)
return df
def within_n_std(df, n=3):
"""
Assert that every value is within ``n`` standard
deviations of its column's mean.
Parameters
==========
df : DataFame
n : int
number of standard devations from the mean
Returns
=======
df : DatFrame
"""
means = df.mean()
stds = df.std()
inliers = (np.abs(df - means) < n * stds)
if not np.all(inliers):
msg = generic.bad_locations(~inliers)
raise AssertionError(msg)
return df
