def split_by_missingvalues():
before_cleaning = Cleaner.count_nan_columns(cleaner.azdias)
cleaner.to_nan()
after_cleaning = Cleaner.count_nan_columns(cleaner.azdias)
l, g, s1, s2 = Cleaner.split_by_treshhold(cleaner.azdias)
cleaner.azdias = l
return before_cleaning, after_cleaning, l.shape, g.shape
def clean_data(df):
l, g, less_trh, gr_trh = Cleaner.split_by_treshhold(df, treshold=34)
df = l
df = Cleaner.to_nan(df, cleaner.summary)
df = recode(df)
df = extract_features(df)
df = drop(df)
df = dummies(df)
return df
def test_split(self):
l, g = Cleaner.split_by_treshhold(self.cleaner.azdias)
self.assertEqual(l.shape, (798293, 85))
self.assertEqual(g.shape, (92928, 85))
self.cleaner.azdias = l