def test_categorize_no_cat(generate_data_no_cat):
assert categorize(pd.DataFrame()) == {
'numeric': [],
'categorical': []
}, "Empty\
dataframe should return dictionary \
with keys but empty list values"
assert categorize(generate_data_no_cat) == {
'numeric': [],
'categorical': []
}, "Dataframe\
def run_pylaundry():
"""
Runs all modules of pylaundry
Arguments
--------
NA
Returns
------
features_selected = list of final features selected
"""
col_dict = categorize(df=X_train)
# second function - fill_missing
clean_data = fill_missing(X_train,
X_test,
col_dict,
num_imp="mean",
cat_imp="mode")
# third function - transform_columns
transformed_data = transform_columns(clean_data['X_train'],
clean_data['X_test'], col_dict)
# fourth function - feature selection
features_selected = select_features(transformed_data['X_train'],
y_train,
n_features=2)
return features_selected
def test_output_type(generate_data):
output = categorize(generate_data)
assert isinstance(output, dict), \
"Output of categorize() should be a dictionary"
assert isinstance(output['numeric'], list), \
"Dictionary value should be list"
assert isinstance(output['categorical'], list), \
"Dictionary value should be list"
def test_categorize_bad_input(generate_data):
try:
categorize('hello!')
except AssertionError:
pass
try:
categorize(np.ones((3, 3)))
except AssertionError:
pass
try:
categorize(generate_data, max_cat=1.3)
except AssertionError:
pass
try:
categorize(generate_data, max_cat=-1)
except AssertionError:
pass
try:
categorize(pd.DataFrame(([1, 2, 3, 4])))
except AssertionError:
pass
def test_categorize_max_cat(generate_data):
output = categorize(generate_data, max_cat=3)
assert output['categorical'] == ['cat2'], "Only cat2 of generate_data()\
should be categorical with max_cat = 3"
assert set(output['numeric']) == set(['num1', 'num2', 'num3', 'cat1']),\
"Cat 1 should be marked numeric with max_cat = 3"
def test_categorize_numeric(generate_data):
output = categorize(generate_data)
assert set(output['numeric']) == set(['num1', 'num2', 'num3']), "num1, \
def test_categorize_float_dtype(generate_data):
df = pd.DataFrame({'col': [1.1, 1.1, 2.2, 2.2]})
output = categorize(df)
assert output['numeric'] == ['col'], "A column with dtype \
def test_categorize_cat_dtype(generate_data):
df = pd.DataFrame({'col': [1.1, 2.2, 3.3, 4.4]})
df['col'] = df['col'].astype('category')
output = categorize(df, max_cat=2)
assert output['categorical'] == ['col'], "A column with \
def test_categorize_categorical(generate_data):
output = categorize(generate_data)
assert set(output['categorical']) == set(['cat1', 'cat2', 'cat3']), "cat1,\