def test_input(generate_wrong_data_one):
"""
The function tess if the input data type is correct or not.
Examples
--------
>>> test_input(generate_wrong_data_one)
"""
df, y = generate_wrong_data_one
try:
select_features.select_features(df, y, n_features=1)
except AssertionError:
pass
def test_columns():
"""
The function tess if the input data has columns or not.
Examples
--------
>>> test_input(generate_wrong_data_one)
"""
df = pd.DataFrame(([1, 'x']))
y = np.array([1, 2, 3])
try:
select_features.select_features(df, y, n_features=1)
except AssertionError:
pass
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_dataframe(generate_wrong_data):
"""
The function tests if the column type is correct in the input data.
Examples
--------
>>> test_dataframe(generate_wrong_data)
"""
df = generate_wrong_data
y = df['y'].values
df = df[['x1', 'x2', 'x3']]
try:
select_features.select_features(df, y, n_features=1)
except AssertionError:
pass
def test_regression_one(generate_data_regression_one):
"""
The function does regression test for multi feature
Examples
--------
>>> test_regression_one(generate_data_regression_one)
"""
df = generate_data_regression_one
y = df['y'].values
df = df[['x1', 'x2', 'x3']]
assert select_features.select_features(df, y, n_features=2) == ["x1", "x2"]
def test_regression(generate_data_regression):
"""
The function does regression test for single feature
Examples
--------
>>> test_regression(generate_data_regression)
"""
df = generate_data_regression
y = df['y'].values
df = df[['x1', 'x2', 'x3']]
assert select_features.select_features(df, y, n_features=1) == ["x1"]
def test_classification_multi(generate_data_classification_multi):
"""
The function does classification test for multiple feature
Examples
--------
>>> test_classification_multi(generate_data_classification_multi)
"""
df = generate_data_classification_multi
y = df['y'].values
df = df[['x1', 'x2', 'x3']]
t = select_features.select_features(df,
y, mode="classification", n_features=2)
assert t == ["x1", "x2"]
def test_classification(generate_data_classification):
"""
The function does classification test for single feature
Examples
--------
>>> test_classification(generate_data_classification)
"""
df = generate_data_classification
y = df['y'].values
df = df[['x1', 'x2', 'x3']]
t = select_features.select_features(df,
y, mode="classification", n_features=1)
assert t == ["x1"]