def test_split_train_test():
"""Test split_train_test()."""
recs = [{
'test_feature_1': 1,
'test_feature_2': 1,
'test_class': 1
}, {
'test_feature_1': 1,
'test_feature_2': 1,
'test_class': 1
}, {
'test_feature_1': 3,
'test_feature_2': 3,
'test_class': 1
}, {
'test_feature_1': 5,
'test_feature_2': 5,
'test_class': 0
}, {
'test_feature_1': 5,
'test_feature_2': 5,
'test_class': 0
}]
test_df = pd.DataFrame(recs)
features = ['test_feature_1', 'test_feature_2']
test_size = 0.33
class_col = 'test_class'
obj = DataWrangling()
return_val = obj.split_train_test(x_data=test_df[features].to_numpy(),
y_labels=test_df[class_col].to_numpy(),
features=features,
test_size=test_size)
expected_keys = ['x_train', 'y_train', 'x_test', 'y_test']
assert all(key in return_val for key in expected_keys)
assert all(
isinstance(val, (pd.Series, pd.DataFrame))
for _, val in return_val.items())
def get_data(n_bins: int) -> dict:
"""Retrieve data and perform preprocessing steps and return result.
Args:
n_bins (int): Number of bins to discretize features into.
Returns:
dict: Dictionary containing test and training sets and labels.
"""
dframe = pd.read_csv(TEST_DATA_PATH)
obj1 = DataWrangling(data_path=TEST_DATA_PATH)
obj1.load_data()
features = [
'Pglucose', 'Preg', 'Dbp', 'BMI', 'Dpfunc', 'Age', 'Insulin', 'Skin'
]
input_df = obj1.data[features + ['Response']].astype(np.float64)
no_zero_vals = obj1.fill_nul_vals(data_frame=input_df,
class_column='Response',
features=features)
new_feature_list = []
for feature in features:
for bin_val in range(1, n_bins + 1):
new_feature_list.append(feature + str(bin_val))
discr_arr = obj1.discretize_features(data_frame=no_zero_vals,
features=features,
n_bins=n_bins)
discr_df = pd.DataFrame(discr_arr, columns=new_feature_list)
discr_df['Response'] = dframe['Response']
splits = obj1.split_train_test(
x_data=discr_df[new_feature_list].to_numpy(),
y_labels=discr_df['Response'].to_numpy(),
features=new_feature_list,
test_size=0.25)
return splits