| import pandas as pd |
| import numpy as np |
|
|
| from imblearn.over_sampling import SMOTENC |
|
|
| |
| regions = ['incheon', 'seoul','busan', 'daegu', 'daejeon', 'gwangju'] |
| file_paths = [f'../../data/data_for_modeling/{region}_train.csv' for region in regions] |
| output_paths = [f'../../data/data_oversampled/smote/smote_1_{region}.csv' for region in regions] |
|
|
| |
| for file_path, output_path in zip(file_paths, output_paths): |
| |
| data = pd.read_csv(file_path, index_col=0) |
| data= data.loc[data['year'].isin([2018,2019]),:] |
| data['cloudcover'] = data['cloudcover'].astype('int') |
| data['lm_cloudcover'] = data['lm_cloudcover'].astype('int') |
| X = data.drop(columns=['multi_class', 'binary_class']) |
| y = data['multi_class'] |
|
|
| |
| X.drop(columns=['ground_temp - temp_C', 'hour_sin', 'hour_cos', 'month_sin', 'month_cos'], inplace=True) |
|
|
| |
| categorical_features_indices = [i for i, dtype in enumerate(X.dtypes) if dtype != 'float64'] |
|
|
| |
| count_class_2 = (y == 2).sum() |
| sampling_strategy = { |
| 0: int(np.ceil(count_class_2 / 1000) * 500), |
| 1: int(np.ceil(count_class_2 / 1000) * 500), |
| 2: count_class_2 |
| } |
|
|
| |
| smotenc = SMOTENC(categorical_features=categorical_features_indices, sampling_strategy=sampling_strategy, random_state=42) |
| X_resampled, y_resampled = smotenc.fit_resample(X, y) |
|
|
| |
| lerp_data = X_resampled.copy() |
| lerp_data['multi_class'] = y_resampled |
|
|
| |
| lerp_data['binary_class'] = lerp_data['multi_class'].apply(lambda x: 0 if x == 2 else 1) |
| lerp_data['hour_sin'] = np.sin(2 * np.pi * lerp_data['hour'] / 24) |
| lerp_data['hour_cos'] = np.cos(2 * np.pi * lerp_data['hour'] / 24) |
| lerp_data['month_sin'] = np.sin(2 * np.pi * lerp_data['month'] / 12) |
| lerp_data['month_cos'] = np.cos(2 * np.pi * lerp_data['month'] / 12) |
| lerp_data['ground_temp - temp_C'] = lerp_data['groundtemp'] - lerp_data['temp_C'] |
|
|
| |
| lerp_data.to_csv(output_path, index = False) |
| print(len(lerp_data[lerp_data['multi_class']==0]),'|',len(lerp_data[lerp_data['multi_class']==1]),'|',len(lerp_data[lerp_data['multi_class']==2])) |
