240403 결과 정리

Author

김보람

Published

April 3, 2024

import pandas as pd
import os

240220

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
EmptyDataError: No columns to parse from file
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1157 GCN NaN 0.963869 0.105485 0.833333 0.187266 0.957759 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 45280.0 0.4
1158 GCN NaN 0.966034 0.115044 0.866667 0.203125 0.957106 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 35280.0 0.4
1159 GCN NaN 0.971528 0.134715 0.866667 0.233184 0.955489 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 25280.0 0.4
1160 GCN NaN 0.972527 0.139037 0.866667 0.239631 0.956621 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 15280.0 0.4
1161 GCN NaN 0.971029 0.132653 0.866667 0.230088 0.957218 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 5280.0 0.4

1162 rows × 18 columns

merged_df.to_csv('./results/240220_meged.csv', index=False)
merged_df['train_cols'] = 'amt'
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1157 GCN NaN 0.963869 0.105485 0.833333 0.187266 0.957759 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 45280.0 0.4
1158 GCN NaN 0.966034 0.115044 0.866667 0.203125 0.957106 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 35280.0 0.4
1159 GCN NaN 0.971528 0.134715 0.866667 0.233184 0.955489 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 25280.0 0.4
1160 GCN NaN 0.972527 0.139037 0.866667 0.239631 0.956621 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 15280.0 0.4
1161 GCN NaN 0.971029 0.132653 0.866667 0.230088 0.957218 True Proposed 0.300000 14014 amt 0.426431 6006 0.005000 NaN 5280.0 0.4

1162 rows × 18 columns

240307

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
2693 NeuralNetFastAI NaN 0.908928 0.926845 0.975234 0.950424 0.890713 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
2694 XGBoost NaN 0.943679 0.956323 0.981928 0.968956 0.951813 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
2695 NeuralNetTorch NaN 0.909527 0.927980 0.974565 0.950702 0.892102 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
2696 LightGBMLarge NaN 0.947274 0.960079 0.981928 0.970880 0.942957 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
2697 WeightedEnsemble_L2 NaN 0.946675 0.957059 0.984605 0.970637 0.954372 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN

2698 rows × 18 columns

merged_df.to_csv('./results/240307_meged.csv', index=False)
merged_df['train_cols'] = 'amt'
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
2693 NeuralNetFastAI NaN 0.908928 0.926845 0.975234 0.950424 0.890713 False Auto_not_best 0.900045 5004 amt 0.901679 1669 0.895147 NaN NaN NaN
2694 XGBoost NaN 0.943679 0.956323 0.981928 0.968956 0.951813 False Auto_not_best 0.900045 5004 amt 0.901679 1669 0.895147 NaN NaN NaN
2695 NeuralNetTorch NaN 0.909527 0.927980 0.974565 0.950702 0.892102 False Auto_not_best 0.900045 5004 amt 0.901679 1669 0.895147 NaN NaN NaN
2696 LightGBMLarge NaN 0.947274 0.960079 0.981928 0.970880 0.942957 False Auto_not_best 0.900045 5004 amt 0.901679 1669 0.895147 NaN NaN NaN
2697 WeightedEnsemble_L2 NaN 0.946675 0.957059 0.984605 0.970637 0.954372 False Auto_not_best 0.900045 5004 amt 0.901679 1669 0.895147 NaN NaN NaN

2698 rows × 18 columns

240326

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1656 LODA 1.380267 0.990775 0.000000 0.000000 0.000000 0.499843 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1657 LOF 1.171791 0.982414 0.001378 0.001345 0.001361 0.496291 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1658 MCD 0.101797 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1659 PCA 0.029553 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1660 ROD 15.238129 0.978524 0.000477 0.000672 0.000558 0.493995 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN

1661 rows × 18 columns

merged_df['train_cols'] = 'amt'
merged_df.to_csv('./results/240326_meged.csv', index=False)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 amt 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1656 LODA 1.380267 0.990775 0.000000 0.000000 0.000000 0.499843 False pyod 0.009000 500499 amt 0.009029 166834 0.008913 NaN NaN NaN
1657 LOF 1.171791 0.982414 0.001378 0.001345 0.001361 0.496291 False pyod 0.009000 500499 amt 0.009029 166834 0.008913 NaN NaN NaN
1658 MCD 0.101797 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 amt 0.009029 166834 0.008913 NaN NaN NaN
1659 PCA 0.029553 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 amt 0.009029 166834 0.008913 NaN NaN NaN
1660 ROD 15.238129 0.978524 0.000477 0.000672 0.000558 0.493995 False pyod 0.009000 500499 amt 0.009029 166834 0.008913 NaN NaN NaN

1661 rows × 18 columns

240403

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1643 LODA 1.380267 0.990775 0.000000 0.000000 0.000000 0.499843 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1644 LOF 1.171791 0.982414 0.001378 0.001345 0.001361 0.496291 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1645 MCD 0.101797 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1646 PCA 0.029553 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
1647 ROD 15.238129 0.978524 0.000477 0.000672 0.000558 0.493995 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN

1648 rows × 18 columns

merged_df.to_csv('./results/240403_meged.csv', index=False)

240404

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
2030 LODA 1.380267 0.990775 0.000000 0.000000 0.000000 0.499843 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
2031 LOF 1.171791 0.982414 0.001378 0.001345 0.001361 0.496291 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
2032 MCD 0.101797 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
2033 PCA 0.029553 0.990787 0.482782 0.471419 0.477033 0.733439 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN
2034 ROD 15.238129 0.978524 0.000477 0.000672 0.000558 0.493995 False pyod 0.009000 500499 ['amt'] 0.009029 166834 0.008913 NaN NaN NaN

2035 rows × 18 columns

merged_df.to_csv('./results/240404_meged.csv', index=False)

240411

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
12823 NeuralNetFastAI NaN 0.997890 0.000000 0.000000 0.000000 0.917705 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
12824 XGBoost NaN 0.996580 0.178571 0.172414 0.175439 0.939455 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
12825 NeuralNetTorch NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
12826 LightGBMLarge NaN 0.997890 0.000000 0.000000 0.000000 0.944964 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
12827 WeightedEnsemble_L2 NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN

12828 rows × 18 columns

240417

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 ECOD 0.003704 0.591404 0.003553 0.843750 0.007076 0.717359 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
1 GMM 0.082634 0.692003 0.003410 0.609375 0.006782 0.650760 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
2 HBOS 0.002123 0.936368 0.020868 0.781250 0.040650 0.858943 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
3 IForest 0.144727 0.815358 0.007263 0.781250 0.014393 0.798334 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
4 INNE 0.326223 0.766636 0.005070 0.687500 0.010065 0.727136 False pyod 0.097074 10010 ['amt'] 0.450350 37088 0.001726 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
13523 NeuralNetFastAI NaN 0.997890 0.000000 0.000000 0.000000 0.917705 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
13524 XGBoost NaN 0.996580 0.178571 0.172414 0.175439 0.939455 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
13525 NeuralNetTorch NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
13526 LightGBMLarge NaN 0.997890 0.000000 0.000000 0.000000 0.944964 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
13527 WeightedEnsemble_L2 NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN

13528 rows × 18 columns

merged_df.loc[merged_df['method'] == 'Auto_not_best', 'method'] = 'Autogluon'
merged_df.to_csv('./results/240414_meged.csv', index=False)

240423

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 KNeighborsUnif NaN 0.943679 0.961741 0.975904 0.968771 0.897824 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
1 KNeighborsDist NaN 0.927501 0.959197 0.959839 0.959518 0.870203 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
2 LightGBMXT NaN 0.929299 0.952632 0.969210 0.960849 0.945900 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
3 LightGBM NaN 0.946675 0.958252 0.983266 0.970598 0.954381 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
4 RandomForestGini NaN 0.927501 0.957972 0.961178 0.959572 0.903513 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
44701 NeuralNetFastAI NaN 0.997890 0.000000 0.000000 0.000000 0.917705 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
44702 XGBoost NaN 0.996580 0.178571 0.172414 0.175439 0.939455 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
44703 NeuralNetTorch NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
44704 LightGBMLarge NaN 0.997890 0.000000 0.000000 0.000000 0.944964 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
44705 WeightedEnsemble_L2 NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN

44706 rows × 18 columns

merged_df.loc[merged_df['method'] == 'Auto_not_best', 'method'] = 'Autogluon'
merged_df.to_csv('./results/240423_meged.csv', index=False)

240430

folder_path = './results'
all_data = []
for file_name in os.listdir(folder_path):

    if file_name.endswith('.csv'):

        df = pd.read_csv(os.path.join(folder_path, file_name))

        all_data.append(df)
merged_df = pd.concat(all_data, ignore_index=True)
merged_df
model time acc pre rec f1 auc graph_based method throw_rate train_size train_cols train_frate test_size test_frate hyper_params theta gamma
0 KNeighborsUnif NaN 0.943679 0.961741 0.975904 0.968771 0.897824 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
1 KNeighborsDist NaN 0.927501 0.959197 0.959839 0.959518 0.870203 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
2 LightGBMXT NaN 0.929299 0.952632 0.969210 0.960849 0.945900 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
3 LightGBM NaN 0.946675 0.958252 0.983266 0.970598 0.954381 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
4 RandomForestGini NaN 0.927501 0.957972 0.961178 0.959572 0.903513 False Auto_not_best 0.900045 5004 ['amt'] 0.901679 1669 0.895147 NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
51405 NeuralNetFastAI NaN 0.997890 0.000000 0.000000 0.000000 0.917705 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
51406 XGBoost NaN 0.996580 0.178571 0.172414 0.175439 0.939455 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
51407 NeuralNetTorch NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
51408 LightGBMLarge NaN 0.997890 0.000000 0.000000 0.000000 0.944964 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN
51409 WeightedEnsemble_L2 NaN 0.997162 0.187500 0.103448 0.133333 0.941711 False Autogluon 0.008901 500499 ['amt'] 0.009087 13741 0.002110 NaN NaN NaN

51410 rows × 18 columns

merged_df.loc[merged_df['method'] == 'Auto_not_best', 'method'] = 'Autogluon'
merged_df.to_csv('./results/240430_meged.csv', index=False)