Delete train.py
Browse files
train.py
DELETED
|
@@ -1,102 +0,0 @@
|
|
| 1 |
-
# -*- coding: utf-8 -*-
|
| 2 |
-
"""train.ipynb
|
| 3 |
-
|
| 4 |
-
Automatically generated by Colab.
|
| 5 |
-
|
| 6 |
-
Original file is located at
|
| 7 |
-
https://colab.research.google.com/drive/1hMAC2s_7RstOym5W6rezL_47Ch3iwR5J
|
| 8 |
-
"""
|
| 9 |
-
|
| 10 |
-
import pandas as pd
|
| 11 |
-
import numpy as np
|
| 12 |
-
import joblib
|
| 13 |
-
|
| 14 |
-
from sklearn.preprocessing import StandardScaler, OneHotEncoder
|
| 15 |
-
from sklearn.impute import KNNImputer, SimpleImputer
|
| 16 |
-
from sklearn.compose import ColumnTransformer
|
| 17 |
-
from sklearn.pipeline import Pipeline
|
| 18 |
-
|
| 19 |
-
from sklearn.linear_model import LogisticRegression
|
| 20 |
-
from sklearn.ensemble import RandomForestClassifier, StackingClassifier, VotingClassifier
|
| 21 |
-
from xgboost import XGBClassifier
|
| 22 |
-
from imblearn.over_sampling import SMOTE
|
| 23 |
-
from imblearn.pipeline import Pipeline as ImbPipeline
|
| 24 |
-
|
| 25 |
-
df = pd.read_csv('loan_dataset.csv')
|
| 26 |
-
X = df.drop('BAD', axis=1)
|
| 27 |
-
y = df['BAD']
|
| 28 |
-
|
| 29 |
-
# Explicitly separate numeric and string columns to fix Pandas4Warnings
|
| 30 |
-
num_cols = X.select_dtypes(include=['int64', 'float64']).columns.tolist()
|
| 31 |
-
cat_cols = X.select_dtypes(include=['object', 'string']).columns.tolist()
|
| 32 |
-
|
| 33 |
-
def cap_outliers_iqr(data, columns):
|
| 34 |
-
data_clean = data.copy()
|
| 35 |
-
for col in columns:
|
| 36 |
-
Q1 = data_clean[col].quantile(0.25)
|
| 37 |
-
Q3 = data_clean[col].quantile(0.75)
|
| 38 |
-
IQR = Q3 - Q1
|
| 39 |
-
if IQR > 0:
|
| 40 |
-
lower_bound = Q1 - 1.5 * IQR
|
| 41 |
-
upper_bound = Q3 + 1.5 * IQR
|
| 42 |
-
data_clean[col] = np.where(data_clean[col] < lower_bound, lower_bound, data_clean[col])
|
| 43 |
-
data_clean[col] = np.where(data_clean[col] > upper_bound, upper_bound, data_clean[col])
|
| 44 |
-
return data_clean
|
| 45 |
-
|
| 46 |
-
X_cleaned = cap_outliers_iqr(X, num_cols)
|
| 47 |
-
|
| 48 |
-
# 3. Build Safe Transformation Layouts
|
| 49 |
-
num_pipeline = Pipeline([
|
| 50 |
-
('imputer', KNNImputer(n_neighbors=5)),
|
| 51 |
-
('scaler', StandardScaler())
|
| 52 |
-
])
|
| 53 |
-
|
| 54 |
-
# Fixed: Uses SimpleImputer on strings before feeding into OneHotEncoder to prevent ValueErrors
|
| 55 |
-
cat_pipeline = Pipeline([
|
| 56 |
-
('imputer', SimpleImputer(strategy='most_frequent')),
|
| 57 |
-
('encoder', OneHotEncoder(handle_unknown='ignore', sparse_output=False))
|
| 58 |
-
])
|
| 59 |
-
|
| 60 |
-
preprocessor = ColumnTransformer([
|
| 61 |
-
('num', num_pipeline, num_cols),
|
| 62 |
-
('cat', cat_pipeline, cat_cols)
|
| 63 |
-
])
|
| 64 |
-
|
| 65 |
-
# 4. Streamlined High-Speed Base Learners
|
| 66 |
-
rf_base = RandomForestClassifier(n_estimators=60, max_depth=8, random_state=42, n_jobs=-1)
|
| 67 |
-
xgb_base = XGBClassifier(n_estimators=60, learning_rate=0.1, max_depth=4, eval_metric='logloss', random_state=42, n_jobs=-1)
|
| 68 |
-
voting_base = VotingClassifier(estimators=[('rf_v', rf_base), ('xgb_v', xgb_base)], voting='soft')
|
| 69 |
-
|
| 70 |
-
# Meta-Classifier Network
|
| 71 |
-
stacking_ensemble = StackingClassifier(
|
| 72 |
-
estimators=[('rf', rf_base), ('xgb', xgb_base), ('voting', voting_base)],
|
| 73 |
-
final_estimator=LogisticRegression(max_iter=500, C=0.1),
|
| 74 |
-
cv=2, # Reduced cross-validation folds to minimize training overhead
|
| 75 |
-
n_jobs=-1
|
| 76 |
-
)
|
| 77 |
-
|
| 78 |
-
production_pipeline = ImbPipeline([
|
| 79 |
-
('preprocessing', preprocessor),
|
| 80 |
-
('smote', SMOTE(random_state=42, sampling_strategy=0.6)),
|
| 81 |
-
('ensemble_model', stacking_ensemble)
|
| 82 |
-
])
|
| 83 |
-
|
| 84 |
-
# Fit and export to disk
|
| 85 |
-
production_pipeline.fit(X_cleaned, y)
|
| 86 |
-
joblib.dump(production_pipeline, 'loan_stacking_model.pkl')
|
| 87 |
-
print("🎉 Pipeline trained successfully and saved as 'loan_stacking_model.pkl'!")
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|