File size: 2,010 Bytes
08d6be3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix, precision_recall_curve, auc
from imblearn.over_sampling import SMOTE
import joblib
import os
# Load data
print("Loading data...")
df = pd.read_csv('c:/card/creditcard.csv')
# Preprocessing
print("Preprocessing...")
scaler_amount = StandardScaler()
scaler_time = StandardScaler()
df['scaled_amount'] = scaler_amount.fit_transform(df['Amount'].values.reshape(-1, 1))
df['scaled_time'] = scaler_time.fit_transform(df['Time'].values.reshape(-1, 1))
# Drop original Time and Amount
df.drop(['Time', 'Amount'], axis=1, inplace=True)
# Define X and y
X = df.drop('Class', axis=1)
y = df['Class']
# Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
# Handle imbalance with SMOTE
print("Applying SMOTE to balance training data...")
sm = SMOTE(random_state=42)
X_train_res, y_train_res = sm.fit_resample(X_train, y_train)
print(f"Original training shape: {X_train.shape}")
print(f"Resampled training shape: {X_train_res.shape}")
# Train Model
print("Training Random Forest Classifier (this might take a minute)...")
model = RandomForestClassifier(n_estimators=50, max_depth=10, random_state=42, n_jobs=-1)
model.fit(X_train_res, y_train_res)
# Evaluate
print("Evaluating model...")
y_pred = model.predict(X_test)
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))
# Save model and scalers
print("Saving model and scalers...")
joblib.dump(model, 'c:/card/fraud_model.joblib')
joblib.dump(scaler_amount, 'c:/card/scaler_amount.joblib')
joblib.dump(scaler_time, 'c:/card/scaler_time.joblib')
print("Done! Files saved to c:/card/")
|