File size: 2,685 Bytes
22de844
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
import pandas as pd
import numpy as np
import pickle

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, f1_score

# =====================
# Load dataset
# =====================
df = pd.read_csv("loan_data.csv")   # upload CSV in same folder

print(df.head())

# Drop ID column
df.drop(columns=['Loan_ID'], inplace=True)

# Encode target
df['Loan_Status'] = df['Loan_Status'].map({'Y': 1, 'N': 0})

# =====================
# Target and features
# =====================
X = df.drop('Loan_Status', axis=1)
y = df['Loan_Status']

# =====================
# Column split
# =====================
numeric_features = X.select_dtypes(include=['int64', 'float64']).columns
categorical_features = X.select_dtypes(include=['object']).columns

# =====================
# Preprocessing
# =====================
num_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler())
])

cat_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('encoder', OneHotEncoder(handle_unknown='ignore'))
])

preprocessor = ColumnTransformer(transformers=[
    ('num', num_transformer, numeric_features),
    ('cat', cat_transformer, categorical_features)
])

# =====================
# Random Forest Model
# =====================
rf_model = RandomForestClassifier(
    n_estimators=200,
    max_depth=10,
    min_samples_split=2,
    random_state=42,
    n_jobs=-1
)

# =====================
# Full Pipeline
# =====================
rf_pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('model', rf_model)
])

# =====================
# Train-test split
# =====================
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

# =====================
# Train
# =====================
rf_pipeline.fit(X_train, y_train)

# =====================
# Evaluation
# =====================
y_pred = rf_pipeline.predict(X_test)

acc = accuracy_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print(f"Accuracy: {acc:.4f}")
print(f"F1 Score: {f1:.4f}")

# =====================
# Save model
# =====================
with open("loan_rf_pipeline.pkl", "wb") as f:
    pickle.dump(rf_pipeline, f)

print("✅ Loan Random Forest pipeline saved as loan_rf_pipeline.pkl")