File size: 4,356 Bytes
ad0def0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
import gradio as gr
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier, IsolationForest
from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score, roc_curve

# -------------------------
# Load Dataset (auto-download from GitHub mirror if not present)
# -------------------------
import os, requests, zipfile

DATA_URL = "https://storage.googleapis.com/download.tensorflow.org/data/creditcard.csv"
DATA_PATH = "creditcard.csv"

if not os.path.exists(DATA_PATH):
    print("Downloading dataset...")
    r = requests.get(DATA_URL)
    with open(DATA_PATH, "wb") as f:
        f.write(r.content)

df = pd.read_csv(DATA_PATH)

# -------------------------
# Preprocess
# -------------------------
X = df.drop("Class", axis=1)
y = df["Class"]

scaler = StandardScaler()
X["Amount"] = scaler.fit_transform(X["Amount"].values.reshape(-1, 1))

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42, stratify=y
)

# -------------------------
# Train Models
# -------------------------
log_reg = LogisticRegression(max_iter=5000, class_weight="balanced", random_state=42)
log_reg.fit(X_train, y_train)

rf = RandomForestClassifier(n_estimators=200, class_weight="balanced", random_state=42)
rf.fit(X_train, y_train)

iso_forest = IsolationForest(
    n_estimators=200, contamination=0.0017, random_state=42
)
iso_forest.fit(X_train)

# -------------------------
# Evaluation
# -------------------------
def evaluate_models():
    results = {}

    # Logistic Regression
    y_pred_lr = log_reg.predict(X_test)
    y_prob_lr = log_reg.predict_proba(X_test)[:, 1]
    results["Logistic Regression"] = classification_report(y_test, y_pred_lr, digits=4)

    # Random Forest
    y_pred_rf = rf.predict(X_test)
    y_prob_rf = rf.predict_proba(X_test)[:, 1]
    results["Random Forest"] = classification_report(y_test, y_pred_rf, digits=4)

    # Isolation Forest
    y_pred_if = iso_forest.predict(X_test)
    y_pred_if = np.where(y_pred_if == -1, 1, 0)
    results["Isolation Forest"] = classification_report(y_test, y_pred_if, digits=4)

    return results


# -------------------------
# Fraud Prediction Function
# -------------------------
def predict_transaction(amount, time, v_features):
    # Build feature vector
    data = np.array([time] + v_features + [amount]).reshape(1, -1)
    data[:, -1] = scaler.transform(data[:, -1].reshape(-1, 1))  # scale amount

    pred_lr = log_reg.predict(data)[0]
    prob_lr = log_reg.predict_proba(data)[0][1]

    pred_rf = rf.predict(data)[0]
    prob_rf = rf.predict_proba(data)[0][1]

    pred_if = iso_forest.predict(data)[0]
    pred_if = 1 if pred_if == -1 else 0

    return {
        "Logistic Regression": f"Fraud={pred_lr} (Prob={prob_lr:.3f})",
        "Random Forest": f"Fraud={pred_rf} (Prob={prob_rf:.3f})",
        "Isolation Forest": f"Fraud={pred_if}",
    }


# -------------------------
# Gradio UI
# -------------------------
def ui_transaction(amount, time, *v_features):
    v_features = list(v_features)
    return predict_transaction(amount, time, v_features)


with gr.Blocks() as demo:
    gr.Markdown("# 💳 Credit Card Fraud Detection\nCompare Logistic Regression, Random Forest & Isolation Forest")

    with gr.Tab("Evaluate Models"):
        btn = gr.Button("Run Evaluation")
        out = gr.Textbox(lines=15, label="Results")

        def run_eval():
            res = evaluate_models()
            return "\n\n".join([f"{k}:\n{v}" for k, v in res.items()])

        btn.click(run_eval, outputs=out)

    with gr.Tab("Predict a Transaction"):
        amount = gr.Number(label="Transaction Amount")
        time = gr.Number(label="Time (seconds since first transaction)")
        v_inputs = [gr.Number(label=f"V{i}") for i in range(1, 29)]

        btn_pred = gr.Button("Predict Fraud")
        out_pred = gr.JSON(label="Predictions")

        btn_pred.click(ui_transaction, inputs=[amount, time] + v_inputs, outputs=out_pred)

demo.launch()