Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -1,85 +1,85 @@
|
|
1 |
-
import
|
2 |
-
import
|
3 |
-
|
4 |
-
from sklearn.
|
5 |
-
from sklearn.
|
6 |
-
import
|
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 |
-
st.
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
st.
|
66 |
-
st.
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
st.
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import numpy as np
|
4 |
+
from sklearn.ensemble import RandomForestClassifier
|
5 |
+
from sklearn.model_selection import train_test_split
|
6 |
+
from sklearn.metrics import accuracy_score, classification_report
|
7 |
+
from datasets import load_dataset
|
8 |
+
|
9 |
+
# Load dataset from Hugging Face
|
10 |
+
dataset = load_dataset("Nooha/cc_fraud_detection_dataset", split="train")
|
11 |
+
df = pd.DataFrame(dataset)
|
12 |
+
|
13 |
+
# Select relevant features and target variable
|
14 |
+
X = df[['Amount', 'Time', 'V1', 'V2', 'V3']]
|
15 |
+
y = df['Class']
|
16 |
+
|
17 |
+
# Split dataset into training and testing sets
|
18 |
+
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
19 |
+
|
20 |
+
# Train a RandomForestClassifier model
|
21 |
+
model = RandomForestClassifier(n_estimators=100, random_state=42)
|
22 |
+
model.fit(X_train, y_train)
|
23 |
+
|
24 |
+
y_pred = model.predict(X_test)
|
25 |
+
|
26 |
+
# Model Performance Metrics
|
27 |
+
accuracy = accuracy_score(y_test, y_pred)
|
28 |
+
class_report_df = pd.DataFrame(classification_report(y_test, y_pred, output_dict=True)).transpose()
|
29 |
+
|
30 |
+
# Application Title
|
31 |
+
st.title('π³ Credit Card Fraud Detection System')
|
32 |
+
|
33 |
+
st.markdown(
|
34 |
+
"""
|
35 |
+
## π Introduction
|
36 |
+
Welcome to the **Credit Card Fraud Detection System**! This tool analyzes credit card transactions to detect fraudulent activity using a **Random Forest model**.
|
37 |
+
"""
|
38 |
+
)
|
39 |
+
|
40 |
+
# Tab Structure
|
41 |
+
tab1, tab2, tab3 = st.tabs(['π Dataset Preview', 'π Model Performance', 'π Fraud Prediction'])
|
42 |
+
|
43 |
+
# Dataset Preview
|
44 |
+
with tab1:
|
45 |
+
st.markdown(
|
46 |
+
"""
|
47 |
+
## π Dataset Preview
|
48 |
+
Below is a sample of the credit card transaction dataset used for fraud detection.
|
49 |
+
"""
|
50 |
+
)
|
51 |
+
st.dataframe(df.head())
|
52 |
+
|
53 |
+
# Model Performance
|
54 |
+
with tab2:
|
55 |
+
st.markdown(
|
56 |
+
"""
|
57 |
+
## π Model Performance
|
58 |
+
- **Accuracy:** Measures overall model performance.
|
59 |
+
- **Classification Report:** Precision, recall, and F1-score breakdown.
|
60 |
+
"""
|
61 |
+
)
|
62 |
+
|
63 |
+
st.write(f"**π Model Accuracy:** {accuracy:.2%}")
|
64 |
+
|
65 |
+
st.markdown("### π Classification Report")
|
66 |
+
st.dataframe(class_report_df)
|
67 |
+
|
68 |
+
# Fraud Prediction
|
69 |
+
with tab3:
|
70 |
+
st.markdown("""
|
71 |
+
## π Fraud Prediction
|
72 |
+
Enter transaction details below to predict if it's fraudulent.
|
73 |
+
""")
|
74 |
+
|
75 |
+
amount_input = st.number_input("π΅ Transaction Amount", min_value=0.0, value=100.0, step=1.0)
|
76 |
+
time_input = st.number_input("β³ Transaction Time", min_value=0.0, value=50000.0, step=1000.0)
|
77 |
+
v1_input = st.number_input("π’ Feature V1", value=0.0, step=0.1)
|
78 |
+
v2_input = st.number_input("π’ Feature V2", value=0.0, step=0.1)
|
79 |
+
v3_input = st.number_input("π’ Feature V3", value=0.0, step=0.1)
|
80 |
+
|
81 |
+
if st.button("π Predict Fraud"):
|
82 |
+
input_data = np.array([[amount_input, time_input, v1_input, v2_input, v3_input]])
|
83 |
+
prediction = model.predict(input_data)[0]
|
84 |
+
result = "π¨ Fraudulent" if prediction == 1 else "β
Legitimate"
|
85 |
+
st.success(f"### π― Prediction: **{result}**")
|