Spaces:
Running
Running
File size: 2,931 Bytes
f460ec4 |
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 |
import streamlit as st
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
from datasets import load_dataset
# Load dataset from Hugging Face
dataset = load_dataset("Nooha/cc_fraud_detection_dataset", split="train")
df = pd.DataFrame(dataset)
# Select relevant features and target variable
X = df[['Amount', 'Time', 'V1', 'V2', 'V3']]
y = df['Class']
# Split dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Train a RandomForestClassifier model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
# Model Performance Metrics
accuracy = accuracy_score(y_test, y_pred)
class_report_df = pd.DataFrame(classification_report(y_test, y_pred, output_dict=True)).transpose()
# Application Title
st.title('💳 Credit Card Fraud Detection System')
st.markdown(
"""
## 📖 Introduction
Welcome to the **Credit Card Fraud Detection System**! This tool analyzes credit card transactions to detect fraudulent activity using a **Random Forest model**.
"""
)
# Tab Structure
tab1, tab2, tab3 = st.tabs(['📊 Dataset Preview', '📈 Model Performance', '🔍 Fraud Prediction'])
# Dataset Preview
with tab1:
st.markdown(
"""
## 📊 Dataset Preview
Below is a sample of the credit card transaction dataset used for fraud detection.
"""
)
st.dataframe(df.head())
# Model Performance
with tab2:
st.markdown(
"""
## 📈 Model Performance
- **Accuracy:** Measures overall model performance.
- **Classification Report:** Precision, recall, and F1-score breakdown.
"""
)
st.write(f"**📌 Model Accuracy:** {accuracy:.2%}")
st.markdown("### 📋 Classification Report")
st.dataframe(class_report_df)
# Fraud Prediction
with tab3:
st.markdown("""
## 🔍 Fraud Prediction
Enter transaction details below to predict if it's fraudulent.
""")
amount_input = st.number_input("💵 Transaction Amount", min_value=0.0, value=100.0, step=1.0)
time_input = st.number_input("⏳ Transaction Time", min_value=0.0, value=50000.0, step=1000.0)
v1_input = st.number_input("🔢 Feature V1", value=0.0, step=0.1)
v2_input = st.number_input("🔢 Feature V2", value=0.0, step=0.1)
v3_input = st.number_input("🔢 Feature V3", value=0.0, step=0.1)
if st.button("🔎 Predict Fraud"):
input_data = np.array([[amount_input, time_input, v1_input, v2_input, v3_input]])
prediction = model.predict(input_data)[0]
result = "🚨 Fraudulent" if prediction == 1 else "✅ Legitimate"
st.success(f"### 🎯 Prediction: **{result}**")
|