uploading application files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+venv/Scripts/python.exe filter=lfs diff=lfs merge=lfs -text
+venv/Scripts/streamlit.exe filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,85 @@
+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
+import streamlit as st
+import altair as alt
+
+try:
+    # Load the data
+    df = pd.read_csv("fraud_data.csv")
+
+    # Prepare the data for the model
+    X = df[['TransactionAmount', 'CustomerAge', 'TransactionFrequency']]
+    y = df['IsFraud']
+
+except FileNotFoundError:
+    st.write("Error: Data file not found.")
+    st.stop()
+
+except Exception as e:
+    st.write(f"An error occurred: {e}")
+    st.stop()
+
+# Split the data 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)
+
+# Create and train a Random Forest Classifier model
+model = RandomForestClassifier(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+
+# Make predictions on the testing set
+y_pred = model.predict(X_test)
+
+# Evaluate the model's performance
+accuracy = accuracy_score(y_test, y_pred)
+report = classification_report(y_test, y_pred, output_dict=True)
+
+# Create a Streamlit app
+st.title("Fraud Detection System")
+
+# Create tabs
+tab1, tab2, tab3 = st.tabs(["Data Visualization", "Model Performance", "Fraud Prediction"])
+
+# Tab 1: Data Visualization
+with tab1:
+    st.write("### Fraud Data")
+    st.write(df)
+
+    # Scatter plot
+    st.write("### Scatter Plot of Features")
+    for col in ['TransactionAmount', 'CustomerAge', 'TransactionFrequency']:
+        st.write(f"**{col} vs Fraudulent Transactions**")
+        st.altair_chart(
+            alt.Chart(df).mark_circle().encode(
+                x=col,
+                y='IsFraud',
+                tooltip=[col, 'IsFraud']
+            ).interactive(),
+            use_container_width=True
+        )
+
+# Tab 2: Model Performance
+with tab2:
+    st.write("### Model Performance")
+    st.write(f"Accuracy: {accuracy:.2f}")
+    st.write("Classification Report:")
+    st.json(report)
+
+# Tab 3: Fraud Prediction
+with tab3:
+    st.write("### Predict Fraudulent Transactions")
+    amount_input = st.number_input("Transaction Amount", min_value=1.0, value=100.0, step=1.0)
+    age_input = st.number_input("Customer Age", min_value=18, value=30, step=1)
+    frequency_input = st.slider("Transaction Frequency (past month)", min_value=1, max_value=100, value=5, step=1)
+
+    if st.button("Predict"):
+        # Create input array for prediction
+        input_data = [[amount_input, age_input, frequency_input]]
+        
+        # Make prediction
+        prediction = model.predict(input_data)[0]
+        result = "Fraudulent" if prediction == 1 else "Legitimate"
+        
+        st.write(f"### Prediction: {result}")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+pandas
+numpy
+scikit-learn
+altair

venv/Scripts/python.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0bffb7a259cd2722df454fdfff41ee13665820cff1f578b1d97d31f9ef93d5
+size 270616

venv/Scripts/streamlit.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3d3c12bf95cde3a585c01215ee2134fd2c3075dfd7c58641cb4d4d1aa24461
+size 108475