Upload 6 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
+credit[[:space:]]fraud[[:space:]]anomaly[[:space:]]detection.pdf filter=lfs diff=lfs merge=lfs -text
+creditcard.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,79 @@
+import streamlit as st
+import pandas as pd
+import pickle
+from sklearn.ensemble import IsolationForest  # Example model, replace if using a different one
+
+st.markdown("<h1 style='text-align: center; font-size: 48px; color: red;'>Credit Card Fraud Anomaly Detection ML App</h1>", unsafe_allow_html=True)
+
+# Load the credit card dataset directly
+@st.cache_data
+def load_dataset():
+    return pd.read_csv('creditcard.csv')  # Path to the creditcard.csv file
+
+# Cache function to convert DataFrame to CSV
+@st.cache_data
+def convert_df(df):
+    return df.to_csv(index=False).encode("utf-8")
+
+# Load pre-trained anomaly detection model
+@st.cache_resource
+def load_model():
+    with open("model.pkl", "rb") as f:
+        model = pickle.load(f)
+    return model
+
+# Load the dataset
+df = load_dataset()
+
+# Display the dataset preview
+st.write("Dataset Preview:")
+st.dataframe(df.head())
+
+# Ensure the dataset has the 'Class' column
+if 'Class' not in df.columns:
+    st.error("The dataset must contain a 'Class' column.")
+else:
+    # Add functionality for row selection
+    st.markdown("### Select a Row for Model Input:")
+
+    # Option to select a row
+    selected_row = st.selectbox("Select a Row", options=range(len(df)), index=0)
+
+    # Add a button below the row selection for anomaly detection
+    detect_button = st.button("Detect Anomaly")
+
+    # If the "Detect" button is clicked
+    if detect_button:
+        # Row to use for the model
+        row_to_use = df.iloc[selected_row]
+
+        # Drop 'Class' column (exclude it from features used for prediction)
+        row_to_use_for_model = row_to_use.drop('Class', errors='ignore')
+
+        # Check if the number of features matches the model's expectations
+        model = load_model()
+
+        if len(row_to_use_for_model) != model.n_features_in_:
+            st.error(f"The model expects {model.n_features_in_} features, but {len(row_to_use_for_model)} were provided.")
+        else:
+            # Apply the model for anomaly detection
+            prediction = model.predict([row_to_use_for_model])
+
+            # Display the row and the anomaly detection result
+            st.write(f"Row selected for anomaly detection:")
+            st.write(row_to_use)
+
+            # Show the anomaly result for the selected row
+            result = "Anomaly" if prediction[0] == -1 else "Not Anomaly"
+            st.write(f"Anomaly Detection Result: {result}")
+
+            # Provide option to download the result
+            result_df = row_to_use.to_frame().T  # Convert Series to DataFrame
+            result_df['Anomaly'] = result
+            result_csv = convert_df(result_df)
+            st.download_button(
+                label="Download Selected Row Result",
+                data=result_csv,
+                file_name="Selected_Row_Anomaly_Result.csv",
+                mime="text/csv",
+            )

credit fraud anomaly detection.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9be34201b7e69022198f3bec4556f5c0ebe7b2da004e4c85bcfec1e09edb69d
+size 828929

creditcard.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76274b691b16a6c49d3f159c883398e03ccd6d1ee12d9d8ee38f4b4b98551a89
+size 150828752

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067eea915e8dab93a19e20104c5baccfc2bfd29a0357f7843bc6f18460f1092a
+size 867587

requirements.txt

@@ -0,0 +1,6 @@
+pandas
+scikit-learn
+numpy
+seaborn
+matplotlib
+streamlit