Upload 3 files

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.ensemble import IsolationForest
+from sklearn.preprocessing import StandardScaler
+
+# App title
+st.title("📈 Anomaly Detection Tool")
+
+# 🎯 Streamlit Tabs
+tab1, tab2, tab3 = st.tabs(["📖 About", "📊 Dataset Overview", "🚨 Anomaly Detection"])
+
+# About Tab
+with tab1:
+    st.write("""
+    This app detects anomalies in time-series data using the Isolation Forest algorithm.
+    Users can visualize detected anomalies.
+    
+    ### How It Works:
+    - **Step 1**: Load a dataset (CSV format from the Numenta Anomaly Benchmark `realKnownCause` dataset)
+    - **Step 2**: Standardize numerical values for better anomaly detection
+    - **Step 3**: Apply **Isolation Forest** to identify outliers
+    - **Step 4**: Visualize the detected anomalies in a time-series plot
+    """)
+
+# Load dataset
+file_path = "ambient_temperature_system_failure.csv"
+df = pd.read_csv(file_path)
+
+# Dataset Overview Tab
+with tab2:
+    st.write("### Dataset Overview")
+    st.write(df.head())
+    
+    # Convert timestamp column to datetime
+    df['timestamp'] = pd.to_datetime(df['timestamp'], errors='coerce')
+    df = df.dropna(subset=['timestamp'])
+    df.set_index('timestamp', inplace=True)
+    
+    st.write("### Processed Dataset")
+    st.write(df.head())
+
+# Anomaly Detection Tab
+with tab3:
+    st.write("### Detect Anomalies in the Data")
+    
+    # Standardize the data
+    scaler = StandardScaler()
+    df['scaled_value'] = scaler.fit_transform(df[['value']])
+    
+    # Apply Isolation Forest
+    contamination_level = st.slider("Select Contamination Level", 0.01, 0.1, 0.05, 0.01)
+    model = IsolationForest(contamination=contamination_level, random_state=42)
+    df['anomaly'] = model.fit_predict(df[['scaled_value']])
+    df['anomaly'] = df['anomaly'].map({1: 0, -1: 1})  # Convert to binary (1: anomaly, 0: normal)
+    
+    # Allow user to set anomaly score threshold
+    threshold = st.slider("Set Anomaly Score Threshold", -1.0, 1.0, 0.0, 0.01)
+    df["anomaly_score"] = model.decision_function(df[["scaled_value"]])
+    df["anomaly"] = df["anomaly_score"] < threshold
+    
+    # Plot results
+    fig, ax = plt.subplots(figsize=(12, 6))
+    ax.plot(df.index, df['value'], label='Value', color='blue')
+    ax.scatter(df.index[df['anomaly'] == 1], df['value'][df['anomaly'] == 1], color='red', label='Anomaly', marker='o')
+    ax.set_xlabel('Timestamp')
+    ax.set_ylabel('Value')
+    ax.set_title('Anomaly Detection in Time-Series Data')
+    ax.legend()
+    st.pyplot(fig)

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+numpy
+matplotlib
+scikit-learn
+openpyxl  # Required for reading Excel files