Update app.py

app.py

@@ -1,10 +1,33 @@
+import pandas as pd
+import numpy as np
+from momentfm import MOMENTPipeline
+from io import StringIO
+
+# Initialize model globally
+model = MOMENTPipeline.from_pretrained(
+    "AutonLab/MOMENT-1-large",
+    model_kwargs={"task_name": "reconstruction"},
+)
+model.init()
+
 def generate_analysis_report(data_input, sensitivity=3.0):
-    """Generate a textual analysis report without visual outputs"""
+    """Generate a comprehensive textual analysis report"""
     try:
         # Process and validate data
         df = pd.read_csv(StringIO(data_input))
-        df['timestamp'] = pd.to_datetime(df['timestamp'])
-        df['value'] = pd.to_numeric(df['value'])
+        
+        # Validate columns
+        if 'timestamp' not in df.columns or 'value' not in df.columns:
+            return "Error: CSV must contain 'timestamp' and 'value' columns"
+            
+        # Convert data types
+        df['timestamp'] = pd.to_datetime(df['timestamp'], errors='coerce')
+        df['value'] = pd.to_numeric(df['value'], errors='coerce')
+        
+        # Check for invalid data
+        if df.isnull().any().any():
+            return "Error: Invalid data format (check timestamp/value formats)"
+            
         df = df.sort_values('timestamp')
         
         # Prepare data for model
@@ -20,45 +43,63 @@ def generate_analysis_report(data_input, sensitivity=3.0):
         threshold = median + sensitivity * (1.4826 * mad)
         
         # Identify anomalies
-        anomalies = df[errors > threshold]
+        anomalies = df[errors > threshold].copy()
+        anomalies['anomaly_score'] = errors[errors > threshold]
+        anomalies = anomalies.sort_values('anomaly_score', ascending=False)
+        
         normal_points = df[errors <= threshold]
         
         # Generate report
         report = f"""
 EQUIPMENT ANALYSIS REPORT
 ========================
+Generated at: {pd.Timestamp.now()}
+Detection sensitivity: {sensitivity} (z-score)
 
-Basic Statistics:
-- Total data points: {len(df)}
-- Time period covered: {df['timestamp'].min()} to {df['timestamp'].max()}
-- Value range: {df['value'].min():.2f} to {df['value'].max():.2f}
-- Median value: {df['value'].median():.2f}
+DATA OVERVIEW
+-------------
+Time period: {df['timestamp'].min()} to {df['timestamp'].max()}
+Total observations: {len(df)}
+Value range: {df['value'].min():.2f} to {df['value'].max():.2f}
+Median value: {df['value'].median():.2f}
+Mean value: {df['value'].mean():.2f}
 
-Anomaly Detection Results:
-- Detection threshold: {threshold:.2f}
-- Anomalies detected: {len(anomalies)} ({len(anomalies)/len(df):.1%} of data)
-- Strongest anomaly: {errors.max():.2f} at {df.loc[errors.argmax(), 'timestamp']}
+ANOMALY DETECTION RESULTS
+-------------------------
+Detection threshold: {threshold:.2f}
+Anomalies detected: {len(anomalies)} ({len(anomalies)/len(df):.1%} of data)
+Strongest anomaly: {errors.max():.2f} at {df.loc[errors.argmax(), 'timestamp']}
 
-Anomaly Details:
-{anomalies.to_string(index=False)}
+TOP ANOMALIES
+-------------
+{anomalies[['timestamp', 'value', 'anomaly_score']].head(15).to_string(index=False, float_format='%.2f')}
 
-Normal Operation Summary:
-- Typical value range: {normal_points['value'].min():.2f} to {normal_points['value'].max():.2f}
-- Stable period duration: {pd.Timedelta(normal_points['timestamp'].max() - normal_points['timestamp'].min())}
+NORMAL OPERATION SUMMARY
+------------------------
+Typical value range: {normal_points['value'].min():.2f} to {normal_points['value'].max():.2f}
+Stable period duration: {pd.Timedelta(normal_points['timestamp'].max() - normal_points['timestamp'].min())}
 
-Recommendations:
-1. Investigate {len(anomalies)} anomalous readings
-2. Focus on period around {anomalies['timestamp'].iloc[0]} for root cause analysis
-3. Consider recalibration if anomalies persist
+RECOMMENDATIONS
+---------------
+1. Investigate top {min(3, len(anomalies))} anomalous readings
+2. Check equipment around {anomalies['timestamp'].iloc[0]} for potential issues
+3. Consider recalibration if anomalies cluster in specific time periods
+4. Review maintenance logs around detected anomalies
 """
-        return report
+        return report.strip()
     
     except Exception as e:
-        return f"Analysis failed: {str(e)}"
+        return f"ANALYSIS ERROR: {str(e)}"
 
-# Example usage:
-report = generate_analysis_report("""
-timestamp,value
+# Gradio Interface for the report-only version
+import gradio as gr
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 📄 Equipment Analysis Report Generator")
+    
+    with gr.Row():
+        with gr.Column():
+            data_input = gr.Textbox(label="Paste CSV Data", lines=10, value="""timestamp,value
 2025-04-01 00:00:00,100
 2025-04-01 01:00:00,102
 2025-04-01 02:00:00,98
@@ -71,7 +112,18 @@ timestamp,value
 2025-04-01 09:00:00,98
 2025-04-01 10:00:00,99
 2025-04-01 11:00:00,102
-2025-04-01 12:00:00,101
-""")
+2025-04-01 12:00:00,101""")
+            sensitivity = gr.Slider(1.0, 5.0, value=3.0, label="Detection Sensitivity")
+            submit_btn = gr.Button("Generate Report", variant="primary")
+        
+        with gr.Column():
+            report_output = gr.Textbox(label="Analysis Report", lines=20, interactive=False)
+    
+    submit_btn.click(
+        generate_analysis_report,
+        inputs=[data_input, sensitivity],
+        outputs=report_output
+    )
 
-print(report)
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)