VectorV17 commited on
Commit
b9b4bb1
·
verified ·
1 Parent(s): 482e907

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +54 -24
app.py CHANGED
@@ -4,7 +4,6 @@ import datetime
4
  import joblib
5
  import pandas as pd
6
  import numpy as np
7
- import mysql.connector
8
  import gradio as gr
9
  from sklearn.ensemble import RandomForestRegressor
10
  from sklearn.preprocessing import StandardScaler
@@ -15,7 +14,7 @@ from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
15
  from reportlab.lib import colors
16
 
17
  # ---------------------------------------------------------------------------
18
- # 1. DATABASE CONFIGURATION (Safe MySQL / FreeDatabase Connector)
19
  # ---------------------------------------------------------------------------
20
  DB_HOST = os.getenv("MYSQL_HOST", "sql6.freedatabase.com")
21
  DB_USER = os.getenv("MYSQL_USER", "your_username")
@@ -25,6 +24,7 @@ DB_PORT = int(os.getenv("MYSQL_PORT", 3306))
25
 
26
  def get_db_connection():
27
  try:
 
28
  conn = mysql.connector.connect(
29
  host=DB_HOST,
30
  user=DB_USER,
@@ -96,13 +96,12 @@ def build_or_load_artifacts():
96
  except Exception:
97
  pass
98
 
99
- # If artifacts are missing, build model from dataset or realistic synthesis
100
  csv_file = "Steel_industry_data.csv"
101
  if os.path.exists(csv_file):
102
  df_train = pd.read_csv(csv_file)
103
  df_train = clean_cols(df_train)
104
  else:
105
- # Synthesize dataset matching standard UCI Steel Industry bounds
106
  np.random.seed(42)
107
  n = 5000
108
  lag_kvarh = np.random.exponential(13.0, n)
@@ -211,7 +210,7 @@ def preprocess_and_predict(df_raw):
211
  return df
212
 
213
  # ---------------------------------------------------------------------------
214
- # 4. PDF GENERATION ENGINE
215
  # ---------------------------------------------------------------------------
216
  def generate_pdf_report(df_results, summary_stats):
217
  pdf_buffer = io.BytesIO()
@@ -244,6 +243,7 @@ def generate_pdf_report(df_results, summary_stats):
244
  summary_data = [
245
  ["Metric Description", "Value"],
246
  ["Total Processed Records", f"{summary_stats['total_records']}"],
 
247
  ["Mean Electricity Demand (kWh)", f"{summary_stats['mean_kwh']:.2f} kWh"],
248
  ["Max Electricity Demand (kWh)", f"{summary_stats['max_kwh']:.2f} kWh"],
249
  ["Total Estimated CO2 Footprint", f"{summary_stats['total_co2']:.4f} Metric Tonnes"],
@@ -264,13 +264,24 @@ def generate_pdf_report(df_results, summary_stats):
264
  elements.append(Spacer(1, 15))
265
 
266
  elements.append(Paragraph("Sample Predictions Preview (First 10 Rows)", styles['Heading2']))
267
- preview_df = df_results[['Predicted_Usage_kWh', 'Estimated_CO2_Tonnes']].head(10).reset_index()
268
 
269
- preview_data = [["Row ID", "Predicted Usage (kWh)", "Estimated CO2 (Tonnes)"]]
 
 
 
 
 
 
270
  for _, row in preview_df.iterrows():
271
- preview_data.append([str(int(row['index'] + 1)), f"{row['Predicted_Usage_kWh']:.2f}", f"{row['Estimated_CO2_Tonnes']:.6f}"])
 
 
 
 
 
 
272
 
273
- pt = Table(preview_data, colWidths=[80, 210, 210])
274
  pt.setStyle(TableStyle([
275
  ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#0284c7')),
276
  ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
@@ -291,7 +302,7 @@ def generate_pdf_report(df_results, summary_stats):
291
  return pdf_path
292
 
293
  # ---------------------------------------------------------------------------
294
- # 5. GRADIO HANDLERS
295
  # ---------------------------------------------------------------------------
296
  def handle_single_prediction(lag_kvarh, lead_kvarh, lag_pf, lead_pf, nsm, hour, month, day_of_week, load_type):
297
  data = {
@@ -311,7 +322,13 @@ def handle_single_prediction(lag_kvarh, lead_kvarh, lag_pf, lead_pf, nsm, hour,
311
  kwh = float(res['Predicted_Usage_kWh'].iloc[0])
312
  co2 = float(res['Estimated_CO2_Tonnes'].iloc[0])
313
 
314
- # Optional Database Logging
 
 
 
 
 
 
315
  conn = get_db_connection()
316
  if conn:
317
  try:
@@ -326,7 +343,7 @@ def handle_single_prediction(lag_kvarh, lead_kvarh, lag_pf, lead_pf, nsm, hour,
326
  except Exception:
327
  pass
328
 
329
- return f"{kwh:.2f} kWh", f"{co2:.6f} Metric Tonnes"
330
 
331
  def handle_csv_upload(file):
332
  if file is None:
@@ -335,9 +352,20 @@ def handle_csv_upload(file):
335
  df_raw = pd.read_csv(file.name)
336
  df_results = preprocess_and_predict(df_raw)
337
 
 
 
 
 
 
 
 
 
 
 
 
 
338
  total_records = len(df_results)
339
 
340
- # Use ground-truth Usage_kWh if present in uploaded CSV, else use predictions
341
  cleaned_raw_cols = [c.strip().replace(' ', '_').replace('(', '').replace(')', '').replace('.', '_') for c in df_raw.columns]
342
  if 'Usage_kWh' in cleaned_raw_cols:
343
  target_col = df_results['Usage_kWh'] if 'Usage_kWh' in df_results.columns else df_results['Predicted_Usage_kWh']
@@ -348,7 +376,7 @@ def handle_csv_upload(file):
348
  max_kwh = float(target_col.max())
349
  total_co2 = float((target_col * 0.00042).sum())
350
 
351
- # Mitigation simulation (10% demand drop on peak intervals > mean)
352
  mitigated_kwh = target_col.copy()
353
  mitigated_kwh[mitigated_kwh > mean_kwh] *= 0.90
354
  mitigated_co2 = float(total_co2 - (mitigated_kwh * 0.00042).sum())
@@ -358,7 +386,8 @@ def handle_csv_upload(file):
358
  'mean_kwh': mean_kwh,
359
  'max_kwh': max_kwh,
360
  'total_co2': total_co2,
361
- 'mitigated_co2': mitigated_co2
 
362
  }
363
 
364
  pdf_path = generate_pdf_report(df_results, summary_stats)
@@ -366,6 +395,7 @@ def handle_csv_upload(file):
366
  summary_text = f"""
367
  ### 📊 Analysis Summary
368
  * **Total Processed Records:** {total_records:,}
 
369
  * **Average Demand:** {mean_kwh:.2f} kWh
370
  * **Peak Demand Recorded:** {max_kwh:.2f} kWh
371
  * **Total Estimated Carbon Footprint:** {total_co2:.4f} Metric Tonnes
@@ -375,7 +405,7 @@ def handle_csv_upload(file):
375
  return df_results, summary_text, pdf_path
376
 
377
  # ---------------------------------------------------------------------------
378
- # 6. SLEEK & GLOSSY GRADIO UI
379
  # ---------------------------------------------------------------------------
380
  custom_css = """
381
  body, .gradio-container {
@@ -457,7 +487,7 @@ with gr.Blocks(css=custom_css, title="Steel Industry Energy Predictor") as demo:
457
 
458
  with gr.Row():
459
  with gr.Column(scale=2):
460
- output_dataframe = gr.Dataframe(label="Predictions Table Preview", interactive=False)
461
  with gr.Column(scale=1):
462
  summary_output = gr.Markdown(value="*Upload a CSV to view analysis summary.*")
463
  pdf_download = gr.File(label="📄 Download PDF Audit Report")
@@ -465,22 +495,22 @@ with gr.Blocks(css=custom_css, title="Steel Industry Energy Predictor") as demo:
465
  # TAB 2: SINGLE PREDICTION RESULT
466
  with gr.TabItem("🎯 Single Record Result"):
467
  with gr.Group(elem_classes=["glass-panel"]):
468
- gr.Markdown("### Single Inspection Prediction Result")
469
  out_kwh = gr.Textbox(label="Predicted Energy Consumption (Usage_kWh)", interactive=False)
470
  out_co2 = gr.Textbox(label="Estimated Carbon Emissions (Tonnes CO2)", interactive=False)
 
471
 
472
- # Inputs list for single predictions
473
  single_inputs = [lag_kvarh, lead_kvarh, lag_pf, lead_pf, nsm, hour, month, day_of_week, load_type]
474
- single_outputs = [out_kwh, out_co2]
475
 
476
- # Explicit button click
477
  predict_btn.click(
478
  fn=handle_single_prediction,
479
  inputs=single_inputs,
480
  outputs=single_outputs
481
  )
482
 
483
- # Real-time change updates for sliders and numbers
484
  for inp in single_inputs:
485
  inp.change(
486
  fn=handle_single_prediction,
@@ -488,14 +518,14 @@ with gr.Blocks(css=custom_css, title="Steel Industry Energy Predictor") as demo:
488
  outputs=single_outputs
489
  )
490
 
491
- # Auto-run prediction on initial page load (prevents blank textboxes)
492
  demo.load(
493
  fn=handle_single_prediction,
494
  inputs=single_inputs,
495
  outputs=single_outputs
496
  )
497
 
498
- # Batch CSV handling
499
  process_csv_btn.click(
500
  fn=handle_csv_upload,
501
  inputs=[file_input],
 
4
  import joblib
5
  import pandas as pd
6
  import numpy as np
 
7
  import gradio as gr
8
  from sklearn.ensemble import RandomForestRegressor
9
  from sklearn.preprocessing import StandardScaler
 
14
  from reportlab.lib import colors
15
 
16
  # ---------------------------------------------------------------------------
17
+ # 1. OPTIONAL DATABASE CONFIGURATION (Safe MySQL / FreeDatabase Connector)
18
  # ---------------------------------------------------------------------------
19
  DB_HOST = os.getenv("MYSQL_HOST", "sql6.freedatabase.com")
20
  DB_USER = os.getenv("MYSQL_USER", "your_username")
 
24
 
25
  def get_db_connection():
26
  try:
27
+ import mysql.connector
28
  conn = mysql.connector.connect(
29
  host=DB_HOST,
30
  user=DB_USER,
 
96
  except Exception:
97
  pass
98
 
 
99
  csv_file = "Steel_industry_data.csv"
100
  if os.path.exists(csv_file):
101
  df_train = pd.read_csv(csv_file)
102
  df_train = clean_cols(df_train)
103
  else:
104
+ # Generate realistic steel plant dataset matching UCI bounds
105
  np.random.seed(42)
106
  n = 5000
107
  lag_kvarh = np.random.exponential(13.0, n)
 
210
  return df
211
 
212
  # ---------------------------------------------------------------------------
213
+ # 4. PDF REPORT GENERATION ENGINE
214
  # ---------------------------------------------------------------------------
215
  def generate_pdf_report(df_results, summary_stats):
216
  pdf_buffer = io.BytesIO()
 
243
  summary_data = [
244
  ["Metric Description", "Value"],
245
  ["Total Processed Records", f"{summary_stats['total_records']}"],
246
+ ["Low Power Factor (<85%) Anomaly Flagged", f"{summary_stats['anomaly_count']} records"],
247
  ["Mean Electricity Demand (kWh)", f"{summary_stats['mean_kwh']:.2f} kWh"],
248
  ["Max Electricity Demand (kWh)", f"{summary_stats['max_kwh']:.2f} kWh"],
249
  ["Total Estimated CO2 Footprint", f"{summary_stats['total_co2']:.4f} Metric Tonnes"],
 
264
  elements.append(Spacer(1, 15))
265
 
266
  elements.append(Paragraph("Sample Predictions Preview (First 10 Rows)", styles['Heading2']))
 
267
 
268
+ cols_to_show = ['Predicted_Usage_kWh', 'Estimated_CO2_Tonnes']
269
+ if 'PF_Status' in df_results.columns:
270
+ cols_to_show.append('PF_Status')
271
+
272
+ preview_df = df_results[cols_to_show].head(10).reset_index()
273
+
274
+ preview_data = [["Row ID", "Predicted Usage (kWh)", "Estimated CO2 (Tonnes)", "PF Status"]]
275
  for _, row in preview_df.iterrows():
276
+ pf_st = row.get('PF_Status', 'N/A')
277
+ preview_data.append([
278
+ str(int(row['index'] + 1)),
279
+ f"{row['Predicted_Usage_kWh']:.2f}",
280
+ f"{row['Estimated_CO2_Tonnes']:.6f}",
281
+ str(pf_st)
282
+ ])
283
 
284
+ pt = Table(preview_data, colWidths=[50, 150, 150, 150])
285
  pt.setStyle(TableStyle([
286
  ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#0284c7')),
287
  ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
 
302
  return pdf_path
303
 
304
  # ---------------------------------------------------------------------------
305
+ # 5. GRADIO UI HANDLERS
306
  # ---------------------------------------------------------------------------
307
  def handle_single_prediction(lag_kvarh, lead_kvarh, lag_pf, lead_pf, nsm, hour, month, day_of_week, load_type):
308
  data = {
 
322
  kwh = float(res['Predicted_Usage_kWh'].iloc[0])
323
  co2 = float(res['Estimated_CO2_Tonnes'].iloc[0])
324
 
325
+ # Low Power Factor (< 85%) Anomaly Diagnostic Output
326
+ if lag_pf < 85.0:
327
+ pf_status = f"⚠️ CRITICAL: Low Power Factor ({lag_pf:.1f}% < 85%). Risk of transformer heat loss & utility surcharge penalties!"
328
+ else:
329
+ pf_status = f"✅ OPTIMAL: Power Factor ({lag_pf:.1f}% ≥ 85%). Operating within safe efficiency limits."
330
+
331
+ # Optional DB record insertion
332
  conn = get_db_connection()
333
  if conn:
334
  try:
 
343
  except Exception:
344
  pass
345
 
346
+ return f"{kwh:.2f} kWh", f"{co2:.6f} Metric Tonnes", pf_status
347
 
348
  def handle_csv_upload(file):
349
  if file is None:
 
352
  df_raw = pd.read_csv(file.name)
353
  df_results = preprocess_and_predict(df_raw)
354
 
355
+ # Tag Anomaly Status Column on Batch CSV Dataframe
356
+ if 'Lagging_Current_Power_Factor' in df_results.columns:
357
+ df_results['PF_Status'] = np.where(
358
+ df_results['Lagging_Current_Power_Factor'] < 85.0,
359
+ '⚠️ CRITICAL (<85%)',
360
+ '✅ NORMAL'
361
+ )
362
+ anomaly_count = int((df_results['Lagging_Current_Power_Factor'] < 85.0).sum())
363
+ else:
364
+ df_results['PF_Status'] = 'N/A'
365
+ anomaly_count = 0
366
+
367
  total_records = len(df_results)
368
 
 
369
  cleaned_raw_cols = [c.strip().replace(' ', '_').replace('(', '').replace(')', '').replace('.', '_') for c in df_raw.columns]
370
  if 'Usage_kWh' in cleaned_raw_cols:
371
  target_col = df_results['Usage_kWh'] if 'Usage_kWh' in df_results.columns else df_results['Predicted_Usage_kWh']
 
376
  max_kwh = float(target_col.max())
377
  total_co2 = float((target_col * 0.00042).sum())
378
 
379
+ # Mitigation simulation (10% drop on peak intervals > mean)
380
  mitigated_kwh = target_col.copy()
381
  mitigated_kwh[mitigated_kwh > mean_kwh] *= 0.90
382
  mitigated_co2 = float(total_co2 - (mitigated_kwh * 0.00042).sum())
 
386
  'mean_kwh': mean_kwh,
387
  'max_kwh': max_kwh,
388
  'total_co2': total_co2,
389
+ 'mitigated_co2': mitigated_co2,
390
+ 'anomaly_count': anomaly_count
391
  }
392
 
393
  pdf_path = generate_pdf_report(df_results, summary_stats)
 
395
  summary_text = f"""
396
  ### 📊 Analysis Summary
397
  * **Total Processed Records:** {total_records:,}
398
+ * **Low PF Anomaly Alerts (<85%):** {anomaly_count:,} records
399
  * **Average Demand:** {mean_kwh:.2f} kWh
400
  * **Peak Demand Recorded:** {max_kwh:.2f} kWh
401
  * **Total Estimated Carbon Footprint:** {total_co2:.4f} Metric Tonnes
 
405
  return df_results, summary_text, pdf_path
406
 
407
  # ---------------------------------------------------------------------------
408
+ # 6. SLEEK & GLOSSY GRADIO UI LAYOUT
409
  # ---------------------------------------------------------------------------
410
  custom_css = """
411
  body, .gradio-container {
 
487
 
488
  with gr.Row():
489
  with gr.Column(scale=2):
490
+ output_dataframe = gr.Dataframe(label="Predictions & Anomaly Status Preview", interactive=False)
491
  with gr.Column(scale=1):
492
  summary_output = gr.Markdown(value="*Upload a CSV to view analysis summary.*")
493
  pdf_download = gr.File(label="📄 Download PDF Audit Report")
 
495
  # TAB 2: SINGLE PREDICTION RESULT
496
  with gr.TabItem("🎯 Single Record Result"):
497
  with gr.Group(elem_classes=["glass-panel"]):
498
+ gr.Markdown("### Single Inspection Diagnostic Result")
499
  out_kwh = gr.Textbox(label="Predicted Energy Consumption (Usage_kWh)", interactive=False)
500
  out_co2 = gr.Textbox(label="Estimated Carbon Emissions (Tonnes CO2)", interactive=False)
501
+ out_pf_status = gr.Textbox(label="⚡ Power Factor Diagnostic & Surcharge Alert", interactive=False)
502
 
 
503
  single_inputs = [lag_kvarh, lead_kvarh, lag_pf, lead_pf, nsm, hour, month, day_of_week, load_type]
504
+ single_outputs = [out_kwh, out_co2, out_pf_status]
505
 
506
+ # Button event
507
  predict_btn.click(
508
  fn=handle_single_prediction,
509
  inputs=single_inputs,
510
  outputs=single_outputs
511
  )
512
 
513
+ # Real-time change event listeners
514
  for inp in single_inputs:
515
  inp.change(
516
  fn=handle_single_prediction,
 
518
  outputs=single_outputs
519
  )
520
 
521
+ # Initial load trigger (prevents blank textboxes on startup)
522
  demo.load(
523
  fn=handle_single_prediction,
524
  inputs=single_inputs,
525
  outputs=single_outputs
526
  )
527
 
528
+ # Batch CSV process button
529
  process_csv_btn.click(
530
  fn=handle_csv_upload,
531
  inputs=[file_input],