Optimized Datagrid.render()

benchmarks/profile_datagrid.py

@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+"""
+DataGrid Performance Profiling Script
+
+Generates a 1000-row DataFrame and profiles the DataGrid.render() method
+to identify performance bottlenecks.
+
+Usage:
+    python benchmarks/profile_datagrid.py
+"""
+
+import cProfile
+import pstats
+from io import StringIO
+
+import numpy as np
+import pandas as pd
+
+from myfasthtml.controls.DataGrid import DataGrid
+from myfasthtml.core.instances import SingleInstance, InstancesManager
+
+
+def generate_test_dataframe(rows=1000, cols=10):
+  """Generate a test DataFrame with mixed column types."""
+  np.random.seed(42)
+  
+  data = {
+      'ID': range(rows),
+      'Name': [f'Person_{i}' for i in range(rows)],
+      'Email': [f'user{i}@example.com' for i in range(rows)],
+      'Age': np.random.randint(18, 80, rows),
+      'Salary': np.random.uniform(30000, 150000, rows),
+      'Active': np.random.choice([True, False], rows),
+      'Score': np.random.uniform(0, 100, rows),
+      'Department': np.random.choice(['Sales', 'Engineering', 'Marketing', 'HR'], rows),
+      'Country': np.random.choice(['France', 'USA', 'Germany', 'UK', 'Spain'], rows),
+      'Rating': np.random.uniform(1.0, 5.0, rows),
+  }
+  
+  # Add extra columns if needed
+  for i in range(cols - len(data)):
+    data[f'Extra_Col_{i}'] = np.random.random(rows)
+  
+  return pd.DataFrame(data)
+
+
+def profile_datagrid_render(df):
+  """Profile the DataGrid render method."""
+  
+  # Clear instances to start fresh
+  InstancesManager.instances.clear()
+  
+  # Create a minimal session
+  session = {
+      "user_info": {
+          "id": "test_tenant_id",
+          "email": "test@email.com",
+          "username": "test user",
+          "role": [],
+      }
+  }
+  
+  # Create root instance as parent
+  root = SingleInstance(parent=None, session=session, _id="profile-root")
+  
+  # Create DataGrid (parent, settings, save_state, _id)
+  datagrid = DataGrid(root)
+  datagrid.init_from_dataframe(df)
+  
+  # Profile the render call
+  profiler = cProfile.Profile()
+  profiler.enable()
+  
+  # Execute render
+  html_output = datagrid.render()
+  
+  profiler.disable()
+  
+  return profiler, html_output
+
+
+def print_profile_stats(profiler, top_n=30):
+  """Print formatted profiling statistics."""
+  s = StringIO()
+  stats = pstats.Stats(profiler, stream=s)
+  
+  print("\n" + "=" * 80)
+  print("PROFILING RESULTS - Top {} functions by cumulative time".format(top_n))
+  print("=" * 80 + "\n")
+  
+  stats.sort_stats('cumulative')
+  stats.print_stats(top_n)
+  
+  output = s.getvalue()
+  print(output)
+  
+  # Extract total time
+  for line in output.split('\n'):
+    if 'function calls' in line:
+      print("\n" + "=" * 80)
+      print("SUMMARY")
+      print("=" * 80)
+      print(line)
+      break
+  
+  print("\n" + "=" * 80)
+  print("Top 10 by total time spent (time * ncalls)")
+  print("=" * 80 + "\n")
+  
+  s = StringIO()
+  stats = pstats.Stats(profiler, stream=s)
+  stats.sort_stats('tottime')
+  stats.print_stats(10)
+  print(s.getvalue())
+
+
+def main():
+  print("Generating test DataFrame (1000 rows × 10 columns)...")
+  df = generate_test_dataframe(rows=1000, cols=10)
+  print(f"DataFrame shape: {df.shape}")
+  print(f"Memory usage: {df.memory_usage(deep=True).sum() / 1024:.2f} KB\n")
+  
+  print("Profiling DataGrid.render()...")
+  profiler, html_output = profile_datagrid_render(df)
+  
+  print(f"\nHTML output length: {len(str(html_output))} characters")
+  
+  print_profile_stats(profiler, top_n=30)
+  
+  # Clean up instances
+  InstancesManager.reset()
+  
+  print("\n✅ Profiling complete!")
+  print("\nNext steps:")
+  print("1. Identify the slowest functions in the 'cumulative time' section")
+  print("2. Look for functions called many times (high ncalls)")
+  print("3. Focus optimization on high cumtime + high ncalls functions")
+
+
+if __name__ == "__main__":
+  main()