CSV Editor

Instructions

Implementation Reference

• src/csv_editor/tools/analytics.py:16-98 (handler)

  Core handler function that executes the get_statistics tool logic: retrieves CSV session data, identifies numeric columns, computes detailed statistics (count, nulls, mean, std, min, max, sum, variance, skewness, kurtosis, optional percentiles and IQR), records the operation, and returns structured results.

  async def get_statistics(
      session_id: str, 
      columns: Optional[List[str]] = None,
      include_percentiles: bool = True,
      ctx: Context = None
  ) -> Dict[str, Any]:
      """
      Get statistical summary of numerical columns.
      
      Args:
          session_id: Session identifier
          columns: Specific columns to analyze (None for all numeric)
          include_percentiles: Include percentile values
          ctx: FastMCP context
          
      Returns:
          Dict with statistics for each column
      """
      try:
          manager = get_session_manager()
          session = manager.get_session(session_id)
          
          if not session or session.df is None:
              return {"success": False, "error": "Invalid session or no data loaded"}
          
          df = session.df
          
          # Select columns to analyze
          if columns:
              missing_cols = [col for col in columns if col not in df.columns]
              if missing_cols:
                  return {"success": False, "error": f"Columns not found: {missing_cols}"}
              numeric_df = df[columns].select_dtypes(include=[np.number])
          else:
              numeric_df = df.select_dtypes(include=[np.number])
          
          if numeric_df.empty:
              return {"success": False, "error": "No numeric columns found"}
          
          # Calculate statistics
          stats = {}
          percentiles = [0.25, 0.5, 0.75] if include_percentiles else []
          
          for col in numeric_df.columns:
              col_data = numeric_df[col].dropna()
              
              col_stats = {
                  "count": int(col_data.count()),
                  "null_count": int(df[col].isna().sum()),
                  "mean": float(col_data.mean()),
                  "std": float(col_data.std()),
                  "min": float(col_data.min()),
                  "max": float(col_data.max()),
                  "sum": float(col_data.sum()),
                  "variance": float(col_data.var()),
                  "skewness": float(col_data.skew()),
                  "kurtosis": float(col_data.kurt())
              }
              
              if include_percentiles:
                  col_stats["25%"] = float(col_data.quantile(0.25))
                  col_stats["50%"] = float(col_data.quantile(0.50))
                  col_stats["75%"] = float(col_data.quantile(0.75))
                  col_stats["iqr"] = col_stats["75%"] - col_stats["25%"]
              
              stats[col] = col_stats
          
          session.record_operation(OperationType.ANALYZE, {
              "type": "statistics",
              "columns": list(stats.keys())
          })
          
          return {
              "success": True,
              "statistics": stats,
              "columns_analyzed": list(stats.keys()),
              "total_rows": len(df)
          }
          
      except Exception as e:
          logger.error(f"Error getting statistics: {str(e)}")
          return {"success": False, "error": str(e)}

• src/csv_editor/server.py:317-326 (registration)

  MCP tool registration for get_statistics using @mcp.tool decorator. This wrapper function defines the tool interface (parameters and docstring used for schema/input validation) and delegates execution to the core implementation via _get_statistics.

  @mcp.tool
  async def get_statistics(
      session_id: str,
      columns: Optional[List[str]] = None,
      include_percentiles: bool = True,
      ctx: Context = None
  ) -> Dict[str, Any]:
      """Get statistical summary of numerical columns."""
      return await _get_statistics(session_id, columns, include_percentiles, ctx)

• src/csv_editor/server.py:307-315 (handler)

  Import statement that brings the get_statistics implementation into server.py, aliased as _get_statistics for use by the registered tool wrapper.

  from .tools.analytics import (
      get_statistics as _get_statistics,
      get_column_statistics as _get_column_statistics,
      get_correlation_matrix as _get_correlation_matrix,
      group_by_aggregate as _group_by_aggregate,
      get_value_counts as _get_value_counts,
      detect_outliers as _detect_outliers,
      profile_data as _profile_data
  )