create_distribution_plots

Instructions

Implementation Reference

• src/visidata_mcp/server.py:768-876 (handler)

  Main handler function that creates distribution plots (histogram, box, violin, or kde) for numeric columns in a dataset. Loads data, filters to numeric columns, creates subplot grid based on column count, generates plots using matplotlib/seaborn, and saves to output path.

  @mcp.tool()
  def create_distribution_plots(file_path: str, output_path: str, 
                              columns: Optional[List[str]] = None,
                              plot_type: str = "histogram") -> str:
      """
      Create distribution plots for numeric columns.
      
      Args:
          file_path: Path to the data file
          output_path: Path where to save the distribution plots
          columns: Optional list of specific columns to plot (if None, uses all numeric columns)
          plot_type: Type of distribution plot (histogram, box, violin, kde)
      
      Returns:
          Information about the created distribution plots
      """
      try:
          if not VISUALIZATION_AVAILABLE:
              return f"Error: {VISUALIZATION_ERROR}"
              
          import pandas as pd
          from pathlib import Path
          import math
          
          # Load the data
          file_extension = Path(file_path).suffix.lower()
          if file_extension == '.csv':
              df = pd.read_csv(file_path)
          elif file_extension == '.json':
              df = pd.read_json(file_path)
          elif file_extension in ['.xlsx', '.xls']:
              df = pd.read_excel(file_path)
          elif file_extension == '.tsv':
              df = pd.read_csv(file_path, sep='\t')
          else:
              df = pd.read_csv(file_path)
          
          # Select numeric columns
          if columns:
              missing_cols = [col for col in columns if col not in df.columns]
              if missing_cols:
                  return f"Error: Columns not found: {missing_cols}"
              numeric_df = df[columns].select_dtypes(include=['number'])
          else:
              numeric_df = df.select_dtypes(include=['number'])
          
          if numeric_df.empty:
              return "Error: No numeric columns found for distribution analysis"
          
          # Calculate subplot dimensions
          n_cols = len(numeric_df.columns)
          if n_cols <= 4:
              n_rows, n_plot_cols = 1, n_cols
          else:
              n_plot_cols = 3
              n_rows = math.ceil(n_cols / n_plot_cols)
          
          # Create subplots
          fig, axes = plt.subplots(n_rows, n_plot_cols, figsize=(5*n_plot_cols, 4*n_rows))
          if n_cols == 1:
              axes = [axes]
          elif n_rows == 1:
              axes = axes if n_cols > 1 else [axes]
          else:
              axes = axes.flatten()
          
          # Create distribution plots
          for i, column in enumerate(numeric_df.columns):
              ax = axes[i] if n_cols > 1 else axes[0]
              
              if plot_type == "histogram":
                  ax.hist(numeric_df[column].dropna(), bins=20, alpha=0.7, edgecolor='black')
                  ax.set_ylabel('Frequency')
              elif plot_type == "box":
                  ax.boxplot(numeric_df[column].dropna())
                  ax.set_ylabel('Value')
              elif plot_type == "violin":
                  sns.violinplot(y=numeric_df[column].dropna(), ax=ax)
              elif plot_type == "kde":
                  sns.kdeplot(data=numeric_df[column].dropna(), ax=ax)
                  ax.set_ylabel('Density')
              else:
                  return f"Error: Unsupported plot type '{plot_type}'. Use: histogram, box, violin, kde"
              
              ax.set_title(f'{plot_type.title()} of {column}')
              ax.set_xlabel(column.replace('_', ' ').title())
              ax.grid(True, alpha=0.3)
          
          # Hide empty subplots
          for i in range(n_cols, len(axes)):
              axes[i].set_visible(False)
          
          plt.tight_layout()
          plt.savefig(output_path, dpi=300, bbox_inches='tight')
          plt.close()
          
          result = {
              "distribution_plots_created": True,
              "plot_type": plot_type,
              "columns_plotted": list(numeric_df.columns),
              "total_plots": len(numeric_df.columns),
              "output_file": output_path,
              "file_size": Path(output_path).stat().st_size if Path(output_path).exists() else 0
          }
          
          return json.dumps(result, indent=2)
          
      except Exception as e:
          return f"Error creating distribution plots: {str(e)}\n{traceback.format_exc()}"

• src/visidata_mcp/server.py:768-768 (registration)

  Tool registration using @mcp.tool() decorator that exposes the create_distribution_plots function as an MCP tool.

  @mcp.tool()