create_skills_location_heatmap

Instructions

Implementation Reference

• src/visidata_mcp/server.py:1200-1314 (handler)

  The create_skills_location_heatmap tool handler creates a heatmap showing skills distribution across locations. It parses comma-separated skills from a specified column, aggregates them by location, calculates percentages, and generates a visualization using seaborn's heatmap function.

  @mcp.tool()
  def create_skills_location_heatmap(file_path: str, skills_column: str, location_column: str, 
                                    output_path: str, top_skills: int = 15, top_locations: int = 10) -> str:
      """
      Create a heatmap showing skills distribution across locations.
      
      Args:
          file_path: Path to the data file
          skills_column: Column name containing comma-separated skills
          location_column: Column name containing location information
          output_path: Path where to save the heatmap image
          top_skills: Number of top skills to include (default: 15)
          top_locations: Number of top locations to include (default: 10)
      
      Returns:
          Information about the created skills-location heatmap
      """
      try:
          if not VISUALIZATION_AVAILABLE:
              return f"Error: {VISUALIZATION_ERROR}"
              
          import pandas as pd
          from pathlib import Path
          from collections import defaultdict, Counter
          
          # 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)
          
          if skills_column not in df.columns:
              return f"Error: Column '{skills_column}' not found in data"
          if location_column not in df.columns:
              return f"Error: Column '{location_column}' not found in data"
          
          # Parse skills and create location-skill matrix
          location_skills = defaultdict(list)
          all_skills = Counter()
          
          for _, row in df.iterrows():
              location = row[location_column]
              skills_str = row[skills_column]
              
              if pd.isna(location) or pd.isna(skills_str):
                  continue
                  
              skills = [skill.strip() for skill in str(skills_str).split(',') if skill.strip()]
              location_skills[location].extend(skills)
              all_skills.update(skills)
          
          # Get top skills and locations
          top_skills_list = [skill for skill, _ in all_skills.most_common(top_skills)]
          
          # Calculate location totals and get top locations
          location_totals = {loc: len(skills) for loc, skills in location_skills.items()}
          top_locations_list = sorted(location_totals.keys(), key=lambda x: location_totals[x], reverse=True)[:top_locations]
          
          # Create matrix
          matrix_data = []
          for location in top_locations_list:
              location_skill_counts = Counter(location_skills[location])
              total_skills_in_location = sum(location_skill_counts.values())
              
              row = []
              for skill in top_skills_list:
                  # Calculate percentage of this skill in this location
                  percentage = (location_skill_counts[skill] / total_skills_in_location * 100) if total_skills_in_location > 0 else 0
                  row.append(percentage)
              matrix_data.append(row)
          
          # Create DataFrame for heatmap
          heatmap_df = pd.DataFrame(matrix_data, index=top_locations_list, columns=top_skills_list)
          
          # Create the heatmap
          plt.figure(figsize=(max(12, len(top_skills_list) * 0.8), max(8, len(top_locations_list) * 0.6)))
          sns.heatmap(heatmap_df, 
                     annot=True, 
                     fmt='.1f',
                     cmap='YlOrRd',
                     cbar_kws={'label': 'Skill Percentage (%)'},
                     linewidths=0.5)
          
          plt.title(f'Skills Distribution Across Top {top_locations} Locations\n(Top {top_skills} Skills)')
          plt.xlabel('Skills')
          plt.ylabel('Locations')
          plt.xticks(rotation=45, ha='right')
          plt.yticks(rotation=0)
          plt.tight_layout()
          
          # Save the plot
          plt.savefig(output_path, dpi=300, bbox_inches='tight')
          plt.close()
          
          result = {
              "skills_location_heatmap_created": True,
              "top_skills_analyzed": len(top_skills_list),
              "top_locations_analyzed": len(top_locations_list),
              "skills_included": top_skills_list,
              "locations_included": top_locations_list,
              "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 skills-location heatmap: {str(e)}\n{traceback.format_exc()}"