get_value_counts
Count unique values in a CSV column to analyze data distribution and identify patterns.
Instructions
Get value counts for a column.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | ||
| column | Yes | ||
| normalize | No | ||
| sort | No | ||
| ascending | No | ||
| top_n | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- Core implementation of get_value_counts tool: retrieves DataFrame from session, computes value counts with options for normalization, sorting, and top_n, converts to dictionary format, adds statistics, and handles errors.
async def get_value_counts( session_id: str, column: str, normalize: bool = False, sort: bool = True, ascending: bool = False, top_n: Optional[int] = None, ctx: Context = None ) -> Dict[str, Any]: """ Get value counts for a column. Args: session_id: Session identifier column: Column name to count values normalize: Return proportions instead of counts sort: Sort by frequency ascending: Sort order top_n: Return only top N values ctx: FastMCP context Returns: Dict with value counts """ 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 if column not in df.columns: return {"success": False, "error": f"Column '{column}' not found"} # Get value counts value_counts = df[column].value_counts( normalize=normalize, sort=sort, ascending=ascending, dropna=False ) # Apply top_n if specified if top_n: value_counts = value_counts.head(top_n) # Convert to dict counts_dict = {} for value, count in value_counts.items(): key = str(value) if not pd.isna(value) else "NaN" counts_dict[key] = float(count) if normalize else int(count) # Calculate additional statistics unique_count = df[column].nunique(dropna=False) null_count = df[column].isna().sum() session.record_operation(OperationType.ANALYZE, { "type": "value_counts", "column": column, "normalize": normalize, "top_n": top_n }) return { "success": True, "column": column, "value_counts": counts_dict, "unique_values": int(unique_count), "null_count": int(null_count), "total_count": len(df), "normalized": normalize } except Exception as e: logger.error(f"Error getting value counts: {str(e)}") return {"success": False, "error": str(e)} - src/csv_editor/server.py:358-368 (registration)Registers the get_value_counts tool using @mcp.tool decorator, providing the tool interface and delegating execution to the imported implementation.
async def get_value_counts( session_id: str, column: str, normalize: bool = False, sort: bool = True, ascending: bool = False, top_n: Optional[int] = None, ctx: Context = None ) -> Dict[str, Any]: """Get value counts for a column.""" return await _get_value_counts(session_id, column, normalize, sort, ascending, top_n, ctx)