Stats Compass

Delete your current session and all its data.

Returns: Deletion result.

Get schemas for all cleaning sub-tools.

Returns available tools: drop_na, impute, dedupe, handle_outliers, etc.

Get schemas for all data manipulation sub-tools.

Returns available tools: get_sample, get_schema, add_column, drop_columns, rename_columns, merge, concat, etc.

Get schemas for all EDA sub-tools.

Returns available tools: describe, correlations, hypothesis_test, data_quality, missing_data_analysis, etc.

Get schemas for all ML sub-tools.

Returns available tools: train_model, evaluate, predict, cross_validate, save_model, etc.

Get schemas for all visualization sub-tools.

Returns available tools: histogram, scatter, bar, line, box, heatmap, roc_curve, confusion_matrix, etc.

Get schemas for all transform sub-tools.

Returns available tools: filter, groupby, pivot, encode, scale, etc.

Execute a cleaning sub-tool.

Args: tool_name: Name of sub-tool (e.g., "drop_na", "impute") params: Parameters for the sub-tool dataframe_name: Override active DataFrame

Execute a data manipulation sub-tool.

Args: tool_name: Name of sub-tool (e.g., "get_sample", "add_column") params: Parameters for the sub-tool dataframe_name: Override active DataFrame

Execute an EDA sub-tool.

Args: tool_name: Name of sub-tool (e.g., "describe", "correlations") params: Parameters for the sub-tool dataframe_name: Override active DataFrame

Execute an ML sub-tool.

Args: tool_name: Name of sub-tool (e.g., "train_model", "predict") params: Parameters for the sub-tool dataframe_name: Override active DataFrame

Execute a visualization sub-tool.

Args: tool_name: Name of sub-tool (e.g., "histogram", "scatter") params: Parameters for the sub-tool dataframe_name: Override active DataFrame

Returns: Plot result with image and download_url (if remote).

Execute a transform sub-tool.

Args: tool_name: Name of sub-tool (e.g., "filter", "groupby") params: Parameters for the sub-tool dataframe_name: Override active DataFrame

Get sample rows from a DataFrame.

Args: dataframe_name: Name of DataFrame (default: active) n: Number of rows (default: 10) method: 'head', 'tail', or 'random'

Returns: Sample rows as records.

Get the schema and metadata of a DataFrame.

Args: dataframe_name: Name of DataFrame (default: active) sample_values: Number of sample values per column

Returns: Schema with columns, dtypes, nulls, and sample values.

Get a presigned URL for uploading a file.

For S3 storage: Returns a presigned PUT URL. For local storage: Returns a file path.

Args: filename: Desired filename (e.g., "my_data.csv") content_type: MIME type (default: text/csv)

Returns: Upload info with url, method, headers, file_key.

List all DataFrames in your session.

Returns: List of DataFrames with name, shape, columns, and active status.

List files in a directory. Useful for finding data files.

Args: directory: Directory path. Supports ~ expansion (e.g., ~/Downloads).

Returns: List of files in the directory.

Load a CSV file from a local path.

Args: path: Absolute path to the CSV file. Supports ~ expansion. name: Name for the DataFrame (default: filename without extension) delimiter: Field delimiter (default: comma) encoding: File encoding (default: utf-8) set_active: Whether to set as active DataFrame (default: True)

Returns: DataFrame info with name, shape, columns, dtypes.

Load a built-in sample dataset.

Available datasets: TATASTEEL, Housing, Bukayo_Saka_7322

Args: name: Dataset name set_active: Whether to set as active DataFrame (default: True)

Returns: DataFrame info with name, shape, columns.

Load an Excel file from a local path.

Args: path: Absolute path to the Excel file. Supports ~ expansion. name: Name for the DataFrame (default: filename without extension) sheet_name: Sheet to load (default: first sheet) set_active: Whether to set as active DataFrame (default: True)

Returns: DataFrame info with name, shape, columns, dtypes.

Health check - verify server is running.

Register an uploaded file and load it as a DataFrame.

After uploading to the URL from get_upload_url(), call this to load the file into your session.

Args: file_key: The file_key returned from get_upload_url() dataframe_name: Name for the DataFrame (default: filename without extension) file_type: File type - "csv" or "excel"

Returns: DataFrame info with name, shape, columns, dtypes.

Run classification workflow: train model, evaluate performance, generate confusion matrix, ROC curve, and feature importance plots.

Args: target_column: Column with class labels to predict dataframe_name: Name of DataFrame (default: active) feature_columns: Feature columns (default: all numeric except target) config: Optional classification configuration dict

Returns: Workflow result with metrics, model ID, and diagnostic charts.

Run comprehensive EDA report: descriptive stats, correlations, missing data analysis, and auto-generated visualizations.

Args: dataframe_name: Name of DataFrame to analyze (default: active) config: Optional EDA configuration dict

Returns: Workflow result with steps, metrics, and charts.

Run data preprocessing pipeline: analyze missing data, apply imputation, handle outliers, and remove duplicates.

Args: dataframe_name: Name of DataFrame to preprocess (default: active) save_as: Name for the cleaned DataFrame (default: auto-generated) config: Optional preprocessing configuration dict

Returns: Workflow result with steps and cleaned DataFrame name.

Run regression workflow: train model, evaluate with RMSE/MAE/R², generate feature importance plots.

Args: target_column: Column with continuous values to predict dataframe_name: Name of DataFrame (default: active) feature_columns: Feature columns (default: all numeric except target) config: Optional regression configuration dict

Returns: Workflow result with metrics, model ID, and charts.

Run time series forecasting: check stationarity, fit ARIMA model, generate forecasts and visualization.

Args: target_column: Column with values to forecast dataframe_name: Name of DataFrame (default: active) date_column: Column with dates (default: uses index) config: Optional time series configuration dict

Returns: Workflow result with forecasts and forecast chart.

Save a DataFrame to a CSV file.

Args: dataframe_name: Name of the DataFrame to save filepath: Path where the CSV file will be saved. For local mode: can be absolute path (e.g., ~/Downloads/data.csv) For remote mode: filename only, saved to session exports index: Whether to write row index (default: False)

Returns: Save result with filepath and download_url (if remote).

Save a trained model to a file.

Args: model_id: ID of the model to save filepath: Path where the model will be saved. For local mode: can be absolute path (e.g., ~/Downloads/model.joblib) For remote mode: filename only, saved to session exports

Returns: Save result with filepath and download_url (if remote).

Get server statistics (admin tool).

Returns: Active sessions count, configuration, and session details.

Get information about your current session.

Returns: Session info including session_id, created_at, dataframes, models.