MCP Server
JSON →Automate data science stages using your own CSV data files.
Install
pip install -r Tools · 15
- information_about_data Give detailed information about the data
- reading_csv Read the csv file
- visualize_correlation_num Visualize the correlation matrix for numerical columns
- visualize_correlation_cat Visualize the correlation matrix for categorical columns
- visualize_correlation_final Visualize the correlation matrix after preprocessing
- visualize_outliers Visualize outliers in the data
- visualize_outliers_final Visualize outliers after preprocessing
- preprocessing_data Preprocess the data (remove outliers, fill nulls, etc.)
- prepare_data Prepare the data for models (encoding, scaling, etc.)
- models Select and evaluate models based on problem type
- visualize_accuracy_matrix Visualize the confusion matrix for predictions
- best_model_hyperparameter Tune the hyperparameters of the best model
- test_external_data Test external data with the best model and return predictions
- predict_value Predict the value of the target column for new input
- feature_importance_analysis Analyze the feature importance of the data using XGBoost
Links
★ 13 GitHub stars