Accelerating Data Science Development using ChatGPT.
- Setup DSAccelerate
- Download the repository zip file or clone it using the git clone command.
- (Recommended) Create a new python environment using conda, venv or any other service.
- Run the
make download
command to set it up.
- Create your new project
- Provide your specifications in the
project_config.json
file. - Run the
make run
command to generate your project.
- Provide your specifications in the
- Setup your new project
- (Recommended) Create a new python environment using conda, venv or any other service for your project.
- Get into your project directory and run the
make requirements
command to setup your environments. - Tweak the generated files as per your requirements and resolve any errors if they occur.
- Finally, run your project using the command
python src/__init__.py
model_algorithm_name
support in PyCaret:
- Logistic Regression ('lr')
- K Neighbors Classifier ('knn')
- Naive Bayes ('nb')
- Decision Tree Classifier ('dt')
- Random Forest Classifier ('rf')
- Extra Trees Classifier ('et')
- Gradient Boosting Classifier ('gbc')
- Extreme Gradient Boosting Classifier ('xgboost')
- Light Gradient Boosting Machine ('lightgbm')
- CatBoost Classifier ('catboost')
- AdaBoost Classifier ('ada')
- Linear Discriminant Analysis ('lda')
- Quadratic Discriminant Analysis ('qda')
- Ridge Classifier ('ridge')
- Ridge Classifier CV ('ridgecv')
- Passive Aggressive Classifier ('pac')
- Perceptron ('perceptron')
- Voting Classifier ('voting')
- Stacking Classifier ('stacking')