statistical-model-implementer

A library (if I do push it to pypi) that takes in training and test datasets and then applies statistical models, calculates metrics and also gives the best performing model.

Example: Using the Winconsin Cancer data that I had analysed earlier.

The train and test set are used as inputs for running the Implementer.

Supervised Learning

Types:

1. Regression
2. Classification

Models Used

Regression

1. Linear Regression (sklearn)
2. Decision Tree Regressor
3. Support Vector Regression
4. Random Forest Regressor
5. AdaBoost Regressor

Classification

1. Logistic Regression (bivariate only)
2. Decision Tree Classifier
3. Support Vector Classifier
4. KNN Classifier
5. AdaBoost Classifier
6. RandomForest Classigier

Metrics used:

1. Classification Report
2. Accuracy Score
3. Confusion Matrix
4. F1 Score

All other metrics that take y_test and predicted Y value as input.