Function reference • alookr

Model Classifier for Binary Classification A collection of tools that support data cleansing and splitting, predictive modeling, and model evaluation.
Cleansing the dataset
`cleanse()`	Cleansing the dataset for classification modeling
`cleanse(<split_df>)`	Cleansing the dataset for classification modeling
`treatment_corr()`	Diagnosis and removal of highly correlated variables
Splitting the dataset
`split_by()`	Split Data into Train and Test Set
`summary(<split_df>)`	Summarizing split_df information
`compare_diag()`	Diagnosis of train set and test set of split_df object
`compare_performance()`	Compare model performance
`compare_plot()`	Comparison plot of train set and test set
`compare_target_category()`	Comparison of categorical variables of train set and test set
`compare_target_numeric()`	Comparison of numerical variables of train set and test set
`extract_set()`	Extract train/test dataset
`sampling_target()`	Extract the data to fit the model
Classification Modeling
`run_models()`	Fit binary classification model
`run_performance()`	Apply calculate performance metrics for model evaluation
`run_predict()`	Predict binary classification model
`plot_performance()`	Visualization for ROC curve
`plot_cutoff()`	Visualization for cut-off selection
`performance_metric()`	Calculate metrics for model evaluation
`matthews()`	Compute Matthews Correlation Coefficient

Reference