Motivation

• Random-Forest classifier for classifying backorder data
• The data is imbalance between 2 label
• Duplicating the Positive-label or Re-sampling the Negative-label to get more balance data-set
• Data set Backorder data

Installation

Dependencies:

• pandas: read / write csv file
• numpy: data format
• sklearn: classifiers

API Reference

• Training from csv data-file and writing model to model-file order_classifier.training_from_csv_data(data_file, model_file)

• Loading model from model-file order_classifier.readModel(file_path)

• Read from file and convert data to numpy format order_preprocess.read_data(file_path)

• Predict order_classifier.predict(data, classifier)

Tests

• Training sample order_classifier.build_classifier_sample()

• Evaluating sample order_classifier.eval_result_rf()