easy-ml/train_test.py

# -*- coding: utf-8 -*-
"""
@author: yq
@time: 2024/11/27
@desc: 
"""
import time

from entitys import DataSplitEntity, DataProcessConfigEntity, TrainConfigEntity
from feature import FilterStrategyFactory
from trainer import TrainPipeline

if __name__ == "__main__":
    time_now = time.time()
    import scorecardpy as sc

    dat = sc.germancredit()
    dat["creditability"] = dat["creditability"].apply(lambda x: 1 if x == "bad" else 0)
    data = DataSplitEntity(dat[:700], None, dat[700:])

    # 特征处理
    filter_strategy_factory = FilterStrategyFactory(
        DataProcessConfigEntity.from_config('./config/data_process_config_template.json'))
    strategy = filter_strategy_factory.get_strategy()
    candidate_feature = strategy.filter(data)
    data_prepared = strategy.feature_generate(data, candidate_feature)
    # 训练
    train_pipeline = TrainPipeline(TrainConfigEntity.from_config('./config/train_config_template.json'))
    train_pipeline.train(data_prepared)
    # 报告生成
    metric_value_dict = strategy.feature_report(data, candidate_feature)
    train_pipeline.generate_report(metric_value_dict)

    print(time.time() - time_now)