zoukankan      html  css  js  c++  java
  • K-fold Train

    # config.py
    TRAINING_FILE = "../input/mnist_train_folds.csv"
    MODEL_OUTPUT = "../models/"
    ===========================================================
    # train.py
    import os
    import config
    import joblib
    import pandas as pd
    from sklearn import metrics
    from sklearn import tree
    def run(fold):
    # read the training data with folds
    df = pd.read_csv(config.TRAINING_FILE)
    # training data is where kfold is not equal to provided fold
    # also, note that we reset the index
    df_train = df[df.kfold != fold].reset_index(drop=True)
    # validation data is where kfold is equal to provided fold
    df_valid = df[df.kfold == fold].reset_index(drop=True)
    # drop the label column from dataframe and convert it to
    # a numpy array by using .values.
    # target is label column in the dataframe
    x_train = df_train.drop("label", axis=1).values
    y_train = df_train.label.values
    # similarly, for validation, we have
    x_valid = df_valid.drop("label", axis=1).values
    y_valid = df_valid.label.values
    # initialize simple decision tree classifier from sklearn
    clf = tree.DecisionTreeClassifier()
    # fir the model on training data
    clf.fit(x_train, y_train)
    # create predictions for validation samples
    preds = clf.predict(x_valid)
    # calculate & print accuracy
    accuracy = metrics.accuracy_score(y_valid, preds)
    print(f"Fold={fold}, Accuracy={accuracy}")
    # save the model
    joblib.dump(
    clf,
    os.path.join(config.MODEL_OUTPUT, f"dt_{fold}.bin")
    )


    if __name__ == "__main__":
    run(fold=0)
    run(fold=1)
    run(fold=2)
    run(fold=3)
    run(fold=4)
  • 相关阅读:
    drf的模型基表与10个单群操作方法
    drf的序列化组件
    drf之请求模块,渲染模块,解析模块,响应模块,异常模块
    drf之接口与接口规范
    MongoDB C# Demo
    如何用Dome4j(2.2.1)创建Xml
    Map、Set的基本概括
    如何自定义xml文件
    HashMap和HashTable的理解与区别
    装箱 拆箱
  • 原文地址:https://www.cnblogs.com/songyuejie/p/14785768.html
Copyright © 2011-2022 走看看