xgboost训练鸢尾花数据集

from sklearn import datasets
from sklearn.pipeline import Pipeline
import pandas as pd
from xgboost import XGBClassifier
from nyoka import xgboost_to_pmml
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score, KFold
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt


# 加载数据
def load_data():
    iris = datasets.load_iris()
    return iris


# 生成features和target
def get_feature():
    target = 'Species'
    iris = load_data()
    features = iris.feature_names
    iris_df = pd.DataFrame(iris.data, columns=features)
    iris_df[target] = iris.target
    X, y = iris_df[features], iris_df[target]
    return X, y


# 切割数据
def data_process():
    # 随机种子和测试集占比
    seed = 123456
    test_size = 0.33
    X, y = get_feature()
    # split data into train and hello_world sets
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=seed)
    return X_train, X_test, y_train, y_test


# 生成管道
def get_pipeline():
    X_train, X_test, y_train, y_test = data_process()
    pipeline = Pipeline([
        ('xgb', XGBClassifier())
    ])
    pipeline.fit(X_train, y_train)
    return pipeline


# 结果分
def result_score():
    pipeline = get_pipeline()
    X_train, X_test, y_train, y_test = data_process()
    score = pipeline.score(X_test, y_test)
    print("Training score: ", score)

    scores = cross_val_score(pipeline, X_train, y_train, cv=10)
    print("Mean cross-validation score: %.2f" % scores.mean())

    # k折交叉验证
    kfold = KFold(n_splits=10, shuffle=True)
    kf_cv_scores = cross_val_score(pipeline, X_train, y_train, cv=kfold)
    print("K-fold CV average score: %.2f" % kf_cv_scores.mean())

    # MSE RMSE
    y_pred = pipeline.predict(X_test)
    mse = mean_squared_error(y_test, y_pred)
    print("MSE: %.2f" % mse)
    print("RMSE: %.2f" % (mse ** (1 / 2.0)))

    # 拟合曲线
    x_ax = range(len(y_test))
    # 散点图
    # plt.scatter(x_ax, y_test, s=5, color="blue", label="original")
    # 折线图
    plt.plot(x_ax, y_test, lw=0.8, color="blue", label="original")
    plt.plot(x_ax, y_pred, lw=0.8, color="red", label="predicted")
    plt.legend()
    plt.show()


# 生成PMML文件
def create_pmml_file():
    pipeline = get_pipeline()
    features, target = get_feature()
    xgboost_to_pmml(pipeline, features, target, "pmml_file/xgb-iris.pmml")


if __name__ == '__main__':
    result_score()
    # create_pmml_file()