我是哭哭我还是苦苦

import numpy as np
import pandas as pd
from sklearn.model_selection import  train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import precision_score, recall_score, roc_curve, accuracy_score
import matplotlib.pyplot as plt

def drop_duplicates(path):
    data = pd.read_csv(path)
    data = data.drop_duplicates()  # 去重
    y = data.iloc[:, -1]
    y = y.drop_duplicates()
    print(y)
# 9 10 8 20 16 19 14 11 12 18 13 5 4 6 21 17 22 1 3 26 23 29 2 27 25 24

def process_data(path):
    data = pd.read_csv(path)
    data = data.drop_duplicates()  # 去重
    # print(data)
    # 定义一个字典 将M 作为键 ；0 作为值。。。
    class_dict = {"M": 0, "F": 1, "I": 2}
    # 将species 下的 替换 成 字典规则
    data["Sex "] = data["Sex "].map(class_dict)  # 将字典的键映射为值 即完成转换
    # print(data)
    data = data.astype(float)
    X = data.iloc[:, :-1]
    y = data.iloc[:, -1] # 9 10 8 20 16 19 14 11 12 18 13 5 4 6 21 17 22 1 3 26 23 29 2 27 25 24
                        # 1 2 3 4 5 6 8 9 10        11 12 13 14 16 17 18 19 20      21 22 23 24 25 26 27 29

    y[y == 1] = 0
    y[y == 2] = 0
    y[y == 3] = 0
    y[y == 4] = 0
    y[y == 5] = 0
    y[y == 6] = 0
    y[y == 7] = 0
    y[y == 8] = 0
    y[y == 9] = 0
    y[y == 10] = 0
    y[y == 11] = 1
    y[y == 12] = 1
    y[y == 13] = 1
    y[y == 14] = 1
    y[y == 16] = 1
    y[y == 17] = 1
    y[y == 18] = 1
    y[y == 19] = 1
    y[y == 20] = 1
    y[y == 21] = 2
    y[y == 22] = 2
    y[y == 23] = 2
    y[y == 24] = 2
    y[y == 25] = 2
    y[y == 26] = 2
    y[y == 27] = 2
    y[y == 29] = 2
    # print(X)
    # print(y)
    # 特征标准化  自变量数据的归一化
    mu = X.mean(0)
    std = X.std(0)
    X = (X - mu) / std  # 归一化  使其范围缩小到(-1,1)
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size = 0.33, random_state = 42)
    return  X_train, X_test, y_train, y_test

def decisionTree( X_train, X_test, y_train, y_test):
    # 默认为gini系数方法 需要指定信息增益的方法-即ID3决策树
    clf = DecisionTreeClassifier(criterion="entropy")# ID3决策树
    clf.fit(X_train,y_train)
    y_predict = clf.predict(X_test)
    # print("预测值-pridict", y_predict)
    print("自己计算-模型准确率", np.sum(y_test == y_predict) / len(y_test))  # 手动计算模型准确率
    # 模型评价
    print("precision_score:", precision_score(y_test, y_predict, average='micro'))
    print("recall_score:", recall_score(y_test, y_predict, average='micro'))
    print("accuracy_score:", accuracy_score(y_test, y_predict))
    # roc曲线绘制
    fpr, tpr, thresholds = roc_curve(y_test, y_predict,pos_label=2)
    plt.xlim(0, 1)
    plt.ylim(0, 1)
    plt.plot(fpr, tpr, color="blue")
    plt.show()

    print("accuracy on training set:",clf.score(X_train, y_train))# 训练集上的精度是 100%，这是因为叶结点都是纯的，树的深度很大
    print("accuracy on test set:{:.3f}".format(clf.score(X_test, y_test)))# 线性模型的精度
    # y_pred = clf.predict(X_test)
    # return y_pred

if __name__ == '__main__':
    path = r"F:\\desktop\\abalone.csv"
    X_train, X_test, y_train, y_test =  process_data(path)
    decisionTree(X_train, X_test, y_train, y_test)