Python机器学习之交叉验证

最新推荐文章于 2025-06-29 20:39:16 发布

happy5205205

最新推荐文章于 2025-06-29 20:39:16 发布

阅读量1.5k

点赞数 2

CC 4.0 BY-SA版权

分类专栏：机器学习

本文链接：https://blog.youkuaiyun.com/happy5205205/article/details/80885040

机器学习专栏收录该内容

6 篇文章

订阅专栏

本文通过使用Python的机器学习库sklearn，对一个水果数据集进行预处理、特征工程及模型训练。主要内容包括数据加载、特征归一化、交叉验证、模型选择与评估等步骤，并展示了如何使用K近邻、支持向量机和决策树等算法。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

数据链接:https://pan.baidu.com/s/1yW6gye5rJQ-Rn_iKlKUm1g 密码:ejki

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split

1、数据加载

# 加载数据集
fruits_df = pd.read_table('fruit_data_with_colors.txt')
print(fruits_df.head())
print('样本个数：', len(fruits_df))
# 创建目标标签和名称的字典
fruit_name_dict = dict(zip(fruits_df['fruit_label'], fruits_df['fruit_name']))
print(fruit_name_dict)
# 划分数据集
X = fruits_df[['mass', 'width', 'height', 'color_score']]
y = fruits_df['fruit_label']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/4, random_state=0)
print('数据集样本数：{}，训练集样本数：{}，测试集样本数：{}'.format(len(X), len(X_train), len(X_test)))

2、特征归一化

from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
for i in range(4):
    print('归一化前，训练数据第{}维特征最大值：{:.3f}，最小值：{:.3f}'.format(i + 1, X_train.iloc[:, i].max(), X_train.iloc[:, i].min()))
    print('归一化后，训练数据第{}维特征最大值：{:.3f}，最小值：{:.3f}'.format(i + 1,X_train_scaled[:, i].max(), X_train_scaled[:, i].min()))
print()

3、交叉验证

 # 单一超参数
 from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import cross_val_score

k_range = [2, 4, 5, 10]
cv_scores = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors=k)
    scores = cross_val_score(knn, X_train_scaled, y_train, cv=3)
    cv_score = np.mean(scores)
    print('k={}，验证集上的准确率={:.3f}'.format(k, cv_score))
    cv_scores.append(cv_score)
best_k = k_range[np.argmax(cv_scores)]
best_knn = KNeighborsClassifier(n_neighbors=best_k)
best_knn.fit(X_train_scaled, y_train)
print('测试集准确率：', best_knn.score(X_test_scaled, y_test))
# 调用  validation_curve 绘制超参数对训练集和验证集的影响
from sklearn.model_selection import validation_curve
from sklearn.svm import SVC
c_range = [1e-3, 1e-2, 0.1, 1, 10, 100, 1000, 10000]
train_scores, test_scores = validation_curve(SVC(kernel='linear'), X_train_scaled, y_train,param_name='C', param_range=c_range,cv=5, scoring='accuracy')
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
plt.figure(figsize=(10, 8))
plt.title('Validation Curve with SVM')
plt.xlabel('C')
plt.ylabel('Score')
plt.ylim(0.0, 1.1)
lw = 2
plt.semilogx(c_range, train_scores_mean, label="Training score",
             color="darkorange", lw=lw)
plt.fill_between(c_range, train_scores_mean - train_scores_std,
                 train_scores_mean + train_scores_std, alpha=0.2,
                 color="darkorange", lw=lw)
plt.semilogx(c_range, test_scores_mean, label="Cross-validation score",
             color="navy", lw=lw)
plt.fill_between(c_range, test_scores_mean - test_scores_std,
                 test_scores_mean + test_scores_std, alpha=0.2,
                 color="navy", lw=lw)
plt.legend(loc="best")
plt.show()
# 从上图可知对SVM，C=100为最优参数
svm_model = SVC(kernel='linear', C=1000)
svm_model.fit(X_train_scaled, y_train)
print(svm_model.score(X_test_scaled, y_test))

# 多个超参数
from sklearn.model_selection import GridSearchCV
from sklearn.tree import DecisionTreeClassifier

parameters = {'max_depth':[3, 5, 7, 9], 'min_samples_leaf': [1, 2, 3, 4]}
clf = GridSearchCV(DecisionTreeClassifier(), parameters, cv=3, scoring='accuracy')
clf.fit(X_train, y_train)
print('最优参数：', clf.best_params_)
print('验证集最高得分：', clf.best_score_)
# 获取最优模型
best_model = clf.best_estimator_
print('测试集上准确率：', best_model.score(X_test, y_test))

4、模型评价指标

k = 1
# 转换为二分类问题
y_train_binary = y_train.copy()
y_test_binary = y_test.copy()
y_train_binary[y_train_binary != 1] = 0
y_test_binary[y_test_binary != 1] = 0
knn = KNeighborsClassifier(k)
knn.fit(X_train_scaled, y_train_binary)
y_pred = knn.predict(X_test_scaled)
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
# 准确率
print('准确率：{:.3f}'.format(accuracy_score(y_test_binary, y_pred)))
# 精确率
print('精确率：{:.3f}'.format(precision_score(y_test_binary, y_pred)))
# 召回率
print('召回率：{:.3f}'.format(recall_score(y_test_binary, y_pred)))
# F1值
print('F1值：{:.3f}'.format(f1_score(y_test_binary, y_pred)))

# PR 曲线
from sklearn.metrics import precision_recall_curve, average_precision_score

# precision, recall, _ = precision_recall_curve(y_test, y_pred)
print('AP值：{:.3f}'.format(average_precision_score(y_test_binary, y_pred)))

# ROC曲线
from sklearn.metrics import roc_auc_score, roc_curve
# fpr, tpr, _ = roc_curve(y_test, y_pred)
print('AUC值：{:.3f}'.format(roc_auc_score(y_test_binary, y_pred)))

# 混淆矩阵
from sklearn.metrics import confusion_matrix

y_pred = best_model.predict(X_test_scaled)
cm = confusion_matrix(y_test, y_pred)
print(cm)
plt.figure()
plt.grid(False)
plt.imshow(cm, cmap='jet')
plt.colorbar()