分类算法——基于heart数据集实现

🕗 发布于 2024-11-27 20:47 分类数据挖掘 人工智能

1 heart数据集——描述性统计分析

import matplotlib.pyplot as plt
import pandas as pd

# Load the dataset
heart = pd.read_csv(r"heart.csv", sep=',')

# Check the columns in the DataFrame
print(heart.columns)

a=heart.loc[:, 'y'].value_counts()
print(a)
heart.loc[:, 'y'].value_counts().plot(kind='bar')
#设置0和1的标签，0为无心脏病，1为有心脏病
plt.xticks([0, 1], ['No heart disease', 'Yes heart disease'])
#设置横坐标旋转45度
plt.xticks(rotation=0)
# 设置矩形数据标签
for x, y in enumerate(heart.loc[:, 'y'].value_counts()):
    plt.text(x, y, '%s' % y, ha='center', va='bottom')
#更改颜色
plt.bar([0, 1], heart.loc[:, 'y'].value_counts(), color=['#FF0000', '#00FF00'])

#设置标题
plt.title('Heart disease distribution')
plt.show()

Index(['sbp', 'tobacco', 'ldl', 'adiposity', 'age', 'y'], dtype='object')
y
0    302
1    160
Name: count, dtype: int64

在这里插入图片描述

2 Cp交叉验证，选择最优的k值进行判别分析

#Cp交叉验证，选择最优的k值进行判别分析
from sklearn.model_selection import cross_val_score
from sklearn.neighbors import KNeighborsClassifier
    
X = heart.iloc[:, 0:5]
y = heart.loc[:, 'y']
k_range = range(1, 31)
k_scores = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors=k)
    scores = cross_val_score(knn, X, y, cv=10, scoring='accuracy')
    k_scores.append(scores.mean())
    
plt.plot(k_range, k_scores)
plt.xlabel('Value of K for KNN')
plt.ylabel('Cross-Validated Accuracy')

#选择最优的k值
k = k_scores.index(max(k_scores)) + 1
print('Optimal k: %d' % k)
#绘制最优k值在图中的位置
plt.plot(k_range, k_scores)
plt.xlabel('Value of K for KNN')
plt.ylabel('Cross-Validated Accuracy')
plt.scatter(k, max(k_scores), color='red')

#显示最优k直在图中等于多少
plt.text(k, max(k_scores), '(%d, %.2f)' % (k, max(k_scores)), ha='center', va='bottom')
plt.show()

Optimal k: 22

在这里插入图片描述

KNN分类器

#使用最优k值建立KNN进行分类
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

# Initialize and fit the KNN classifier
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)

# Predict and print accuracy
y_pred = knn.predict(X_test)
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))

#绘制决策区域
from matplotlib.colors import ListedColormap
import numpy as np
from sklearn.decomposition import PCA

def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    # Reduce dimensionality to 2D using PCA
    pca = PCA(n_components=2)
    X_pca = pca.fit_transform(X)

    # setup marker generator and color map
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])

    # plot the decision surface
    x1_min, x1_max = X_pca[:, 0].min() - 1, X_pca[:, 0].max() + 1
    x2_min, x2_max = X_pca[:, 1].min() - 1, X_pca[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
                           np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(pca.inverse_transform(np.array([xx1.ravel(), xx2.ravel()]).T))
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())

    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X_pca[y == cl, 0], y=X_pca[y == cl, 1],
                    alpha=0.8, c=[cmap(idx)],
                    marker=markers[idx], label=cl)

    # highlight test samples
    if test_idx:
        X_test, y_test = X_pca[test_idx, :2], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1],
                    alpha=1.0, linewidth=1, marker='o',
                    s=55, label='test set')
        
# Plot decision regions using PCA-transformed features
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined, y=y_combined, classifier=knn, test_idx=range(len(y_train), len(y_train) + len(y_test)))
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(loc='upper left')
plt.show()

Accuracy: 0.69

在这里插入图片描述

朴素贝叶斯分类器

#朴素贝叶斯分类器
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.naive_bayes import GaussianNB
from matplotlib.colors import ListedColormap

# Load the dataset
heart = pd.read_csv(r"heart.csv", sep=',')

# Select features and target
X = heart.iloc[:, 0:5]
y = heart.loc[:, 'y']

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

# Initialize and fit the Gaussian Naive Bayes classifier
gnb = GaussianNB()
gnb.fit(X_train, y_train)

# Predict and print accuracy
y_pred = gnb.predict(X_test)
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))

# Define the function to plot decision regions
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.decomposition import PCA

def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    # Reduce dimensionality to 2D using PCA
    pca = PCA(n_components=2)
    X_pca = pca.fit_transform(X)

    # setup marker generator and color map
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])

    # plot the decision surface
    x1_min, x1_max = X_pca[:, 0].min() - 1, X_pca[:, 0].max() + 1
    x2_min, x2_max = X_pca[:, 1].min() - 1, X_pca[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
                           np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(pca.inverse_transform(np.array([xx1.ravel(), xx2.ravel()]).T))
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())

    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X_pca[y == cl, 0], y=X_pca[y == cl, 1],
                    alpha=0.8, c=[cmap(idx)],
                    marker=markers[idx], label=cl)

    # # highlight test samples
    # if test_idx:
    #     X_test, y_test = X_pca[test_idx, :2], y[test_idx]
    #     plt.scatter(X_test[:, 0], X_test[:, 1],
    #                 alpha=1.0, linewidth=1, marker='o',
    #                 s=55, label='test set')

# Plot decision regions using PCA-transformed features
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined, y=y_combined, classifier=gnb, test_idx=range(len(y_train), len(y_train) + len(y_test)))
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(loc='upper left')
plt.show()

Accuracy: 0.70

在这里插入图片描述

SVM分类器

#使用SVM进行分类
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
    
from sklearn.svm import SVC

# Load the dataset
heart = pd.read_csv(r"heart.csv", sep=',')
# Select features and target
X = heart.iloc[:, 0:5]
y = heart.loc[:, 'y']
    
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

# Initialize and fit the SVM classifier
svm = SVC(kernel='linear', C=1.0, random_state=0)
svm.fit(X_train, y_train)

# Predict and print accuracy
y_pred = svm.predict(X_test)
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))

Accuracy: 0.66


# Plot decision regions using PCA-transformed features
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined, y=y_combined, classifier=svm, test_idx=range(len(y_train), len(y_train) + len(y_test)))
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(loc='upper left')
plt.show()

在这里插入图片描述

随机森林分类

# Import necessary libraries
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_graphviz
import pydotplus
from IPython.display import Image

# Load the dataset
heart = pd.read_csv(r"heart.csv", sep=',')

# Select features and target
X = heart.iloc[:, 0:5]
y = heart.loc[:, 'y']

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

# Initialize and fit the Decision Tree classifier
tree = DecisionTreeClassifier(max_depth=3, random_state=0)
tree.fit(X_train, y_train)

# Predict and print accuracy
y_pred = tree.predict(X_test)
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))

# Export the decision tree to a file
export_graphviz(tree, out_file='tree.dot', feature_names=X.columns)

# Convert the dot file to a png
graph = pydotplus.graph_from_dot_file('tree.dot')
Image(graph.create_png())

# Plot decision regions using PCA-transformed features
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined, y=y_combined, classifier=tree, test_idx=range(len(y_train), len(y_train) + len(y_test)))
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(loc='upper left')
plt.show()

Accuracy: 0.68

在这里插入图片描述

决策树分类


#绘制出决策树
from sklearn.tree import plot_tree
plt.figure(figsize=(20, 10))
plot_tree(tree, filled=True, feature_names=X.columns, class_names=['0', '1'])
plt.show()

在这里插入图片描述

原文地址：https://blog.csdn.net/2301_76574743/article/details/144000642

免责声明：本站文章内容转载自网络资源，如本站内容侵犯了原著者的合法权益，可联系本站删除。更多内容请关注自学内容网（zxcms.com）！

上一篇：【Linux】vim的使用
下一篇：Spring Boot 与 Spring Cloud Alibaba 版本兼容对照

基于python flask的网页五子棋实现，包括多种语言，可以悔棋、重新开始
这个基于 Flask 的五子棋游戏实现了一个简单而有趣的在线对战平台，支持多语言、悔棋和重新开始等功能。通过 Flask 提供的强大功能和前端交互，玩家可以方便地进行游戏，并享受一个流畅的五子棋体验。
阅读更多2024-11-27
如何通过高效的缓存策略无缝加速湖仓查询
StarRocks 可以根据当前磁盘的容量动态的对 Cache 的容量占用进行调整，保证磁盘空间尽可能被使用，同时在磁盘空间占用率较高时为导入、ETL、Spill 等任务让出更多空间，保证磁盘和系统的
阅读更多2024-11-27
麒麟系统x86安装达梦数据库
操作系统：银河麒麟V10，CPU： x86_64 架构数据库：dm8_20220915_x86_kylin10_64。
阅读更多2024-11-27
基于Springboot的心灵治愈交流平台系统的设计与实现
基于Springboot的心灵治愈交流平台系统，后端框架使用Springboot+mybatis，前端框架使用Vue+hrml，数据库使用mysql，使用B/S架构实现前台用户系统和后台管理员系统，和
阅读更多2024-11-27
数字信号处理实验报告六：数字信号处理在多音频拨号系统中的应用
通过对多音频拨号系统的分析与仿真实验，了解双音多频信号的产生、检测，包括对双音多频信号进行DFT时的参数选择等，使学生初步了解数字信号处理在实际中的使用方法和重要性。双音多频（Dual Tone Mu
阅读更多2024-11-27
Vue 3 Transition 组件教程
Vue 的 Transition 组件是一个内置的组件，专门用于处理元素或组件的进入、离开和状态变化的动画效果。它提供了一种简单而强大的方式来为元素添加过渡和动画。
阅读更多2024-11-27
Android 用 platform.pk8 和 platform.x509.pem 生成 keystore 系统签名文件
最近需要开发一个拥有系统级权限的应用，就了解了下系统应用的签名方式，这里来简单介绍下。在进行 Android 应用开发的时候，如果开发的是系统应用，那么就需要有系统签名才能正常运行，而系统应用一般是放
阅读更多2024-11-27
【Unity3D插件】Unity3D HDRP Outline高亮发光轮廓描边插件教程
最近用Unity3D的HDRP（高清渲染管线）开发项目，发现普通项目的高亮插件都不管用了，材质也不管用了。这里就不管材质升级HDRP的问题，主要分享一个在HDRP接下来，就来看一下如何使用吧。是一款可
阅读更多2024-11-27
SQL server 计算同比和环比
同比是指与去年同期相比的增长率，而环比是指与上一期相比的增长率。以下是如何在 SQL Server 中计算同比和环比的示例。•CurrentYearSales：计算 2023 年每个月的总销售额。•L
阅读更多2024-11-27
企业网络安全之OPENVPN
VPN 直译就是虚拟专用通道，是提供给企业之间或者个人与公司之间安全数据传输的隧道。虚拟私有网络（VPN）隧道是通过 Internet 隧道技术将两个不同地理位置的网络安全的连接起来的技术。当两个网络
阅读更多2024-11-27

分类算法——基于heart数据集实现

1 heart数据集——描述性统计分析

2 Cp交叉验证，选择最优的k值进行判别分析

KNN分类器

朴素贝叶斯分类器

SVM分类器

随机森林分类

决策树分类

相关文章