分类算法——基于heart数据集实现

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 KNeighborsClassifierX = 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 PCAdef plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):# Reduce dimensionality to 2D using PCApca = PCA(n_components=2)X_pca = pca.fit_transform(X)# setup marker generator and color mapmarkers = ('s', 'x', 'o', '^', 'v')colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')cmap = ListedColormap(colors[:len(np.unique(y))])# plot the decision surfacex1_min, x1_max = X_pca[:, 0].min() - 1, X_pca[:, 0].max() + 1x2_min, x2_max = X_pca[:, 1].min() - 1, X_pca[:, 1].max() + 1xx1, 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 samplesif 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 PCAdef plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):# Reduce dimensionality to 2D using PCApca = PCA(n_components=2)X_pca = pca.fit_transform(X)# setup marker generator and color mapmarkers = ('s', 'x', 'o', '^', 'v')colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')cmap = ListedColormap(colors[:len(np.unique(y))])# plot the decision surfacex1_min, x1_max = X_pca[:, 0].min() - 1, X_pca[:, 0].max() + 1x2_min, x2_max = X_pca[:, 1].min() - 1, X_pca[:, 1].max() + 1xx1, 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_scorefrom 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()