运用scikit-learn库进行主成分分析和线性判别分析

一、主成分分析

在进行数据分析之前，先对数据进行预处理。数据获取来自网站https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data。

# 读取酒数据
import pandas as pd
df_wine = pd.read_csv('wine.csv', header=None)
df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash', 
'Alcalinity of ash', 'Magnesium', 'Total phenols', 
'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins', 
'Color intensity', 'Hue', 'OD280/OD315 of diluted wines', 'Proline']

# 将数据分为训练集和测试集，并标准化
from sklearn.cross_validation import train_test_split
X, y = df_wine.iloc[:,1:], df_wine.iloc[:, 0]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 0)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.fit_transform(X_test)

# 定义决策区域函数
from matplotlib.colors import ListedColormap

def plot_decision_regions(X, y, classifier, resolution=0.02):

    # 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[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
                         np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(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())

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

from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
pca = PCA(n_components = 2)
lr = LogisticRegression()
# 对数据进行降维
X_train_pca = pca.fit_transform(X_train_std)
X_test_pca = pca.transform(X_test_std)
# 对降维后的数据进行分类
lr.fit(X_train_pca, y_train)
# 对分类结果可视化
plot_decision_regions(X_train_pca, y_train, classifier = lr)
plt.xlabel('PC 1')
plt.ylabel('PC 2')
plt.legend(loc = 'lower left')
plt.show()

# 对测试数据进行分类
plot_decision_regions(X_test_pca, y_test, classifier = lr)
plt.xlabel('PC 1')
plt.ylabel('PC 2')
plt.legend(loc = 'lower left')
plt.show()

# 保留所有主成分，并查看方差贡献率
pca = PCA(n_components = None)
X_train_pca = pca.fit_transform(X_train_std)
# 查看方差贡献率
pca.explained_variance_ratio_
# 查看特征值
pca.explained_variance_

二、线性判别分析

# 线性判别分析对数据降维
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
lda = LDA(n_components = 2)
X_train_lda = lda.fit_transform(X_train_std, y_train)
# Logistic回归对降维后的数据进行分类
lr = LogisticRegression()
lr = lr.fit(X_train_lda, y_train)
# 可视化分类后的数据
plot_decision_regions(X_train_lda, y_train, classifier = lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc = 'lower left')
plt.show()

# 对测试数据进行分类并可视化
X_test_lda = lda.fit_transform(X_test_std,y_test)
plot_decision_regions(X_test_lda,y_test,classifier = lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc = 'lower left')
plt.show()