工具包机器学习6.docxVIP

#导入必要的工具包

import?pandas?as?pd

import?numpy?as?np

import?time

from?matplotlib?import?cm

import?matplotlib.pyplot?as?plt

#%matplotlib?inline

#读取训练数据,训练集中有42000个样本

train?=?pd.read_csv(./data/MNIST_train.csv)

y_train?=?train.label.values

X_train?=?train.drop(label,axis=1).values

#将像素值[0,255]??--?[0,1]

X_train?=?X_train?/?255.0

#?原始输入的特征维数和样本数目

print(the?shape?of?train_image:?{}.format(X_train.shape))

#显示示例图像

plt.figure(figsize=(14,12))

for?digit_num?in?range(0,64):

????plt.subplot(8,8,digit_num+1)

????grid_data?=?X_train[digit_num].reshape(28,28)??#?reshape?from?1d?to?2d?pixel?array

????plt.imshow(grid_data,?interpolation?=?none,?cmap?=?gray?)

????plt.xticks([])

????plt.yticks([])

plt.tight_layout()

#K均值聚类

from?sklearn.cluster?import?KMeans

kmeans?=?KMeans(n_clusters?=?OPT_K)

y_pred_kmeans?=?kmeans.fit_predict(X_pca)

stats?=?clusters_stats(y_pred_kmeans,?y_selected,?MAX_K)

purity?=?clusters_purity(stats)

print(Overall?purity?of?KMeans:?%f?%?purity)

#print(Plotting?the?first?2?clusters)

plot_clusters(y_pred_kmeans,?y_selected,?stats,?MAX_K)

#GMM

from?sklearn.mixture?import?GaussianMixture

gmm?=?GaussianMixture(n_components=OPT_K,?random_state=random_state)

gmm.fit(X_pca)

y_pred_gmm?=?gmm.predict(X_pca)

stats?=?clusters_stats(y_pred_gmm,?y_selected,?MAX_K)

purity?=?clusters_purity(stats)

print(Overall?purity?of?GMM:?%f?%?purity)

print(Plotting?the?first?2?clusters)

plot_clusters(y_pred_gmm,?y_selected,?stats,?MAX_K)

#层次聚类

from?sklearn.cluster?import?AgglomerativeClustering

hierarchical_cluster?=?AgglomerativeClustering(n_clusters=K_Ag,?linkage=ward)

y_pred_hierarchical?=?hierarchical_cluster.fit_predict(X_pca)

stats?=?clusters_stats(y_pred_hierarchical,?y_selected,?K_Ag)

purity?=?clusters_purity(stats)

print(Overall?purity?of?Agglomerative?Clustering:?%f?%?purity)

print(Plotting?the?first?2?clusters)

plot_clusters(y_pred_hierarchical,?y_selected,?stats,?K_Ag)

#最优参数

eps?=?distanceDec[780]

dbscan?=?DBSCAN(eps?=?eps,?min_samples?=?10)?????

#?模型拟合

dbscan.fit(X_pca)

y_pred_dbs