sklearn tsne

采用tsne画数据集的分布图

from sklearn.manifold import TSNE
import numpy as np
import time
import matplotlib.pyplot as plt
import pandas as pd

#     fig = plt.figure()
#     ax = fig.add_subplot(1, 1, 1, projection='3d')
#     for i in range(X.shape[0]):
#         ax.text(X[i, 0], X[i, 1], X[i, 2], str(digits.target[i]),
#                 color=plt.cm.Set1(y[i] / 10.),
#                 fontdict={'weight': 'bold', 'size': 9})
#     if title is not None:
#         plt.title(title)


name = ['adenocarcinoma']
for j in range(len(name)):
    dataset = pd.read_csv('C:/Users/' + name[j] + '.csv', header=None)
    print(name[j], dataset.shape)
    shape = dataset.shape[1] - 1
    shape1 = dataset.shape[0]
    x = dataset.iloc[:, :-1].values
    y = dataset.iloc[:, -1].values
    tsne = TSNE(n_components=2, init='pca', random_state=0)
    t0 = time.time()
    result = tsne.fit_transform(x)
    print(result.shape)
    x_min, x_max = np.min(result, 0), np.max(result, 0)  # 每列中的最小值和最大值
    data = (result - x_min) / (x_max - x_min)  # 归一化
    # print(x_min)
    # print(x_max)
    print('----')
    # print(data)
    # 3d图像
    # fig = plt.figure()
    # ax = fig.add_subplot(1, 1, 1, projection='3d')
    # for i in range(data.shape[0]):
    #     ax.text(data[i, 0], data[i, 1], data[i, 2], str(y[i]),
    #             color=plt.cm.Set1(y[i] / 10.),
    #             fontdict={'weight': 'bold', 'size': 9})
    # 2d图像
    fig = plt.figure(figsize=(10, 7))
    markers = ["+", "o", "<", ">", "*", ".", ",", "p", "3"]
    for i in range(data.shape[0]):
        plt.text(data[i, 0], data[i, 1], str(y[i]), color=plt.cm.Set1(y[i]),
                 fontdict={'weight': 'bold', 'size': 9})
    plt.xlim()
    plt.ylim()
    plt.title(name[j])
    plt.savefig('C:/Users/tsne_' + name[j] + '.png', dpi=500)