sklearn02

1. from matplotlib.colors import ListedColormap
   This may be most useful when indexing directly into a colormap, but it can also be used to generate special colormaps for ordinary mapping.

2. from sklearn.model_selection import train_test_split
   进行数据集划分train_test_split(*arrays,**options)
   *arrays可以是列表、numpy数组、scipy稀疏矩阵或pandas数据框。

3. from sklearn.preprocessing import StandardScaler 
   StandardScaler他可以在驯良数据集上做了标准转换操作之后，把相同的转换应用到测试训练集中
   例子:
   #调用fit方法，根据已有的训练数据创建一个标准化的转换器
   scaler=StandardScaler().fit(x)
   现在比如来了一组新的样本，也想得到相同的转换

   new_x = [[-1., 1., 0.]]
   scaler.transform(new_x)

4. from sklearn.datasets import make_circles,make_moons,make_classification 

          make_circles(n_samples=100, noise=0.1):形成环形图，返回值：X (array of shape [n_samples, 2]) – The generated samples.
y (array of shape [n_samples]) – The integer labels (0 or 1) for class membership of each sample.

          make_moons(n_samples=100, noise=0.1)：形成形图，返回值：X (array of shape [n_samples, 2]) – The generated samples.
y (array of shape [n_samples]) – The integer labels (0 or 1) for class membership of each sample.

         make_classification(n_samples=100)返回值：X (array of shape [n_samples, n_features]) – The generated samples.
y (array of shape [n_samples]) – The integer labels for class membership of each sample.

5.plt.scatter(x1[:, 0], x1[:, 1], marker='o', c=y1)：maker='o'圈