sklearn提供的自带的数据集(make_blobs)

from sklearn.datasets import load_iris
#加载数据集
iris=load_iris()
iris.keys()　　#dict_keys(['target', 'DESCR', 'data', 'target_names', 'feature_names'])
#数据的条数和维数
n_samples,n_features=iris.data.shape
print("Number of sample:",n_samples)  #Number of sample: 150
print("Number of feature",n_features)　　#Number of feature 4
#第一个样例
print(iris.data[0])　　　　　　#[ 5.1  3.5  1.4  0.2]
print(iris.data.shape)　　　　#(150, 4)
print(iris.target.shape)　　#(150,)
print(iris.target)
"""
　　[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
　　0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
　　1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2
　　2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
　　2 2]


"""
import numpy as np
print(iris.target_names)　　#['setosa' 'versicolor' 'virginica']
np.bincount(iris.target)　　#[50 50 50]

import matplotlib.pyplot as plt
#以第3个索引为划分依据，x_index的值可以为0，1，2，3
x_index=3
color=['blue','red','green']
for label,color in zip(range(len(iris.target_names)),color):
    plt.hist(iris.data[iris.target==label,x_index],label=iris.target_names[label],color=color)

plt.xlabel(iris.feature_names[x_index])
plt.legend(loc="Upper right")
plt.show()

#画散点图，第一维的数据作为x轴和第二维的数据作为y轴
x_index=0
y_index=1
colors=['blue','red','green']
for label,color in zip(range(len(iris.target_names)),colors):
    plt.scatter(iris.data[iris.target==label,x_index],
                iris.data[iris.target==label,y_index],
                label=iris.target_names[label],
                c=color)
plt.xlabel(iris.feature_names[x_index])
plt.ylabel(iris.feature_names[y_index])
plt.legend(loc='upper left')
plt.show()

from sklearn.datasets import load_digits
digits=load_digits()
print(digits.data.shape)
import matplotlib.pyplot as plt
plt.gray()
plt.matshow(digits.images[0])
plt.show()

from sklearn.datasets import load_digits
digits=load_digits()
digits.keys()
n_samples,n_features=digits.data.shape
print((n_samples,n_features))

print(digits.data.shape)
print(digits.images.shape)

import numpy as np
print(np.all(digits.images.reshape((1797,64))==digits.data))

fig=plt.figure(figsize=(6,6))
fig.subplots_adjust(left=0,right=1,bottom=0,top=1,hspace=0.05,wspace=0.05)
#绘制数字：每张图像8*8像素点
for i in range(64):
    ax=fig.add_subplot(8,8,i+1,xticks=[],yticks=[])
    ax.imshow(digits.images[i],cmap=plt.cm.binary,interpolation='nearest')
    #用目标值标记图像
    ax.text(0,7,str(digits.target[i]))
plt.show()

from sklearn.datasets import load_svmlight_file
x_train,y_train=load_svmlight_file("/path/to/train_dataset.txt","")#如果要加在多个数据的时候，可以用逗号隔开

#生成多类单标签数据集
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_blobs
center=[[1,1],[-1,-1],[1,-1]]
cluster_std=0.3
X,labels=make_blobs(n_samples=200,centers=center,n_features=2,
                    cluster_std=cluster_std,random_state=0)
print('X.shape',X.shape)
print("labels",set(labels))

unique_lables=set(labels)
colors=plt.cm.Spectral(np.linspace(0,1,len(unique_lables)))
for k,col in zip(unique_lables,colors):
    x_k=X[labels==k]
    plt.plot(x_k[:,0],x_k[:,1],'o',markerfacecolor=col,markeredgecolor="k",
             markersize=14)
plt.title('data by make_blob()')
plt.show()

#生成用于分类的数据集
from sklearn.datasets.samples_generator import make_classification
X,labels=make_classification(n_samples=200,n_features=2,n_redundant=0,n_informative=2,
                             random_state=1,n_clusters_per_class=2)
rng=np.random.RandomState(2)
X+=2*rng.uniform(size=X.shape)

unique_lables=set(labels)
colors=plt.cm.Spectral(np.linspace(0,1,len(unique_lables)))
for k,col in zip(unique_lables,colors):
    x_k=X[labels==k]
    plt.plot(x_k[:,0],x_k[:,1],'o',markerfacecolor=col,markeredgecolor="k",
             markersize=14)
plt.title('data by make_classification()')
plt.show()

#生成球形判决界面的数据
from sklearn.datasets.samples_generator import make_circles
X,labels=make_circles(n_samples=200,noise=0.2,factor=0.2,random_state=1)
print("X.shape:",X.shape)
print("labels:",set(labels))

unique_lables=set(labels)
colors=plt.cm.Spectral(np.linspace(0,1,len(unique_lables)))
for k,col in zip(unique_lables,colors):
    x_k=X[labels==k]
    plt.plot(x_k[:,0],x_k[:,1],'o',markerfacecolor=col,markeredgecolor="k",
             markersize=14)
plt.title('data by make_moons()')
plt.show()

from sklearn.datasets.samples_generator import make_blobs
centers = [(-3, -3),(3, 3)]
cluster_std = [0.5,0.7]
X,y = make_blobs(n_samples=1000, centers=centers,n_features=2, random_state=0, cluster_std=cluster_std)

%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.style.use('ggplot')
plt.figure(figsize=(20,5));
plt.subplot(1, 2, 1 );
plt.scatter(X[:,0] , X[:,1],  c = y, alpha = 0.7);
plt.subplot(1, 2, 2);
plt.hist(y)
plt.show()

from sklearn.datasets.samples_generator import make_blobs
centers = [(-3, -3),(0,0),(3, 3)]
cluster_std = [0.5,0.7,0.5]
X,y = make_blobs(n_samples=2000, centers=centers,n_features=2, random_state=0, cluster_std=cluster_std)

%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.style.use('ggplot')
plt.figure(figsize=(20,5));
plt.subplot(1, 2, 1 );
plt.scatter(X[:,0] , X[:,1],  c = y, alpha = 0.7);
plt.subplot(1, 2, 2);
plt.hist(y)
plt.show()

from sklearn.datasets.samples_generator import make_classification
X,y = make_classification(n_samples=2000, n_features=10, n_informative=4, n_classes=4, random_state=0)

%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.style.use('ggplot')
plt.figure(figsize=(20,5));
plt.subplot(1, 2, 1 );
plt.scatter(X[:,0] , X[:,1],  c = y, alpha = 0.7);
plt.subplot(1, 2, 2);
plt.hist(y)
plt.show()

from sklearn.datasets.samples_generator import make_gaussian_quantiles
X,y = make_gaussian_quantiles(mean=(1,1), cov=1.0, n_samples=1000, n_features=2, n_classes=2, shuffle=True, random_state=None)

%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.style.use('ggplot')
plt.figure(figsize=(20,5));
plt.subplot(1, 2, 1 );
plt.scatter(X[:,0] , X[:,1],  c = y, alpha = 0.7);
plt.subplot(1, 2, 2);
plt.hist(y)
plt.show()

from sklearn.datasets.samples_generator import make_hastie_10_2
X,y = make_hastie_10_2(n_samples=1000, random_state=None)

%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.style.use('ggplot')
plt.figure(figsize=(20,5));
plt.subplot(1, 2, 1 );
plt.scatter(X[:,0] , X[:,1],  c = y, alpha = 0.7);
plt.subplot(1, 2, 2);
plt.hist(y)
plt.show()