DEEPlearning

skl4

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import numpy as np
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import KNeighborsClassifier

iris = datasets.load_iris()
iris_X = iris.data
iris_y = iris.target

#print (iris_X[:2, :])
#print(iris_y)
X_train, X_test, y_train, y_test = train_test_split(
        iris_X, iris_y, test_size = 0.3)

#print(y_train)
#会打乱数据

knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
#自动完成train,knn是已经预测好了的

print(knn.predict(X_test))
print(y_test)

y_pre = knn.predict(X_test)
print (np.sum(y_pre - y_test))
View Code

 skl5

使用数据

 1 # -*- coding: utf-8 -*-
 2 """
 3 Spyder Editor
 4 
 5 This is a temporary script file.
 6 """
 7 
 8 import numpy as np
 9 from sklearn import datasets
10 from sklearn.linear_model import LinearRegression
11 
12 loaded_data = datasets.load_boston()
13 data_X = loaded_data.data #属性
14 data_y = loaded_data.target
15 
16 model = LinearRegression()
17 model.fit(data_X, data_y)
18 
19 print (model.predict(data_X[:4,:]))
20 print (data_y[:4])
View Code

自己创建数据

 1 import numpy as np
 2 from sklearn import datasets
 3 from sklearn.linear_model import LinearRegression
 4 import matplotlib.pyplot as plt
 5 
 6 X, y = datasets.make_regression(n_samples = 100,
 7                                 n_features = 1,
 8                                 n_targets = 1,
 9                                 noise = 1)
10 
11 
12 plt.scatter(X,y)
13 plt.show()
View Code

skl6

属性

 1 from sklearn import datasets
 2 from sklearn.linear_model import LinearRegression
 3 
 4 
 5 loaded_data = datasets.load_boston()
 6 data_X = loaded_data.data
 7 data_y = loaded_data.target
 8 
 9 model = LinearRegression()
10 model.fit(data_X, data_y)
11 
12 print(model.predict(data_X[:4,:]))
13 print(model.score(data_X, data_y))
14 #0.7406
15 #R^2 coeddicient of determination
View Code

skl7

normalization

from sklearn import preprocessing

X = preprocessing.scale(X)

 1 from sklearn import preprocessing
 2 import numpy as np
 3 from sklearn.cross_validation import train_test_split
 4 from sklearn.datasets.samples_generator import make_classification
 5 from sklearn.svm import SVC
 6 import matplotlib.pyplot as plt
 7 
 8 a = np.array([[10, 2.7, 3.6],
 9              [-100, 5, -2],
10              [120, 20, 40]], dtype = np.float64)
11 #print(a)
12 #print(preprocessing.scale(a))
13 
14 X,y = make_classification(n_samples = 300, n_features = 2,
15                           n_redundant = 0, n_informative = 2,
16                           random_state = 22, n_clusters_per_class = 1, 
17                           scale = 100)
18 #plt.scatter(X[:,0], X[:,1], c=y)
19 #plt.show()
20 
21 #X = preprocessing.minmax_scale(X,feature_range = (0,1))
22 X = preprocessing.scale(X)
23 X_train, X_test,y_train,y_test = train_test_split(X, y,test_size = 0.3)
24 clf = SVC()
25 clf.fit(X_train, y_train)
26 print(clf.score(X_test, y_test))
View Code

 

 

posted @ 2017-09-23 20:45  yunyouhua  阅读(137)  评论(0)  编辑  收藏  举报