zoukankan      html  css  js  c++  java
  • 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

     

  • 相关阅读:
    BZOJ 1251 序列终结者(Splay)
    ZOJ 2112 Dynamic Rankings(动态区间第 k 大+块状链表)
    POJ 2887 Big String(块状链表)
    BZOJ 1093 [ZJOI2007] 最大半连通子图(强联通缩点+DP)
    Codeforces Beta Round #13 C. Sequence (DP)
    Codeforces Round #184 (Div. 2) E. Playing with String(博弈)
    MemSQL start[c]up Round 2
    Codeforces Round #195 A B C 三题合集 (Div. 2)
    哈密尔顿回路总结
    最大团问题
  • 原文地址:https://www.cnblogs.com/yunyouhua/p/7582492.html
Copyright © 2011-2022 走看看