sklearn 机器学习基本用法

# # 科学计算模块
# import numpy as np
# import pandas as pd
# # 绘图模块
# import matplotlib as mpl
# import matplotlib.pyplot as plt
# from sklearn.linear_model import LinearRegression
# from sklearn import datasets
# from sklearn.model_selection import train_test_split
# from sklearn.neighbors import KNeighborsClassifier
# from sklearn import preprocessing
# from sklearn.svm import SVC
# #栾尾花数据预测
# # X,y = datasets.load_iris(return_X_y=True)
# # x_train ,x_test,y_train,y_test=train_test_split(X,y,test_size=0.3)
# # knn=KNeighborsClassifier()
# # knn.fit(x_train,y_train)
# # print(knn.predict(x_test))
# # print(y_test)
# #knn.coef_   斜率
# #knn.intercept_ 截距      y=0.3x+6
# 
# #datasets 自定义数据
# # X,y = datasets.make_regression(n_samples=100,n_features=2,n_targets=2,noise=2)
# # plt.scatter(X,y)
# # plt.show()
# 
# #标准数字化
# # X,y=datasets.make_classification(n_samples=300,n_features=2,n_redundant=0,n_informative=2,random_state=22,n_clusters_per_class=1,scale=100)
# # # sp=np.array(X).shape
# # print(np.array(y).shape)
# # # plt.scatter(X[:,0],X[:,1],c=y)
# # # plt.show()
# # X=preprocessing.scale(X)  #因为数据差距比较大，此处将数据标准化，可增加预测相似度
# # x_train,x_test,y_train,y_test=train_test_split(X,y,test_size=0.3)
# # clf=SVC()
# # clf.fit(x_train,y_train)
# # print(clf.score(x_test,y_test))  #评估预测集，与预测集的相似度，相当于predict 与 y_test 对比度
# 
# 
# #栾尾花数据交叉验证
# from sklearn.model_selection import cross_val_score     #交叉验证可选择好用的model ,参数等等
# X,y = datasets.load_iris(return_X_y=True)
# x_train ,x_test,y_train,y_test=train_test_split(X,y,test_size=0.3)
# # knn=KNeighborsClassifier(n_neighbors=5)
# # scores=cross_val_score(knn,X,y,cv=5,scoring='accuracy')
# # print(scores.mean())    #此处是将数据分成5组取出5组的概率，最后取均值
# 
# #此处判断k值在什么区间这个概率较大
# # k_range=range(2,31)
# # k_scores=[]
# # for k in k_range:
# #     knn = KNeighborsClassifier(n_neighbors=k)
# #     #scores = cross_val_score(knn, X, y, cv=10, scoring='accuracy') #for classfication   选择概率大的
#     # loss = -cross_val_score(knn, X, y, cv=10, scoring='mean_squared_error') #for regression 选择误差小的
#     # k_scores.append(scores.mean())
# #
# # plt.plot(k_range,k_scores)
# # plt.show()
# 
# import pickle
# #保存读取model.fit() 数据
# clf=SVC()
# iris=datasets.load_iris()
# X,y=iris.data,iris.target
# clf.fit(X,y)
# #
# # # pickle.dump()
# # with open('./model_iris' ,'wb') as ff:
# #     pickle.dump(clf, ff)
# #
# # with open('./model_iris', 'rb') as ff:
# #     clf2=pickle.load(ff)
# #     print(clf2.predict([X[0:1]]))
# 
# import joblib
# joblib.dump(clf,'./model_iris')
# clf3=joblib.load('./model_iris')
# print(clf3.predict([X[0:1]]))

学习链接

11 Save_哔哩哔哩_bilibili