调用分类问题
发布时间:2020-12-20 12:53:58 所属栏目:Python 来源:网络整理
导读:# !/usr/bin/python # -*- coding:utf-8 -*- import numpy as np from sklearn.linear_model import LogisticRegression import matplotlib.pyplot as plt import matplotlib as mpl from sklearn import preprocessing import pandas as pd from sklearn.pr
#!/usr/bin/python # -*- coding:utf-8 -*- import numpy as np from sklearn.linear_model import LogisticRegression import matplotlib.pyplot as plt import matplotlib as mpl from sklearn import preprocessing import pandas as pd from sklearn.preprocessing import StandardScaler from sklearn.pipeline import Pipeline def iris_type(s): it = {b‘Iris-setosa‘: 0,b‘Iris-versicolor‘: 1,b‘Iris-virginica‘: 2} return it[s] if __name__ == "__main__": path = u‘C:8.iris.data‘ # 数据文件路径 # # 路径,浮点型数据,逗号分隔,第4列使用函数iris_type单独处理 data = np.loadtxt(path,dtype=float,delimiter=‘,‘,converters={4: iris_type}) print("data",data) # 将数据的0到3列组成x,第4列得到y x,y = np.split(data,(4,),axis=1) # 为了可视化,仅使用前两列特征 x = x[:,:2] print("x:",x) print("y:",y) # # x = StandardScaler().fit_transform(x) # lr = LogisticRegression() # Logistic回归模型 # lr.fit(x,y.ravel()) # 根据数据[x,y],计算回归参数 # # 等价形式 lr = Pipeline([(‘sc‘,StandardScaler()),(‘clf‘,LogisticRegression()) ]) lr.fit(x,y.ravel()) # 画图 N,M = 500,500 # 横纵各采样多少个值 x1_min,x1_max = x[:,0].min(),x[:,0].max() # 第0列的范围 x2_min,x2_max = x[:,1].min(),1].max() # 第1列的范围 t1 = np.linspace(x1_min,x1_max,N) t2 = np.linspace(x2_min,x2_max,M) x1,x2 = np.meshgrid(t1,t2) # 生成网格采样点 x_test = np.stack((x1.flat,x2.flat),axis=1) # 测试点 # 无意义,只是为了凑另外两个维度 # x3 = np.ones(x1.size) * np.average(x[:,2]) # x4 = np.ones(x1.size) * np.average(x[:,3]) # x_test = np.stack((x1.flat,x2.flat,x3,x4),axis=1) # 测试点 cm_light = mpl.colors.ListedColormap([‘#77E0A0‘,‘#FF8080‘,‘#A0A0FF‘]) cm_dark = mpl.colors.ListedColormap([‘g‘,‘r‘,‘b‘]) y_hat = lr.predict(x_test) # 预测值 y_hat = y_hat.reshape(x1.shape) # 使之与输入的形状相同 plt.pcolormesh(x1,x2,y_hat,cmap=cm_light) # 预测值的显示 print("===="*30) print(len(x[:,0])) plt.scatter(x[:,0],1],c=np.squeeze(y),edgecolors=‘k‘,s=50,cmap=cm_dark) # 样本的显示 plt.xlabel(‘petal length‘) plt.ylabel(‘petal width‘) plt.xlim(x1_min,x1_max) plt.ylim(x2_min,x2_max) plt.grid() # plt.savefig(‘2.png‘) plt.show() # 训练集上的预测结果 y_hat = lr.predict(x) y = y.reshape(-1) result = y_hat == y print(y_hat) print(result) acc = np.mean(result) print(‘准确度: %.2f%%‘ % (100 * acc)) (编辑:李大同) 【声明】本站内容均来自网络,其相关言论仅代表作者个人观点,不代表本站立场。若无意侵犯到您的权利,请及时与联系站长删除相关内容! |