为了可视化方便只使用两个特征
iris = load_iris()X = iris.data[:,:2]y = iris.target X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=666) #默认使用OVR方法进行多分类log_reg = LogisticRegression()log_reg.fit(X_train,y_train) log_reg.score(X_train,y_train)print(log_reg.predict(X_test)) [1 2 1 2 0 1 1 2 1 1 1 0 0 0 2 1 0 2 2 2 1 0 2 0 1 1 0 1 2 2 0 0 1 2 1 1 2 2]绘制决策边界
def plot_decision_boundary(model, axis): x0, x1 = np.meshgrid( np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1), np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1), ) X_new = np.c_[x0.ravel(), x1.ravel()] y_predict = model.predict(X_new) zz = y_predict.reshape(x0.shape) from matplotlib.colors import ListedColormap custom_cmap = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF']) plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap) plot_decision_boundary(log_reg,[4,8.0,1.5,4.5])plt.scatter(X[y==0,0],X[y==0,1])plt.scatter(X[y==1,0],X[y==1,1])plt.scatter(X[y==2,0],X[y==2,1]) ovo #这次不用默认参数,而是用mult..(0V0),使用这种方式则需要改变计算方式log_reg2 = LogisticRegression(multi_class='multinomial',solver='newton-cg') log_reg2.fit(X_train,y_train)log_reg2.score(X_test,y_test) 0.7894736842105263 plot_decision_boundary(log_reg2,[4,8.0,1.5,4.5])plt.scatter(X[y==0,0],X[y==0,1])plt.scatter(X[y==1,0],X[y==1,1])plt.scatter(X[y==2,0],X[y==2,1]) 使用全部特征（4个）X = iris.datay = iris.targetX_train,X_test,y_train,y_test = train_test_split(X,y,random_state=666)log_reg = LogisticRegression()log_reg.fit(X_train,y_train)log_reg.score(X_test,y_test)预测结果非常精准
1.0 OVO和OVR #OvO 和 OvRfrom sklearn.multiclass import OneVsRestClassifierovr = OneVsRestClassifier(log_reg)ovr.fit(X_train,y_train)ovr.score(X_test,y_test) 0.9736842105263158 from sklearn.multiclass import OneVsOneClassifierovo = OneVsOneClassifier(log_reg)ovo.fit(X_train,y_train)ovo.score(X_test,y_test)#ovo比ovr耗时比较长，精确度高。 1.0