sklearn獲得某個參數的不同取值在訓練集和測試集上的表現的曲線刻畫
阿新 • • 發佈：2018-11-01
cati from ssi plot tor atp test scores pyplot
from sklearn.svm import SVC from sklearn.datasets import make_classification import numpy as np X,y = make_classification() def plot_validation_curve(estimator,X,y,param_name="gamma", param_range=np.logspace(-6,-1,5),cv=5,scoring="accuracy"): """ 描述：獲得某個參數的不同取值在訓練集和測試集上的表現""" from sklearn.model_selection import validation_curve import matplotlib.pyplot as plt train_scores,test_scores = validation_curve(estimator=estimator, X=X, y=y, cv=cv, scoring=scoring, param_name=param_name, param_range=param_range) train_scores_mean = np.mean(train_scores, axis=1) train_scores_std = np.std(train_scores, axis=1) test_scores_mean= np.mean(test_scores, axis=1) test_scores_std = np.std(test_scores, axis=1) plt.title("Validation Curve") plt.xlabel("$\gamma$") plt.ylabel("Score") plt.ylim(0.0, 1.1) plt.semilogx(param_range,train_scores_mean,label="Training score",color="darkorange", lw=2) plt.fill_between(param_range, train_scores_mean-train_scores_std, train_scores_mean+train_scores_std, alpha=0.2, color="darkorange", lw=2) plt.semilogx(param_range, test_scores_mean, label="Cross-validation score",color="navy", lw=2) plt.fill_between(param_range, test_scores_mean - test_scores_std, test_scores_mean + test_scores_std, alpha=0.2, color="navy", lw=2) plt.legend(loc="best") plt.show() plot_validation_curve(estimator=SVC(), X=X,y=y, param_name="gamma", param_range=np.logspace(-6,-1,5),cv=5,scoring="accuracy")
sklearn獲得某個參數的不同取值在訓練集和測試集上的表現的曲線刻畫