五一电子网站建设,mip网站,中山网站排名,公司制作网站费用数据来源是#xff1a;头条新闻数据#xff0c;经过处理之后的部分数据如下#xff1a; 首先通过交叉验证#xff0c;取选择模型#xff1a;
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.s…数据来源是头条新闻数据经过处理之后的部分数据如下 首先通过交叉验证取选择模型
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import LinearSVCfrom sklearn.model_selection import cross_val_score
models [RandomForestClassifier(n_estimators200,max_depth 3,random_state 0),LinearSVC(),MultinomialNB(),LogisticRegression(random_state0),]
cv 5
cv_df pd.DataFrame(index range(cv*len(models)))entries []for model in models:model_name model.__class__.__name__accuracies cross_val_score(model,features,labels,scoring accuracy,cv cv)for fold_idx,accuracy in enumerate(accuracies):print(model_name,fold_idx,accuracy)entries.append((model_name,fold_idx,accuracy))
print(entries[:10])#entries加入的是元组
cv_df pd.DataFrame(entries,columns [model_name,fold_idx,accuracy])
也可以将结果可视化展示
import seaborn as sns
sns.boxplot(xmodel_name,yaccuracy,data cv_df)
sns.stripplot(xmodel_name,yaccuracy,data cv_df,size 8, jitter True,edgecolor gray,linewidth 2)
plt.show()通过混淆矩阵去查看各个分类的结果
from sklearn.metrics import confusion_matrixconf_mat confusion_matrix(y_test,y_pred)fig,ax plt.subplots(figsize(10,10))
sns.heatmap(conf_mat,annot True,fmt d,xticklabels category_id_df.label_content.values,yticklabels category_id_df.label_content.values)plt.ylabel(Actual )plt.xlabel(Predicted)plt.show()
