通过学习曲线识别过拟合和欠拟合

from sklearn.model_selection import learning_curve

#The function below builds the model and returns cross validation scores, train score and learning curve data def learn_curve(X,y,c): ''' param X: Matrix of input featuresparam y: Vector of Target/Labelc: Inverse Regularization variable to control overfitting (high value causes overfitting, low value causes underfitting)''' '''We aren't splitting the data into train and test because we will use StratifiedKFoldCV.KFold CV is a preferred method compared to hold out CV, since the model is tested on all the examples.Hold out CV is preferred when the model takes too long to train and we have a huge test set that truly represents the universe'''  le = LabelEncoder() # Label encoding the target sc = StandardScaler() # Scaling the input features y = le.fit_transform(y)#Label Encoding the target log_reg = LogisticRegression(max_iter=200,random_state=11,C=c) # LogisticRegression model # Pipeline with scaling and classification as steps, must use a pipelne since we are using KFoldCV lr = Pipeline(steps=(['scaler',sc],['classifier',log_reg]))   cv = StratifiedKFold(n_splits=5,random_state=11,shuffle=True) # Creating a StratifiedKFold object with 5 folds cv_scores = cross_val_score(lr,X,y,scoring="accuracy",cv=cv) # Storing the CV scores (accuracy) of each fold   lr.fit(X,y) # Fitting the model  train_score = lr.score(X,y) # Scoring the model on train set  #Building the learning curve train_size,train_scores,test_scores =learning_curve(estimator=lr,X=X,y=y,cv=cv,scoring="accuracy",random_state=11) train_scores = 1-np.mean(train_scores,axis=1)#converting the accuracy score to misclassification rate test_scores = 1-np.mean(test_scores,axis=1)#converting the accuracy score to misclassification rate lc =pd.DataFrame({"Training_size":train_size,"Training_loss":train_scores,"Validation_loss":test_scores}).melt(id_vars="Training_size") return {"cv_scores":cv_scores,"train_score":train_score,"learning_curve":lc}

lc = learn_curve(X,y,1) print(f'Cross Validation Accuracies:\n{"-"*25}\n{list(lc["cv_scores"])}\n\n\ Mean Cross Validation Accuracy:\n{"-"*25}\n{np.mean(lc["cv_scores"])}\n\n\ Standard Deviation of Deep HUB Cross Validation Accuracy:\n{"-"*25}\n{np.std(lc["cv_scores"])}\n\n\ Training Accuracy:\n{"-"*15}\n{lc["train_score"]}\n\n') sns.lineplot(data=lc["learning_curve"],x="Training_size",y="value",hue="variable") plt.title("Learning Curve of Good Fit Model") plt.ylabel("Misclassification Rate/Loss");

lc = learn_curve(X,y,10000) print(f'Cross Validation Accuracies:\n{"-"*25}\n{list(lc["cv_scores"])}\n\n\ Mean Cross Validation Deep HUB Accuracy:\n{"-"*25}\n{np.mean(lc["cv_scores"])}\n\n\ Standard Deviation of Cross Validation Accuracy:\n{"-"*25}\n{np.std(lc["cv_scores"])} (High Variance)\n\n\ Training Accuracy:\n{"-"*15}\n{lc["train_score"]}\n\n') sns.lineplot(data=lc["learning_curve"],x="Training_size",y="value",hue="variable") plt.title("Learning Curve of an Overfit Model") plt.ylabel("Misclassification Rate/Loss");

lc = learn_curve(X,y,1/10000) print(f'Cross Validation Accuracies:\n{"-"*25}\n{list(lc["cv_scores"])}\n\n\ Mean Cross Validation Accuracy:\n{"-"*25}\n{np.mean(lc["cv_scores"])}\n\n\ Standard Deviation of Cross Validation Accuracy:\n{"-"*25}\n{np.std(lc["cv_scores"])} (Low variance)\n\n\ Training Deep HUB Accuracy:\n{"-"*15}\n{lc["train_score"]}\n\n') sns.lineplot(data=lc["learning_curve"],x="Training_size",y="value",hue="variable") plt.title("Learning Curve of an Underfit Model") plt.ylabel("Misclassification Rate/Loss");