cross val

cv_1.py

import pandas as pd
from sklearn.model_selection import train_test_split,StratifiedKFold,cross_validate
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

cv_2.py

X = load_iris()["data"].copy()
y = load_iris()["target"].copy()

cv_3.py

#Splitting the data into train and test_val sets.
X_train,X_test_val,y_train,y_test_val = train_test_split(X,y,test_size=0.3,random_state=11)

#Splitting the test_val set into 'test' and 'validation' sets.
X_val,X_test,y_val,y_test = train_test_split(X_test_val,y_test_val,test_size=0.15,random_state=11)

#Initializing the logistic regression model and fitting it to the training set.
lr = LogisticRegression(random_state=11,max_iter=1000)
lr.fit(X_train,y_train)

#Predicting the validation set using the trained model and finding the accuracy score.
pred = lr.predict(X_val)
accuracy_score(y_val,pred)

cv_4.py

f_pred = lr.predict(X_test)
accuracy_score(y_test,f_pred)

cv_5.py

kfold = StratifiedKFold(n_splits=3,random_state=11,shuffle=True)

cv_6.py

cv_result = cross_validate(estimator=lr,
                      X=X_train,
                      y=y_train,
                      scoring="accuracy",
                      cv=kfold,
                      return_train_score=True)

cv_7.py

cv_result.keys()

cv_8.py

#validation set scores of the three folds
cv_result["test_score"]

cv_9.py

#mean of the validation scores
cv_result["test_score"].mean()