Login using Social Account
     Continue with GoogleLogin using your credentials
Let us predict the labels for train and test data, get the confusion matrix, and calculate the recall values.
Note:
confusion_matrix
: computes confusion matrix to evaluate the accuracy of classification.
By definition, a confusion matrix C is such that Ci,j is equal to the number of observations known to be in the group i and predicted to be in group j.
Thus in binary classification, the count of true negatives is C00, false negatives is C10, true positives is C11 and false positives is C01.
recall
is calculated by (true positives)/(true positives + false negatives).
Note that we are calculating recall value because we want to detect fraudulent credit card transactions. It might be tolerable to classify some valid transactions as fraudulent, but it is not tolerable to misclassify the fraudulent transactions as valid ones.
Store the best estimator from the gridsearchcv in lr_gridcv_best
.
lr_gridcv_best = clf.best_estimator_
Use predict
method of lr_gridcv_best
on X_test
and store the predictions in y_test_pre
.
y_test_pre = lr_gridcv_best.<< your code comes here >>(X_test)
Call the confusion_matrix
function imported from sklearn.metrics
. Pass y_test, y_test_pre
as arguments.
cnf_matrix_test = << your code comes here >>(y_test, y_test_pre)
Calculate the recall for test data predictions by the best model.
print("Recall metric in the test dataset:", (cnf_matrix_test[1,1]/(cnf_matrix_test[1,0]+cnf_matrix_test[1,1] )))
Use predict
method of lr_gridcv_best
on X_train_res
and store the predictions in y_train_pre
.
y_train_pre = lr_gridcv_best.<< your code comes here >>(X_train_res)
Call the confusion_matrix
function imported from sklearn.metrics
. Pass y_train_res, y_train_pre
as arguments.
cnf_matrix_train = << your code comes here >>(y_train_res, y_train_pre)
Calculate the recall for resampled train data predictions by the best model.
print("Recall metric in the train dataset:", (cnf_matrix_train[1,1]/(cnf_matrix_train[1,0]+cnf_matrix_train[1,1] )))
Taking you to the next exercise in seconds...
Want to create exercises like this yourself? Click here.
Note - Having trouble with the assessment engine? Follow the steps listed here
Loading comments...