F-beta score
The F-beta score is a weighted harmonic mean between precision and recall, and is used to weight precision and recall differently. It is likely that one would care more about weighting precision over recall, which can be done with a lower beta
between 0 and 1. In this exercise, you will calculate the precision and recall of an MLP classifier along with the F-beta score using a beta = 0.5
.
X_train
, y_train
, X_test
, y_test
are available in your workspace, and the features have already been standardized. pandas
as pd
and sklearn
are also available in your workspace. fbeta_score()
from sklearn.metrics
is available as well.
This is a part of the course
“Predicting CTR with Machine Learning in Python”
Exercise instructions
- Split the data into training and testing data.
- Define a MLP classifier, train using
.fit()
, and predict using.predict()
. - Use implementations from
sklearn
to get the precision, recall scores, and F-beta scores.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Set up MLP classifier, train and predict
X_train, X_test, y_train, y_test = ____(
____, ____, test_size = .2, random_state = 0)
clf = ____(hidden_layer_sizes = (16, ),
max_iter = 10, random_state = 0)
y_pred = clf.____(____, _____).____(X_test)
# Evaluate precision and recall
prec = ____(y_test, ____, average = 'weighted')
recall = ____(y_test, ____, average = 'weighted')
fbeta = ____(y_test, ____, ____ = 0.5, average = 'weighted')
print("Precision: %s, Recall: %s, F-beta score: %s" %(prec, recall, fbeta))