Is this the correct Estimator for Logistic Regression in TF 1.10?
There used to be a function called:
LogisticRegressor which is deprecated
In README.md file it says:
LogisticRegressor: Not supported. Instead, use binary_classification_head with a custom model_fn, or with DNNEstimator
When I look into documentation in tensorflow.org I see an example on Census data:
"We will train a logistic regression model that, given an individual's information, outputs a number between 0 and 1—this can be interpreted as the probability that the individual has an annual income of over 50,000 dollars." Which is using:
model = tf.estimator.LinearClassifier( model_dir=tempfile.mkdtemp(), feature_columns=base_columns + crossed_columns, optimizer=tf.train.FtrlOptimizer(learning_rate=0.1))
1) Is there any sample with Logistic Regression for new TF estimator API.
2) Which one would be a good dataset to do Logistic Regression?