How to create function columns for the TensorFlow classifier

Question

I have a very simple binary classification dataset in a csv file that looks like this:

"feature1","feature2","label"
1,0,1
0,1,0
...

where the column "label"indicates the class (1 is positive, 0 is negative). The number of functions is actually quite large, but it does not matter for this question.

Here is how I read the data:

train = pandas.read_csv(TRAINING_FILE)
y_train, X_train = train['label'], train[['feature1', 'feature2']].fillna(0)

test = pandas.read_csv(TEST_FILE)
y_test, X_test = test['label'], test[['feature1', 'feature2']].fillna(0)

I want to run tensorflow.contrib.learn.LinearClassifier, and tensorflow.contrib.learn.DNNClassifierfrom these data. For example, I initialize DNN as follows:

classifier = DNNClassifier(hidden_units=[3, 5, 3],
                               n_classes=2,
                               feature_columns=feature_columns, # ???
                               activation_fn=nn.relu,
                               enable_centered_bias=False,
                               model_dir=MODEL_DIR_DNN)

So, how exactly should I create feature_columnswhen all functions are binary as well (0 or 1 are the only possible values)?

Here is a learning model:

classifier.fit(X_train.values,
                   y_train.values,
                   batch_size=dnn_batch_size,
                   steps=dnn_steps)

A solution with replacing parameters fit()with an input function will also be great.

Thank!

PS I am using TensorFlow version 1.0.1

Answer 1

, :

feature_columns = tf.contrib.learn.infer_real_valued_columns_from_input(X_train)

-, infer_real_valued_columns_from_input() .