# How can Tensorflow be used with Estimators to inspect a specific column of titanic dataset?

TensorflowServer Side ProgrammingProgramming

A specific column in the titanic dataset can be inspected by accessing the column-to-be-inspected and using the ‘DenseFeatures’ and converting it into a Numpy array.

We will use the Keras Sequential API, which is helpful in building a sequential model that is used to work with a plain stack of layers, where every layer has exactly one input tensor and one output tensor.

A neural network that contains at least one layer is known as a convolutional layer. We can use the Convolutional Neural Network to build learning model.

An Estimator is TensorFlow's high-level representation of a complete model. It is designed for easy scaling and asynchronous training. We will train a logistic regression model using the tf.estimator API. The model is used as a baseline for other algorithms. We use the titanic dataset with the goal of predicting passenger survival, given characteristics such as gender, age, class, etc.

## Example

print("Results of a specific column are being inspected")
age_column = feature_columns[7]
tf.keras.layers.DenseFeatures([age_column])(feature_batch).numpy()

## Output

Results of a specific column are being inspected
array([[61. ],
[17. ],
[19. ],
[55.5],
[26. ],
[20. ],
[24. ],
[ 9. ],
[31. ],
[28. ]], dtype=float32)

## Explanation

• The result of a specific feature column is inspected.
• This is done with the help of the tf.keras.layers.DenseFeatures layer.
Published on 12-Feb-2021 12:16:42