Demo entry 6780237

Predicting Income with the Census Income Dataset

   

Submitted by anonymous on Dec 24, 2018 at 01:50
Language: Python 3. Code size: 2.6 kB.

  age = tf.feature_column.numeric_column('age')
  education_num = tf.feature_column.numeric_column('education_num')
  capital_gain = tf.feature_column.numeric_column('capital_gain')
  capital_loss = tf.feature_column.numeric_column('capital_loss')
  hours_per_week = tf.feature_column.numeric_column('hours_per_week')

  education = tf.feature_column.categorical_column_with_vocabulary_list(
      'education', [
          'Bachelors', 'HS-grad', '11th', 'Masters', '9th', 'Some-college',
          'Assoc-acdm', 'Assoc-voc', '7th-8th', 'Doctorate', 'Prof-school',
          '5th-6th', '10th', '1st-4th', 'Preschool', '12th'])

  marital_status = tf.feature_column.categorical_column_with_vocabulary_list(
      'marital_status', [
          'Married-civ-spouse', 'Divorced', 'Married-spouse-absent',
          'Never-married', 'Separated', 'Married-AF-spouse', 'Widowed'])

  relationship = tf.feature_column.categorical_column_with_vocabulary_list(
      'relationship', [
          'Husband', 'Not-in-family', 'Wife', 'Own-child', 'Unmarried',
          'Other-relative'])

  workclass = tf.feature_column.categorical_column_with_vocabulary_list(
      'workclass', [
          'Self-emp-not-inc', 'Private', 'State-gov', 'Federal-gov',
          'Local-gov', '?', 'Self-emp-inc', 'Without-pay', 'Never-worked'])

  # To show an example of hashing:
  occupation = tf.feature_column.categorical_column_with_hash_bucket(
      'occupation', hash_bucket_size=_HASH_BUCKET_SIZE)

  # Transformations.
  age_buckets = tf.feature_column.bucketized_column(
      age, boundaries=[18, 25, 30, 35, 40, 45, 50, 55, 60, 65])

  # Wide columns and deep columns.
  base_columns = [
      education, marital_status, relationship, workclass, occupation,
      age_buckets,
  ]

  crossed_columns = [
      tf.feature_column.crossed_column(
          ['education', 'occupation'], hash_bucket_size=_HASH_BUCKET_SIZE),
      tf.feature_column.crossed_column(
          [age_buckets, 'education', 'occupation'],
          hash_bucket_size=_HASH_BUCKET_SIZE),
  ]

  wide_columns = base_columns + crossed_columns

  deep_columns = [
      age,
      education_num,
      capital_gain,
      capital_loss,
      hours_per_week,
      tf.feature_column.indicator_column(workclass),
      tf.feature_column.indicator_column(education),
      tf.feature_column.indicator_column(marital_status),
      tf.feature_column.indicator_column(relationship),
      # To show an example of embedding
      tf.feature_column.embedding_column(occupation, dimension=8),
  ]

This snippet took 0.01 seconds to highlight.

Back to the Entry List or Home.

Delete this entry (admin only).