In [ ]:

    

# TensorFlow Wide & Deep Learning Tutorial

#python wide_n_deep_tutorial.py --model_type=wide_n_deep


    

In [ ]:

    

wide_columns = [
  gender, native_country, education, occupation, workclass, relationship, age_buckets,
  tf.contrib.layers.crossed_column([education, occupation], hash_bucket_size=int(1e4)),
  tf.contrib.layers.crossed_column([native_country, occupation], hash_bucket_size=int(1e4)),
  tf.contrib.layers.crossed_column([age_buckets, education, occupation], hash_bucket_size=int(1e6))]


    

In [ ]:

    

deep_columns = [
  tf.contrib.layers.embedding_column(workclass, dimension=8),
  tf.contrib.layers.embedding_column(education, dimension=8),
  tf.contrib.layers.embedding_column(gender, dimension=8),
  tf.contrib.layers.embedding_column(relationship, dimension=8),
  tf.contrib.layers.embedding_column(native_country, dimension=8),
  tf.contrib.layers.embedding_column(occupation, dimension=8),
  age, education_num, capital_gain, capital_loss, hours_per_week]


    

In [ ]:

    

import tempfile
model_dir = tempfile.mkdtemp()
m = tf.contrib.learn.DNNLinearCombinedClassifier(
    model_dir=model_dir,
    linear_feature_columns=wide_columns,
    dnn_feature_columns=deep_columns,
    dnn_hidden_units=[100, 50])


    

In [ ]:

    

import pandas as pd
import urllib

# Define the column names for the data sets.
COLUMNS = ["age", "workclass", "fnlwgt", "education", "education_num",
  "marital_status", "occupation", "relationship", "race", "gender",
  "capital_gain", "capital_loss", "hours_per_week", "native_country", "income_bracket"]
LABEL_COLUMN = 'label'
CATEGORICAL_COLUMNS = ["workclass", "education", "marital_status", "occupation",
                       "relationship", "race", "gender", "native_country"]
CONTINUOUS_COLUMNS = ["age", "education_num", "capital_gain", "capital_loss",
                      "hours_per_week"]

# Download the training and test data to temporary files.
# Alternatively, you can download them yourself and change train_file and
# test_file to your own paths.
train_file = tempfile.NamedTemporaryFile()
test_file = tempfile.NamedTemporaryFile()
urllib.urlretrieve("http://mlr.cs.umass.edu/ml/machine-learning-databases/adult/adult.data", train_file.name)
urllib.urlretrieve("http://mlr.cs.umass.edu/ml/machine-learning-databases/adult/adult.test", test_file.name)

# Read the training and test data sets into Pandas dataframe.
df_train = pd.read_csv(train_file, names=COLUMNS, skipinitialspace=True)
df_test = pd.read_csv(test_file, names=COLUMNS, skipinitialspace=True, skiprows=1)
df_train[LABEL_COLUMN] = (df_train['income_bracket'].apply(lambda x: '>50K' in x)).astype(int)
df_test[LABEL_COLUMN] = (df_test['income_bracket'].apply(lambda x: '>50K' in x)).astype(int)

def input_fn(df):
  # Creates a dictionary mapping from each continuous feature column name (k) to
  # the values of that column stored in a constant Tensor.
  continuous_cols = {k: tf.constant(df[k].values)
                     for k in CONTINUOUS_COLUMNS}
  # Creates a dictionary mapping from each categorical feature column name (k)
  # to the values of that column stored in a tf.SparseTensor.
  categorical_cols = {k: tf.SparseTensor(
      indices=[[i, 0] for i in range(df[k].size)],
      values=df[k].values,
      dense_shape=[df[k].size, 1])
                      for k in CATEGORICAL_COLUMNS}
  # Merges the two dictionaries into one.
  feature_cols = dict(continuous_cols.items() + categorical_cols.items())
  # Converts the label column into a constant Tensor.
  label = tf.constant(df[LABEL_COLUMN].values)
  # Returns the feature columns and the label.
  return feature_cols, label

def train_input_fn():
  return input_fn(df_train)

def eval_input_fn():
  return input_fn(df_test)


    

In [ ]:

    

m.fit(input_fn=train_input_fn, steps=200)
results = m.evaluate(input_fn=eval_input_fn, steps=1)
for key in sorted(results):
    print("%s: %s" % (key, results[key]))