1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
|
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Example code for TensorFlow Wide & Deep Tutorial using TF.Learn API."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
import tempfile
from six.moves import urllib
import pandas as pd
import tensorflow as tf
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"]
def maybe_download(train_data, test_data):
"""Maybe downloads training data and returns train and test file names."""
if train_data:
train_file_name = train_data
else:
train_file = tempfile.NamedTemporaryFile(delete=False)
urllib.request.urlretrieve("http://mlr.cs.umass.edu/ml/machine-learning-databases/adult/adult.data", train_file.name) # pylint: disable=line-too-long
train_file_name = train_file.name
train_file.close()
print("Training data is downloaded to %s" % train_file_name)
if test_data:
test_file_name = test_data
else:
test_file = tempfile.NamedTemporaryFile(delete=False)
urllib.request.urlretrieve("http://mlr.cs.umass.edu/ml/machine-learning-databases/adult/adult.test", test_file.name) # pylint: disable=line-too-long
test_file_name = test_file.name
test_file.close()
print("Test data is downloaded to %s" % test_file_name)
return train_file_name, test_file_name
def build_estimator(model_dir, model_type):
"""Build an estimator."""
# Sparse base columns.
gender = tf.contrib.layers.sparse_column_with_keys(column_name="gender",
keys=["female", "male"])
education = tf.contrib.layers.sparse_column_with_hash_bucket(
"education", hash_bucket_size=1000)
relationship = tf.contrib.layers.sparse_column_with_hash_bucket(
"relationship", hash_bucket_size=100)
workclass = tf.contrib.layers.sparse_column_with_hash_bucket(
"workclass", hash_bucket_size=100)
occupation = tf.contrib.layers.sparse_column_with_hash_bucket(
"occupation", hash_bucket_size=1000)
native_country = tf.contrib.layers.sparse_column_with_hash_bucket(
"native_country", hash_bucket_size=1000)
# Continuous base columns.
age = tf.contrib.layers.real_valued_column("age")
education_num = tf.contrib.layers.real_valued_column("education_num")
capital_gain = tf.contrib.layers.real_valued_column("capital_gain")
capital_loss = tf.contrib.layers.real_valued_column("capital_loss")
hours_per_week = tf.contrib.layers.real_valued_column("hours_per_week")
# Transformations.
age_buckets = tf.contrib.layers.bucketized_column(age,
boundaries=[
18, 25, 30, 35, 40, 45,
50, 55, 60, 65
])
# Wide columns and deep columns.
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(
[age_buckets, education, occupation],
hash_bucket_size=int(1e6)),
tf.contrib.layers.crossed_column([native_country, occupation],
hash_bucket_size=int(1e4))]
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,
]
if model_type == "wide":
m = tf.contrib.learn.LinearClassifier(model_dir=model_dir,
feature_columns=wide_columns)
elif model_type == "deep":
m = tf.contrib.learn.DNNClassifier(model_dir=model_dir,
feature_columns=deep_columns,
hidden_units=[100, 50])
else:
m = tf.contrib.learn.DNNLinearCombinedClassifier(
model_dir=model_dir,
linear_feature_columns=wide_columns,
dnn_feature_columns=deep_columns,
dnn_hidden_units=[100, 50],
fix_global_step_increment_bug=True)
return m
def input_fn(df):
"""Input builder function."""
# 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)
feature_cols.update(categorical_cols)
# 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_and_eval(model_dir, model_type, train_steps, train_data, test_data):
"""Train and evaluate the model."""
train_file_name, test_file_name = maybe_download(train_data, test_data)
df_train = pd.read_csv(
tf.gfile.Open(train_file_name),
names=COLUMNS,
skipinitialspace=True,
engine="python")
df_test = pd.read_csv(
tf.gfile.Open(test_file_name),
names=COLUMNS,
skipinitialspace=True,
skiprows=1,
engine="python")
# remove NaN elements
df_train = df_train.dropna(how='any', axis=0)
df_test = df_test.dropna(how='any', axis=0)
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)
model_dir = tempfile.mkdtemp() if not model_dir else model_dir
print("model directory = %s" % model_dir)
m = build_estimator(model_dir, model_type)
m.fit(input_fn=lambda: input_fn(df_train), steps=train_steps)
results = m.evaluate(input_fn=lambda: input_fn(df_test), steps=1)
for key in sorted(results):
print("%s: %s" % (key, results[key]))
FLAGS = None
def main(_):
train_and_eval(FLAGS.model_dir, FLAGS.model_type, FLAGS.train_steps,
FLAGS.train_data, FLAGS.test_data)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.register("type", "bool", lambda v: v.lower() == "true")
parser.add_argument(
"--model_dir",
type=str,
default="",
help="Base directory for output models."
)
parser.add_argument(
"--model_type",
type=str,
default="wide_n_deep",
help="Valid model types: {'wide', 'deep', 'wide_n_deep'}."
)
parser.add_argument(
"--train_steps",
type=int,
default=200,
help="Number of training steps."
)
parser.add_argument(
"--train_data",
type=str,
default="",
help="Path to the training data."
)
parser.add_argument(
"--test_data",
type=str,
default="",
help="Path to the test data."
)
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
|
