Skip to content

GitLab

"src/vscode:/vscode.git/clone" did not exist on "6e58fcedf930b5f8307c5e330ad404a41883e5db"
Commit f9ac9618 authored by Hongkun Yu's avatar Hongkun Yu Committed by A. Unique TensorFlower
Browse files

Remove this r1 folder from the master branch in June, 2020. 

PiperOrigin-RevId: 317772122
parent d4f5c193
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 1135 deletions
official/r1/utils/tpu_test.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2018 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.
# ==============================================================================
"""Test TPU optimized matmul embedding."""
import numpy as np
import tensorflow as tf
from official.r1.utils import tpu as tpu_utils
TEST_CASES = [
dict(embedding_dim=256, vocab_size=1000, sequence_length=64,
batch_size=32, seed=54131),
dict(embedding_dim=8, vocab_size=15, sequence_length=12,
batch_size=256, seed=536413),
dict(embedding_dim=2048, vocab_size=512, sequence_length=50,
batch_size=8, seed=35124)
]
class TPUBaseTester(tf.test.TestCase):
def construct_embedding_and_values(self, embedding_dim, vocab_size,
sequence_length, batch_size, seed):
np.random.seed(seed)
embeddings = np.random.random(size=(vocab_size, embedding_dim))
embedding_table = tf.convert_to_tensor(value=embeddings, dtype=tf.float32)
tokens = np.random.randint(low=1, high=vocab_size-1,
size=(batch_size, sequence_length))
for i in range(batch_size):
tokens[i, np.random.randint(low=0, high=sequence_length-1):] = 0
values = tf.convert_to_tensor(value=tokens, dtype=tf.int32)
mask = tf.cast(tf.not_equal(values, 0), dtype=tf.float32)
return embedding_table, values, mask
def _test_embedding(self, embedding_dim, vocab_size,
sequence_length, batch_size, seed):
"""Test that matmul embedding matches embedding lookup (gather)."""
with self.test_session():
embedding_table, values, mask = self.construct_embedding_and_values(
embedding_dim=embedding_dim,
vocab_size=vocab_size,
sequence_length=sequence_length,
batch_size=batch_size,
seed=seed
)
embedding = (tf.nn.embedding_lookup(params=embedding_table, ids=values) *
tf.expand_dims(mask, -1))
matmul_embedding = tpu_utils.embedding_matmul(
embedding_table=embedding_table, values=values, mask=mask)
self.assertAllClose(embedding, matmul_embedding)
def _test_masking(self, embedding_dim, vocab_size,
sequence_length, batch_size, seed):
"""Test that matmul embedding properly zeros masked positions."""
with self.test_session():
embedding_table, values, mask = self.construct_embedding_and_values(
embedding_dim=embedding_dim,
vocab_size=vocab_size,
sequence_length=sequence_length,
batch_size=batch_size,
seed=seed
)
matmul_embedding = tpu_utils.embedding_matmul(
embedding_table=embedding_table, values=values, mask=mask)
self.assertAllClose(matmul_embedding,
matmul_embedding * tf.expand_dims(mask, -1))
def test_embedding_0(self):
self._test_embedding(**TEST_CASES[0])
def test_embedding_1(self):
self._test_embedding(**TEST_CASES[1])
def test_embedding_2(self):
self._test_embedding(**TEST_CASES[2])
def test_masking_0(self):
self._test_masking(**TEST_CASES[0])
def test_masking_1(self):
self._test_masking(**TEST_CASES[1])
def test_masking_2(self):
self._test_masking(**TEST_CASES[2])
if __name__ == "__main__":
tf.test.main()
official/r1/wide_deep/README.md deleted 100644 → 0
View file @ d4f5c193
![No Maintenance Intended](https://img.shields.io/badge/No%20Maintenance%20Intended-%E2%9C%95-red.svg)
![TensorFlow Requirement: 1.x](https://img.shields.io/badge/TensorFlow%20Requirement-1.x-brightgreen)
![TensorFlow 2 Not Supported](https://img.shields.io/badge/TensorFlow%202%20Not%20Supported-%E2%9C%95-red.svg)
# Predicting Income with the Census Income Dataset
The implementation is based on TensorFlow 1.x.
## Overview
The [Census Income Data Set](https://archive.ics.uci.edu/ml/datasets/Census+Income) contains over 48,000 samples with attributes including age, occupation, education, and income (a binary label, either `>50K` or `<=50K`). The dataset is split into roughly 32,000 training and 16,000 testing samples.
Here, we use the [wide and deep model](https://research.googleblog.com/2016/06/wide-deep-learning-better-together-with.html) to predict the income labels. The **wide model** is able to memorize interactions with data with a large number of features but not able to generalize these learned interactions on new data. The **deep model** generalizes well but is unable to learn exceptions within the data. The **wide and deep model** combines the two models and is able to generalize while learning exceptions.
For the purposes of this example code, the Census Income Data Set was chosen to allow the model to train in a reasonable amount of time. You'll notice that the deep model performs almost as well as the wide and deep model on this dataset. The wide and deep model truly shines on larger data sets with high-cardinality features, where each feature has millions/billions of unique possible values (which is the specialty of the wide model).
Finally, a key point. As a modeler and developer, think about how this dataset is used and the potential benefits and harm a model's predictions can cause. A model like this could reinforce societal biases and disparities. Is a feature relevant to the problem you want to solve, or will it introduce bias? For more information, read about [ML fairness](https://developers.google.com/machine-learning/fairness-overview/).
---
The code sample in this directory uses the high level `tf.estimator.Estimator` API. This API is great for fast iteration and quickly adapting models to your own datasets without major code overhauls. It allows you to move from single-worker training to distributed training, and it makes it easy to export model binaries for prediction.
The input function for the `Estimator` uses `tf.contrib.data.TextLineDataset`, which creates a `Dataset` object. The `Dataset` API makes it easy to apply transformations (map, batch, shuffle, etc.) to the data. [Read more here](https://www.tensorflow.org/guide/datasets).
The `Estimator` and `Dataset` APIs are both highly encouraged for fast development and efficient training.
## Running the code
First make sure you've [added the models folder to your Python path](/official/#running-the-models); otherwise you may encounter an error like `ImportError: No module named official.wide_deep`.
### Setup
The [Census Income Data Set](https://archive.ics.uci.edu/ml/datasets/Census+Income) that this sample uses for training is hosted by the [UC Irvine Machine Learning Repository](https://archive.ics.uci.edu/ml/datasets/). We have provided a script that downloads and cleans the necessary files.
```
python census_dataset.py
```
This will download the files to `/tmp/census_data`. To change the directory, set the `--data_dir` flag.
### Training
You can run the code locally as follows:
```
python census_main.py
```
The model is saved to `/tmp/census_model` by default, which can be changed using the `--model_dir` flag.
To run the *wide* or *deep*-only models, set the `--model_type` flag to `wide` or `deep`. Other flags are configurable as well; see `census_main.py` for details.
The final accuracy should be over 83% with any of the three model types.
You can also experiment with `-inter` and `-intra` flag to explore inter/intra op parallelism for potential better performance as follows:
```
python census_main.py --inter=<int> --intra=<int>
```
Please note the above optional inter/intra op does not affect model accuracy. These are TensorFlow framework configurations that only affect execution time.
For more details regarding the above inter/intra flags, please refer to [Optimizing_for_CPU](https://www.tensorflow.org/performance/performance_guide#optimizing_for_cpu) or [TensorFlow config.proto source code](https://github.com/tensorflow/tensorflow/blob/26b4dfa65d360f2793ad75083c797d57f8661b93/tensorflow/core/protobuf/config.proto#L165).
### TensorBoard
Run TensorBoard to inspect the details about the graph and training progression.
```
tensorboard --logdir=/tmp/census_model
```
## Inference with SavedModel
You can export the model into Tensorflow [SavedModel](https://www.tensorflow.org/guide/saved_model) format by using the argument `--export_dir`:
```
python census_main.py --export_dir /tmp/wide_deep_saved_model
```
After the model finishes training, use [`saved_model_cli`](https://www.tensorflow.org/guide/saved_model#cli_to_inspect_and_execute_savedmodel) to inspect and execute the SavedModel.
Try the following commands to inspect the SavedModel:
**Replace `${TIMESTAMP}` with the folder produced (e.g. 1524249124)**
```
# List possible tag_sets. Only one metagraph is saved, so there will be one option.
saved_model_cli show --dir /tmp/wide_deep_saved_model/${TIMESTAMP}/
# Show SignatureDefs for tag_set=serve. SignatureDefs define the outputs to show.
saved_model_cli show --dir /tmp/wide_deep_saved_model/${TIMESTAMP}/ \
--tag_set serve --all
```
### Inference
Let's use the model to predict the income group of two examples:
```
saved_model_cli run --dir /tmp/wide_deep_saved_model/${TIMESTAMP}/ \
--tag_set serve --signature_def="predict" \
--input_examples='examples=[{"age":[46.], "education_num":[10.], "capital_gain":[7688.], "capital_loss":[0.], "hours_per_week":[38.]}, {"age":[24.], "education_num":[13.], "capital_gain":[0.], "capital_loss":[0.], "hours_per_week":[50.]}]'
```
This will print out the predicted classes and class probabilities. Class 0 is the <=50k group and 1 is the >50k group.
## Additional Links
If you are interested in distributed training, take a look at [Distributed TensorFlow](https://www.tensorflow.org/deploy/distributed).
You can also [run this model on Cloud ML Engine](https://cloud.google.com/ml-engine/docs/getting-started-training-prediction), which provides [hyperparameter tuning](https://cloud.google.com/ml-engine/docs/getting-started-training-prediction#hyperparameter_tuning) to maximize your model's results and enables [deploying your model for prediction](https://cloud.google.com/ml-engine/docs/getting-started-training-prediction#deploy_a_model_to_support_prediction).
official/r1/wide_deep/census_dataset.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2017 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.
# ==============================================================================
"""Download and clean the Census Income Dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
# pylint: disable=wrong-import-order
from absl import app as absl_app
from absl import flags
from six.moves import urllib
from six.moves import zip
import tensorflow.compat.v1 as tf
# pylint: enable=wrong-import-order
from official.utils.flags import core as flags_core
DATA_URL = 'https://archive.ics.uci.edu/ml/machine-learning-databases/adult'
TRAINING_FILE = 'adult.data'
TRAINING_URL = '%s/%s' % (DATA_URL, TRAINING_FILE)
EVAL_FILE = 'adult.test'
EVAL_URL = '%s/%s' % (DATA_URL, EVAL_FILE)
_CSV_COLUMNS = [
'age', 'workclass', 'fnlwgt', 'education', 'education_num',
'marital_status', 'occupation', 'relationship', 'race', 'gender',
'capital_gain', 'capital_loss', 'hours_per_week', 'native_country',
'income_bracket'
]
_CSV_COLUMN_DEFAULTS = [[0], [''], [0], [''], [0], [''], [''], [''], [''], [''],
[0], [0], [0], [''], ['']]
_HASH_BUCKET_SIZE = 1000
_NUM_EXAMPLES = {
'train': 32561,
'validation': 16281,
}
def _download_and_clean_file(filename, url):
"""Downloads data from url, and makes changes to match the CSV format."""
temp_file, _ = urllib.request.urlretrieve(url)
with tf.gfile.Open(temp_file, 'r') as temp_eval_file:
with tf.gfile.Open(filename, 'w') as eval_file:
for line in temp_eval_file:
line = line.strip()
line = line.replace(', ', ',')
if not line or ',' not in line:
continue
if line[-1] == '.':
line = line[:-1]
line += '\n'
eval_file.write(line)
tf.gfile.Remove(temp_file)
def download(data_dir):
"""Download census data if it is not already present."""
tf.gfile.MakeDirs(data_dir)
training_file_path = os.path.join(data_dir, TRAINING_FILE)
if not tf.gfile.Exists(training_file_path):
_download_and_clean_file(training_file_path, TRAINING_URL)
eval_file_path = os.path.join(data_dir, EVAL_FILE)
if not tf.gfile.Exists(eval_file_path):
_download_and_clean_file(eval_file_path, EVAL_URL)
def build_model_columns():
"""Builds a set of wide and deep feature columns."""
# Continuous variable columns
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),
]
return wide_columns, deep_columns
def input_fn(data_file, num_epochs, shuffle, batch_size):
"""Generate an input function for the Estimator."""
assert tf.gfile.Exists(data_file), (
'%s not found. Please make sure you have run census_dataset.py and '
'set the --data_dir argument to the correct path.' % data_file)
def parse_csv(value):
tf.logging.info('Parsing {}'.format(data_file))
columns = tf.decode_csv(value, record_defaults=_CSV_COLUMN_DEFAULTS)
features = dict(list(zip(_CSV_COLUMNS, columns)))
labels = features.pop('income_bracket')
classes = tf.equal(labels, '>50K') # binary classification
return features, classes
# Extract lines from input files using the Dataset API.
dataset = tf.data.TextLineDataset(data_file)
if shuffle:
dataset = dataset.shuffle(buffer_size=_NUM_EXAMPLES['train'])
dataset = dataset.map(parse_csv, num_parallel_calls=5)
# We call repeat after shuffling, rather than before, to prevent separate
# epochs from blending together.
dataset = dataset.repeat(num_epochs)
dataset = dataset.batch(batch_size)
return dataset
def define_data_download_flags():
"""Add flags specifying data download arguments."""
flags.DEFINE_string(
name="data_dir", default="/tmp/census_data/",
help=flags_core.help_wrap(
"Directory to download and extract data."))
def main(_):
download(flags.FLAGS.data_dir)
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
define_data_download_flags()
absl_app.run(main)
official/r1/wide_deep/census_main.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2018 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.
# ==============================================================================
"""Train DNN on census income dataset."""
import os
from absl import app as absl_app
from absl import flags
import tensorflow.compat.v1 as tf
from official.r1.utils.logs import logger
from official.r1.wide_deep import census_dataset
from official.r1.wide_deep import wide_deep_run_loop
from official.utils.flags import core as flags_core
def define_census_flags():
wide_deep_run_loop.define_wide_deep_flags()
flags.adopt_module_key_flags(wide_deep_run_loop)
flags_core.set_defaults(data_dir='/tmp/census_data',
model_dir='/tmp/census_model',
train_epochs=40,
epochs_between_evals=2,
inter_op_parallelism_threads=0,
intra_op_parallelism_threads=0,
batch_size=40)
def build_estimator(model_dir, model_type, model_column_fn, inter_op, intra_op):
"""Build an estimator appropriate for the given model type."""
wide_columns, deep_columns = model_column_fn()
hidden_units = [100, 75, 50, 25]
# Create a tf.estimator.RunConfig to ensure the model is run on CPU, which
# trains faster than GPU for this model.
run_config = tf.estimator.RunConfig().replace(
session_config=tf.ConfigProto(device_count={'GPU': 0},
inter_op_parallelism_threads=inter_op,
intra_op_parallelism_threads=intra_op))
if model_type == 'wide':
return tf.estimator.LinearClassifier(
model_dir=model_dir,
feature_columns=wide_columns,
config=run_config)
elif model_type == 'deep':
return tf.estimator.DNNClassifier(
model_dir=model_dir,
feature_columns=deep_columns,
hidden_units=hidden_units,
config=run_config)
else:
return tf.estimator.DNNLinearCombinedClassifier(
model_dir=model_dir,
linear_feature_columns=wide_columns,
dnn_feature_columns=deep_columns,
dnn_hidden_units=hidden_units,
config=run_config)
def run_census(flags_obj):
"""Construct all necessary functions and call run_loop.
Args:
flags_obj: Object containing user specified flags.
"""
if flags_obj.download_if_missing:
census_dataset.download(flags_obj.data_dir)
train_file = os.path.join(flags_obj.data_dir, census_dataset.TRAINING_FILE)
test_file = os.path.join(flags_obj.data_dir, census_dataset.EVAL_FILE)
# Train and evaluate the model every `flags.epochs_between_evals` epochs.
def train_input_fn():
return census_dataset.input_fn(
train_file, flags_obj.epochs_between_evals, True, flags_obj.batch_size)
def eval_input_fn():
return census_dataset.input_fn(test_file, 1, False, flags_obj.batch_size)
tensors_to_log = {
'average_loss': '{loss_prefix}head/truediv',
'loss': '{loss_prefix}head/weighted_loss/Sum'
}
wide_deep_run_loop.run_loop(
name="Census Income", train_input_fn=train_input_fn,
eval_input_fn=eval_input_fn,
model_column_fn=census_dataset.build_model_columns,
build_estimator_fn=build_estimator,
flags_obj=flags_obj,
tensors_to_log=tensors_to_log,
early_stop=True)
def main(_):
with logger.benchmark_context(flags.FLAGS):
run_census(flags.FLAGS)
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
define_census_flags()
absl_app.run(main)
official/r1/wide_deep/census_test.csv deleted 100644 → 0
View file @ d4f5c193
39,State-gov,77516,Bachelors,13,Never-married,Adm-clerical,Not-in-family,,,2174,0,40,,<=50K
50,Self-emp-not-inc,83311,Bachelors,13,Married-civ-spouse,Exec-managerial,Husband,,,0,0,13,,<=50K
38,Private,215646,HS-grad,9,Divorced,Handlers-cleaners,Not-in-family,,,0,0,40,,<=50K
53,Private,234721,11th,7,Married-civ-spouse,Handlers-cleaners,Husband,,,0,0,40,,<=50K
28,Private,338409,Bachelors,13,Married-civ-spouse,Prof-specialty,Wife,,,0,0,40,,<=50K
37,Private,284582,Masters,14,Married-civ-spouse,Exec-managerial,Wife,,,0,0,40,,<=50K
49,Private,160187,9th,5,Married-spouse-absent,Other-service,Not-in-family,,,0,0,16,,<=50K
52,Self-emp-not-inc,209642,HS-grad,9,Married-civ-spouse,Exec-managerial,Husband,,,0,0,45,,>50K
31,Private,45781,Masters,14,Never-married,Prof-specialty,Not-in-family,,,14084,0,50,,>50K
42,Private,159449,Bachelors,13,Married-civ-spouse,Exec-managerial,Husband,,,5178,0,40,,>50K
37,Private,280464,Some-college,10,Married-civ-spouse,Exec-managerial,Husband,,,0,0,80,,>50K
30,State-gov,141297,Bachelors,13,Married-civ-spouse,Prof-specialty,Husband,,,0,0,40,,>50K
23,Private,122272,Bachelors,13,Never-married,Adm-clerical,Own-child,,,0,0,30,,<=50K
32,Private,205019,Assoc-acdm,12,Never-married,Sales,Not-in-family,,,0,0,50,,<=50K
40,Private,121772,Assoc-voc,11,Married-civ-spouse,Craft-repair,Husband,,,0,0,40,,>50K
34,Private,245487,7th-8th,4,Married-civ-spouse,Transport-moving,Husband,,,0,0,45,,<=50K
25,Self-emp-not-inc,176756,HS-grad,9,Never-married,Farming-fishing,Own-child,,,0,0,35,,<=50K
32,Private,186824,HS-grad,9,Never-married,Machine-op-inspct,Unmarried,,,0,0,40,,<=50K
38,Private,28887,11th,7,Married-civ-spouse,Sales,Husband,,,0,0,50,,<=50K
43,Self-emp-not-inc,292175,Masters,14,Divorced,Exec-managerial,Unmarried,,,0,0,45,,>50K
40,Private,193524,Doctorate,16,Married-civ-spouse,Prof-specialty,Husband,,,0,0,60,,>50K
56,Local-gov,216851,Bachelors,13,Married-civ-spouse,Tech-support,Husband,,,0,0,40,,>50K
54,?,180211,Some-college,10,Married-civ-spouse,?,Husband,,,0,0,60,,>50K
22,State-gov,311512,Some-college,10,Married-civ-spouse,Other-service,Husband,,,0,0,15,,<=50K
31,Private,84154,Some-college,10,Married-civ-spouse,Sales,Husband,,,0,0,38,,>50K
57,Federal-gov,337895,Bachelors,13,Married-civ-spouse,Prof-specialty,Husband,,,0,0,40,,>50K
47,Private,51835,Prof-school,15,Married-civ-spouse,Prof-specialty,Wife,,,0,1902,60,,>50K
50,Federal-gov,251585,Bachelors,13,Divorced,Exec-managerial,Not-in-family,,,0,0,55,,>50K
25,Private,289980,HS-grad,9,Never-married,Handlers-cleaners,Not-in-family,,,0,0,35,,<=50K
42,Private,116632,Doctorate,16,Married-civ-spouse,Prof-specialty,Husband,,,0,0,45,,>50K
official/r1/wide_deep/census_test.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2017 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.
# ==============================================================================
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from absl import logging
import tensorflow.compat.v1 as tf
from official.r1.wide_deep import census_dataset
from official.r1.wide_deep import census_main
from official.utils.testing import integration
logging.set_verbosity(logging.ERROR)
TEST_INPUT = ('18,Self-emp-not-inc,987,Bachelors,12,Married-civ-spouse,abc,'
'Husband,zyx,wvu,34,56,78,tsr,<=50K')
TEST_INPUT_VALUES = {
'age': 18,
'education_num': 12,
'capital_gain': 34,
'capital_loss': 56,
'hours_per_week': 78,
'education': 'Bachelors',
'marital_status': 'Married-civ-spouse',
'relationship': 'Husband',
'workclass': 'Self-emp-not-inc',
'occupation': 'abc',
}
TEST_CSV = os.path.join(os.path.dirname(__file__), 'census_test.csv')
class BaseTest(tf.test.TestCase):
"""Tests for Wide Deep model."""
@classmethod
def setUpClass(cls): # pylint: disable=invalid-name
super(BaseTest, cls).setUpClass()
census_main.define_census_flags()
def setUp(self):
# Create temporary CSV file
self.temp_dir = self.get_temp_dir()
self.input_csv = os.path.join(self.temp_dir, 'test.csv')
with tf.io.gfile.GFile(self.input_csv, 'w') as temp_csv:
temp_csv.write(TEST_INPUT)
with tf.io.gfile.GFile(TEST_CSV, 'r') as temp_csv:
test_csv_contents = temp_csv.read()
# Used for end-to-end tests.
for fname in [census_dataset.TRAINING_FILE, census_dataset.EVAL_FILE]:
with tf.io.gfile.GFile(
os.path.join(self.temp_dir, fname), 'w') as test_csv:
test_csv.write(test_csv_contents)
def test_input_fn(self):
dataset = census_dataset.input_fn(self.input_csv, 1, False, 1)
features, labels = dataset.make_one_shot_iterator().get_next()
with self.test_session() as sess:
features, labels = sess.run((features, labels))
# Compare the two features dictionaries.
for key in TEST_INPUT_VALUES:
self.assertTrue(key in features)
self.assertEqual(len(features[key]), 1)
feature_value = features[key][0]
# Convert from bytes to string for Python 3.
if isinstance(feature_value, bytes):
feature_value = feature_value.decode()
self.assertEqual(TEST_INPUT_VALUES[key], feature_value)
self.assertFalse(labels)
def build_and_test_estimator(self, model_type):
"""Ensure that model trains and minimizes loss."""
model = census_main.build_estimator(
self.temp_dir, model_type,
model_column_fn=census_dataset.build_model_columns,
inter_op=0, intra_op=0)
# Train for 1 step to initialize model and evaluate initial loss
def get_input_fn(num_epochs, shuffle, batch_size):
def input_fn():
return census_dataset.input_fn(
TEST_CSV, num_epochs=num_epochs, shuffle=shuffle,
batch_size=batch_size)
return input_fn
model.train(input_fn=get_input_fn(1, True, 1), steps=1)
initial_results = model.evaluate(input_fn=get_input_fn(1, False, 1))
# Train for 100 epochs at batch size 3 and evaluate final loss
model.train(input_fn=get_input_fn(100, True, 3))
final_results = model.evaluate(input_fn=get_input_fn(1, False, 1))
print('%s initial results:' % model_type, initial_results)
print('%s final results:' % model_type, final_results)
# Ensure loss has decreased, while accuracy and both AUCs have increased.
self.assertLess(final_results['loss'], initial_results['loss'])
self.assertGreater(final_results['auc'], initial_results['auc'])
self.assertGreater(final_results['auc_precision_recall'],
initial_results['auc_precision_recall'])
self.assertGreater(final_results['accuracy'], initial_results['accuracy'])
def test_wide_deep_estimator_training(self):
self.build_and_test_estimator('wide_deep')
def test_end_to_end_wide(self):
integration.run_synthetic(
main=census_main.main, tmp_root=self.get_temp_dir(),
extra_flags=[
'--data_dir', self.get_temp_dir(),
'--model_type', 'wide',
'--download_if_missing=false'
],
synth=False)
def test_end_to_end_deep(self):
integration.run_synthetic(
main=census_main.main, tmp_root=self.get_temp_dir(),
extra_flags=[
'--data_dir', self.get_temp_dir(),
'--model_type', 'deep',
'--download_if_missing=false'
],
synth=False)
def test_end_to_end_wide_deep(self):
integration.run_synthetic(
main=census_main.main, tmp_root=self.get_temp_dir(),
extra_flags=[
'--data_dir', self.get_temp_dir(),
'--model_type', 'wide_deep',
'--download_if_missing=false'
],
synth=False)
if __name__ == '__main__':
tf.disable_eager_execution()
tf.test.main()
official/r1/wide_deep/movielens_dataset.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2018 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.
# ==============================================================================
"""Prepare MovieLens dataset for wide-deep."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import functools
import os
# pylint: disable=wrong-import-order
from absl import app as absl_app
from absl import flags
import numpy as np
import tensorflow.compat.v1 as tf
# pylint: enable=wrong-import-order
from official.recommendation import movielens
from official.r1.utils.data import file_io
from official.utils.flags import core as flags_core
_BUFFER_SUBDIR = "wide_deep_buffer"
_FEATURE_MAP = {
movielens.USER_COLUMN: tf.compat.v1.FixedLenFeature([1], dtype=tf.int64),
movielens.ITEM_COLUMN: tf.compat.v1.FixedLenFeature([1], dtype=tf.int64),
movielens.TIMESTAMP_COLUMN: tf.compat.v1.FixedLenFeature([1],
dtype=tf.int64),
movielens.GENRE_COLUMN: tf.compat.v1.FixedLenFeature(
[movielens.N_GENRE], dtype=tf.int64),
movielens.RATING_COLUMN: tf.compat.v1.FixedLenFeature([1],
dtype=tf.float32),
}
_BUFFER_SIZE = {
movielens.ML_1M: {"train": 107978119, "eval": 26994538},
movielens.ML_20M: {"train": 2175203810, "eval": 543802008}
}
_USER_EMBEDDING_DIM = 16
_ITEM_EMBEDDING_DIM = 64
def build_model_columns(dataset):
"""Builds a set of wide and deep feature columns."""
user_id = tf.feature_column.categorical_column_with_vocabulary_list(
movielens.USER_COLUMN, range(1, movielens.NUM_USER_IDS[dataset]))
user_embedding = tf.feature_column.embedding_column(
user_id, _USER_EMBEDDING_DIM, max_norm=np.sqrt(_USER_EMBEDDING_DIM))
item_id = tf.feature_column.categorical_column_with_vocabulary_list(
movielens.ITEM_COLUMN, range(1, movielens.NUM_ITEM_IDS))
item_embedding = tf.feature_column.embedding_column(
item_id, _ITEM_EMBEDDING_DIM, max_norm=np.sqrt(_ITEM_EMBEDDING_DIM))
time = tf.feature_column.numeric_column(movielens.TIMESTAMP_COLUMN)
genres = tf.feature_column.numeric_column(
movielens.GENRE_COLUMN, shape=(movielens.N_GENRE,), dtype=tf.uint8)
deep_columns = [user_embedding, item_embedding, time, genres]
wide_columns = []
return wide_columns, deep_columns
def _deserialize(examples_serialized):
features = tf.parse_example(examples_serialized, _FEATURE_MAP)
return features, features[movielens.RATING_COLUMN] / movielens.MAX_RATING
def _buffer_path(data_dir, dataset, name):
return os.path.join(data_dir, _BUFFER_SUBDIR,
"{}_{}_buffer".format(dataset, name))
def _df_to_input_fn(df, name, dataset, data_dir, batch_size, repeat, shuffle):
"""Serialize a dataframe and write it to a buffer file."""
buffer_path = _buffer_path(data_dir, dataset, name)
expected_size = _BUFFER_SIZE[dataset].get(name)
file_io.write_to_buffer(
dataframe=df, buffer_path=buffer_path,
columns=list(_FEATURE_MAP.keys()), expected_size=expected_size)
def input_fn():
dataset = tf.data.TFRecordDataset(buffer_path)
# batch comes before map because map can deserialize multiple examples.
dataset = dataset.batch(batch_size)
dataset = dataset.map(_deserialize, num_parallel_calls=16)
if shuffle:
dataset = dataset.shuffle(shuffle)
dataset = dataset.repeat(repeat)
return dataset.prefetch(1)
return input_fn
def _check_buffers(data_dir, dataset):
train_path = os.path.join(data_dir, _BUFFER_SUBDIR,
"{}_{}_buffer".format(dataset, "train"))
eval_path = os.path.join(data_dir, _BUFFER_SUBDIR,
"{}_{}_buffer".format(dataset, "eval"))
if not tf.gfile.Exists(train_path) or not tf.gfile.Exists(eval_path):
return False
return all([
tf.gfile.Stat(_buffer_path(data_dir, dataset, "train")).length ==
_BUFFER_SIZE[dataset]["train"],
tf.gfile.Stat(_buffer_path(data_dir, dataset, "eval")).length ==
_BUFFER_SIZE[dataset]["eval"],
])
def construct_input_fns(dataset, data_dir, batch_size=16, repeat=1):
"""Construct train and test input functions, as well as the column fn."""
if _check_buffers(data_dir, dataset):
train_df, eval_df = None, None
else:
df = movielens.csv_to_joint_dataframe(dataset=dataset, data_dir=data_dir)
df = movielens.integerize_genres(dataframe=df)
df = df.drop(columns=[movielens.TITLE_COLUMN])
train_df = df.sample(frac=0.8, random_state=0)
eval_df = df.drop(train_df.index)
train_df = train_df.reset_index(drop=True)
eval_df = eval_df.reset_index(drop=True)
train_input_fn = _df_to_input_fn(
df=train_df, name="train", dataset=dataset, data_dir=data_dir,
batch_size=batch_size, repeat=repeat,
shuffle=movielens.NUM_RATINGS[dataset])
eval_input_fn = _df_to_input_fn(
df=eval_df, name="eval", dataset=dataset, data_dir=data_dir,
batch_size=batch_size, repeat=repeat, shuffle=None)
model_column_fn = functools.partial(build_model_columns, dataset=dataset)
train_input_fn()
return train_input_fn, eval_input_fn, model_column_fn
def main(_):
movielens.download(dataset=flags.FLAGS.dataset, data_dir=flags.FLAGS.data_dir)
construct_input_fns(flags.FLAGS.dataset, flags.FLAGS.data_dir)
if __name__ == "__main__":
tf.logging.set_verbosity(tf.logging.INFO)
movielens.define_data_download_flags()
flags.adopt_module_key_flags(movielens)
flags_core.set_defaults(dataset="ml-1m")
absl_app.run(main)
official/r1/wide_deep/movielens_main.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2018 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.
# ==============================================================================
"""Train DNN on Kaggle movie dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from absl import app as absl_app
from absl import flags
import tensorflow.compat.v1 as tf
from official.r1.utils.logs import logger
from official.r1.wide_deep import movielens_dataset
from official.r1.wide_deep import wide_deep_run_loop
from official.recommendation import movielens
from official.utils.flags import core as flags_core
def define_movie_flags():
"""Define flags for movie dataset training."""
wide_deep_run_loop.define_wide_deep_flags()
flags.DEFINE_enum(
name="dataset", default=movielens.ML_1M,
enum_values=movielens.DATASETS, case_sensitive=False,
help=flags_core.help_wrap("Dataset to be trained and evaluated."))
flags.adopt_module_key_flags(wide_deep_run_loop)
flags_core.set_defaults(data_dir="/tmp/movielens-data/",
model_dir='/tmp/movie_model',
model_type="deep",
train_epochs=50,
epochs_between_evals=5,
inter_op_parallelism_threads=0,
intra_op_parallelism_threads=0,
batch_size=256)
@flags.validator("stop_threshold",
message="stop_threshold not supported for movielens model")
def _no_stop(stop_threshold):
return stop_threshold is None
def build_estimator(model_dir, model_type, model_column_fn, inter_op, intra_op):
"""Build an estimator appropriate for the given model type."""
if model_type != "deep":
raise NotImplementedError("movie dataset only supports `deep` model_type")
_, deep_columns = model_column_fn()
hidden_units = [256, 256, 256, 128]
run_config = tf.estimator.RunConfig().replace(
session_config=tf.ConfigProto(device_count={'GPU': 0},
inter_op_parallelism_threads=inter_op,
intra_op_parallelism_threads=intra_op))
return tf.estimator.DNNRegressor(
model_dir=model_dir,
feature_columns=deep_columns,
hidden_units=hidden_units,
optimizer=tf.compat.v1.train.AdamOptimizer(),
activation_fn=tf.nn.sigmoid,
dropout=0.3,
loss_reduction=tf.losses.Reduction.MEAN)
def run_movie(flags_obj):
"""Construct all necessary functions and call run_loop.
Args:
flags_obj: Object containing user specified flags.
"""
if flags_obj.download_if_missing:
movielens.download(dataset=flags_obj.dataset, data_dir=flags_obj.data_dir)
train_input_fn, eval_input_fn, model_column_fn = \
movielens_dataset.construct_input_fns(
dataset=flags_obj.dataset, data_dir=flags_obj.data_dir,
batch_size=flags_obj.batch_size, repeat=flags_obj.epochs_between_evals)
tensors_to_log = {
'loss': '{loss_prefix}head/weighted_loss/value'
}
wide_deep_run_loop.run_loop(
name="MovieLens", train_input_fn=train_input_fn,
eval_input_fn=eval_input_fn,
model_column_fn=model_column_fn,
build_estimator_fn=build_estimator,
flags_obj=flags_obj,
tensors_to_log=tensors_to_log,
early_stop=False)
def main(_):
with logger.benchmark_context(flags.FLAGS):
run_movie(flags.FLAGS)
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
define_movie_flags()
absl_app.run(main)
official/r1/wide_deep/wide_deep_run_loop.py deleted 100644 → 0
View file @ d4f5c193
# Copyright 2017 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.
# ==============================================================================
"""Core run logic for TensorFlow Wide & Deep Tutorial using tf.estimator API."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import shutil
from absl import app as absl_app
from absl import flags
import tensorflow.compat.v1 as tf
from official.r1.utils.logs import hooks_helper
from official.r1.utils.logs import logger
from official.utils.flags import core as flags_core
from official.utils.misc import model_helpers
LOSS_PREFIX = {'wide': 'linear/', 'deep': 'dnn/'}
def define_wide_deep_flags():
"""Add supervised learning flags, as well as wide-deep model type."""
flags_core.define_base(clean=True, train_epochs=True,
epochs_between_evals=True, stop_threshold=True,
hooks=True, export_dir=True)
flags_core.define_benchmark()
flags_core.define_performance(
num_parallel_calls=False, inter_op=True, intra_op=True,
synthetic_data=False, max_train_steps=False, dtype=False,
all_reduce_alg=False)
flags.adopt_module_key_flags(flags_core)
flags.DEFINE_enum(
name="model_type", short_name="mt", default="wide_deep",
enum_values=['wide', 'deep', 'wide_deep'],
help="Select model topology.")
flags.DEFINE_boolean(
name="download_if_missing", default=True, help=flags_core.help_wrap(
"Download data to data_dir if it is not already present."))
def export_model(model, model_type, export_dir, model_column_fn):
"""Export to SavedModel format.
Args:
model: Estimator object
model_type: string indicating model type. "wide", "deep" or "wide_deep"
export_dir: directory to export the model.
model_column_fn: Function to generate model feature columns.
"""
wide_columns, deep_columns = model_column_fn()
if model_type == 'wide':
columns = wide_columns
elif model_type == 'deep':
columns = deep_columns
else:
columns = wide_columns + deep_columns
feature_spec = tf.feature_column.make_parse_example_spec(columns)
example_input_fn = (
tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec))
model.export_savedmodel(export_dir, example_input_fn,
strip_default_attrs=True)
def run_loop(name, train_input_fn, eval_input_fn, model_column_fn,
build_estimator_fn, flags_obj, tensors_to_log, early_stop=False):
"""Define training loop."""
model_helpers.apply_clean(flags.FLAGS)
model = build_estimator_fn(
model_dir=flags_obj.model_dir, model_type=flags_obj.model_type,
model_column_fn=model_column_fn,
inter_op=flags_obj.inter_op_parallelism_threads,
intra_op=flags_obj.intra_op_parallelism_threads)
run_params = {
'batch_size': flags_obj.batch_size,
'train_epochs': flags_obj.train_epochs,
'model_type': flags_obj.model_type,
}
benchmark_logger = logger.get_benchmark_logger()
benchmark_logger.log_run_info('wide_deep', name, run_params,
test_id=flags_obj.benchmark_test_id)
loss_prefix = LOSS_PREFIX.get(flags_obj.model_type, '')
tensors_to_log = {k: v.format(loss_prefix=loss_prefix)
for k, v in tensors_to_log.items()}
train_hooks = hooks_helper.get_train_hooks(
flags_obj.hooks, model_dir=flags_obj.model_dir,
batch_size=flags_obj.batch_size, tensors_to_log=tensors_to_log)
# Train and evaluate the model every `flags.epochs_between_evals` epochs.
for n in range(flags_obj.train_epochs // flags_obj.epochs_between_evals):
model.train(input_fn=train_input_fn, hooks=train_hooks)
results = model.evaluate(input_fn=eval_input_fn)
# Display evaluation metrics
tf.logging.info('Results at epoch %d / %d',
(n + 1) * flags_obj.epochs_between_evals,
flags_obj.train_epochs)
tf.logging.info('-' * 60)
for key in sorted(results):
tf.logging.info('%s: %s' % (key, results[key]))
benchmark_logger.log_evaluation_result(results)
if early_stop and model_helpers.past_stop_threshold(
flags_obj.stop_threshold, results['accuracy']):
break
# Export the model
if flags_obj.export_dir is not None:
export_model(model, flags_obj.model_type, flags_obj.export_dir,
model_column_fn)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment