def simple_csv_linear_classifier(export_path, eval_export_path):
"""Trains and exports a simple linear classifier."""
def parse_csv(rows_string_tensor):
"""Takes the string input tensor and returns a dict of rank-2 tensors."""
csv_columns = ['age', 'language', 'label']
csv_column_defaults = [[0.0], ['unknown'], [0.0]]
# Takes a rank-1 tensor and converts it into rank-2 tensor
# Example if the data is ['csv,line,1', 'csv,line,2', ..] to
# [['csv,line,1'], ['csv,line,2']] which after parsing will result in a
# tuple of tensors: [['csv'], ['csv']], [['line'], ['line']], [[1], [2]]
row_columns = tf.expand_dims(rows_string_tensor, -1)
columns = tf.io.decode_csv(records=row_columns,
record_defaults=csv_column_defaults)
features = dict(zip(csv_columns, columns))
return features
def eval_input_receiver_fn():
"""Eval input receiver function."""
csv_row = tf.compat.v1.placeholder(dtype=tf.string,
shape=[None],
name='input_csv_row')
features = parse_csv(csv_row)
receiver_tensors = {'examples': csv_row}
return export.EvalInputReceiver(features=features,
labels=features['label'],
receiver_tensors=receiver_tensors)
def input_fn():
"""Train input function."""
return {
'age':
tf.constant([[1], [2], [3], [4]]),
'language':
tf.SparseTensor(
values=['english', 'english', 'chinese', 'chinese'],
indices=[[0, 0], [1, 0], [2, 0], [3, 0]],
dense_shape=[4, 1])
}, tf.constant([[1], [1], [0], [0]])
language = tf.feature_column.categorical_column_with_vocabulary_list(
'language', ['english', 'chinese'])
age = tf.feature_column.numeric_column('age')
all_features = [age, language]
feature_spec = tf.feature_column.make_parse_example_spec(all_features)
classifier = tf_estimator.LinearClassifier(
feature_columns=all_features, loss_reduction=tf.losses.Reduction.SUM)
classifier.train(input_fn=input_fn, steps=1000)
return util.export_model_and_eval_model(
estimator=classifier,
serving_input_receiver_fn=(
tf_estimator.export.build_parsing_serving_input_receiver_fn(
feature_spec)),
eval_input_receiver_fn=eval_input_receiver_fn,
export_path=export_path,
eval_export_path=eval_export_path)
def linear_model(output_dir):
real, sparse = get_features()
all = {}
all.update(real)
all.update(sparse)
estimator = tflearn.LinearClassifier(model_dir=output_dir,
feature_columns=all.values())
return estimator
def linear_model(output_dir):
real, sparse = get_features()
all = {}
all.update(real)
all.update(sparse)
estimator = tflearn.LinearClassifier(model_dir=output_dir,
feature_columns=all.values())
estimator = tf.contrib.estimator.add_metrics(estimator, my_rmse)
return estimator
def build_estimator(model_dir, model_type):
"""build an estimator"""
if model_type == 'wide':
m = estimator.LinearClassifier(model_dir=model_dir,
feature_columns=base_columns +
crossed_columns)
elif model_type == 'deep':
m = estimator.DNNClassifier(model_dir=model_dir,
feature_columns=deep_columns,
hidden_units=[100, 50])
else:
m = estimator.DNNLinearCombinedClassifier(
model_dir=model_dir,
linear_feature_columns=crossed_columns,
dnn_feature_columns=deep_columns,
dnn_hidden_units=[100, 50])
return m
def train_and_evaluate(working_dir,
num_train_instances=common.NUM_TRAIN_INSTANCES,
num_test_instances=common.NUM_TEST_INSTANCES):
"""Train the model on training data and evaluate on test data.
Args:
working_dir: Directory to read transformed data and metadata from and to
write exported model to.
num_train_instances: Number of instances in train set
num_test_instances: Number of instances in test set
Returns:
The results from the estimator's 'evaluate' method
"""
tf_transform_output = tft.TFTransformOutput(working_dir)
run_config = tf_estimator.RunConfig()
estimator = tf_estimator.LinearClassifier(
feature_columns=get_feature_columns(tf_transform_output),
config=run_config,
loss_reduction=tf.losses.Reduction.SUM)
# Fit the model using the default optimizer.
train_input_fn = _make_training_input_fn(
tf_transform_output,
os.path.join(working_dir,
common.TRANSFORMED_TRAIN_DATA_FILEBASE + '*'),
batch_size=common.TRAIN_BATCH_SIZE)
estimator.train(input_fn=train_input_fn,
max_steps=common.TRAIN_NUM_EPOCHS * num_train_instances /
common.TRAIN_BATCH_SIZE)
# Evaluate model on test dataset.
eval_input_fn = _make_training_input_fn(
tf_transform_output,
os.path.join(working_dir, common.TRANSFORMED_TEST_DATA_FILEBASE + '*'),
batch_size=1)
# Export the model.
serving_input_fn = _make_serving_input_fn(tf_transform_output)
exported_model_dir = os.path.join(working_dir, common.EXPORTED_MODEL_DIR)
estimator.export_saved_model(exported_model_dir, serving_input_fn)
return estimator.evaluate(input_fn=eval_input_fn, steps=num_test_instances)
def simple_linear_classifier_multivalent(export_path, eval_export_path):
"""Trains and exports a simple linear classifier with multivalent features."""
def input_fn():
"""Train input function."""
return {
'animals':
tf.SparseTensor(
values=[
'cat', 'dog', 'bird', 'cat', 'dog', 'cat', 'bird', 'dog',
'bird', 'cat', 'dog', 'bird'
],
indices=[[0, 0], [1, 0], [2, 0], [4, 0], [4, 1], [5, 0], [5, 1],
[6, 0], [6, 1], [7, 0], [7, 1], [7, 2]],
dense_shape=[8, 3])
}, tf.constant([[0], [0], [0], [0], [1], [0], [0], [1]])
animals = tf.feature_column.categorical_column_with_vocabulary_list(
'animals', ['bird', 'cat', 'dog'])
label = tf.feature_column.numeric_column('label')
all_features = [animals]
feature_spec = tf.feature_column.make_parse_example_spec(all_features)
eval_feature_spec = tf.feature_column.make_parse_example_spec(all_features +
[label])
classifier = tf_estimator.LinearClassifier(
feature_columns=all_features, loss_reduction=tf.losses.Reduction.SUM)
classifier.train(input_fn=input_fn, steps=5000)
return util.export_model_and_eval_model(
estimator=classifier,
serving_input_receiver_fn=(
tf_estimator.export.build_parsing_serving_input_receiver_fn(
feature_spec)),
eval_input_receiver_fn=export.build_parsing_eval_input_receiver_fn(
eval_feature_spec, label_key='label'),
export_path=export_path,
eval_export_path=eval_export_path)