def train_and_evaluate(transformed_train_filepattern,
transformed_test_filepattern, transformed_metadata_dir,
num_train_instances=NUM_TRAIN_INSTANCES,
num_test_instances=NUM_TEST_INSTANCES):
"""Train the model on training data and evaluate on test data.
Args:
transformed_train_filepattern: File pattern for transformed training data
shards
transformed_test_filepattern: File pattern for transformed test data shards
transformed_metadata_dir: Directory containing transformed data metadata
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
"""
# Wrap scalars as real valued columns.
real_valued_columns = [feature_column.real_valued_column(key)
for key in NUMERIC_COLUMNS]
# Wrap categorical columns. Note the combiner is irrelevant since the input
# only has one value set per feature per instance.
one_hot_columns = [
feature_column.sparse_column_with_integerized_feature(
key, bucket_size=bucket_size, combiner='sum')
for key, bucket_size in zip(CATEGORICAL_COLUMNS, BUCKET_SIZES)]
estimator = learn.LinearClassifier(real_valued_columns + one_hot_columns)
transformed_metadata = metadata_io.read_metadata(transformed_metadata_dir)
train_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_train_filepattern,
training_batch_size=TRAIN_BATCH_SIZE,
label_keys=[LABEL_COLUMN])
# Estimate the model using the default optimizer.
estimator.fit(
input_fn=train_input_fn,
max_steps=TRAIN_NUM_EPOCHS * num_train_instances / TRAIN_BATCH_SIZE)
# Evaluate model on test dataset.
eval_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_test_filepattern,
training_batch_size=1,
label_keys=[LABEL_COLUMN])
return estimator.evaluate(input_fn=eval_input_fn, steps=num_test_instances)
def train_and_evaluate(transformed_train_filepattern,
transformed_test_filepattern,
transformed_metadata_dir,
num_train_instances=NUM_TRAIN_INSTANCES,
num_test_instances=NUM_TEST_INSTANCES):
"""Train the model on training data and evaluate on evaluation data.
Args:
transformed_train_filepattern: Base filename for transformed training data
shards
transformed_test_filepattern: Base filename for transformed evaluation data
shards
transformed_metadata_dir: Directory containing transformed data metadata
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
"""
# Unrecognized tokens are represented by -1, but
# sparse_column_with_integerized_feature uses the mod operator to map integers
# to the range [0, bucket_size). By choosing bucket_size=VOCAB_SIZE + 1, we
# represent unrecognized tokens as VOCAB_SIZE.
review_column = feature_column.sparse_column_with_integerized_feature(
REVIEW_COLUMN, bucket_size=VOCAB_SIZE + 1, combiner='sum')
weighted_reviews = feature_column.weighted_sparse_column(
review_column, REVIEW_WEIGHT)
estimator = learn.LinearClassifier([weighted_reviews])
transformed_metadata = metadata_io.read_metadata(transformed_metadata_dir)
train_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_train_filepattern,
training_batch_size=TRAIN_BATCH_SIZE,
label_keys=[LABEL_COLUMN])
# Estimate the model using the default optimizer.
estimator.fit(input_fn=train_input_fn,
max_steps=TRAIN_NUM_EPOCHS * num_train_instances /
TRAIN_BATCH_SIZE)
# Evaluate model on eval dataset.
eval_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_test_filepattern,
training_batch_size=1,
label_keys=[LABEL_COLUMN])
return estimator.evaluate(input_fn=eval_input_fn, steps=num_test_instances)
def train_and_evaluate(transformed_train_data_base, transformed_eval_data_base,
transformed_metadata_dir):
"""Train the model on training data and evaluate on evaluation data.
Args:
transformed_train_data_base: Base filename for transformed training data
shards
transformed_eval_data_base: Base filename for cleaned evaluation data
shards
transformed_metadata_dir: Directory containing transformed data metadata.
Returns:
The results from the estimator's 'evaluate' method.
"""
# Wrap scalars as real valued columns.
real_valued_columns = [
feature_column.real_valued_column(key) for key in NUMERIC_COLUMNS
]
# Wrap categorical columns.
one_hot_columns = [
feature_column.sparse_column_with_integerized_feature(
key, bucket_size=bucket_size)
for key, bucket_size in zip(CATEGORICAL_COLUMNS, BUCKET_SIZES)
]
estimator = learn.LinearClassifier(real_valued_columns + one_hot_columns)
transformed_metadata = metadata_io.read_metadata(transformed_metadata_dir)
train_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_train_data_base + '*',
training_batch_size=TRAIN_BATCH_SIZE,
label_keys=['label'])
# Estimate the model using the default optimizer.
estimator.fit(input_fn=train_input_fn,
max_steps=TRAIN_NUM_EPOCHS * NUM_TRAIN_INSTANCES /
TRAIN_BATCH_SIZE)
# Evaluate model on eval dataset.
eval_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_eval_data_base + '*',
training_batch_size=1,
label_keys=['label'])
return estimator.evaluate(input_fn=eval_input_fn, steps=NUM_EVAL_INSTANCES)
def train_and_evaluate(output_dir):
review_column = feature_column.sparse_column_with_integerized_feature(
const.REVIEW_COLUMN, bucket_size=vocab_size + 1, combiner='sum')
weighted_reviews = feature_column.weighted_sparse_column(
review_column, const.REVIEW_WEIGHT)
estimator = learn.LinearClassifier(
feature_columns=[weighted_reviews],
n_classes=2,
model_dir=output_dir,
config=tf.contrib.learn.RunConfig(save_checkpoints_secs=30))
transformed_metadata = metadata_io.read_metadata(
transformed_metadata_dir)
raw_metadata = metadata_io.read_metadata(raw_metadata_dir)
train_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_train_file_pattern,
training_batch_size=train_batch_size,
label_keys=[const.LABEL_COLUMN])
eval_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_test_file_pattern,
training_batch_size=1,
label_keys=[const.LABEL_COLUMN])
serving_input_fn = input_fn_maker.build_default_transforming_serving_input_fn(
raw_metadata=raw_metadata,
transform_savedmodel_dir=output_dir + '/transform_fn',
raw_label_keys=[],
raw_feature_keys=[const.REVIEW_COLUMN])
export_strategy = saved_model_export_utils.make_export_strategy(
serving_input_fn,
exports_to_keep=5,
default_output_alternative_key=None)
return tf.contrib.learn.Experiment(estimator=estimator,
train_steps=train_num_epochs *
num_train_instances /
train_batch_size,
eval_steps=num_test_instances,
train_input_fn=train_input_fn,
eval_input_fn=eval_input_fn,
export_strategies=export_strategy,
min_eval_frequency=500)
def train_and_evaluate(transformed_train_filepattern,
transformed_test_filepattern, transformed_metadata_dir,
serving_graph_dir):
"""Train the model on training data and evaluate on test data.
Args:
transformed_train_filepattern: File pattern for transformed training data
shards
transformed_test_filepattern: File pattern for transformed test data shards
transformed_metadata_dir: Directory containing transformed data metadata
serving_graph_dir: Directory to save the serving graph
Returns:
The results from the estimator's 'evaluate' method
"""
# Wrap scalars as real valued columns.
real_valued_columns = [
feature_column.real_valued_column(key) for key in NUMERIC_COLUMNS
]
# Wrap categorical columns. Note the combiner is irrelevant since the input
# only has one value set per feature per instance.
one_hot_columns = [
feature_column.sparse_column_with_integerized_feature(
key, bucket_size=bucket_size, combiner='sum')
for key, bucket_size in zip(CATEGORICAL_COLUMNS, BUCKET_SIZES)
]
estimator = learn.LinearClassifier(real_valued_columns + one_hot_columns)
transformed_metadata = metadata_io.read_metadata(transformed_metadata_dir)
train_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_train_filepattern,
training_batch_size=TRAIN_BATCH_SIZE,
label_keys=[LABEL_COLUMN])
# Estimate the model using the default optimizer.
estimator.fit(input_fn=train_input_fn,
max_steps=TRAIN_NUM_EPOCHS * NUM_TRAIN_INSTANCES /
TRAIN_BATCH_SIZE)
# Write the serving graph to disk for use in tf.serving
in_columns = [
'age', 'workclass', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain',
'capital-loss', 'hours-per-week', 'native-country'
]
if not serving_graph_dir is None:
serving_input_fn = input_fn_maker.build_default_transforming_serving_input_fn(
raw_metadata=raw_data_metadata,
transform_savedmodel_dir=serving_graph_dir + '/transform_fn',
raw_label_keys=[],
raw_feature_keys=in_columns)
estimator.export_savedmodel(serving_graph_dir, serving_input_fn)
# Evaluate model on test dataset.
eval_input_fn = input_fn_maker.build_training_input_fn(
transformed_metadata,
transformed_test_filepattern,
training_batch_size=1,
label_keys=[LABEL_COLUMN])
return estimator.evaluate(input_fn=eval_input_fn, steps=NUM_TEST_INSTANCES)
