def _input_fn(filenames, tf_transform_output, batch_size=200):
"""Generates features and labels for training or evaluation.
Args:
filenames: [str] list of CSV files to read data from.
tf_transform_output: A TFTransformOutput.
batch_size: int First dimension size of the Tensors returned by input_fn
Returns:
A (features, indices) tuple where features is a dictionary of
Tensors, and indices is a single Tensor of label indices.
"""
transformed_feature_spec = (
tf_transform_output.transformed_feature_spec().copy())
dataset = tf.data.experimental.make_batched_features_dataset(
filenames,
batch_size,
transformed_feature_spec,
reader=_gzip_reader_fn)
transformed_features = tf.compat.v1.data.make_one_shot_iterator(
dataset).get_next()
# We pop the label because we do not want to use it as a feature while we're
# training.
return transformed_features, transformed_features.pop(
features.transformed_name(features.LABEL_KEY))
def preprocessing_fn(inputs):
"""tf.transform's callback function for preprocessing inputs.
Args:
inputs: map from feature keys to raw not-yet-transformed features.
Returns:
Map from string feature key to transformed feature operations.
"""
outputs = {}
for key in features.DENSE_FLOAT_FEATURE_KEYS:
# Preserve this feature as a dense float, setting nan's to the mean.
outputs[features.transformed_name(key)] = tft.scale_to_z_score(
_fill_in_missing(inputs[key]))
for key in features.VOCAB_FEATURE_KEYS:
# Build a vocabulary for this feature.
outputs[features.transformed_name(
key)] = tft.compute_and_apply_vocabulary(
_fill_in_missing(inputs[key]),
top_k=features.VOCAB_SIZE,
num_oov_buckets=features.OOV_SIZE)
for key, num_buckets in zip(features.BUCKET_FEATURE_KEYS,
features.BUCKET_FEATURE_BUCKET_COUNT):
outputs[features.transformed_name(key)] = tft.bucketize(
_fill_in_missing(inputs[key]),
num_buckets,
always_return_num_quantiles=False)
for key in features.CATEGORICAL_FEATURE_KEYS:
outputs[features.transformed_name(key)] = _fill_in_missing(inputs[key])
# Was this passenger a big tipper?
fare_key = 'fare'
taxi_fare = _fill_in_missing(inputs[fare_key])
tips = _fill_in_missing(inputs[features.LABEL_KEY])
outputs[features.transformed_name(
features.LABEL_KEY)] = tf.compat.v1.where(
tf.math.is_nan(taxi_fare),
tf.cast(tf.zeros_like(taxi_fare), tf.int64),
# Test if the tip was > 20% of the fare.
tf.cast(tf.greater(tips, tf.multiply(taxi_fare, tf.constant(0.2))),
tf.int64))
return outputs
def _eval_input_receiver_fn(tf_transform_output, schema):
"""Build everything needed for the tf-model-analysis to run the model.
Args:
tf_transform_output: A TFTransformOutput.
schema: the schema of the input data.
Returns:
EvalInputReceiver function, which contains:
- Tensorflow graph which parses raw untransformed features, applies the
tf-transform preprocessing operators.
- Set of raw, untransformed features.
- Label against which predictions will be compared.
"""
# Notice that the inputs are raw features, not transformed features here.
raw_feature_spec = _get_raw_feature_spec(schema)
serialized_tf_example = tf.compat.v1.placeholder(
dtype=tf.string, shape=[None], name='input_example_tensor')
# Add a parse_example operator to the tensorflow graph, which will parse
# raw, untransformed, tf examples.
raw_features = tf.io.parse_example(serialized=serialized_tf_example,
features=raw_feature_spec)
# Now that we have our raw examples, process them through the tf-transform
# function computed during the preprocessing step.
transformed_features = tf_transform_output.transform_raw_features(
raw_features)
# The key name MUST be 'examples'.
receiver_tensors = {'examples': serialized_tf_example}
# NOTE: Model is driven by transformed features (since training works on the
# materialized output of TFT, but slicing will happen on raw features.
raw_features.update(transformed_features)
return tfma.export.EvalInputReceiver(
features=raw_features,
receiver_tensors=receiver_tensors,
labels=transformed_features[features.transformed_name(
features.LABEL_KEY)])