def evaluate(
self,
test_dataset: data.TFRecordDataset,
inference_signature: str = None,
additional_features: dict = {},
group_metrics_min_queries: int = 50,
logs_dir: Optional[str] = None,
logging_frequency: int = 25,
compute_intermediate_stats: bool = True,
):
"""
Evaluate the RelevanceModel
Parameters
----------
test_dataset: an instance of tf.data.dataset
inference_signature : str, optional
If using a SavedModel for prediction, specify the inference signature to be used for computing scores
additional_features : dict, optional
Dictionary containing new feature name and function definition to
compute them. Use this to compute additional features from the scores.
For example, converting ranking scores for each document into ranks for
the query
group_metrics_min_queries : int, optional
Minimum count threshold per group to be considered for computing
groupwise metrics
logs_dir : str, optional
Path to directory to save logs
logging_frequency : int
Value representing how often(in batches) to log status
compute_intermediate_stats : bool
[Currently ignored] Determines if group metrics and other intermediate stats on the test set should be computed
Returns
-------
df_overall_metrics : `pd.DataFrame` object
`pd.DataFrame` containing overall metrics
df_groupwise_metrics : `pd.DataFrame` object
`pd.DataFrame` containing groupwise metrics if
group_metric_keys are defined in the FeatureConfig
metrics_dict : dict
metrics as a dictionary of metric names mapping to values
Notes
-----
You can directly do a `model.evaluate()` only if the keras model is compiled
Override this method to implement your own evaluation metrics.
"""
metrics_dict = dict()
group_metrics_keys = self.feature_config.get_group_metrics_keys()
evaluation_features = (group_metrics_keys + [
self.feature_config.get_query_key(),
self.feature_config.get_label(),
self.feature_config.get_rank(),
] + [
f for f in self.feature_config.get_secondary_labels() if f.get(
"node_name",
f["name"] not in self.feature_config.get_group_metrics_keys(
"node_name"),
)
])
additional_features[RankingConstants.
NEW_RANK] = prediction_helper.convert_score_to_rank
_predict_fn = get_predict_fn(
model=self.model,
tfrecord_type=self.tfrecord_type,
feature_config=self.feature_config,
inference_signature=inference_signature,
is_compiled=self.is_compiled,
output_name=self.output_name,
features_to_return=evaluation_features,
additional_features=additional_features,
max_sequence_size=self.max_sequence_size,
)
batch_count = 0
df_grouped_stats = pd.DataFrame()
for predictions_dict in test_dataset.map(_predict_fn).take(-1):
predictions_df = pd.DataFrame(predictions_dict)
df_batch_grouped_stats = metrics_helper.get_grouped_stats(
df=predictions_df,
query_key_col=self.feature_config.get_query_key("node_name"),
label_col=self.feature_config.get_label("node_name"),
old_rank_col=self.feature_config.get_rank("node_name"),
new_rank_col=RankingConstants.NEW_RANK,
group_keys=self.feature_config.get_group_metrics_keys(
"node_name"),
secondary_labels=self.feature_config.get_secondary_labels(
"node_name"),
)
if df_grouped_stats.empty:
df_grouped_stats = df_batch_grouped_stats
else:
df_grouped_stats = df_grouped_stats.add(df_batch_grouped_stats,
fill_value=0.0)
batch_count += 1
if batch_count % logging_frequency == 0:
self.logger.info(
"Finished evaluating {} batches".format(batch_count))
# Compute overall metrics
df_overall_metrics = metrics_helper.summarize_grouped_stats(
df_grouped_stats)
self.logger.info("Overall Metrics: \n{}".format(df_overall_metrics))
# Log metrics to weights and biases
metrics_dict.update({
"test_{}".format(k): v
for k, v in df_overall_metrics.to_dict().items()
})
df_group_metrics = None
df_group_metrics_summary = None
if group_metrics_keys:
# Filter groups by min_query_count
df_grouped_stats = df_grouped_stats[
df_grouped_stats["query_count"] >= group_metrics_min_queries]
# Compute group metrics
df_group_metrics = df_grouped_stats.apply(
metrics_helper.summarize_grouped_stats, axis=1)
if logs_dir:
self.file_io.write_df(
df_group_metrics,
outfile=os.path.join(
logs_dir,
RelevanceModelConstants.GROUP_METRICS_CSV_FILE),
)
# Compute group metrics summary
df_group_metrics_summary = df_group_metrics.describe()
self.logger.info("Computing group metrics using keys: {}".format(
self.feature_config.get_group_metrics_keys("node_name")))
self.logger.info("Groupwise Metrics: \n{}".format(
df_group_metrics_summary.T))
# Log metrics to weights and biases
metrics_dict.update({
"test_group_mean_{}".format(k): v
for k, v in
df_group_metrics_summary.T["mean"].to_dict().items()
})
return df_overall_metrics, df_group_metrics, metrics_dict
def evaluate(
self,
test_dataset: data.TFRecordDataset,
inference_signature: str = None,
additional_features: dict = {},
group_metrics_min_queries: int = 50,
logs_dir: Optional[str] = None,
logging_frequency: int = 25,
):
"""
Evaluate the ranking model
Args:
test_dataset: an instance of tf.data.dataset
inference_signature: If using a SavedModel for prediction, specify the inference signature
logging_frequency: integer representing how often(in batches) to log status
metric_group_keys: list of fields to compute group based metrics on
save_to_file: set to True to save predictions to file like self.predict()
Returns:
metrics and groupwise metrics as pandas DataFrames
"""
group_metrics_keys = self.feature_config.get_group_metrics_keys()
evaluation_features = (group_metrics_keys + [
self.feature_config.get_query_key(),
self.feature_config.get_label(),
self.feature_config.get_rank(),
] + [
f for f in self.feature_config.get_secondary_labels() if f.get(
"node_name",
f["name"] not in self.feature_config.get_group_metrics_keys(
"node_name"),
)
])
additional_features[RankingConstants.
NEW_RANK] = prediction_helper.convert_score_to_rank
_predict_fn = get_predict_fn(
model=self.model,
tfrecord_type=self.tfrecord_type,
feature_config=self.feature_config,
inference_signature=inference_signature,
is_compiled=self.is_compiled,
output_name=self.output_name,
features_to_return=evaluation_features,
additional_features=additional_features,
max_sequence_size=self.max_sequence_size,
)
batch_count = 0
df_grouped_stats = pd.DataFrame()
for predictions_dict in test_dataset.map(_predict_fn).take(-1):
predictions_df = pd.DataFrame(predictions_dict)
df_batch_grouped_stats = metrics_helper.get_grouped_stats(
df=predictions_df,
query_key_col=self.feature_config.get_query_key("node_name"),
label_col=self.feature_config.get_label("node_name"),
old_rank_col=self.feature_config.get_rank("node_name"),
new_rank_col=RankingConstants.NEW_RANK,
group_keys=self.feature_config.get_group_metrics_keys(
"node_name"),
secondary_labels=self.feature_config.get_secondary_labels(
"node_name"),
)
if df_grouped_stats.empty:
df_grouped_stats = df_batch_grouped_stats
else:
df_grouped_stats = df_grouped_stats.add(df_batch_grouped_stats,
fill_value=0.0)
batch_count += 1
if batch_count % logging_frequency == 0:
self.logger.info(
"Finished evaluating {} batches".format(batch_count))
# Compute overall metrics
df_overall_metrics = metrics_helper.summarize_grouped_stats(
df_grouped_stats)
self.logger.info("Overall Metrics: \n{}".format(df_overall_metrics))
df_group_metrics = None
df_group_metrics_summary = None
if group_metrics_keys:
# Filter groups by min_query_count
df_grouped_stats = df_grouped_stats[
df_grouped_stats["query_count"] >= group_metrics_min_queries]
# Compute group metrics
df_group_metrics = df_grouped_stats.apply(
metrics_helper.summarize_grouped_stats, axis=1)
if logs_dir:
self.file_io.write_df(
df_group_metrics,
outfile=os.path.join(
logs_dir,
RelevanceModelConstants.GROUP_METRICS_CSV_FILE),
)
# Compute group metrics summary
df_group_metrics_summary = df_group_metrics.describe()
self.logger.info("Computing group metrics using keys: {}".format(
self.feature_config.get_group_metrics_keys("node_name")))
self.logger.info("Groupwise Metrics: \n{}".format(
df_group_metrics_summary.T))
return df_overall_metrics, df_group_metrics
