def topic_distribution(topic_models, fields, args, session_file=None):
"""Computes a topic distribution for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set,
test_set_header,
fields,
None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude, headers = use_prediction_headers(test_reader, fields, args)
# Local topic distributions: Topic distributions are computed
# locally using topic models'
# method
message = u.dated("Creating local topic distributions.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_topic_distribution(topic_models,
test_reader,
output,
args,
exclude=exclude,
headers=headers)
test_reader.close()
def prediction(models, fields, args, session_file=None):
"""Computes a supervised model prediction
for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set,
test_set_header,
fields,
None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(args.prediction_header,
output,
test_reader,
fields,
args,
args.objective_field,
quality="probability")
# Local predictions: Predictions are computed locally
message = u.dated("Creating local predictions.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_prediction(models, test_reader, output, args, exclude=exclude)
test_reader.close()
def anomaly_score(anomalies, fields, args, session_file=None):
"""Computes an anomaly score for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set,
test_set_header,
fields,
None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(args.prediction_header, output,
test_reader, fields, args)
# Local anomaly scores: Anomaly scores are computed locally using
# the local anomaly detector method
message = u.dated("Creating local anomaly scores.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_anomaly_score(anomalies,
test_reader,
output,
args,
exclude=exclude)
test_reader.close()
def centroid(clusters, fields, args, session_file=None):
"""Computes a centroid for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set, test_set_header, fields, None, test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(args.prediction_header, output, test_reader, fields, args)
# Local centroids: Centroids are computed locally using clusters'
# centroids distances
message = u.dated("Creating local centroids.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_centroid(clusters, test_reader, output, args, exclude=exclude)
test_reader.close()
def anomaly_score(anomalies, fields, args, session_file=None):
"""Computes an anomaly score for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set, test_set_header, fields, None, test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(args.prediction_header, output, test_reader, fields, args)
# Local anomaly scores: Anomaly scores are computed locally using
# the local anomaly detector method
message = u.dated("Creating local anomaly scores.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_anomaly_score(anomalies, test_reader, output, args, exclude=exclude)
test_reader.close()
def centroid(clusters, fields, args, session_file=None):
"""Computes a centroid for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set, test_set_header, fields,
None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(
args.prediction_header, output, test_reader, fields, args)
# Local centroids: Centroids are computed locally using clusters'
# centroids distances
message = u.dated("Creating local centroids.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_centroid(clusters, test_reader, output, args, exclude=exclude)
test_reader.close()
def topic_distribution(topic_models, fields, args, session_file=None):
"""Computes a topic distribution for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set, test_set_header, fields,
None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude, headers = use_prediction_headers(
test_reader, fields, args)
# Local topic distributions: Topic distributions are computed
# locally using topic models'
# method
message = u.dated("Creating local topic distributions.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_topic_distribution(topic_models, test_reader, output,
args, exclude=exclude, headers=headers)
test_reader.close()
def lr_prediction(linear_regressions, fields, args, session_file=None):
"""Computes a linear regression prediction
for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.predictions
test_reader = TestReader(test_set, test_set_header, fields,
None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(
args.prediction_header, output, test_reader, fields, args,
args.objective_field, quality="probability")
# Local predictions: Predictions are computed locally
message = u.dated("Creating local predictions.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_prediction(linear_regressions, test_reader,
output, args, exclude=exclude)
test_reader.close()
def projection(pca, fields, args, session_file=None):
"""Computes the projection
for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.projections
test_reader = TestReader(test_set, test_set_header, fields, None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
local_pca, kwargs = _local_pca(pca, args)
pca_headers = ["PC%s" % (i + 1) for i in \
range(0, len(local_pca.projection({})))]
# columns to exclude if input_data is added to the projections field
exclude = use_projection_headers(
args.projection_header, output, test_reader, fields, args,
pca_headers)
# Local projection: Projections are computed locally
message = u.dated("Creating local projections.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_projection(local_pca, kwargs, test_reader,
output, args, exclude=exclude)
test_reader.close()
def projection(pca, fields, args, session_file=None):
"""Computes the projection
for each entry in the `test_set`.
"""
test_set = args.test_set
test_set_header = args.test_header
output = args.projections
test_reader = TestReader(test_set, test_set_header, fields, None,
test_separator=args.test_separator)
with UnicodeWriter(output, lineterminator="\n") as output:
local_pca, kwargs = _local_pca(pca, args)
pca_headers = ["PC%s" % (i + 1) for i in \
range(0, len(local_pca.projection({})))]
# columns to exclude if input_data is added to the projections field
exclude = use_projection_headers(
args.projection_header, output, test_reader, fields, args,
pca_headers)
# Local projection: Projections are computed locally
message = u.dated("Creating local projections.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
local_projection(local_pca, kwargs, test_reader,
output, args, exclude=exclude)
test_reader.close()
def predict(models,
fields,
args,
api=None,
log=None,
resume=False,
session_file=None,
labels=None,
models_per_label=1,
other_label=OTHER,
multi_label_data=None):
"""Computes a prediction for each entry in the `test_set`.
Predictions computed locally using MultiModels on subgroups of models.
Chosing a max_batch_models value not bigger than the number_of_models
flag will lead to the last case, where memory usage is bounded and each
model predictions are saved for further use.
"""
test_set = args.test_set
test_set_header = args.test_header
objective_field = args.objective_field
output = args.predictions
test_reader = TestReader(test_set,
test_set_header,
fields,
objective_field,
test_separator=args.test_separator)
prediction_file = output
output_path = u.check_dir(output)
with UnicodeWriter(output) as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(args.prediction_header, output,
test_reader, fields, args,
objective_field)
# Remote predictions: predictions are computed in bigml.com and stored
# in a file named after the model in the following syntax:
# model_[id of the model]__predictions.csv
# For instance,
# model_50c0de043b563519830001c2_predictions.csv
# Predictions are computed individually only if no_batch flag is set
if args.remote and args.no_batch and not args.multi_label:
if args.ensemble is not None:
remote_predict_ensemble(args.ensemble, test_reader,
prediction_file, api, args, resume,
output_path, session_file, log,
exclude)
else:
remote_predict_models(models, test_reader, prediction_file,
api, args, resume, output_path,
session_file, log, exclude)
return
# Local predictions: Predictions are computed locally using models'
# rules with MultiModel's predict method
message = u.dated("Creating local predictions.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
options = {}
if args.method == THRESHOLD_CODE:
options.update(threshold=args.threshold)
if args.threshold_class is None:
local_model = Model(models[0])
# default class is the first class that appears in the dataset
# objective field summary, which might be different from the
# objective summary of each model becaus model are built with
# sampling
objective_field = local_model.objective_id
distribution = local_model.tree.fields[objective_field][ \
"summary"]["categories"]
args.threshold_class = distribution[0][0]
options.update(category=args.threshold_class)
# For a model we build a Model and for a small number of models,
# we build a MultiModel using all of
# the given models and issue a combined prediction
if (len(models) <= args.max_batch_models \
and args.fast and \
not args.multi_label and args.max_categories == 0 \
and args.method != COMBINATION):
local_predict(models, test_reader, output, args, options, exclude)
elif args.boosting:
local_predict(args.ensemble, test_reader, output, args, options,
exclude)
# For large numbers of models, we split the list of models in chunks
# and build a MultiModel for each chunk, issue and store predictions
# for each model and combine all of them eventually.
else:
# Local predictions: predictions are computed locally using
# models' rules with MultiModel's predict method and combined using
# aggregation if the objective field is a multi-labelled field
# or one of the available combination methods: plurality,
# confidence weighted and probability weighted
if args.multi_label:
method = AGGREGATION
elif args.max_categories > 0:
method = COMBINATION
else:
method = args.method
# For multi-labelled models, the --models flag keeps the order
# of the labels and the models but the --model-tag flag
# retrieves the models with no order, so the correspondence with
# each label must be restored.
ordered = True
if args.multi_label and (args.model_tag is not None
or models_per_label > 1):
ordered = False
local_batch_predict(models,
test_reader,
prediction_file,
api,
args,
resume=resume,
output_path=output_path,
output=output,
method=method,
options=options,
session_file=session_file,
labels=labels,
ordered=ordered,
exclude=exclude,
models_per_label=models_per_label,
other_label=other_label,
multi_label_data=multi_label_data)
test_reader.close()
def predict(models, fields, args, api=None, log=None,
resume=False, session_file=None,
labels=None, models_per_label=1, other_label=OTHER,
multi_label_data=None):
"""Computes a prediction for each entry in the `test_set`.
Predictions computed locally using MultiModels on subgroups of models.
Chosing a max_batch_models value not bigger than the number_of_models
flag will lead to the last case, where memory usage is bounded and each
model predictions are saved for further use.
"""
test_set = args.test_set
test_set_header = args.test_header
objective_field = args.objective_field
output = args.predictions
test_reader = TestReader(test_set, test_set_header, fields,
objective_field,
test_separator=args.test_separator)
prediction_file = output
output_path = u.check_dir(output)
with UnicodeWriter(output) as output:
# columns to exclude if input_data is added to the prediction field
exclude = use_prediction_headers(
args.prediction_header, output, test_reader, fields, args,
objective_field)
# Remote predictions: predictions are computed in bigml.com and stored
# in a file named after the model in the following syntax:
# model_[id of the model]__predictions.csv
# For instance,
# model_50c0de043b563519830001c2_predictions.csv
# Predictions are computed individually only if no_batch flag is set
if (args.remote and args.no_batch and not args.multi_label
and args.method != THRESHOLD_CODE):
if args.ensemble is not None:
remote_predict_ensemble(args.ensemble, test_reader,
prediction_file, api, args, resume,
output_path, session_file, log,
exclude)
else:
remote_predict_models(models, test_reader, prediction_file,
api, args, resume, output_path,
session_file, log, exclude)
return
# Local predictions: Predictions are computed locally using models'
# rules with MultiModel's predict method
message = u.dated("Creating local predictions.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
options = {}
if args.method == THRESHOLD_CODE:
options.update(threshold=args.threshold)
if args.threshold_class is None:
local_model = Model(models[0])
args.threshold_class = local_model.tree.distribution[0][0]
options.update(category=args.threshold_class)
# For a model we build a Model and for a small number of models,
# we build a MultiModel using all of
# the given models and issue a combined prediction
if (len(models) <= args.max_batch_models and args.fast and
not args.multi_label and args.max_categories == 0
and args.method != COMBINATION):
local_predict(models, test_reader, output, args, options, exclude)
# For large numbers of models, we split the list of models in chunks
# and build a MultiModel for each chunk, issue and store predictions
# for each model and combine all of them eventually.
else:
# Local predictions: predictions are computed locally using
# models' rules with MultiModel's predict method and combined using
# aggregation if the objective field is a multi-labelled field
# or one of the available combination methods: plurality,
# confidence weighted and probability weighted
if args.multi_label:
method = AGGREGATION
elif args.max_categories > 0:
method = COMBINATION
else:
method = args.method
# For multi-labelled models, the --models flag keeps the order
# of the labels and the models but the --model-tag flag
# retrieves the models with no order, so the correspondence with
# each label must be restored.
ordered = True
if args.multi_label and (args.model_tag is not None
or models_per_label > 1):
ordered = False
local_batch_predict(models, test_reader, prediction_file, api,
args, resume=resume,
output_path=output_path,
output=output, method=method, options=options,
session_file=session_file, labels=labels,
ordered=ordered, exclude=exclude,
models_per_label=models_per_label,
other_label=other_label,
multi_label_data=multi_label_data)
test_reader.close()