def train_test_metrics(train_dataset_path,
test_dataset_path,
output_path,
config_path=None,
exclude_slot_metrics=False,
include_errors=False,
verbose=False):
if verbose:
set_nlu_logger(logging.DEBUG)
if config_path is not None:
with Path(config_path).open("r", encoding="utf-8") as f:
config = json.load(f)
engine_cls = make_engine_cls(config)
else:
engine_cls = SnipsNLUEngine
metrics_args = dict(train_dataset=train_dataset_path,
test_dataset=test_dataset_path,
engine_class=engine_cls,
include_slot_metrics=not exclude_slot_metrics)
with Path(train_dataset_path).open("r", encoding="utf8") as f:
load_resources(json.load(f)["language"])
from snips_nlu_metrics import compute_train_test_metrics
metrics = compute_train_test_metrics(**metrics_args)
if not include_errors:
metrics.pop("parsing_errors")
with Path(output_path).open(mode="w", encoding="utf8") as f:
f.write(json_string(metrics))
def parse(training_path, query, verbose=False, intents_filter=None):
"""Load a trained NLU engine and play with its parsing API interactively"""
import csv
import logging
from builtins import input, str
from snips_nlu import SnipsNLUEngine
from snips_nlu.cli.utils import set_nlu_logger
if verbose == 1:
set_nlu_logger(logging.INFO)
elif verbose >= 2:
set_nlu_logger(logging.DEBUG)
if intents_filter:
# use csv in order to properly handle commas and other special
# characters in intent names
intents_filter = next(csv.reader([intents_filter]))
else:
intents_filter = None
engine = SnipsNLUEngine.from_path(training_path)
if query:
print_parsing_result(engine, query, intents_filter)
return
while True:
query = input("Enter a query (type 'q' to quit): ").strip()
if not isinstance(query, str):
query = query.decode("utf-8")
if query == "q":
break
print_parsing_result(engine, query, intents_filter)
def parse(training_path, query, verbose=False):
"""Load a trained NLU engine and play with its parsing API interactively"""
import logging
from builtins import input, str
from snips_nlu import SnipsNLUEngine
from snips_nlu.cli.utils import set_nlu_logger
if verbose == 1:
set_nlu_logger(logging.INFO)
elif verbose >= 2:
set_nlu_logger(logging.DEBUG)
engine = SnipsNLUEngine.from_path(training_path)
if query:
print_parsing_result(engine, query)
return
while True:
query = input("Enter a query (type 'q' to quit): ").strip()
if not isinstance(query, str):
query = query.decode("utf-8")
if query == "q":
break
print_parsing_result(engine, query)
def parse(training_path, query, verbose=False):
"""Load a trained NLU engine and play with its parsing API interactively"""
if verbose:
set_nlu_logger(logging.DEBUG)
engine = SnipsNLUEngine.from_path(training_path)
if query:
print_parsing_result(engine, query)
return
while True:
query = input("Enter a query (type 'q' to quit): ").strip()
if query == "q":
break
print_parsing_result(engine, query)
def cross_val_metrics(dataset_path,
output_path,
config_path=None,
nb_folds=5,
train_size_ratio=1.0,
exclude_slot_metrics=False,
include_errors=False,
verbose=0):
import json
import logging
from pathlib import Path
from snips_nlu_metrics import compute_cross_val_metrics
from snips_nlu import SnipsNLUEngine
from snips_nlu.cli.utils import set_nlu_logger
from snips_nlu.common.utils import json_string
if verbose == 1:
set_nlu_logger(logging.INFO)
elif verbose >= 2:
set_nlu_logger(logging.DEBUG)
def progression_handler(progress):
print("%d%%" % int(progress * 100))
if config_path is not None:
with Path(config_path).open("r", encoding="utf-8") as f:
config = json.load(f)
engine_cls = make_engine_cls(config)
else:
engine_cls = SnipsNLUEngine
metrics_args = dict(dataset=dataset_path,
engine_class=engine_cls,
progression_handler=progression_handler,
nb_folds=nb_folds,
train_size_ratio=train_size_ratio,
include_slot_metrics=not exclude_slot_metrics,
slot_matching_lambda=_match_trimmed_values)
metrics = compute_cross_val_metrics(**metrics_args)
if not include_errors:
metrics.pop("parsing_errors")
with Path(output_path).open(mode="w", encoding="utf8") as f:
f.write(json_string(metrics))
def train(dataset_path, output_path, config_path, verbose):
"""Train an NLU engine on the provided dataset"""
if verbose:
set_nlu_logger(logging.DEBUG)
with Path(dataset_path).open("r", encoding="utf8") as f:
dataset = json.load(f)
config = None
if config_path is not None:
with Path(config_path).open("r", encoding="utf8") as f:
config = json.load(f)
print("Create and train the engine...")
engine = SnipsNLUEngine(config).fit(dataset)
print("Persisting the engine...")
engine.persist(output_path)
print("Saved the trained engine to %s" % output_path)
def cross_val_metrics(dataset_path,
output_path,
config_path=None,
nb_folds=5,
train_size_ratio=1.0,
exclude_slot_metrics=False,
include_errors=False,
verbose=False):
if verbose:
set_nlu_logger(logging.DEBUG)
def progression_handler(progress):
print("%d%%" % int(progress * 100))
if config_path is not None:
with Path(config_path).open("r", encoding="utf-8") as f:
config = json.load(f)
engine_cls = make_engine_cls(config)
else:
engine_cls = SnipsNLUEngine
metrics_args = dict(
dataset=dataset_path,
engine_class=engine_cls,
progression_handler=progression_handler,
nb_folds=nb_folds,
train_size_ratio=train_size_ratio,
include_slot_metrics=not exclude_slot_metrics,
)
with Path(dataset_path).open("r", encoding="utf8") as f:
load_resources(json.load(f)["language"])
from snips_nlu_metrics import compute_cross_val_metrics
metrics = compute_cross_val_metrics(**metrics_args)
if not include_errors:
metrics.pop("parsing_errors")
with Path(output_path).open(mode="w", encoding="utf8") as f:
f.write(json_string(metrics))
def train_test_metrics(train_dataset_path,
test_dataset_path,
output_path,
config_path=None,
exclude_slot_metrics=False,
include_errors=False,
verbosity=0):
import json
import logging
from pathlib import Path
from snips_nlu_metrics import compute_train_test_metrics
from snips_nlu import SnipsNLUEngine
from snips_nlu.cli.utils import set_nlu_logger
from snips_nlu.common.utils import json_string
if verbosity == 1:
set_nlu_logger(logging.INFO)
elif verbosity >= 2:
set_nlu_logger(logging.DEBUG)
if config_path is not None:
with Path(config_path).open("r", encoding="utf-8") as f:
config = json.load(f)
engine_cls = make_engine_cls(config)
else:
engine_cls = SnipsNLUEngine
metrics_args = dict(train_dataset=train_dataset_path,
test_dataset=test_dataset_path,
engine_class=engine_cls,
include_slot_metrics=not exclude_slot_metrics,
slot_matching_lambda=_match_trimmed_values)
metrics = compute_train_test_metrics(**metrics_args)
if not include_errors:
metrics.pop("parsing_errors")
with Path(output_path).open(mode="w", encoding="utf8") as f:
f.write(json_string(metrics))
def train(dataset_path,
output_path,
config_path=None,
verbose=False,
random_seed=None):
"""Train an NLU engine on the provided dataset"""
import json
import logging
from pathlib import Path
from snips_nlu import SnipsNLUEngine
from snips_nlu.cli.utils import set_nlu_logger
from snips_nlu.common.utils import check_random_state
if verbose == 1:
set_nlu_logger(logging.INFO)
elif verbose >= 2:
set_nlu_logger(logging.DEBUG)
with Path(dataset_path).open("r", encoding="utf8") as f:
dataset = json.load(f)
config = None
if config_path is not None:
with Path(config_path).open("r", encoding="utf8") as f:
config = json.load(f)
random_state = check_random_state(random_seed)
print("Create and train the engine...")
engine = SnipsNLUEngine(config, random_state=random_state).fit(dataset)
print("Persisting the engine...")
engine.persist(output_path)
print("Saved the trained engine to %s" % output_path)