def train_model(self, data, model_library, model):
"""data is an instance of DragnetModelData
model_library is a list of model definitions as input to
run_train_models
model provides model.make_features to make the features
"""
from mozsci.map_train import run_train_models
# to train the model need a set of all the features and their labels
# the features + labels are block level
# get the features from the first document to see how many features we have
features, labels, weights = self.make_features_from_data(data, model)
# cap weights!
weights = np.minimum(weights, 200)
# do kfold cross validation
folds = cv_kfold(len(labels), self.kfolds, seed=2)
if self.weighted:
errors = run_train_models(processes=4, model_library=model_library,
X=features, y=labels, folds=folds, weights=weights)
else:
errors = run_train_models(processes=4, model_library=model_library,
X=features, y=labels, folds=folds)
return errors, features, labels, weights, folds
def train_model(self, data, model_library, features_to_use):
"""data is an instance of DragnetModelData
model_library: the block_models to train as a list of model
definitions as input to run_train_models
features_to_use = a list of the features to use. Must be one of
the features known by AllFeatures
"""
from . import AllFeatures
from .blocks import TagCountReadabilityBlockifier as Blkr
from mozsci.map_train import run_train_models
# assemble the features
feature_instances = []
for f in features_to_use:
feature_instances.append(AllFeatures.get(f))
# do feature centering
print("Initializing features")
for f in feature_instances:
# check to see if this feature needs to be init
# if so, then init it, take the return object and serialize to json
if hasattr(f, 'init_params'):
# initialize it
model_init = ContentExtractionModel(Blkr, [f], None)
features, labels, weights = self.make_features_from_data(
data, model_init, train=True)
mean_std = f.init_params(features)
f.set_params(mean_std)
model_to_train = ContentExtractionModel(Blkr, feature_instances, None)
# train the model
print("Training the model")
features, labels, weights = self.make_features_from_data(
data, model_to_train, training_or_test='training')
# cap weights!
weights = np.minimum(weights, 200)
# do kfold cross validation
if self.kfolds > 1:
folds = cv_kfold(len(labels), self.kfolds, seed=2)
else:
folds = None
if self.weighted:
errors = run_train_models(
processes=1, model_library=model_library,
X=features, y=labels, folds=folds, weights=weights)
else:
errors = run_train_models(
processes=1, model_library=model_library,
X=features, y=labels, folds=folds)
return errors, features, labels, weights, folds
def train_model(self, data, model_library, features_to_use):
"""data is an instance of DragnetModelData
model_library: the block_models to train as a list of model
definitions as input to run_train_models
features_to_use = a list of the features to use. Must be one of
the features known by AllFeatures
"""
from . import AllFeatures
from .blocks import TagCountReadabilityBlockifier as Blkr
from mozsci.map_train import run_train_models
# assemble the features
feature_instances = []
for f in features_to_use:
feature_instances.append(AllFeatures.get(f))
# do feature centering
print("Initializing features")
for f in feature_instances:
# check to see if this feature needs to be init
# if so, then init it, take the return object and serialize to json
if hasattr(f, 'init_params'):
# initialize it
model_init = ContentExtractionModel(Blkr, [f], None)
features, labels, weights = self.make_features_from_data(
data, model_init, train=True)
mean_std = f.init_params(features)
f.set_params(mean_std)
model_to_train = ContentExtractionModel(Blkr, feature_instances, None)
# train the model
print("Training the model")
features, labels, weights = self.make_features_from_data(
data, model_to_train, training_or_test='training')
# cap weights!
weights = np.minimum(weights, 200)
# do kfold cross validation
if self.kfolds > 1:
folds = cv_kfold(len(labels), self.kfolds, seed=2)
else:
folds = None
if self.weighted:
errors = run_train_models(
processes=1, model_library=model_library,
X=features, y=labels, folds=folds, weights=weights)
else:
errors = run_train_models(
processes=1, model_library=model_library,
X=features, y=labels, folds=folds)
return errors, features, labels, weights, folds
def test_run_train_models(self):
import re
model_library = [[LogisticRegression, classification_error, None, (), {'lam':0.5}],
[LogisticRegression, classification_error, None, (), {'lam':50}]]
errors = run_train_models(2, model_library, X=self.X, y=self.y)
for k in errors.keys():
if re.search("{'lam': 0.5}", k):
err_check = errors[k]
self.assertTrue(abs(err_check['train'] - 0.06) < 1e-8)
def test_run_train_models(self):
import re
model_library = [[
LogisticRegression, classification_error, None, (), {
'lam': 0.5
}
], [LogisticRegression, classification_error, None, (), {
'lam': 50
}]]
errors = run_train_models(2, model_library, X=self.X, y=self.y)
for k in errors.keys():
if re.search("{'lam': 0.5}", k):
err_check = errors[k]
self.assertTrue(abs(err_check['train'] - 0.06) < 1e-8)
