from sklearn.cross_validation import ShuffleSplit
from sklearn.grid_search import RandomizedSearchCV
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from nnet.oldstyle.base_optimize import name_from_file
from nnet.prepare import LogTransform
from nnet.score_logging import get_logloss_loggingscorer
from settings import OPTIMIZE_RESULTS_DIR
from nnet.scikit import NNet
from settings import LOGS_DIR, VERBOSITY, SUBMISSIONS_DIR, PRIORS
from utils.features import PositiveSparseFeatureGenerator, PositiveSparseRowFeatureGenerator
from utils.ioutil import makeSubmission
from utils.loading import get_preproc_data
from utils.postprocess import scale_to_priors
train, labels, test = get_preproc_data(None, expand_confidence=None)
cpus = max(cpu_count() - 1, 1)
random = RandomState()
opt = RandomizedSearchCV(
estimator=Pipeline([
('row', PositiveSparseRowFeatureGenerator()),
('gen23',
PositiveSparseFeatureGenerator(difficult_classes=(2, 3),
extra_features=40)),
('gen234',
PositiveSparseFeatureGenerator(difficult_classes=(2, 3, 4),
extra_features=40)),
('gen19',
PositiveSparseFeatureGenerator(difficult_classes=(1, 9),
from nnet.oldstyle.base_optimize import name_from_file
from nnet.prepare import LogTransform
from nnet.scikit import NNet
from utils.features import PositiveSparseRowFeatureGenerator, PositiveSparseFeatureGenerator
from nndist.distance import DistanceFeatureGenerator
from utils.loading import get_preproc_data
train, labels, test = get_preproc_data(Pipeline([
('row', PositiveSparseRowFeatureGenerator()),
('distp31', DistanceFeatureGenerator(n_neighbors=3, distance_p=1)),
('distp52', DistanceFeatureGenerator(n_neighbors=5, distance_p=2)),
('gen23',
PositiveSparseFeatureGenerator(difficult_classes=(2, 3),
extra_features=40)),
('gen234',
PositiveSparseFeatureGenerator(difficult_classes=(2, 3, 4),
extra_features=40)),
('gen19',
PositiveSparseFeatureGenerator(difficult_classes=(1, 9),
extra_features=40)),
('log', LogTransform()),
('scale03', MinMaxScaler(feature_range=(0, 3))),
]),
expand_confidence=0.9)
net = NNet(
name=name_from_file(),
dense1_nonlinearity='rectify',
dense1_init='glorot_normal',
auto_stopping=True,
max_epochs=1000,
from sklearn.grid_search import RandomizedSearchCV
from sklearn.metrics.scorer import log_loss_scorer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from nnet.oldstyle.base_optimize import name_from_file
from nnet.prepare import LogTransform
from nnet.scikit import NNet
from settings import LOGS_DIR, VERBOSITY, SUBMISSIONS_DIR
from utils.features import PositiveSparseFeatureGenerator, PositiveSparseRowFeatureGenerator, DistanceFeatureGenerator
from utils.ioutil import makeSubmission
from utils.loading import get_preproc_data, get_training_data, get_testing_data
train, labels, test = get_preproc_data(
Pipeline([
('row', PositiveSparseRowFeatureGenerator()),
#('distp31', DistanceFeatureGenerator(n_neighbors = 3, distance_p = 1)),
#('distp52', DistanceFeatureGenerator(n_neighbors = 5, distance_p = 2)),
]),
expand_confidence=0.9)
#train, labels = get_training_data()[:2]
#test = get_testing_data()[0]
#cpus = max(cpu_count() - 1, 1)
#random = RandomState()
opt = RandomizedSearchCV(
estimator=Pipeline([
('gen23',
PositiveSparseFeatureGenerator(difficult_classes=(2, 3),
extra_features=40)),
('gen234',
# Due to this error:
# ValueError: Loading weights from a list of parameter values is no longer supported.
# Please send me something like the return value of 'net.get_all_param_values()' instead.
# testing new method
import warnings
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from nnet.prepare import LogTransform
from nnet.scikit import NNet
from utils.loading import get_preproc_data
warnings.filterwarnings("ignore")
train, labels, test = get_preproc_data(Pipeline([
('log', LogTransform()),
('scale03', MinMaxScaler(feature_range=(0, 3))),
]),
expand_confidence=0.9)
nn = NNet(max_epochs=1)
nn.fit(train, labels)
nn.save(filepath='/tmp/test')
nn = NNet.load(filepath='/tmp/test')
w = nn.net.get_all_params_values()
print w
nn.net.load_params_from(w)
