def keras_model():
from keras.regularizers import l2, activity_l2
from aiding_funcs.embeddings_handling import get_the_folds, join_folds
from keras.layers.recurrent import LSTM
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.embeddings import Embedding
from keras.regularizers import l1, activity_l1
import pickle
embeddings = pickle.load( open( "/data/dpappas/personality/emb.p", "rb" ) )
train = pickle.load( open( "/data/dpappas/personality/train.p", "rb" ) )
no_of_folds = 10
folds = get_the_folds(train,no_of_folds)
train_data = join_folds(folds,folds.keys()[:-1])
validation_data = folds[folds.keys()[-1]]
max_input_length = validation_data['features'].shape[1]
LSTM_size = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
Dense_size = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
opt = {{choice([ 'adadelta','sgd','rmsprop', 'adagrad', 'adadelta', 'adam'])}}
is_trainable = {{choice([ True, False ])}}
D = embeddings.shape[-1]
out_dim = 5
model = Sequential()
model.add(Embedding(input_dim = embeddings.shape[0], output_dim=D, weights=[embeddings], trainable=is_trainable, input_length = max_input_length))
model.add(LSTM(LSTM_size, activation = 'sigmoid'))
model.add(Dense(Dense_size, activation = 'sigmoid',W_regularizer=l2({{uniform(0, 1)}}), activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.add(Dense(out_dim, activation = 'linear',W_regularizer=l2({{uniform(0, 1)}}), activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.compile(loss='mse', optimizer= opt) # kalutera leei rmsprop o fchollet enw adam leei enas allos
model.fit(train_data['features'], train_data['labels'], nb_epoch=50, show_accuracy=False, verbose=2)
score = model.evaluate( validation_data['features'], validation_data['labels'])
#score = model.evaluate( train_data['features'], train_data['labels'])
return {'loss': score, 'status': STATUS_OK}
def keras_model():
from keras.models import Sequential
from keras.layers.core import Dense, Reshape, Activation, Flatten, Dropout
from keras.regularizers import l1, activity_l1, l2, activity_l2
from aiding_funcs.embeddings_handling import get_the_folds, join_folds
from aiding_funcs.label_handling import MaxMin, myRMSE, MaxMinFit
import pickle
train = pickle.load( open( "/data/dpappas/personality/train.p", "rb" ) )
no_of_folds = 10
folds = get_the_folds(train,no_of_folds)
train_data = join_folds(folds,folds.keys()[:-1])
validation_data = folds[folds.keys()[-1]]
mins, maxs = MaxMin(train_data['AV'])
T_AV = MaxMinFit(train_data['AV'], mins, maxs)
Dense_size = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
Dense_size2 = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
Dense_size3 = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
opt = {{choice([ 'adadelta','sgd','rmsprop', 'adagrad', 'adadelta', 'adam'])}}
out_dim = 5
model = Sequential()
model.add(Dense(Dense_size, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}}),input_dim = train_data['AV'].shape[-1] ))
model.add(Dense(Dense_size2, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.add(Dense(Dense_size3, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.add(Dense(out_dim, activation='linear',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.compile(loss='rmse', optimizer=opt)
model.fit(T_AV, train_data['labels'], nb_epoch=500, show_accuracy=False, verbose=2)
#score = model.evaluate( validation_data['features'], validation_data['labels'])
score = model.evaluate( T_AV, train_data['labels'])
print("score : " +str(score))
return {'loss': score, 'status': STATUS_OK}
def keras_model():
from keras.models import Sequential, Graph
from keras.layers.embeddings import Embedding
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Reshape, Activation, Flatten, Dropout
from keras.regularizers import l1, activity_l1, l2, activity_l2
from aiding_funcs.embeddings_handling import get_the_folds, join_folds
import pickle
embeddings = pickle.load( open( "/data/dpappas/personality/emb.p", "rb" ) )
train = pickle.load( open( "/data/dpappas/personality/train.p", "rb" ) )
no_of_folds = 10
folds = get_the_folds(train,no_of_folds)
train_data = join_folds(folds,folds.keys()[:-1])
validation_data = folds[folds.keys()[-1]]
max_input_length = validation_data['features'].shape[1]
CNN_filters = {{choice([5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195,200])}}
CNN_rows = {{choice([1,2,3,4,5,6,7,8,9,10])}}
Dense_size = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
Dense_size2 = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
Dense_size3 = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
opt = {{choice([ 'adadelta','sgd', 'adam'])}}
is_trainable = {{choice([ True, False ])}}
D = embeddings.shape[-1]
cols = D
out_dim = train_data['labels'].shape[-1]
graph = Graph()
graph.add_input(name='txt_data', input_shape=[train_data['features'].shape[-1]], dtype='int')
graph.add_node(Embedding( input_dim = embeddings.shape[0], output_dim=D, weights=[embeddings], trainable=is_trainable, input_length = max_input_length), name='Emb', input='txt_data')
graph.add_node(Reshape((1, max_input_length, D)), name = "Reshape", input='Emb')
graph.add_node( Convolution2D(CNN_filters, CNN_rows, cols, activation='sigmoid' ) , name='Conv', input='Reshape')
sh = graph.nodes['Conv'].output_shape
graph.add_node( MaxPooling2D(pool_size=(sh[-2], sh[-1])) , name='MaxPool', input='Conv')
graph.add_node( Flatten() , name='Flat', input='MaxPool')
graph.add_node( Dense(Dense_size, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})) , name='Dtxt', input='Flat')
graph.add_node( Dropout({{uniform(0, 1)}}) , name='Dropout1', input='Dtxt')
graph.add_input(name='av_data', input_shape=[train_data['AV'].shape[-1]])
graph.add_node( Dense(Dense_size2, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})) , name='Dav', input='av_data')
graph.add_node( Dropout({{uniform(0, 1)}}) , name='Dropout2', input='Dav')
graph.add_node( Dense(Dense_size3, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})), name='Dense1', inputs=['Dropout2', 'Dropout1'], merge_mode='concat')
graph.add_node( Dropout({{uniform(0, 1)}}) , name='Dropout3', input='Dense1')
graph.add_node( Dense(out_dim, activation='linear') , name='Dense2', input='Dropout3')
graph.add_output(name='output', input = 'Dense2')
graph.compile(optimizer=opt, loss={'output':'rmse'})
graph.fit(
{
'txt_data':train_data['features'],
'av_data':train_data['AV'],
'output':train_data['labels']
},
nb_epoch=500,
batch_size=64
)
scores = graph.evaluate({'txt_data':validation_data['features'], 'av_data':validation_data['AV'], 'output':validation_data['labels']})
print(scores)
return {'loss': scores, 'status': STATUS_OK}
def keras_model():
from keras.models import Sequential
from keras.layers.core import Dense
from keras.regularizers import l2, activity_l2
from aiding_funcs.embeddings_handling import get_the_folds, join_folds
from aiding_funcs.label_handling import MaxMin, MaxMinFit
import pickle
print('loading test.p')
test = pickle.load( open( "/data/dpappas/Common_Crawl_840B_tokkens_pickles/test.p", "rb" ) )
print('loading train.p')
train = pickle.load( open( "/data/dpappas/Common_Crawl_840B_tokkens_pickles/train.p", "rb" ) )
no_of_folds = 10
folds = get_the_folds(train,no_of_folds)
train_data = join_folds(folds,folds.keys()[:-1])
validation_data = folds[folds.keys()[-1]]
mins, maxs = MaxMin(train_data['labels'])
T_l = MaxMinFit(train_data['labels'], mins, maxs)
t_l = MaxMinFit(validation_data['labels'], mins, maxs)
Dense_size = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
Dense_size2 = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
opt = {{choice([ 'adadelta','sgd','rmsprop', 'adagrad', 'adadelta', 'adam'])}}
out_dim = 5
activity_l2_0 = {{uniform(0, 1)}}
activity_l2_1 = {{uniform(0, 1)}}
activity_l2_2 = {{uniform(0, 1)}}
l2_0 = {{uniform(0, 1)}}
l2_1 = {{uniform(0, 1)}}
l2_2 = {{uniform(0, 1)}}
model = Sequential()
model.add(Dense(Dense_size, activation='sigmoid',W_regularizer=l2(l2_0),activity_regularizer=activity_l2(activity_l2_0),input_dim = train_data['skipthoughts'].shape[-1] ))
model.add(Dense(Dense_size2, activation='sigmoid',W_regularizer=l2(l2_1),activity_regularizer=activity_l2(activity_l2_1)))
model.add(Dense(out_dim, activation='linear',W_regularizer=l2(l2_2),activity_regularizer=activity_l2(activity_l2_2)))
model.compile(loss='rmse', optimizer=opt)
#model.fit(train_data['skipthoughts'], train_data['labels'], nb_epoch=500, show_accuracy=False, verbose=2)
#score = model.evaluate( train_data['skipthoughts'], train_data['labels'])
model.fit(train_data['skipthoughts'], T_l, nb_epoch=500, show_accuracy=False, verbose=2)
score = model.evaluate( train_data['skipthoughts'], T_l)
print("score : " +str(score))
return {'loss': score, 'status': STATUS_OK}
def keras_model():
from keras.models import Sequential
from keras.layers.embeddings import Embedding
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Reshape, Activation, Flatten, Dropout
from keras.regularizers import l1, activity_l1, l2, activity_l2
from aiding_funcs.embeddings_handling import get_the_folds, join_folds
import pickle
embeddings = pickle.load( open( "/data/dpappas/personality/emb.p", "rb" ) )
train = pickle.load( open( "/data/dpappas/personality/train.p", "rb" ) )
no_of_folds = 10
folds = get_the_folds(train,no_of_folds)
train_data = join_folds(folds,folds.keys()[:-1])
validation_data = folds[folds.keys()[-1]]
max_input_length = validation_data['features'].shape[1]
CNN_filters = {{choice([5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95])}}
CNN_rows = {{choice([1,2,3,4,5,6])}}
Dense_size = {{choice([50, 100, 150, 200, 250, 300, 350, 400, 450, 500])}}
opt = {{choice([ 'adadelta','sgd','rmsprop', 'adagrad', 'adadelta', 'adam'])}}
is_trainable = {{choice([ True, False ])}}
D = embeddings.shape[-1]
cols = D
out_dim = 5
model = Sequential()
model.add(Embedding(input_dim = embeddings.shape[0], output_dim=D, weights=[embeddings], trainable=is_trainable, input_length = max_input_length))
model.add(Reshape((1, max_input_length, D)))
model.add(Convolution2D( CNN_filters, CNN_rows, cols, dim_ordering='th', activation='sigmoid' ))
sh = model.layers[-1].output_shape
model.add(MaxPooling2D(pool_size=(sh[-2], sh[-1]),dim_ordering = 'th'))
model.add(Flatten())
model.add(Dense(Dense_size, activation='sigmoid',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.add(Dense(out_dim, activation='linear',W_regularizer=l2({{uniform(0, 1)}}),activity_regularizer=activity_l2({{uniform(0, 1)}})))
model.compile(loss='mse', optimizer=opt)
model.fit(train_data['features'], train_data['labels'], nb_epoch=50, show_accuracy=False, verbose=2)
#score = model.evaluate( validation_data['features'], validation_data['labels'])
score = model.evaluate( train_data['features'], train_data['labels'])
return {'loss': score, 'status': STATUS_OK}
pred = clf.predict(test_X)
f1 = metrics.f1_score(test_y, pred, average='weighted')
accuracy = metrics.accuracy_score(test_y, pred)
print(" Acc: %f "%(accuracy))
result = {'f1' : f1,'accuracy' : accuracy,'train size' : len(train_y), 'test size' : len(test_y) }
return result
print('loading test.p')
test = pickle.load( open( "/data/dpappas/Common_Crawl_840B_tokkens_pickles/test.p", "rb" ) )
print('loading train.p')
train = pickle.load( open( "/data/dpappas/Common_Crawl_840B_tokkens_pickles/train.p", "rb" ) )
no_of_folds = 10
folds = get_the_folds(train,no_of_folds)
ret = {}
train_folds = range(9)
train_data = join_folds(folds,train_folds)
validation_data = folds[folds.keys()[-1]]
train_X = train_data['skipthoughts']
train_y = train_data['labels']
test_X = validation_data['skipthoughts']
test_y = validation_data['labels']
ret = {}
for index in range(5):
train_y_2 = train_y[:,index]
test_y_2 = test_y[:,index]