from hare import Hare, Conversation
from hare.tensorflowbrain import BiGruBrain
mockhare = Hare()
mockhare.brain = BiGruBrain()
for i in range(10000):
convo = Conversation()
convo.add_utterance(speaker='a', content='c c c c c')
convo.add_utterance(speaker='b', content='c c c c c')
convo.add_utterance(speaker='b', content='c c c c b')
convo.add_utterance(speaker='a', content='c c c c a')
convo.label_speaker('b', 1)
mockhare.add_conversation(convo)
mockhare.train()
mockhare.visualize_history_for_conversation()
from sys import argv
from hare import Hare
from hare.brain import DictBasedBrain
from hare.conversation import import_conversations
THRESHOLDS = [0.01, 0.025, 0.05, 0.075, 0.1, 0.25, 0.5, 0.75]
CONVERSATIONS_FILE = '../datasets/LoL/heldout_conversations_anon.txt'
NR_OF_CONVERSATIONS = 1000
print('Importing conversations')
conversations = import_conversations(CONVERSATIONS_FILE)[:NR_OF_CONVERSATIONS]
print('Loading pretrained model')
exp_hare = Hare(name='dict_based')
exp_hare.brain = DictBasedBrain()
exp_hare.brain.bad_words = [
'f**k', 'fck', 'fuk', 'shit', 'stfu', 'wtf', 'suck', 'noob', 'newb',
'n00b', 'f*g', 'loser'
]
result_file = open('moba_dic', 'w')
for n, conversation in enumerate(conversations):
print('Processing conv', n)
exp_hare.add_conversation(conversation)
exp_hare.save_history_for_conversation(result_file, n)
from hare import Hare, Conversation
from hare.brain import BiGruBrain
brain: BiGruBrain = BiGruBrain()
brain.embedding_location = '/vol/bigdata/word_embeddings/glove/glove.6B.50d.txt'
brain.verbose = True
hare = Hare()
hare.brain = brain
convo = Conversation()
convo.add_utterance(speaker='a', content='hate you')
convo.add_utterance(speaker='b', content='i love you')
convo.label_speaker('a', 1)
hare.add_conversation(convo)
hare.train()
hare.save('/vol/tensusers2/wstoop/HaRe/hare/pretrained/simple')
hare.update_status_history_for_conversation()
hare.visualize_history_for_conversation()
elif line[0] == '#':
try:
current_conversation.label_speaker(line.split()[1], 1)
except IndexError:
continue
conversations.append(current_conversation)
current_conversation = Conversation()
if len(conversations) % 100 == 0:
print(len(conversations))
if len(conversations) == NR_OF_CONVERSATIONS:
break
continue
speaker, content = line.split('\t')
current_conversation.add_utterance(speaker, content)
#Add to a hare object
moba_hare = Hare()
for conversation in conversations:
moba_hare.add_conversation(conversation)
moba_hare.brain = BiGruBrain()
moba_hare.brain.downsampling = True
moba_hare.brain._max_sequence_length = 500
moba_hare.train()
moba_hare.save('moba')
from hare import Hare, Conversation
from hare.tensorflowbrain import LSTMBrain, BiGruBrain
from hare.conversation import import_conversations
from hare.embedding import load_embedding_dictionary
#Load the conversations
DATA_ROOT = '../datasets/LoL/'
CONVERSATIONS_FILE = DATA_ROOT+'train_conversations_anon.txt'
print('Importing conversations')
conversations = import_conversations(CONVERSATIONS_FILE)
#Add to a hare object
moba_hare = Hare()
for conversation in conversations:
moba_hare.add_conversation(conversation)
brain = BiGruBrain()
brain.embedding_location = DATA_ROOT+'train_toxic_embeddings'
brain.verbose = True
brain.downsampling = True
brain.learning_epochs = 10
brain._max_sequence_length = 500
brain.include_casing_information = True
moba_hare.brain = brain
moba_hare.train()
moba_hare.save('m05')
current_conversation = Conversation()
if len(conversations) % 100 == 0:
print(len(conversations))
if len(conversations) == NR_OF_CONVERSATIONS:
break
continue
speaker, content = line.split('\t')
current_conversation.add_utterance(speaker, content)
#Add to a hare object
for downsample_ratio in DOWNSAMPLE_RATIOS:
for training_size in TRAINING_SIZES:
print('===', 'training', downsample_ratio, training_size, '===')
exp_hare = Hare()
for conversation in conversations[:training_size]:
exp_hare.add_conversation(conversation)
exp_hare.brain = BiGruBrain()
exp_hare.brain.downsampling = True
exp_hare.brain.downsampling_ratio = downsample_ratio
exp_hare.brain._max_sequence_length = 500
exp_hare.train()
exp_hare.save('moba_' + str(downsample_ratio) + '_' +
str(training_size))
from hare import Hare, Conversation
from hare.brain import RandomBrain
random_hare = Hare()
random_hare.brain = RandomBrain()
convo = Conversation()
random_hare.add_conversation(convo)
convo.add_utterance(speaker='a', content='hello')
convo.add_utterance(speaker='b', content='hello')
convo.add_utterance(speaker='a', content='how is everyone doing?')
random_hare.update_status_history_for_conversation(0)
print(random_hare.status_per_conversation[0])
convo.label_speaker('b', 0.9)
acc = random_hare.calculate_retrospective_accuracy()
print(acc)
from hare import load_pretrained, load_example_conversations
from hare.visualize import visualize_retrospective_precision_and_recall
from hare import Hare
from hare.brain import DictBasedBrain
moba_hare = Hare()
moba_hare.brain = DictBasedBrain()
for conversation in load_example_conversations():
moba_hare.add_conversation(conversation)
THRESHOLDS = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
visualize_retrospective_precision_and_recall(moba_hare)