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()
#Add the precalculated conversation history to hare objects
hares = []
for conv_hist_file in CONVERSATION_HISTORY_FILES:
status_per_conversation = []
for n, line in enumerate(open(conv_hist_file)):
status_per_conversation.append(loads(line)[:CONVERSATION_LENGTH])
if n % 100 == 0:
print(conv_hist_file, n)
for threshold in THRESHOLDS:
h = Hare(name=threshold)
h.status_per_conversation = status_per_conversation
h.cut_off_value = threshold
hares.append(h)
#Load the conversations
conversations = []
current_conversation = Conversation()
for line in open(CONVERSATIONS_FILE):
line = line.strip()
if len(line) == 0:
continue
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 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)
#Add the precalculated conversation history to hare objects
hares = []
for conv_hist_file in CONVERSATION_HISTORY_FILES:
status_per_conversation = []
for n, line in enumerate(open(conv_hist_file)):
status_per_conversation.append(loads(line)[:CONVERSATION_LENGTH])
if n % 100 == 0:
print(conv_hist_file, n)
for threshold in THRESHOLDS:
h = Hare(name=conv_hist_file + ':' + str(threshold))
h.status_per_conversation = status_per_conversation
h.cut_off_value = threshold
hares.append(h)
#Load the conversations
conversations = []
current_conversation = Conversation()
for line in open(CONVERSATIONS_FILE):
line = line.strip()
if len(line) == 0:
continue
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')
# to do met conversation.remove_speaker()
#Create a hare object for each threshold
for threshold in thresholds:
detector_name = conv_hist_file + '@' + str(threshold)
folder_name = OUTPUT_FOLDER + detector_name + '/'
try:
rmtree(folder_name)
except FileNotFoundError:
pass
mkdir(folder_name)
h = Hare(name=detector_name)
h.status_per_conversation = status_per_conversation
h.cut_off_value = threshold
for conversation in conversations:
h.add_conversation(conversation)
hares.append(h)
per_player = []
tp = []
fp = []
fbeta = {b: [] for b in BETA_VALUES}
#Calculate metrics for this detector/threshold combi
for utterance_index in range(CONVERSATION_LENGTH):
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)
for convo_index, conversation in enumerate(conversations):
#For this conversation, we want to know the conversation history for every detector
for detector, thresholds in DETECTOR_THRESHOLDS.items():
conversation_history = loads(open_conversation_history_files[detector].readline())
scores_for_this_conversation = []
#We check what scores this means for every threshold
for threshold in thresholds:
if threshold not in all_scores[detector].keys():
all_scores[detector][threshold] = []
h = Hare()
h.add_conversation(conversation)
h.status_per_conversation = [conversation_history]
h.cut_off_value = threshold
for point_in_conversation in INTERESTING_POINTS_IN_CONVERSATION:
true, predicted = h.get_true_and_predicted_scores_at_utterance_index(point_in_conversation,categorize_predicted_scores=True)
score = fbeta_score(true, predicted, 1)
scores_for_this_conversation.append(score)
if convo_index == 0:
headers.append(detector+':'+str(threshold)+':'+str(point_in_conversation))
all_scores[detector][threshold].append(scores_for_this_conversation[-len(INTERESTING_POINTS_IN_CONVERSATION):])
CONVERSATION_LENGTH = 200
#Add the precalculated conversation history to hare objects
hares = []
for conv_hist_file in CONVERSATION_HISTORY_FILES:
status_per_conversation = []
for n, line in enumerate(open(conv_hist_file)):
status_per_conversation.append(loads(line)[:CONVERSATION_LENGTH])
if n % 100 == 0:
print(conv_hist_file, n)
h = Hare(name=conv_hist_file)
h.status_per_conversation = status_per_conversation
hares.append(h)
#Load the conversations
conversations = []
current_conversation = Conversation()
for line in open(CONVERSATIONS_FILE):
line = line.strip()
if len(line) == 0:
continue
elif line[0] == '#':
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
CONVERSATIONS_FILE = 'datasets/LoL/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)
moba_hare.brain = BiGruBrain()
moba_hare.brain.embedding_location = 'datasets/LoL/train_toxic_embeddings'
moba_hare.brain.verbose = True
moba_hare.brain.downsampling = True
moba_hare.brain.learning_epochs = 10
moba_hare.brain._max_sequence_length = 500
moba_hare.train()
moba_hare.save('moba_bigru_embedding')
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)
