trainers

Package Contents

BasicTrainer

BERTopicTrainer

FASTopicTrainer

LDAGensimTrainer

LDASklearnTrainer

NMFGensimTrainer

NMFSklearnTrainer

CrosslingualTrainer

DynamicTrainer

DTMTrainer

HierarchicalTrainer

HDPGensimTrainer

class BasicTrainer(model, dataset, num_top_words=15, epochs=200, learning_rate=0.002, batch_size=200, lr_scheduler=None, lr_step_size=125, log_interval=5, verbose=False)
model
dataset
num_top_words = 15
epochs = 200
learning_rate = 0.002
batch_size = 200
lr_scheduler = None
lr_step_size = 125
log_interval = 5
verbose = False
make_optimizer()
make_lr_scheduler(optimizer)
train()
test(bow)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class BERTopicTrainer(dataset, num_topics=50, num_top_words=15)
model
dataset
train()
test(texts)
get_beta()
get_top_words()
export_theta()
class FASTopicTrainer(dataset, num_topics=50, num_top_words=15, preprocess=None, epochs=200, DT_alpha=3.0, TW_alpha=2.0, theta_temp=1.0, verbose=False)
dataset
num_top_words = 15
model
epochs = 200
train()
test(texts)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class LDAGensimTrainer(dataset, num_topics=50, num_top_words=15, max_iter=1, alpha='symmetric', eta=None, verbose=False)
dataset
num_topics = 50
vocab_size
max_iter = 1
alpha = 'symmetric'
eta = None
verbose = False
num_top_words = 15
train()
test(bow)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class LDASklearnTrainer(model, dataset, num_top_words=15, verbose=False)
model
dataset
num_top_words = 15
verbose = False
train()
test(bow)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class NMFGensimTrainer(dataset, num_topics=50, num_top_words=15, max_iter=1)
dataset
num_topics = 50
num_top_words = 15
vocab_size
max_iter = 1
train()
test(bow)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class NMFSklearnTrainer(model, dataset, num_top_words=15)
model
dataset
num_top_words = 15
train()
test(bow)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class CrosslingualTrainer(model, dataset, num_top_words=15, epochs=500, learning_rate=0.002, batch_size=200, lr_scheduler=None, lr_step_size=125, log_interval=5, verbose=False)
model
dataset
num_top_words = 15
epochs = 500
learning_rate = 0.002
batch_size = 200
lr_scheduler = None
lr_step_size = 125
log_interval = 5
make_optimizer()
make_lr_scheduler(optimizer)
train()
test(bow_en, bow_cn)
infer_theta(bow, lang)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class DynamicTrainer(model, dataset, num_top_words=15, epochs=200, learning_rate=0.002, batch_size=200, lr_scheduler=None, lr_step_size=125, log_interval=5, verbose=False)
model
dataset
num_top_words = 15
epochs = 200
learning_rate = 0.002
batch_size = 200
lr_scheduler = None
lr_step_size = 125
log_interval = 5
verbose = False
make_optimizer()
make_lr_scheduler(optimizer)
train()
test(bow, times)
get_beta()
get_top_words(num_top_words=None)
export_theta()
class DTMTrainer(dataset, num_topics=50, num_top_words=15, alphas=0.01, chain_variance=0.005, passes=10, lda_inference_max_iter=25, em_min_iter=6, em_max_iter=20, verbose=False)
dataset
vocab_size
num_topics = 50
num_top_words = 15
alphas = 0.01
chain_variance = 0.005
passes = 10
lda_inference_max_iter = 25
em_min_iter = 6
em_max_iter = 20
verbose = False
train()
test(bow)
get_theta()
get_beta()
get_top_words(num_top_words=None)
export_theta()
class HierarchicalTrainer(model, dataset, num_top_words=15, epochs=200, learning_rate=0.002, batch_size=200, lr_scheduler=None, lr_step_size=125, log_interval=5, verbose=False)
model
dataset
num_top_words = 15
epochs = 200
learning_rate = 0.002
batch_size = 200
lr_scheduler = None
lr_step_size = 125
log_interval = 5
verbose = False
make_optimizer()
make_lr_scheduler(optimizer)
train()
test(bow)
get_phi()
get_beta()
get_top_words(num_top_words=None, annotation=False)
export_theta()
class HDPGensimTrainer(dataset, num_top_words=15, max_chunks=None, max_time=None, chunksize=256, kappa=1.0, tau=64.0, K=15, T=150, alpha=1, gamma=1, eta=0.01, scale=1.0, var_converge=0.0001, verbose=False)
dataset
num_top_words = 15
vocab_size
max_chunks = None
max_time = None
chunksize = 256
kappa = 1.0
tau = 64.0
K = 15
T = 150
alpha = 1
gamma = 1
eta = 0.01
scale = 1.0
var_converge = 0.0001
verbose = False
train()
test(bow)
get_beta()
get_top_words(num_top_words=None)
export_theta()