def train(self,load_file='',num_epochs=10,chunks=1000,learning_rate=0.001,n_units=256,dropout=0.5):
if self.vocab == []:
self.create_vocab()
if self.training_labels == []:
train_df = self.load_train_df(load_file)
else:
train_df = pd.DataFrame({'sub_seqs':self.training_sequences,'sub_label':self.training_labels,'seq_length':self.training_seq_lengths})
train,test = self.split_train_test(train_df,0.99)
print("Training Model with learning_rate = " + str(learning_rate) + " n_units = " + str(n_units) + " dropout = " +str(dropout))
self.model = rnn.train_model(train,test,self.vocab_size,self.sequence_chunk_size,num_epochs=num_epochs,chunks=chunks,
learning_rate=learning_rate,n_units=n_units,dropout=dropout)
return self.model
import tensorflow
import urllib
import zipfile
from tensorflow import nottingham_util
import rnn
url = "http://www-etud.iro.umontreal.ca/~boulanni/Nottingham.zip"
urllib.urlretrieve(url, "dataset.zip")
zip = zipfile.ZipFile(r'dataset.zip')
zip.extractall('data')
nottingham_util.create_model()
rnn.train_model()
import urllib
import zipfile
import nottingham_util
import rnn
zip = zipfile.ZipFile(r'dataset.zip')
zip.extractall('data')
# build the model
nottingham_util.create_model()
# train the model
rnn.train_model()
# use this to train a model on Democratic tweets
import rnn
# change this to train on a different dataset
training_name = "dem_tweets"
# leave these alone
data_folder = "data"
models_folder = "models"
new_tweets_folder = "tweets"
data_file = "{}/{}.txt".format(data_folder, training_name)
ckpt_file = "{}/{}/model.ckpt".format(models_folder, training_name)
rnn.train_model(iterations=20000, data_file=data_file, ckpt_file=ckpt_file)
