In [ ]:

from fastai import *        # Quick access to most common functionality
from fastai.text import *   # Quick access to NLP functionality

Text example¶

An example of creating a language model and then transfering to a classifier.

In [ ]:

path = untar_data(URLs.IMDB_SAMPLE)
path

Out[ ]:

PosixPath('/home/ubuntu/.fastai/data/imdb_sample')

Open and view the independent and dependent variables:

In [ ]:

df = pd.read_csv(path/'texts.csv', header=None)
df.head()

Out[ ]:

	0	1	2
0	label	text	is_valid
1	0	Un-bleeping-believable! Meg Ryan doesn't even ...	False
2	1	This is a extremely well-made film. The acting...	False
3	0	Every once in a long while a movie will come a...	False
4	1	Name just says it all. I watched this movie wi...	False

Create a DataBunch for each of the language model and the classifier:

In [ ]:

data_lm = TextLMDataBunch.from_csv(path, 'texts.csv')
data_clas = TextClasDataBunch.from_csv(path, 'texts.csv', vocab=data_lm.train_ds.vocab, bs=42)

We'll fine-tune the language model. fast.ai has a pre-trained English model available that we can download, we jsut have to specify it like this:

In [ ]:

learn = language_model_learner(data_lm, pretrained_model=URLs.WT103)
learn.unfreeze()
learn.fit(2, slice(1e-4,1e-2))

Total time: 00:48
epoch  train_loss  valid_loss  accuracy
1      4.898340    4.119840    0.254581  (00:24)
2      4.610869    4.052252    0.260789  (00:23)

Save our language model's encoder:

In [ ]:

learn.save_encoder('enc')

Fine tune it to create a classifier:

In [ ]:

learn = text_classifier_learner(data_clas)
learn.load_encoder('enc')
learn.fit(3, 1e-3)

In [ ]: