gobbli.dataset.cmu_movie_summary module¶
-
class
gobbli.dataset.cmu_movie_summary.
MovieSummaryDataset
(*args, **kwargs)[source]¶ Bases:
gobbli.dataset.base.BaseDataset
gobbli Dataset for the CMU Movie Summary dataset, framed as a multilabel classification problem predicting movie genres from plot summaries.
http://www.cs.cmu.edu/~ark/personas/
Blank constructor needed to satisfy mypy
-
METADATA_FILE
= 'MovieSummaries/movie.metadata.tsv'¶
-
PLOT_SUMMARIES_FILE
= 'MovieSummaries/plot_summaries.txt'¶
-
TRAIN_PCT
= 0.8¶
-
classmethod
data_dir
()¶ - Return type
Path
-
embed_input
(embed_batch_size=32, pooling=<EmbedPooling.MEAN: 'mean'>, limit=None)¶ - Return type
-
classmethod
load
(*args, **kwargs)¶ - Return type
-
predict_input
(predict_batch_size=32, limit=None)¶ - Return type
-
train_input
(train_batch_size=32, valid_batch_size=8, num_train_epochs=3, valid_proportion=0.2, split_seed=1234, shuffle_seed=1234, limit=None)¶ - Return type
-