Commit History

Add new model trained on sentiment140
419453c

Tymec commited on

Cache label data along with tokenized text data
af84d9b

Tymec commited on

Fix broken tokenization
447f97e

Tymec commited on

Add slang map
e1645d7

Tymec commited on

Add progress bar to serialize
632adc4

Tymec commited on

Add more vectorizers, classifiers and CLI options
b0ade1a

Tymec commited on

Refactor typing and update tokenization rules
228859a

Tymec commited on

Add document frequency threshold
c5ed75e

Tymec commited on

Ignore amazonreviews test
d09d1f6

Tymec commited on

Chunked serialization
afaacd1

Tymec commited on

Update options, force GC, tweak parameters and add flags
18cc46a

Tymec commited on

Ability to change number of parallel jobs for search
8471e78

Tymec commited on

Create model in train_model
3854a1f

Tymec commited on

Tokenization rework
2c1f9dd

Tymec commited on

Add dataset for testing
e50b20c

Tymec commited on

Slight optimizations
0ca5366

Tymec commited on

Change HF entry point and add examples
b42b884

Tymec commited on

Handle missing spacy model
7ce074d

Tymec commited on

Import spacy model as module
7b9e59d

Tymec commited on

Add evaluate command
cdf1241

Tymec commited on

Use spacy instead of nltk and move data functions to separate module
a092d54

Tymec commited on

Remove unused constanst
9a96b6b

Tymec commited on

Add cross validation
5a2db0a

Tymec commited on

Use stopwords from NLTK and download NLTK data
204391c

Tymec commited on

Fix merge
0993d5e

Tymec commited on

Merge branch 'master' of https://github.com/Tymec/projekt-psi
b43b167

Tymec commited on

Completely change the structure of the project
85ac990

Tymec commited on

Model
391bd16

Tymec commited on

Restructure project into package structure
667fe9d

Tymec commited on