-
-
Notifications
You must be signed in to change notification settings - Fork 4.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
58 additions
and
54 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,17 +1,17 @@ | ||
""" | ||
This package contains implementations of various streaming corpus I/O format. | ||
""" | ||
|
||
# flake8: noqa | ||
# bring corpus classes directly into package namespace, to save some typing | ||
from .indexedcorpus import IndexedCorpus # noqa:F401 must appear before the other classes | ||
from .indexedcorpus import IndexedCorpus # must appear before the other classes | ||
|
||
from .mmcorpus import MmCorpus # noqa:F401 | ||
from .bleicorpus import BleiCorpus # noqa:F401 | ||
from .svmlightcorpus import SvmLightCorpus # noqa:F401 | ||
from .lowcorpus import LowCorpus # noqa:F401 | ||
from .dictionary import Dictionary # noqa:F401 | ||
from .hashdictionary import HashDictionary # noqa:F401 | ||
from .wikicorpus import WikiCorpus # noqa:F401 | ||
from .textcorpus import TextCorpus # noqa:F401 | ||
from .ucicorpus import UciCorpus # noqa:F401 | ||
from .malletcorpus import MalletCorpus # noqa:F401 | ||
from .mmcorpus import MmCorpus | ||
from .bleicorpus import BleiCorpus | ||
from .svmlightcorpus import SvmLightCorpus | ||
from .lowcorpus import LowCorpus | ||
from .dictionary import Dictionary | ||
from .hashdictionary import HashDictionary | ||
from .wikicorpus import WikiCorpus | ||
from .textcorpus import TextCorpus | ||
from .ucicorpus import UciCorpus | ||
from .malletcorpus import MalletCorpus |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,10 +1,10 @@ | ||
""" | ||
This package contains wrappers for other topic modeling programs. | ||
""" | ||
|
||
from .ldamallet import LdaMallet # noqa:F401 | ||
from .dtmmodel import DtmModel # noqa:F401 | ||
from .ldavowpalwabbit import LdaVowpalWabbit # noqa:F401 | ||
from .fasttext import FastText # noqa:F401 | ||
from .wordrank import Wordrank # noqa:F401 | ||
from .varembed import VarEmbed # noqa:F401 | ||
# flake8: noqa | ||
from .ldamallet import LdaMallet | ||
from .dtmmodel import DtmModel | ||
from .ldavowpalwabbit import LdaVowpalWabbit | ||
from .fasttext import FastText | ||
from .wordrank import Wordrank | ||
from .varembed import VarEmbed |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,7 +1,11 @@ | ||
""" | ||
This package contains functions to preprocess raw text | ||
""" | ||
|
||
# flake8: noqa | ||
# bring model classes directly into package namespace, to save some typing | ||
from .porter import PorterStemmer | ||
from .preprocessing import * | ||
from .preprocessing import remove_stopwords, strip_punctuation, strip_tags, \ | ||
strip_short, strip_numeric, strip_non_alphanum, \ | ||
strip_multiple_whitespaces, split_alphanum, \ | ||
stem_text, preprocess_string, preprocess_documents, \ | ||
read_file, read_files |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,4 +1,4 @@ | ||
|
||
# flake8: noqa | ||
# bring model classes directly into package namespace, to save some typing | ||
from .summarizer import summarize, summarize_corpus # noqa:F401 | ||
from .keywords import keywords # noqa:F401 | ||
from .summarizer import summarize, summarize_corpus | ||
from .keywords import keywords |