mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
Add setup steps
This commit is contained in:
parent
56bca8d9f6
commit
ae96848245
|
@ -3799,6 +3799,9 @@
|
||||||
"description": "tmtoolkit is a set of tools for text mining and topic modeling with Python developed especially for the use in the social sciences, in journalism or related disciplines. It aims for easy installation, extensive documentation and a clear programming interface while offering good performance on large datasets by the means of vectorized operations (via NumPy) and parallel computation (using Python’s multiprocessing module and the loky package).",
|
"description": "tmtoolkit is a set of tools for text mining and topic modeling with Python developed especially for the use in the social sciences, in journalism or related disciplines. It aims for easy installation, extensive documentation and a clear programming interface while offering good performance on large datasets by the means of vectorized operations (via NumPy) and parallel computation (using Python’s multiprocessing module and the loky package).",
|
||||||
"github": "WZBSocialScienceCenter/tmtoolkit",
|
"github": "WZBSocialScienceCenter/tmtoolkit",
|
||||||
"code_example": [
|
"code_example": [
|
||||||
|
"# Note: This requires these setup steps:",
|
||||||
|
"# pip install tmtoolkit[recommended]",
|
||||||
|
"# python -m tmtoolkit setup en",
|
||||||
"from tmtoolkit.corpus import Corpus, tokens_table, lemmatize, to_lowercase, dtm",
|
"from tmtoolkit.corpus import Corpus, tokens_table, lemmatize, to_lowercase, dtm",
|
||||||
"from tmtoolkit.bow.bow_stats import tfidf, sorted_terms_table",
|
"from tmtoolkit.bow.bow_stats import tfidf, sorted_terms_table",
|
||||||
"# load built-in sample dataset and use 4 worker processes",
|
"# load built-in sample dataset and use 4 worker processes",
|
||||||
|
|
Loading…
Reference in New Issue
Block a user