Git-Mirrors/textfiles-politics
1
0
Fork 0
mirror of https://github.com/nhammer514/textfiles-politics.git synced 2025-05-07 00:56:12 -04:00
Code Issues Projects Releases Packages Wiki Activity

restores xml root element to pre-src

Browse source
This commit is contained in:
ebeshero 2023-04-28 02:15:04 -04:00
parent cb909e97f3
commit 22a4906740
483 changed files with 32919 additions and 33179 deletions
Download patch file Download diff file Expand all files Collapse all files

1000
pythonCode/conspPERSON.txt
View file

File diff suppressed because it is too large Load diff

3
pythonCode/personTagger.py
View file

@ -6,7 +6,7 @@ from saxonche import PySaxonProcessor
#### Loads all of the necessary variables and functions.
nlp = spacy.cli.download("en_core_web_lg")
#nlp = spacy.cli.download("en_core_web_lg")
nlp = spacy.load("en_core_web_lg")
#########################################################################################
# ebb: After reading the NLP output, we know spaCy is making some mistakes.
@ -1024,6 +1024,7 @@ patterns = [
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Earline\s+?Roberts"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Lee\s+?Bowers,\s+?Jr\."}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Locust"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Starmaster"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Nuri\s+?Al-Said"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Pamela\s+?Courson"}}]},
{"label": "PERSON", "pattern": [{"TEXT": {"REGEX": "Jimmy\s+?Hendrix"}}]},