Rename library

Signed-off-by: András Schmelczer <andras@schmelczer.dev>

example/README.md

@@ -7,6 +7,6 @@ mkdir ss-data && cd ss-data
 wget https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/manifest.txt
 wget -B https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/ -i manifest.txt
 cd -
-python3 -m good_ai.open_s3 --secrets s3.ini --push ss-data
+python3 -m great_ai.open_s3 --secrets s3.ini --push ss-data
 rm -rf ss-data
 ```

example/main_batch.py

@@ -6,7 +6,7 @@ from random import shuffle
 from devtools import debug
 from predict_domain import predict_domain
 
-from good_ai import process_batch
+from great_ai import process_batch
 
 if __name__ == "__main__":
     with open(".cache/data-1/s2-corpus-323.json") as f:

example/main_service.py

@@ -3,7 +3,7 @@
 
 from predict_domain import predict_domain
 
-from good_ai import serve
+from great_ai import serve
 
 if __name__ == "__main__":
     serve(predict_domain)

example/predict_domain.py

@@ -5,8 +5,8 @@ from preprocess import preprocess
 from pydantic import BaseModel
 from sklearn.pipeline import Pipeline
 
-from good_ai import log_argument, log_metric, use_model
-from good_ai.utilities.clean import clean
+from great_ai import log_argument, log_metric, use_model
+from great_ai.utilities.clean import clean
 
 
 class DomainPrediction(BaseModel):

example/preprocess.py

@@ -1,8 +1,8 @@
 import re
 
-from good_ai.utilities.lemmatize_text import lemmatize_text
+from great_ai.utilities.lemmatize_text import lemmatize_text
 
 
 def preprocess(text: str) -> str:
-    lemmas = [re.sub(r"\d+", "NUM", lemma) for lemma in lemmatize_text(text)]
+    lemmas = [re.sub(r"\d[\d.,]*", "NUM", lemma) for lemma in lemmatize_text(text)]
     return " ".join(lemmas)