requiring ntlk at least 3.9.1; making associated change from punkt to punkt_tab (#102)

agmoore4 · web-flow · commit 09f804b26801 · 2024-10-24T14:47:02.000-04:00
diff --git a/pvops/text/preprocess.py b/pvops/text/preprocess.py
@@ -7,9 +7,9 @@
 from datetime import datetime, timedelta
 
 try:
-    nltk.data.find('tokenizers/punkt')
+    nltk.data.find('tokenizers/punkt_tab')
 except LookupError:
-    nltk.download('punkt')
+    nltk.download('punkt_tab')
 
 def preprocessor(
     om_df, lst_stopwords, col_dict, print_info=False, extract_dates_only=False
diff --git a/requirements.txt b/requirements.txt
@@ -3,7 +3,7 @@ pandas
 numpy
 scipy
 scikit-learn
-nltk
+nltk>=3.9.1
 datefinder
 matplotlib
 seaborn
