made small tweaks to cleaning module

Author: ZachEichen

text_extensions_for_pandas/cleaning/__init__.py

@@ -14,10 +14,11 @@
 #
 
 ################################################################################
-# io module
+# cleaning module
 #
-# Functions in text_extensions_for_pandas that create DataFrames and convert
-# them to other formats.
+# Functions in text_extensions_for_pandas that allow for identification of 
+# possibly incorrect labels, and quick training of models on bert embeddings
+# of a corpus
 
 # Expose the public APIs that users should get from importing the top-level
 # library.

text_extensions_for_pandas/cleaning/analysis.py

@@ -20,6 +20,7 @@
 
 import numpy as np
 import pandas as pd
+from typing import *
 
 import text_extensions_for_pandas as tp
 
@@ -28,7 +29,6 @@
 
 tp = importlib.reload(tp)
 
-from typing import *
 
 
 def create_f1_score_report(

text_extensions_for_pandas/cleaning/preprocess.py

@@ -269,7 +269,7 @@ def preprocess_documents(
         else:
             for fold in bert_docs_by_fold.keys():
                 for docnum in range(len(bert_docs_by_fold[fold])):
-                    bert_docs_by_fold[fold][docnum][iob_col].fillna(
+                    bert_docs_by_fold[fold][docnum][label_col].fillna(
                         default_label_type, inplace=True
                     )
                     bert_docs_by_fold[fold][docnum][