From d57cd3c5a9b5f7936db21933e4f425c7a90059b5 Mon Sep 17 00:00:00 2001 From: PriyaDCosta <76833529+PriyaDCosta@users.noreply.github.com> Date: Thu, 11 Apr 2024 09:36:00 -0400 Subject: [PATCH] added preprocessing to exclude quotes --- feature_engine/feature_builder.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/feature_engine/feature_builder.py b/feature_engine/feature_builder.py index 6f258fa7..5b13e181 100644 --- a/feature_engine/feature_builder.py +++ b/feature_engine/feature_builder.py @@ -224,7 +224,7 @@ def preprocess_chat_data(self, col: str="message", turns=False, conversation_id= # create new column that retains punctuation self.chat_data["message_lower_with_punc"] = self.chat_data[col].astype(str).apply(preprocess_text_lowercase_but_retain_punctuation) - # create new column that removes any quoted text - for conflict + # create new column that removes any quoted text - for conflict self.chat_data["message_without_quotes"] = self.chat_data[col].astype(str).apply(preprocess_remove_quotes_from_dataset) # Preprocessing the text in `col` and then overwriting the column `col`.