fix bug in which politeness features were in the wrong order

feature_engine/featurize.py

@@ -28,7 +28,7 @@
 	# )
 	# feature_builder.featurize(col="message")
 
-	# # Tiny multi-task
+	# Tiny multi-task
 	# tiny_multi_task_feature_builder = FeatureBuilder(
 	# 	input_file_path = "../feature_engine/tpm-data/cleaned_data/test_data/multi_task_TINY.csv",
 	# 	vector_directory = "../feature_engine/tpm-data/vector_data/",

feature_engine/testing/data/cleaned_data/test_chat_level.csv

@@ -87,6 +87,7 @@ I respond to that too",num_block_quote_responses,2
 1,A,hello,Hello,1
 1,B,So how should we answer this,Token_count,6
 1,A,We can start here. What is the question?,YesNo_Questions,0
+<<<<<<< HEAD
 1,B,I am not sure. Where is the rest of our team?,WH_Questions,1
 1,B,"Please help me figure this out, I really want to do well on this please",Please,2
 2,C,Hey,Hello,1
@@ -100,6 +101,19 @@ I respond to that too",num_block_quote_responses,2
 3,G,hey,indirect_greeting,1
 3,G,I think we should try something else,1st_person_start,1
 3,F,Ok whatever. You should leave the team then,2nd_person_start,1
+=======
+1,B,I am not sure. Where is the rest of our team?,First_Person_Single,1
+1,B,"Well please help me figure this out, I really want to do well on this please okay",factuality,1
+2,C,Okay bro lets split it 50/50,Impersonal_Pronoun,0
+2,D,Maybe but how about 60/40? I doubt its fair otherwise,hedges,1
+2,C,Seems possible,hashedge,1
+2,E,I see what youre thinking but I disagree,Acknowledgement,1
+2,E,We get only one chance so we should understand how to split it,Acknowledgement,1
+2,D,"I just don't agree, I'm making the 60/40 split",Adverb_Limiter,1
+3,F,greetings everybody. should we use the first option?,Hello,1
+3,G,I think we should try something else,1st_person_start,1
+3,F,Ok whatever. You should leave the team then,2nd_person_start,0
+>>>>>>> c0510aabb22fa300950d6f3e3b9762ac2e7e56ae
 4,H,Honestly thank you so so much,factuality,1
 4,H,What's the plan?,direct_question,1
 4,I,That is the dumbest idea I've heard; youre actually dumb af,hasnegative,1
@@ -110,20 +124,30 @@ I respond to that too",num_block_quote_responses,2
 5,K,Sorry sorry I didn't mean to,apologizing,1
 6,L,I don't really want to work with you all but let's get this over with,Impersonal_Pronoun,1
 6,J,Fine by me,Affirmation,0
+<<<<<<< HEAD
 6,K,Ok so which part should we do first? the first or second?,YesNo_Questions,1
 7,L,Please don't do that?,please_start,1
 7,L,I don't think that will work,hashedge,1
 7,M,I'm exhuasted rn,hasnegative,0
 7,M,i don't really care please just finish this up,haspositive,0
 7,N,Please don't do that?,Please,1
+=======
+6,K,Ok so which part should we do first? the first or second?,YesNo_Questions,0
+7,L,please don't do that?,please_start,1
+7,L,I don't think that will work,hashedge,1
+7,M,I'm exhuasted rn,hasnegative,0
+7,M,i don't really care please just finish this up,haspositive,0
+7,N,Please don't do that?,please_start,1
+>>>>>>> c0510aabb22fa300950d6f3e3b9762ac2e7e56ae
 7,N,I don't think that will work,Hedges,0
 7,O,I'm exhuasted rn,Negative_Emotion,0
 7,O,i don't really care please just finish this up,Positive_Emotion,1
-8,P,i appreciate all this from you,Gratitude,1
+8,P,i appreciate all this from you,gratitude,1
 8,P,"well we should start rn, our part is long",1st_person_pl,1
 8,Q,ok forgive me for this error but,apologizing,1
 8,Q,you have to redo the whole thing,2nd_person,0
 8,R,ok so who will work with me? where should we begin?,direct_question,0
+<<<<<<< HEAD
 8,S,i appreciate all this from you,Gratitude,1
 8,S,"well we should start rn, our part is long",First_Person_Plural,1
 8,T,ok forgive us for this error but,Apology,0
@@ -142,4 +166,11 @@ I respond to that too",num_block_quote_responses,2
 19,A,"I understand your perspective and agree that I would not want to have resentment in the workplace against women, as that would further compound the issue we are looking at. I do think that it is true that women are underrepresented in STEM careers and am a believer that something should be done to address this discrepancy, even if that is not implementing a priority for women in hiring decisions. While I don\'t think that companies should explicitly hire simply because of their gender, I do think that they should be mindful of the gender gap in STEM and look to address those issues through their hiring practices.",Disagreement,1
 20,A,"I understand your perspective and agree that I would not want to have resentment in the workplace against women, as that would further compound the issue we are looking at. I do think that it is true that women are underrepresented in STEM careers and am a believer that something should be done to address this discrepancy, even if that is not implementing a priority for women in hiring decisions. While I don\'t think that companies should explicitly hire simply because of their gender, I do think that they should be mindful of the gender gap in STEM and look to address those issues through their hiring practices.",Acknowledgement,1
 21,A,"I understand your perspective and agree that I would not want to have resentment in the workplace against women, as that would further compound the issue we are looking at. I do think that it is true that women are underrepresented in STEM careers and am a believer that something should be done to address this discrepancy, even if that is not implementing a priority for women in hiring decisions. While I don\'t think that companies should explicitly hire simply because of their gender, I do think that they should be mindful of the gender gap in STEM and look to address those issues through their hiring practices.",First_Person_Plural,1
-22,A,"I understand your perspective and agree that I would not want to have resentment in the workplace against women, as that would further compound the issue we are looking at. I do think that it is true that women are underrepresented in STEM careers and am a believer that something should be done to address this discrepancy, even if that is not implementing a priority for women in hiring decisions. While I don\'t think that companies should explicitly hire simply because of their gender, I do think that they should be mindful of the gender gap in STEM and look to address those issues through their hiring practices.",For_Me,0
+22,A,"I understand your perspective and agree that I would not want to have resentment in the workplace against women, as that would further compound the issue we are looking at. I do think that it is true that women are underrepresented in STEM careers and am a believer that something should be done to address this discrepancy, even if that is not implementing a priority for women in hiring decisions. While I don\'t think that companies should explicitly hire simply because of their gender, I do think that they should be mindful of the gender gap in STEM and look to address those issues through their hiring practices.",For_Me,0
+=======
+8,S,i appreciate all this from you,Gratitude,0
+8,S,"well we should start rn, our part is long",Token_count,9
+8,T,ok forgive us for this error but,Apology,0
+8,T,I think you have to redo the whole thing,First_Person_Single,1
+8,U,ok so who will work with me? where should we begin?,WH_Questions,0
+>>>>>>> c0510aabb22fa300950d6f3e3b9762ac2e7e56ae

feature_engine/utils/preprocess.py

@@ -25,6 +25,10 @@ def assert_key_columns_present(df):
 	# Assert that key columns are present
 	if {'conversation_num', 'message', 'speaker_nickname'}.issubset(df.columns):
 		print("Confirmed that data has `conversation_num`, `message`, and `speaker_nickname` columns!")
+		# ensure no NA's in essential columns
+		df['message'] = df['message'].fillna('')
+		df['conversation_num'] = df['conversation_num'].fillna(0)
+		df['speaker_nickname'] = df['speaker_nickname'].fillna(0)
 	else:
 		print("One of `conversation_num`, `message`, or `speaker_nickname` is missing! Raising error...")
 		print("Columns available: ")