prediction saving added and some restructuring

README.md

+Make sure these directories are present
+`mkdir datasets models plots_and_graphs predicted_datasets word_embeddings`
+
 to add pretrained word embedding models, write in terminal:
 
 `cd word_embeddings` 
@@ -8,5 +11,15 @@ to add pretrained word embedding models, write in terminal:
 
 to get debiased version of pretrained word2Vec embedding, use the link: <br /> https://drive.google.com/file/d/1_PvT4ZvtZjhq4HPywA8-u06epht9ccOw/view?usp=sharing
 
-install 
-gensim, pymongo, dnspython 
+install requirements.txt
+
+config.py - constants
+evaluation.py - contains evaluation metrics
+model.py - contains model descriptions and training and prediction modules
+preprocessing.py - contains embeddings and preprocessing tasks
+sampling.py - contains data extraction and sampling tasks
+train.py - contains the runnable flow of the project 
+
+
+
+run train.py
\ No newline at end of file

config.py

@@ -76,12 +76,25 @@ DATASET_NAMES = {
 
 }
 
+PREDICTED_DATASET = {
+	
+# Naming convention : pred_[sv|rf|nn]_[cv|wv|tv]_[tri|med]_[ran|bal]_[test_spit]_[b|r]
+	
+	('svm','w2v','trial','balanced',0.2,'raw') 	: 'predicted_datasets/pred_sv_wv_tri_bal_0.2_r',
+	('svm','w2v','trial','balanced',0.2,'bio') 	: 'predicted_datasets/pred_sv_wv_tri_bal_0.2_b',
+	('svm','self_w2v','trial','balanced',0.2,'raw') 	: 'predicted_datasets/pred_sv_tv_tri_bal_0.2_r',
+	('svm','self_w2v','trial','balanced',0.2,'bio') 	: 'predicted_datasets/pred_sv_tv_tri_bal_0.2_b',
+	('svm','w2v','medical','balanced',0.2,'raw') 	: 'predicted_datasets/pred_sv_wv_med_bal_0.2_r',
+	('svm','w2v','medical','balanced',0.2,'bio') 	: 'predicted_datasets/pred_sv_wv_med_bal_0.2_b',
+
+}
+
 
 PLOT_NAMES = {
 	
 # Naming convention : plot_[tgp|aod]_[M|F]_[sv|rf|nn]_[cv|wv|tv]_[tri|med]_[ran|bal]_[test_spit]_[b|r]
 
 	('tgp','svm','self_w2v','trial','balanced',0.2,'bio') : 'plots_and_graphs/plot_tgp_sv_tv_tri_bal_0.2_b',
-	('aod','svm','self_w2v','trial','balanced',0.2,'bio') : 'plots_and_graphs/plot_aod_sv_tv_tri_bal_0.2_b',
+	('aod','svm','self_w2v','trial','balanced',0.2,'bio') : 'plots_and_graphs/plot_aod_sv_tv_tri_bal_0.2_b'
 
 }
\ No newline at end of file

model.py

@@ -12,8 +12,8 @@ def model_training(X_train, Y_train, model, embedding, class_group, sampling, te
 	elif model == 'nn':
 		trained_model = nn_train(X_train, Y_train)
 
-	dump(trained_model, DATASET_NAMES['model',model,embedding,class_group,sampling,test_size,MASKED[masking]]+'.joblib')
 	print("\t saving file :",DATASET_NAMES['model',model,embedding,class_group,sampling,test_size,MASKED[masking]])
+	dump(trained_model, DATASET_NAMES['model',model,embedding,class_group,sampling,test_size,MASKED[masking]]+'.joblib')
 
 
 def model_prediction(X_test, Y_test, model, embedding, class_group, sampling, test_size, masking):

requirements.txt

 distlib==0.3.1
 pymongo==3.11.4
 virtualenv==20.4.2
+gensim==4.0.1
+pymongo
+dnspython 
\ No newline at end of file

sampling.py

@@ -12,8 +12,8 @@ def get_data_from_mongo(class_group):
 
 	data =  list(collection.find({'$or':[{'title':title} for title in CLASS_GROUP[class_group]]}))
 
-	dump(data, DATASET_NAMES['datasets',class_group]+'.joblib')
 	print("\t saving file : ",DATASET_NAMES['datasets',class_group])
+	dump(data, DATASET_NAMES['datasets',class_group]+'.joblib')
 	return(data)
 
 
@@ -39,8 +39,8 @@ def data_selection(data, class_group, sampling, test_size, masking=True):
 		
 		train,test = train_test_split(data, test_size = test_size, random_state = SEED)
 	
-	dump([train,test], DATASET_NAMES['datasets',class_group,sampling,test_size]+'.joblib')
 	print("\t saving file : ",DATASET_NAMES['datasets',class_group,sampling,test_size])
+	dump([train,test], DATASET_NAMES['datasets',class_group,sampling,test_size]+'.joblib')
 	
 		
 	return train,test

train.py

-from config import CLASS_GROUP, TITLE, MASKED, SEED, DATASET_NAMES
+from config import CLASS_GROUP, TITLE, MASKED, SEED, DATASET_NAMES, PREDICTED_DATASET
 from preprocessing import embedding_fit_transform, embedding_transform
 from sampling import data_selection, load_data
 from model import model_training, model_prediction
 from evaluation import tpr_gender_gap, average_odds_difference
 import pandas as pd
+from joblib import dump, load
+
 
 
 def main(load_data_from_saved, embedding_train, model_train, predict, evaluate, class_group, sampling, embedding, model, test_size, masking):
@@ -28,19 +30,35 @@ def main(load_data_from_saved, embedding_train, model_train, predict, evaluate,
 		X_test = embedding_transform(test_set[MASKED[masking]], embedding, class_group, sampling, test_size, masking)
 		Y_test = test_set[TITLE]
 		pred, acc = model_prediction(X_test, Y_test, model, embedding, class_group, sampling, test_size, masking)
+		predicted_dataset = pd.DataFrame({MASKED[masking]:test_set[MASKED[masking]], TITLE:test_set[TITLE], 'predicted':pred})
+
+		print("\t saving file :",PREDICTED_DATASET[model, embedding, class_group, sampling, test_size, MASKED[masking]])
+		dump(predicted_dataset, PREDICTED_DATASET[model, embedding, class_group, sampling, test_size, MASKED[masking]] + '.joblib')
+
 		print("\nModel accuracy:", acc)
 	
 	# evaluation
+	# TO-DO:
+	# combine the prediction in evaluation to the saved prediction
+
 	if evaluate:
 		scores,x_males,y_males,x_females,y_females = tpr_gender_gap(None,test_set, model, embedding, class_group, sampling, test_size, masking)
 		scores,x_males,y_males,x_females,y_females = average_odds_difference(scores,test_set, model, embedding, class_group, sampling, test_size, masking)
-	print(scores)		
+		print(scores)		
 
 
 '''
-sampling -> random, balanced(upsample, downsample, weighted)
-embedding -> cv: count_vectorize(self-trained), w2v: word2vec_embedding(pre-trained), self_w2v:w2v(self-trained)
-model -> svm, rf, nn
+load_data_from_saved 	-> True if saved data to be used and False if new data to be taken 
+embedding_train 		-> True to train new embedding and False to use the saved one
+model_train 			-> True to train new model and False to use the saved one
+predict 				-> True to perform predictions on the test set and False otherwise
+evaluate 				-> True to perform bias evaluations on the test set and False otherwise
+class_group 			-> choice of domain of occupations ('trial','medical') 
+sampling 				-> choice of sampling ('random', 'balanced')
+embedding 				-> choice of embeddings to be used ('cv': count_vectorize(self-trained), 'w2v': word2vec_embedding(pre-trained), 'self_w2v':w2v(self-trained))
+model 					-> choice of models to be trained ('svm', 'rf', 'nn')
+test_size 				-> proportion of data to be used for tesing (IntegerValue) 
+masking 				-> True for 'bio' data and False for 'raw' data
 '''
 if __name__ == "__main__":
 	import time
@@ -50,10 +68,10 @@ if __name__ == "__main__":
 		embedding_train = False,
 		model_train = False, 
 		predict = True,
-		evaluate = True,
+		evaluate = False,
 		class_group = 'trial', 
 		sampling = 'balanced', 
-		embedding = 'self_w2v', 
+		embedding = ''self_w2v'', 
 		model = 'svm', 
 		test_size = 0.2, 
 		masking = True)