modeles terminés, pas testés

sentiment_analysis.py

@@ -13,9 +13,6 @@ from scipy.sparse import csr_matrix, hstack
 # nltk.download('sentiwordnet')
 
 
-# from sklearn.naive_bayes import MultinomialNB
-# from sklearn.linear_model import LogisticRegression
-
 train_pos_reviews_fn = "./data/train-positive-t1.txt"
 train_neg_reviews_fn = "./data/train-negative-t1.txt"
 test_pos_reviews_fn = "./data/test-pos-t1.txt"
@@ -160,3 +157,33 @@ if __name__ == '__main__':
         v_final_test.append(v_select_final_test)
             
     # Scoring des modèles
+    
+    modeles_nb = []
+    scores_nb = []
+    modeles_reg = []
+    scores_reg = []
+    for norm_method in range(0,2):
+        modeles_select_vector_nb = []
+        scores_select_vector_nb = []
+        modeles_select_vector_reg = []
+        scores_select_vector_reg = []
+        for select_method in range(0,3):
+            modeles_vector_nb = []
+            scores_vector_nb = []
+            modeles_vector_reg = []
+            scores_vector_reg = []
+            for vector_method in range(0,3):
+                modele_nb = sfun.train_naive_model(v_final_train[norm_method][select_method][vector_method],train_dataset_response)
+                score_nb = modele_nb.predict(v_final_test[norm_method][select_method][vector_method])
+                modele_reg = sfun.train_regression_model(v_final_train[norm_method][select_method][vector_method],train_dataset_response)
+                score_reg = modele_reg.predict(v_final_test[norm_method][select_method][vector_method])
+                modeles_vector_reg.append(modele_reg)
+                scores_vector_reg.append(score_reg)
+            modeles_select_vector_nb.append(modeles_vector_nb)
+            scores_select_vector_nb.append(scores_vector_nb)
+            modeles_select_vector_reg.append(modeles_vector_reg)
+            scores_select_vector_reg.append(scores_vector_reg)
+        modeles_nb.append(modeles_select_vector_nb)
+        scores_nb.append(scores_select_vector_nb)
+        modeles_reg.append(modeles_select_vector_reg)
+        scores_reg.append(scores_select_vector_reg)

sentiment_analysis_functions.py

@@ -13,6 +13,8 @@ from collections import defaultdict
 from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
 from nltk.corpus import wordnet as wn
 from nltk.corpus import sentiwordnet as swn
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.linear_model import LogisticRegression
 
 # Normalisation
 
@@ -182,9 +184,13 @@ def attribute_polarity_count(norm_reviews):
 
 # Training
 
-def train_naive_model(reviews):
-    return 0
+def train_naive_model(reviews_vectors,reviews_response):
+    mnb = MultinomialNB()
+    mnb.fit(reviews_vectors,reviews_response)
+    return mnb
 
 
-def train_regression_model(reviews):
-    return 0
+def train_regression_model(reviews_vectors,reviews_response):
+    lrm = LogisticRegression(solver='liblinear', max_iter=1000)
+    lrm.fit(reviews_vectors,reviews_response)
+    return lrm