Made train dataset

BECK/app.py

@@ -25,24 +25,27 @@
 preprocesamiento = Preprocesamiento()
 # Vector Space Embedding
 w2v = ModelWord2Vec()
-
-comment_test = preprocesamiento.preprocesamiento_con_ortografia(
-    comments_array[0])
-array_item = []
-# Get Vector Beck
-item_string = 'Pensamiento o deseos suicidas'
-for key in beck_data_preprocessing[item_string].keys():
-  array_item.append(beck_data_preprocessing[item_string][key]["data"])
-
-print(comment_test)
-i = 0
-for item in array_item:
-  coseno = w2v.get_cosine_distance(item, comment_test) 
-  print(f'{item_string} - Item BECK {i} distancia coseno: ${coseno}')
-  euclidian = w2v.get_euclidian_distance(["hoy", "me", "quiero", "morir"], ["no", "morir"])
-  print(f'{item_string} - Item BECK {i} distancia euclidiana: ${euclidian}')
-  i += 1
-
-
-result = w2v.getVectorBeck(comment_test, beck_data_preprocessing)
-print(result)
+word1 = ["hoy", "querer", "morir"]
+word2 = ["ser", "dia", "suicidar"]
+w2v.add_corpus(word1)
+w2v.add_corpus(word2)
+# comment_test = preprocesamiento.preprocesamiento_con_ortografia(
+#     comments_array[0])
+# array_item = []
+# # Get Vector Beck
+# item_string = 'Pensamiento o deseos suicidas'
+# for key in beck_data_preprocessing[item_string].keys():
+#   array_item.append(beck_data_preprocessing[item_string][key]["data"])
+
+# print(comment_test)
+# i = 0
+# for item in array_item:
+#   coseno = w2v.get_cosine_distance(item, comment_test) 
+#   print(f'{item_string} - Item BECK {i} distancia coseno: ${coseno}')
+#   euclidian = w2v.get_euclidian_distance(["hoy", "me", "quiero", "morir"], ["no", "morir"])
+#   print(f'{item_string} - Item BECK {i} distancia euclidiana: ${euclidian}')
+#   i += 1
+
+
+# result = w2v.getVectorBeck(comment_test, beck_data_preprocessing)
+# print(result)

BECK/coseno_vs_euclidian.py → BECK/helpers/coseno_vs_euclidian.py

@@ -4,7 +4,7 @@
 import pprint
 from model_word2vec_service import ModelWord2Vec
 
-df = pd.read_excel("./datasets/DATASET_ENTRENAMIENTO.xlsx",index_col=[1,2]).reset_index()
+df = pd.read_csv("../DATASET_ENTRENAMIENTO.csv", encoding='latin-1')
 comments = list(df["text"])
 classes =  list(df["class"])
 
@@ -14,7 +14,7 @@
 preprocesamiento = Preprocesamiento()
 
 w2v = ModelWord2Vec()
-df_cve = pd.read_csv('./coseno_vs_euclidian.csv')
+df_cve = pd.read_csv('../coseno.csv')
 columns = list(df_cve.columns)[2:]
 
 # Lectura beck
@@ -39,11 +39,8 @@
     w2v.add_corpus(comment_preprocesado)
     for item in beck_data_preprocessing.keys():
       for result in beck_data_preprocessing[item].keys():
-        new_comment[columns[contador]] = w2v.get_cosine_distance(comment_preprocesado, beck_data_preprocessing[item][result]["data"])
-        contador += 1
-        new_comment[columns[contador]] = w2v.get_euclidian_distance(comment_preprocesado, beck_data_preprocessing[item][result]["data"])
-        # new_comment[columns[contador]] = 0
-        contador += 1
+        new_comment[columns[contador]] = w2v.get_cosine_similarity(comment_preprocesado, beck_data_preprocessing[item][result]["data"])
+        contador += 1      
 
     # Add to dataframe
     new_comment["Clase"] =  classes[class_comment]

BECK/model_word2vec_service.py

@@ -66,15 +66,15 @@ def get_euclidian_distance(self, corpus_a, corpus_b):
       return np.linalg.norm(np.array(vector_corpus_a) - np.array(vector_corpus_b))
 
 
-  def get_cosine_distance(self, corpus_a, corpus_b):
+  def get_cosine_similarity(self, corpus_a, corpus_b):
     """
     La función toma dos cadenas como entrada y devuelve la distancia del coseno entre las dos cadenas.
     
     :param corpus_a: El primer corpus a comparar
     :param corpus_b: El corpus para comparar con el corpus_a corpus
     :return: La distancia del coseno entre los dos corpus.
     """
-    return self.model.wv.wmdistance(corpus_a, corpus_b)
+    return self.model.wv.n_similarity(corpus_a, corpus_b)
 
   def get_word_vector(self, word):
     """