Change to tfidf

.gitignore

@@ -0,0 +1 @@
+.idea

classifier.py

@@ -1,5 +1,6 @@
 import string
 from gensim.models.doc2vec import Doc2Vec, TaggedDocument
+from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.cluster import KMeans
 from sklearn.naive_bayes import MultinomialNB
 from sklearn.preprocessing import MinMaxScaler, normalize
@@ -23,15 +24,15 @@ def train():
         y.append(t[0])
         doc = t[1]
         doc = doc.lower().split(' ')
-        doc = [''.join(char for char in word if char not in string.punctuation) for word in doc]
+        # doc = [''.join(char for char in word if char not in string.punctuation) for word in doc]
         doc = list(filter(lambda word: (word not in stopwords) and (word != ''), doc))
+        doc = ' '.join(doc)
         docs_preprocessed.append(doc)
     y = [int(numeric_string) for numeric_string in y]
-    tagged_documents = [TaggedDocument(doc, [i]) for i, doc in enumerate(docs_preprocessed)]
     global d2v_model
-    d2v_model = Doc2Vec(tagged_documents, epochs=300, dm=0)
+    d2v_model = TfidfVectorizer()
-    X = d2v_model.dv.vectors
+    X = d2v_model.fit_transform(docs_preprocessed)
-    X = scaler.fit_transform(X)
+    # X = scaler.fit_transform(X)
     classifier.fit(X, y)
 
 def classify(path):
@@ -40,12 +41,10 @@ def classify(path):
     docs_preprocessed = []
     for doc in docs:
         doc = doc.lower().split(' ')
-        doc = [''.join(char for char in word if char not in string.punctuation) for word in doc]
+        # doc = [''.join(char for char in word if char not in string.punctuation) for word in doc]
         doc = list(filter(lambda word: (word not in stopwords) and (word != ''), doc))
         docs_preprocessed.append(doc)
-    test_vectors = []
+    test_vectors = d2v_model.transform(docs)
-    for doc in docs_preprocessed:
-        test_vectors.append(d2v_model.infer_vector(doc))
     results = classifier.predict(test_vectors)
     with open(path + 'out.tsv', 'w') as file:
         for result in results: