v0.1

clust.py

@@ -1,45 +1,49 @@
 from infBack import get_vect as gv
 from sklearn.feature_extraction.text import TfidfVectorizer
+from stopWords import stopWrdList
 import numpy as np
 
 
-def stopWrdList():
-    sw = open('stop.words')
-    prue = []
-    prue.append(sw.readlines())
-    return [l.strip('\n\r') for l in prue[0]]
+def clustering():
 
+    # This are the relevant news cue words
+    voc = ["ine", "pri", "pan", "prd", "pt", "pvem", "verde", "movimiento", "ciudadano", "panal", "alianza", "morena", "partido", "encuentro", "social", "electoral"]
 
-voc = ["ine", "pri", "pan", "prd", "pt", "pvem", "verde", "movimiento", "ciudadano", "panal", "alianza", "morena", "partido", "encuentro", "social", "electoral"]
+    stop_words = stopWrdList()
 
-stop_words = stopWrdList()
+    dataVect = gv()
 
-dataVect = gv()
+    dataVect = np.array(dataVect)
 
-dataVect = np.array(dataVect)
+    corpus = dataVect[:, 2]
 
-corpus = dataVect[:, 2]
+    vectorizer = TfidfVectorizer(strip_accents='ascii', analyzer='word', stop_words=stop_words, vocabulary=voc)
 
-vectorizer = TfidfVectorizer(strip_accents='ascii', analyzer='word', stop_words=stop_words, vocabulary=voc)
+    X = vectorizer.fit_transform(corpus)
 
-X = vectorizer.fit_transform(corpus)
+    del dataVect, stop_words, vectorizer  # , corpus
 
-del dataVect, stop_words, vectorizer  # , corpus
+    J = X.toarray()
 
-J = X.toarray()
+    # The indexes are extracted to obtain only the relevant news from the general corpus
 
-# print(J)
+    index = []
 
-index = []
+    for x in range(0, len(J)):
+        if sum(J[x]) != 0:
+            index.append(x)
 
-for x in range(0, len(J)):
-    if sum(J[x]) != 0:
-        index.append(x)
+    index = tuple(index)
 
-index = tuple(index)
+    electCorp = [corpus[x] for x in index]
 
-electCorp = [corpus[x] for x in index]
+    del corpus
 
-del corpus
+    # This section of the code processes the political party news in order to give a emotional classification
 
-print(electCorp)
+    temp = []
+
+    for i in electCorp:
+        temp.append(i.split(' '))
+
+    return temp

infBack.py

@@ -27,8 +27,6 @@ def get_vect():
     return impDat
 
 
-# print(len(get_vect()))
-
 
 # this section of the code show how to extract relevant data from the dictionaries
 """

main.py

@@ -0,0 +1,19 @@
+
+from retEmoDict import emoDic
+from newsTrain import classifyNews
+from clust import clustering
+
+
+temp = clustering()
+
+emoDict = emoDic()
+
+rest = []
+
+for i in temp:
+    rest.append(classifyNews(i, emoDict))
+
+
+for i in rest:
+    print(i)
+

newsTrain.py

@@ -0,0 +1,77 @@
+
+
+def classifyNews(word_array, dict):
+
+    default = 'NA'
+    alegria = []
+    enojo = []
+    miedo = []
+    repulsion = []
+    sorpresa = []
+    tristeza = []
+    proper = []
+    part = []
+
+    for word in word_array:
+        if dict.get(str(word), default) == 'Alegría':
+            alegria.append(1)
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Enojo':
+            enojo.append(1)
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Miedo':
+            miedo.append(1)
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Repulsión':
+            repulsion.append(1)
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Sorpresa':
+            sorpresa.append(1)
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Tristeza':
+            tristeza.append(1)
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Positivo':
+            part.append('PRI')
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Negativo':
+            part.append('CONTRA')
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'Neutro':
+            part.append('NEU')
+            proper.append(word)
+
+        if dict.get(str(word), default) == 'NA':
+            proper.append(word)
+
+
+    part = set(part)
+    flag = list(part)
+    vect = set(proper)
+    vect = list(vect)
+    tot = len(word_array)
+
+    alegria = sum(alegria)
+    enojo = sum(enojo)
+    miedo = sum(miedo)
+    repulsion = sum(repulsion)
+    sorpresa = sum(sorpresa)
+    tristeza = sum(tristeza)
+
+    pos = (alegria + sorpresa) / tot
+    neg = (enojo + miedo + repulsion + tristeza) / tot
+
+    if len(flag) == 0:
+        flag = ['NEU']
+
+    return [('Positive:', pos), ('Negative:', neg), flag, vect]
+
+

retEmoDict.py

@@ -0,0 +1,45 @@
+
+def emoDic():
+
+    emoDict = open('SEL.txt', 'r', encoding='utf-8')
+    temp = emoDict.read()
+
+    emoDict = temp.split('\n')
+
+    temp = []
+
+    for i in emoDict:
+        temp.append(i.split('\t'))
+
+    n = len(temp) -1
+
+    del temp[n]
+
+    for i in temp:
+        del i[1]
+
+    emoDict = {i[0]: i[1] for i in temp}
+
+    emoDict['PRI'] = 'Positivo'
+    emoDict['INE'] = 'Neutro'
+    emoDict['electoral'] = 'Neutro'
+    emoDict['Electoral'] = 'Neutro'
+    emoDict['PAN'] = 'Negativo'
+    emoDict['partido'] = 'Neutro'
+    emoDict['Partido'] = 'Neutro'
+    emoDict['PRD'] = 'Negativo'
+    emoDict['PT'] = 'Negativo'
+    emoDict['PANAL'] = 'Negativo'
+    emoDict['PVEM'] = 'Negativo'
+    emoDict['Movimiento'] = 'Negativo'
+    emoDict['Ciudadano'] = 'Negativo'
+    emoDict['Alianza'] = 'Negativo'
+    emoDict['Morena'] = 'Negtivo'
+    emoDict['electoral'] = 'Neutro'
+    emoDict['Electoral'] = 'Neutro'
+    emoDict['Encuentro'] = 'Negativo'
+    emoDict['Social'] = 'Negativo'
+    emoDict['Peña'] = 'Positivo'
+    emoDict['Nieto'] = 'Sorpresa' #['Sorpresa', 'Positivo']
+
+    return emoDict

stopWords.py

@@ -0,0 +1,7 @@
+
+
+def stopWrdList():
+    sw = open('stop.words')
+    prue = []
+    prue.append(sw.readlines())
+    return [l.strip('\n\r') for l in prue[0]]