def main(No_ch=0):
#######################DEPRESION#################################
# Adquisicion del corpus >>>>>>>> INICIO
print("Adquisicion de corpus de depresion")
dic.chunks_paths = []
dic.loadchunkXML('dpp')
dic.analyzeChunk('dpp', No_ch)
dic.chunks_paths = []
dic.loadchunkXML('dpn')
dic.analyzeChunk('dpn', No_ch)
print('Numero de chunks en types ', len(dic.types['dpp']))
print('Numero de chunks en types ', len(dic.types['dpn']))
dic.initialize_class_types('dp')
dic.appendPost('dpp', 'dp')
dic.appendPost('dpn', 'dp')
print('Numero de instancias en depresion', len(dic.types['dp']['rows']))
dic.types['dp']['cols'] = dic.fillOnesZeros('dp')
print('Matriz Y', len(dic.types['dp']['cols']))
dic.types['dp']['names'] = ['Negative', 'Positive']
# print(dic.types['dp']['rows'])
# Adquisicion del corpus >>>>>>>> FIN
# Normalizado del corpus >>>>>>>>>> INICIO
norm_train_corpus = norm.parseForTokensFixed(dic.types['dp']['rows'])
print(norm_train_corpus)
chunk.newUser(uid, posts)
dic.chunks_paths = []
dic.loadchunkXML('dpn')
dic.analyzeChunk('dpn', No_ch)
for v in dic.chunks_paths[No_ch - 1]:
(uid, posts) = dic.PostForUser(v)
chunk.newUser(uid, posts)
print('Numero de chunks en types ', len(dic.types['dpp']))
print('Numero de chunks en types ', len(dic.types['dpn']))
dic.initialize_class_types('dp')
IDLVdic = {}
dic.appendPost('dpp', 'dp')
dic.appendPost('dpn', 'dp')
chunk.loadVocabulary()
chunk.calcIDLV()
print('Numero de instancias en depresion', len(dic.types['dp']['rows']))
dic.types['dp']['cols'] = dic.fillOnesZeros('dp')
print(len(dic.types['dp']['cols']))
# Adquisicion del corpus >>>>>>>> FIN
# Normalizado del corpus >>>>>>>>>> INICIO
norm_train_corpus = [
norm.remove_special_characters(text) for text in dic.types['dp']['rows']
]
train_corpus = [norm.remove_stopwords(text) for text in norm_train_corpus]
# Normalizado del corpus >>>>>>>>>> FIN
def main(No_ch=0):
# Adquisicion del corpus >>>>>>>> INICIO
print("Adquisición de corpus de depresion")
dic.chunks_paths = []
dic.loadchunkXML('dpp')
dic.analyzeChunk('dpp', No_ch)
dic.chunks_paths = []
dic.loadchunkXML('dpn')
dic.analyzeChunk('dpn', No_ch)
print('Numero de chunks en types ', len(dic.types['dpp']))
print('Numero de chunks en types ', len(dic.types['dpn']))
dic.initialize_class_types('dp')
dic.appendPost('dpp', 'dp')
dic.appendPost('dpn', 'dp')
print('Numero de instancias en depresion', len(dic.types['dp']['rows']))
dic.types['dp']['cols'] = dic.fillOnesZeros('dp')
print('Matriz Y', len(dic.types['dp']['cols']))
dic.types['dp']['names'] = ['Negative', 'Positive']
# Adquisicion del corpus >>>>>>>> FIN
# Normalizado del corpus >>>>>>>>>> INICIO
norm_train_corpus = norm.normalize_corpus(dic.types['dp']['rows'])
# Normalizado del corpus >>>>>>>>>> FIN
from feature_extractor import bow_extractor, tfidf_extractor, bow_extractor_maxdf
from sklearn.feature_selection import mutual_info_classif
import nltk
import gensim
# BOW features
bow_vectorizer, bow_train_features = bow_extractor(norm_train_corpus)
feature_names = bow_vectorizer.get_feature_names()
print('Numero de caracteristicas tomadas en cuenta', len(feature_names))
from sklearn.naive_bayes import MultinomialNB
nb = MultinomialNB()
from sklearn.model_selection import cross_val_predict
y_predicted = cross_val_predict(nb,
bow_train_features,
dic.types['dp']['cols'],
cv=10)
evaluator.get_metrics(dic.types['dp']['cols'], y_predicted)
bow_vectorizer, bow_train_features = bow_extractor_maxdf(norm_train_corpus)
res = dict(
zip(
feature_names,
mutual_info_classif(bow_train_features,
dic.types['dp']['cols'],
discrete_features=True)))
for feat in res.keys():
print(feat, str(res[feat]), '\n')
# y_predicted = cross_val_predict( nb, bow_train_features, dic.types['dp']['cols'], cv=10)
# evaluator.get_metrics(dic.types['dp']['cols'], y_predicted)
# Adquisicion del corpus >>>>>>>> INICIO
print("Adquisición de corpus de anorexia")
dic.chunks_paths = []
dic.loadchunkXML('axp')
dic.analyzeChunk('axp', No_ch)
dic.chunks_paths = []
dic.loadchunkXML('axn')
dic.analyzeChunk('axn', No_ch)
print('Numero de chunks en types ', len(dic.types['axp']))
print('Numero de chunks en types ', len(dic.types['axn']))
dic.initialize_class_types('ax')
dic.appendPost('axp', 'ax')
dic.appendPost('axn', 'ax')
print('Numero de instancias en anorexia', len(dic.types['ax']['rows']))
dic.types['ax']['cols'] = dic.fillOnesZeros('ax')
print('Matriz Y', len(dic.types['ax']['cols']))
dic.types['ax']['names'] = ['Negative', 'Positive']
# Adquisicion del corpus >>>>>>>> FIN
# Normalizado del corpus >>>>>>>>>> INICIO
norm_train_corpus = norm.normalize_corpus(dic.types['ax']['rows'])
# Normalizado del corpus >>>>>>>>>> FIN
# BOW features
bow_vectorizer, bow_train_features = bow_extractor(norm_train_corpus)
feature_names = bow_vectorizer.get_feature_names()
print('Numero de caracteristicas tomadas en cuenta', len(feature_names))
nb = MultinomialNB()
y_predicted = cross_val_predict(nb,
bow_train_features,
dic.types['ax']['cols'],
cv=10)
evaluator.get_metrics(dic.types['ax']['cols'], y_predicted)
bow_vectorizer, bow_train_features = bow_extractor_maxdf(norm_train_corpus)
res = dict(
zip(
feature_names,
mutual_info_classif(bow_train_features,
dic.types['ax']['cols'],
discrete_features=True)))
for feat in res.keys():
print(feat, str(res[feat]), '\n')
chunk.newUser(uid, posts)
dic.chunks_paths = []
dic.loadchunkXML('axn')
dic.analyzeChunk('axn', No_ch)
for v in dic.chunks_paths[No_ch - 1]:
(uid, posts) = dic.PostForUser(v)
chunk.newUser(uid, posts)
print('Numero de chunks en types ', len(dic.types['axp']))
print('Numero de chunks en types ', len(dic.types['axn']))
IDLVdic = {}
dic.initialize_class_types('ax')
dic.appendPost('axp', 'ax')
dic.appendPost('axn', 'ax')
chunk.loadVocabulary()
chunk.calcIDLV()
print('Numero de instancias en depresion: ', len(dic.types['ax']['rows']))
print('Vocabulario en el chunk: ', len(chunk.vocablos.keys()))
dic.types['ax']['cols'] = dic.fillOnesZeros('ax')
print(len(dic.types['ax']['cols']))
tfs = [(v.IDLV(0), k) for k, v in chunk.vocablos.items()]
tfs.sort()
tfs.reverse()
for i in range(0, 1000):
IDLVdic[tfs[i][1]] = tfs[i][0]
norm.thousand_words = IDLVdic.keys()