def previous_main():
DEBUGMODE = 0
numFeatures = 100
path_dataset_dav_windows = 'Dati/training_set_text.csv'
path_class_csv = 'Dati/training_set_features.csv'
path_model_file = 'Dati/model.dat'
cleaner = TweetsCleaner.TweetsCleaner()
loader = DatasetLoader.DatasetLoader()
model = VectorModel.VectorModel()
classificator = BayesanClassificator.BayesanClassificator()
evaluator = ClassifierEvaluation.ClassifierEvaluation()
tweets_dataset = loader.LoadTweets(path_dataset_dav_windows)
tweets_cleaned = cleaner.ProcessDatasetDict(tweets_dataset)
features_dataset = loader.LoadFeatures(path_class_csv, 400)
"""
Trasforma il vettore delle features in un dizionario con chiave IdDoc e valore la classe corrispondente
(1 : neutra, 2: positiva, 3: negativa, 4: mista
"""
classes_dataset = loader.createClasses(features_dataset)
"""
Genero il Modello TF-IDF
"""
all_phrases = list(tweets_cleaned.values())[:400]
count = 0
phrases_tuples = []
for phrase in all_phrases:
phrases_tuples.append((count, phrase))
count += 1
if not DEBUGMODE or not os.path.exists(path_model_file):
tfidf = model.get_tfidf(phrases_tuples)
model.persist_tfidf(tfidf, path_model_file)
else:
tfidf = model.deserialize_tfidf(path_model_file)
doc_index = model.get_doc_index(tfidf)
# prendo le etichette delle classi per la gold solution
labels = numpy.array(list(classes_dataset.values()))
# applico LSA
reduced = model.LSA(model.get_doc_index_table(doc_index), numFeatures)
# scalo in [0,1]
reduced = loader.NormalizeDataset(reduced)
BayesTest(reduced, labels)
import TweetsCleaner
import VectorModel
import ClassifierEvaluation
import pickle
if __name__ == "__main__":
DEBUGMODE = 1
path_dataset_dav_windows = 'Dati/training_set_text.csv'
path_class_csv = 'Dati/training_set_features.csv'
path_model_file = 'Dati/model.dat'
cleaner = TweetsCleaner.TweetsCleaner()
loader = DatasetLoader.DatasetLoader()
model = VectorModel.VectorModel()
evaluator = ClassifierEvaluation.ClassifierEvaluation()
tweets_dataset = loader.LoadTweets(path_dataset_dav_windows)
tweets_cleaned = cleaner.ProcessDatasetDict(tweets_dataset)
features_dataset = loader.LoadFeatures(path_class_csv)
"""
Trasforma il vettore delle features in un dizionario con chiave IdDoc e valore la classe corrispondente
(1 : neutra, 2: positiva, 3: negativa, 4: mista
"""
classes_dataset = loader.createClasses(features_dataset)
"""
Genero il Modello TF-IDF
"""
all_phrases = list(tweets_cleaned.values())
