def cnn_fold(k, path_to_json, path_to_img, epochs=10, img_size=(28, 28), verbose=False):
kfold = KFold(k, path_to_json, path_to_img)
stats = [None] * 5
for i in xrange(k):
print '{}: Fold {} of {}'.format(datetime.now(), i + 1, k)
train_df, test_df = kfold.get_datasets(i)
train_set = DatasetImages(train_df, img_size)
train_set.oversample()
test_set = DatasetImages(test_df, img_size)
model = ModelLipnet4(verbose=True)
model.fit(train_set=train_set,
test_set=None,
nb_epoch=epochs)
stats[i] = model.evaluate(test_set)
return stats
def svm_folds(k, path_to_json):
kfold = KFold(k, path_to_json, '')
stats = [None] * k
for i in xrange(k):
print '{}: Fold {} of {}'.format(datetime.now(), i + 1, k)
# get train and test dataframes
train_df, test_df = kfold.get_datasets(i)
# create train and test datasets
test_set = DatasetVironovaSVM(train_df, do_oversampling=False)
train_set = DatasetVironovaSVM(train_df, do_oversampling=False)
# get confusion matrix from SVM model
cf = svm.svm(train_set, test_set)
stats[i] = cf
return stats
def svm_folds(k, path_to_json):
kfold = KFold(k, path_to_json, '')
stats = [None] * k
for i in xrange(k):
print '{}: Fold {} of {}'.format(datetime.now(), i + 1, k)
# get train and test dataframes
train_df, test_df = kfold.get_datasets(i)
# create train and test datasets
test_set = DatasetVironovaSVM(train_df, do_oversampling=False)
train_set = DatasetVironovaSVM(train_df, do_oversampling=False)
# get confusion matrix from SVM model
cf = svm.svm(train_set, test_set)
stats[i] = cf
return stats
def cnn_fold(k,
path_to_json,
path_to_img,
epochs=10,
img_size=(28, 28),
verbose=False):
kfold = KFold(k, path_to_json, path_to_img)
stats = [None] * 5
for i in xrange(k):
print '{}: Fold {} of {}'.format(datetime.now(), i + 1, k)
train_df, test_df = kfold.get_datasets(i)
train_set = DatasetImages(train_df, img_size)
train_set.oversample()
test_set = DatasetImages(test_df, img_size)
model = ModelLipnet4(verbose=True)
model.fit(train_set=train_set, test_set=None, nb_epoch=epochs)
stats[i] = model.evaluate(test_set)
return stats
from tbrs import TermBasedRandomSampling
from preprocessing2 import Preprocessing
from naivebayes import NBMultinomial
from weighting import Weighting
from kfold import KFold
from confusionmatrix import ConfusionMatrix
import time
start = time.time()
data = pd.read_excel(r'C:\Users\PPATK\Desktop\Code 2\Code\Skripsi.xlsx',
"Data Coding")
data_tweet = data['Tweet']
data_target = data['Label']
kfold = KFold(data_tweet, data_target, 10)
data_train, data_test = kfold.get_data_sequence()
i = 0
print("kfold")
print(time.time() - start)
start = time.time()
prepro = Preprocessing()
cleaned_data, terms, asd = prepro.preprocessing(data_train[i]["tweet"])
print("preprocessing")
print(time.time() - start)
start = time.time()
tbrs = TermBasedRandomSampling(X=10, Y=10, L=40)
stopwords = tbrs.create_stopwords(cleaned_data, terms)