def load():
if os.path.exists(model_path):
print "Loading model..."
model = pickle.load(open(model_path, "rb"))
classifier.load(model)
else:
print "Training model..."
train('dataset/twss.txt', 'yes')
train('dataset/non_twss.txt', 'no')
model = classifier.model
pickle.dump(model, open(model_path, "wb"))
def load():
if os.path.exists(model_path):
print "Loading model..."
model = pickle.load(open(model_path, "rb"))
classifier.load(model)
else:
print "Training model..."
train('dataset/twss.txt', 'yes')
train('dataset/non_twss.txt', 'no')
model = classifier.model
pickle.dump(model, open(model_path, "wb"))
def main():
data_folder = 'data/sources/wikipedia'
models_folder = 'classifier/models'
save_loc = '/usr/share/nginx/html/wiki'
if not os.path.exists(data_folder):
os.makedirs(data_folder)
if next(os.walk(data_folder))[1]:
retrain = True
if retrain:
input, target, classes = data.sample(data_folder)
model = classifier.build(input.shape, target.shape)
classifier.train(model, input, target)
classifier.save(models_folder, model, classes)
else:
model, classes = classifier.load(models_folder, sorted(os.listdir(models_folder))[-1])
for root, dirs, files in os.walk(data_folder):
for file in files:
if not file.startswith('.'):
with open(root+'/'+file) as f:
input = data.str2mat(f.read())
output = classifier.run(model, input)
data.backtest(save_loc+'/'+file, classes, input, output)
else:
print("""\nNo data found.\nPut subfolders of files by class, within the 'data' folder.""")
def main(model_path, vector_path, class_file):
print "going to load model"
class_map = load_class_map(class_file)
model = classifier.load(model_path)
vectorizer = text_vectorizer.load_vectorizer(vector_path)
test_data = ["Looks nice and beautiful and very good ", "this is bad"]
vector = text_vectorizer.vectorize(test_data, vectorizer)
i = 0
label_list = list(classifier.predict_label(model, vector))
for lbl in label_list:
print "class predicted for \"" + str(test_data[i]) + "\" is " + str(class_map[lbl])
i += 1
import keras
import classifier
classifier = classifier.load()
from model import Encoder, Decoder, input_shape
from keras.models import Model
from keras.layers import Input
from keras.datasets import mnist
import numpy as np
(x, y), _ = mnist.load_data()
#x1 ,y1 = x[y==1], y[y==1] # y is full of 1 :P
x = x.astype('float') / 255
x = x.reshape((-1, *input_shape))
x_n = [x[y == i] for i in range(10)]
X = x_n
e1 = Encoder()
d1 = Decoder()
e5 = Encoder()
d5 = Decoder()
i1 = Input(input_shape)
i5 = Input(input_shape)
auto1 = d1(e1(i1))
auto5 = d5(e5(i5))
TEST_FILENAME = './data/smtest.csv'
SKLEARN_PATH = './data/models/sklearn'
SPARK_PATH = './data/models/spark'
if __name__ == '__main__':
# read the training data
xtrain, ytrain = classifier.readdata(TRAIN_FILENAME)
xtest, ytest = classifier.readdata(TEST_FILENAME)
countvect, transformer, model = classifier.train(xtrain, ytrain)
acc, model = classifier.test(model, xtest, ytest, countvect, transformer)
print('Sklearn acc: {}'.format(acc))
print('Saving sklearn')
classifier.save(SKLEARN_PATH, model, countvect, transformer)
countvect, transformer, model = classifier.load(SKLEARN_PATH)
print(classifier.predict(model, ['i like something'], countvect, transformer))
# start looping over tweets
# for tweet in db.gettweets():
# text = [tweet['text']]
# prediction = clf.predict(classifier.transform(text))
# print(text, ' ^^ ', prediction)
# time.sleep(0.5)
sc = spark.context('TwitterSentimentAnalysis')
xdata, ydata = classifier.readdata(TRAIN_FILENAME)
proc = spark.preprocess(sc, xdata, labels=ydata)
traindata, testdata = spark.traintestsplit(proc)
model = spark.train(traindata)
