def __init__(self, queryFile, candidatePath, mu, corpusFile, sigma, lamda):
self.query = {}
self.candidate = candidatePath
self.tweet = {}
self.mu = mu
self.sigma = sigma #similarity threshold
self.lamda = lamda #cluster threshold
self.jaccInstance = Jaccard()
self.klInstance = Distance(mu, corpusFile)
print "corpus read done!"
def __init__(self, train_path, test_path):
self.train_path = train_path
self.test_path = test_path
self.preprocessor = Preprocessor()
self.trn = pd.DataFrame(columns=Classifier._COLS) # Read data_frame
self.tst = pd.DataFrame(columns=Classifier._COLS) # Read data_frame
self.trn_gs = pd.DataFrame(columns=Classifier._GS_COLS) # Known labels
self.tst_gs = pd.DataFrame(columns=Classifier._GS_COLS) # Known labels
self.tok_trn = []
self.tok_tst = []
self.feature_extractor = FeatureExtractor()
self.jaccard = Jaccard()
self.rfr = RFR()
self.nn = MLPRegressor(hidden_layer_sizes=(100, 30, 30),
validation_fraction=0.3,
alpha=0.3,
warm_start=False,
max_iter=1000,
activation='logistic')
