data_helpers.py

import numpy as np
import re
import os
def clean_str(string):
    """
    Tokenization/string cleaning for all datasets except for SST.
    Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
    """
    # string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
    # string = re.sub(r"\'s", " \'s", string)
    # string = re.sub(r"\'ve", " \'ve", string)
    # string = re.sub(r"n\'t", " n\'t", string)
    # string = re.sub(r"\'re", " \'re", string)
    # string = re.sub(r"\'d", " \'d", string)
    # string = re.sub(r"\'ll", " \'ll", string)
    string = re.sub(r",", " , ", string)
    string = re.sub(r"!", " ! ", string)
    string = re.sub(r"。", " 。 ", string)
    string = re.sub(r"-", " - ", string)
    string = re.sub(r"\(", " \( ", string)
    string = re.sub(r"\)", " \) ", string)
    string = re.sub(r"\?", " \? ", string)
    # string = re.sub(r"\s{2,}", " ", string)
    return string.strip().lower()

def load_data_and_labels(positive_data_file, negative_data_file):
    """
    Loads MR polarity data from files, splits the data into words and generates labels.
    Returns split sentences and labels.
    """
    file_lst = os.listdir('Task1data/fenciTrain/')
    l = len(file_lst)
    x_text = []
    y = []
    for i,file in enumerate(file_lst):
        kind = list(open('Task1data/fenciTrain/'+file, "r", encoding='utf-8').readlines())
        kind = [s.strip() for s in kind]
        zeros = []
        it = 0
        while it < l:
            zeros.append(0)
            it += 1
        zeros[i] = 1
        y_text = [zeros for _ in kind]
        if len(y)==0:
            y = y_text
        else:
            y = np.concatenate([y, y_text], 0)
        x_text = x_text + kind
    x_text = [clean_str(sent) for sent in x_text]
    return [x_text, y]

# if __name__ == '__main__':
#     load_data_and_labels('','')

def batch_iter(data, batch_size, num_epochs, shuffle=True):
    """
    Generates a batch iterator for a dataset.
    """
    data = np.array(data)
    data_size = len(data)
    num_batches_per_epoch = int((len(data)-1)/batch_size) + 1
    for epoch in range(num_epochs):
        # Shuffle the data at each epoch
        if shuffle:
            shuffle_indices = np.random.permutation(np.arange(data_size))
            shuffled_data = data[shuffle_indices]
        else:
            shuffled_data = data
        for batch_num in range(num_batches_per_epoch):
            start_index = batch_num * batch_size
            end_index = min((batch_num + 1) * batch_size, data_size)
            yield shuffled_data[start_index:end_index]