modified read_data for generating word array

read_data_m.py

def read_data_modified(fname):
    data = []
    with open(fname) as f:
        for line in f.readlines():
            line = re.sub('[!@#%^&:;,`\.\']', '', line)
            data.extend(line.replace('\n', '').strip().lower().split(' '))
    return data