python_utils.py

import time
import functools

def split_list_into_sized_chunks(l,n):
    """Yield successive n-sized chunks from l."""
    for i in range(0, len(l), n):
        yield l[i:i + n]


def clock(func):
    @functools.wraps(func)
    def clocked(*args, **kwargs):
        t0 = time.time()
        result = func(*args, **kwargs)
        elapsed = time.time() - t0
        name = func.__name__
        arg_lst = []
        if args:
            arg_lst.append(', '.join(repr(arg) for arg in args))
        if kwargs:
            pairs = ['%s=%r' % (k, w) for k, w in sorted(kwargs.items())]
            arg_lst.append(', '.join(pairs))
        arg_str = ', '.join(arg_lst)
        print('[%0.8fs] %s(%s) -> %r ' % (elapsed, name, arg_str, result))
        
        return result
    return clocked


#打印进度条
def printProgress (iteration, total, prefix = '', suffix = '', decimals = 2, barLength = 100):
    """
    Call in a loop to create terminal progress bar
    @params:
        iteration   - Required  : current iteration (Int)
        total       - Required  : total iterations (Int)
        prefix      - Optional  : prefix string (Str)
        suffix      - Optional  : suffix string (Str)
        decimals    - Optional  : number of decimals in percent complete (Int) 
        barLength   - Optional  : character length of bar (Int) 
    """
    filledLength    = int(round(barLength * iteration / float(total)))
    percents        = round(100.00 * (iteration / float(total)), decimals)
    bar             = '#' * filledLength + '-' * (barLength - filledLength)
    Sys.stdout.write('%s [%s] %s%s %s\r' % (prefix, bar, percents, '%', suffix)),
    Sys.stdout.flush()
    if iteration == total:
        print("\n")

#生成词云
def gen_wrod_cloud(file)
    # error _imagingft C module is not installed
    # sudo apt-get install libfreetype6-dev
    # pip uninstall pillow
    # pip install --no-cache-dir pillow
    import jieba
    from wordcloud import WordCloud
    import matplotlib.pyplot as plt
    text_from_file = open(file, 'rb').read()
    wordlist = jieba.cut(text_from_file, cut_all=True)           # 首先使用 jieba 中文分词工具进行分词
    wordlist_space_split = ' '.join(wordlist)
    my_wordcloud = WordCloud().generate(wordlist_space_split)

    plt.imshow(my_wordcloud)            
    plt.axis('on')                     
    plt.show()