gen_trick.py 文件源码

def delete_conversion_data():
    train_data = pd.read_hdf(FilePath + 'train_0613_nodelconvert')
    print 'read finish'
    advertiser_conversion_list = find_delete_advertiser()
    print len(advertiser_conversion_list)

    for item in advertiser_conversion_list:
        t = threading.Thread(target=get_index_to_delete,args=(train_data,item))
        t.start()
    while len(result_list)<len(advertiser_conversion_list):
        pass
    train_data.drop(delete_list, axis=0, inplace=True)
    train_data = train_data.reset_index()
    del train_data['index']
    print 'train write begin'
    train_data.to_hdf(FilePath + 'train_0613', 'all')
    delete_list = Series(delete_list)
    delete_list.to_csv(FilePath + 'delete_negsample_index_oftrain0613.csv', mode='a', index=False)