add_feature = [
    'all_return_day1_return_count',  # -- 1/3/7/14日内总回流  #12
    'all_return_day3_return_count',
    'all_return_day7_return_count',
    'all_return_day14_return_count',

    'three_return_day1_return_count',  # -- 1/3/7/14日内前三层回流 #14
    'three_return_day3_return_count',
    'three_return_day7_return_count',
    'three_return_day14_return_count',

    'four_up_return_day1_return_count',  # -- 1/3/7/14日内四+层回流 #15
    'four_up_return_day3_return_count',
    'four_up_return_day7_return_count',
    'four_up_return_day14_return_count',

    'one_return_day1_return_count',  # -- 1/3/7/14日内一层回流  #13
    'one_return_day3_return_count',
    'one_return_day7_return_count',
    'one_return_day14_return_count',

    'four_up_return_div_three_return_day1',  # -- 1/3/7/14日内四+层回流/前三层回流   #23
    'four_up_return_div_three_return_day3',
    'four_up_return_div_three_return_day7',
    'four_up_return_div_three_return_day14',

    'all_return_day1_view_day1_return_count',  # -- 1/3/7/14日内曝光在1/3/7/14日内回流  #8
    'all_return_day3_view_day3_return_count',
    'all_return_day7_view_day7_return_count',
    'all_return_day14_view_day14_return_count',

    'three_return_day1_view_day1_return_count',  # -- 1/3/7/14日内曝光在1/3/7/14日内前三层回流 #10
    'three_return_day3_view_day3_return_count',
    'three_return_day7_view_day7_return_count',
    'three_return_day14_view_day14_return_count',

    'four_up_return_day1_view_day1_return_count',  # -- 1/3/7/14日内曝光在1/3/7/14日内四+层回流  # 11
    'four_up_return_day3_view_day3_return_count',
    'four_up_return_day7_view_day7_return_count',
    'four_up_return_day14_view_day14_return_count',

    'one_return_day1_view_day1_return_count',  ##-- 1/3/7/14日内曝光在1/3/7/14日内一层回流 #9
    'one_return_day3_view_day3_return_count',
    'one_return_day7_view_day7_return_count',
    'one_return_day14_view_day14_return_count',

    'all_return_day1_on_day1_return_count',  # 前day1+1 / day1+3/day1+7/day1+14 到前 day1+1日内曝光在 day1的总回流   #16
    'all_return_day3_on_day1_return_count',
    'all_return_day7_on_day1_return_count',
    'all_return_day14_on_day1_return_count',

    'four_up_return_day1_view_day1_return_div_three_d1',  # -- 1/3/7/14日内曝光在1/3/7/14日内四+层回流/前三层回流  #22
    'four_up_return_day3_view_day3_return_div_three_d3',
    'four_up_return_day7_view_day7_return_div_three_d7',
    'four_up_return_day14_view_day14_return_div_three_d14',

    'day1ctr',  # -- 1/3/7/14/30/60日内播放/曝光   #17
    'day3ctr',
    'day7ctr',
    'day14ctr',
    'day30ctr',
    'day60ctr',

    'day1sov',  # --  1/3/7/14/30/60日内分享/曝光  #18
    'day3sov',
    'day7sov',
    'day14sov',
    'day30sov',
    'day60sov',

    'day1rov',  # -- 1/3/7/14日内曝光的回流/曝光   #19
    'day3rov',
    'day7rov',
    'day14rov',

    'day1soc',  # -- 1/3/7/14/30/60日内分享/播放  #20
    'day3soc',
    'day7soc',
    'day14soc',
    'day30soc',
    'day60soc',

    'day1roc',  # -- 1/3/7/14日内曝光的回流/播放  #21
    'day3roc',
    'day7roc',
    'day14roc',

    'oneday_day1rov',  # -- 1/3/7/14日内曝光在今日的回流/ 1/3/7/14日内曝光  #24
    'oneday_day3rov',
    'oneday_day7rov',
    'oneday_day14rov',
    'futre7dayreturn'
    
    ,'todyviewcount_rank'
    ,'day1viewcount_rank'
]

featurename = [
    'dt',
    'videoid',
    'day1playcount',
    'day1returncount',
    'day1sharecount',
    'day1viewcount',
    'day14playcount',
    'day14returncount',
    'day14sharecount',
    'day14viewcount',
    'day30playcount',
    'day30returncount',
    'day30sharecount',
    'day30viewcount',
    'day3playcount',
    'day3returncount',
    'day3sharecount',
    'day3viewcount',
    'day60playcount',
    'day60returncount',
    'day60sharecount',
    'day60viewcount',
    'day7playcount',
    'day7returncount',
    'day7sharecount',
    'day7viewcount',
    'videocategory11',
    'videocategory12',
    'videocategory45',
    'videocategory49',
    'videocategory1',
    'videocategory2',
    'videocategory3',
    'videocategory4',
    'videocategory5',
    'videocategory6',
    'videocategory7',
    'videocategory8',
    'videocategory9',
    'videocategory85',
    'videocategory10',
    'videocategory555',
    'usercategory1',
    'usercategory2',
    'usercategory3',
    'usercategory4',
    'usercategory5',
    'usercategory6',
    'usercategory7',
    'usercategory8',
    'usercategory9',
    'usercategory10',
    'usercategory11',
    'usercategory12',
    'usercategory45',
    'usercategory49',
    'usercategory85',
    'usercategory555',
    'todyviewcount',
    'day5returncount_1_stage',
    'day5returncount_2_stage',
    'day5returncount_3_stage',
    'day5returncount_4_stage',
    'stage_one_retrn',
    'stage_two_retrn',
    'stage_three_retrn',
    'stage_four_retrn']
words = ['videotags','words_without_tags']
featurename = featurename + add_feature + words

# 首页特征
root_page_1day = ['day1playcount', 'day1returncount', 'day1sharecount', 'day1viewcount']

root_page_3day = ['day3playcount', 'day3returncount', 'day3sharecount', 'day3viewcount']

root_page_7day = ['day7playcount', 'day7returncount', 'day7sharecount', 'day7viewcount']

root_page_14day = ['day14playcount', 'day14returncount', 'day14sharecount', 'day14viewcount']

root_page_30day = ['day30playcount', 'day30returncount', 'day30sharecount', 'day30viewcount']

root_page_60day = ['day60playcount', 'day60returncount', 'day60sharecount', 'day60viewcount']

return_5day = ['day5returncount_1_stage', 'day5returncount_2_stage', 'day5returncount_3_stage',
               'day5returncount_4_stage']
cate_feat = ['videocategory1', 'videocategory10', 'videocategory11', 'videocategory12',
             'videocategory2', 'videocategory3', 'videocategory4', 'videocategory45',
             'videocategory49', 'videocategory5', 'videocategory6',
             'videocategory7', 'videocategory8', 'videocategory85', 'videocategory9', 'videocategory555']
one_hot_feature = ['videotags','words_without_tags','videoid']
#

def cal_feature(df):
    start = time.time()
    for i in range(len(root_page_1day)):
        
        
        newfeat_div = root_page_60day[i] + '_divide_' + root_page_30day[i]
#         df[newfeat_div] = df.apply(lambda s: s[root_page_30day[i]] / s[root_page_60day[i]]\
#                                           if s[root_page_60day[i]] != 0 else 0, axis=1) 
        df[newfeat_div] = df[root_page_30day[i]]/ df[root_page_60day[i]]
    
        newfeat_diff = root_page_60day[i] + '_dif_' + root_page_30day[i]
#         df[newfeat_diff] = df.apply(lambda s: s[root_page_60day[i]]-s[root_page_30day[i]],\
#                                                 axis=1) 
        df[newfeat_diff] = df[root_page_60day[i]] - df[root_page_30day[i]]

    end = time.time()
    running_time = end-start
    print('stage 1: time cost : %.5f sec' %running_time)
     
  
    start = time.time()
    for i in range(len(root_page_1day)):
        newfeat_div = root_page_30day[i] + '_divide_' + root_page_7day[i]
#         df[newfeat_div] = df.apply(lambda s: s[root_page_7day[i]] / s[root_page_30day[i]]\
#                                           if s[root_page_30day[i]] != 0 else 0, axis=1) 

        df[newfeat_div] = df[root_page_7day[i]]/df[root_page_30day[i]]
        newfeat_diff = root_page_30day[i] + '_dif_' + root_page_7day[i]
#         df[newfeat_diff] = df.apply(lambda s: s[root_page_7day[i]] - s[root_page_3day[i]],\
#                                                 axis=1) 
        df[newfeat_diff] = df[root_page_7day[i]] - df[root_page_3day[i]]
    end = time.time()
    running_time = end-start
    print('stage 2: time cost : %.5f sec' %running_time) 
    
    
    start = time.time()
    for i in range(len(root_page_1day)):
        newfeat_div = root_page_7day[i] + '_divide_' + root_page_3day[i]
#         df[newfeat_div] = df.apply(lambda s: s[root_page_3day[i]] / s[root_page_7day[i]]\
#                                           if s[root_page_7day[i]] != 0 else 0, axis=1)
        df[newfeat_div] = df[root_page_3day[i]]/df[root_page_7day[i]]

        newfeat_diff = root_page_7day[i] + '_dif_' + root_page_3day[i]
#         df[newfeat_diff] = df.apply(lambda s: s[root_page_7day[i]] - s[root_page_3day[i]],\
#                                                 axis=1) 
        df[newfeat_diff] = df[root_page_7day[i]] - df[root_page_3day[i]]
    end = time.time()
    running_time = end-start
    print('stage 3: time cost : %.5f sec' %running_time)
    
    start = time.time()
    for i in range(len(root_page_1day)):
        newfeat_div = root_page_3day[i] + '_divide_' + root_page_1day[i]
#         df[newfeat_div] = df.apply(lambda s: s[root_page_1day[i]] / s[root_page_3day[i]]\
#                                           if s[root_page_3day[i]] != 0 else 0, axis=1) 
        df[newfeat_div] = df[root_page_1day[i]] / df[root_page_3day[i]]
        newfeat_diff = root_page_3day[i] + '_dif_' + root_page_1day[i]
#         df[newfeat_diff] = df.apply(lambda s: s[root_page_3day[i]] - s[root_page_1day[i]],\
#                                                 axis=1) 
        df[newfeat_diff] = df[root_page_3day[i]] - df[root_page_1day[i]]
    end = time.time()
    running_time = end-start
    print('stage 4: time cost : %.5f sec' %running_time)
    df = df.replace([np.inf, -np.inf], np.nan)
    df = df.fillna(0)
    return df