Test the idea that if we combine rank of CF and rank of features, whether we can get a better rank of prediction.

Possible issues:

I did not treat each purchase as individual event, instead, I calculate the CF based on users.



In [264]:

    
import pandas as pd
import numpy as np
import os
import scipy as sp
from sklearn.metrics.pairwise import cosine_similarity
import operator
import cv2
import glob
from keras.preprocessing import image
from matplotlib import pyplot as plt
import seaborn as sns
import random
%matplotlib inline



In [39]:

    
view_image = pd.DataFrame(glob.glob('view_data_image/*.jpg'))
view_image['produuct'] = view_image[0].apply(lambda x: int(x[16:-4]))
view_image.columns = [['file', 'product']]



In [410]:

    
def dot(K, L):
    if len(K) != len(L): return 0
    return sum(i[0]*i[1] for i in zip(K, L))

def similarity(item_1, item_2):
    return dot(item_1, item_2) / np.sqrt(dot(item_1, item_1)*dot(item_2, item_2))

def average(lists):
    return [np.mean(i) for i in zip(*[l for l in lists])]
def plot_top_rank(product_id):
    candidate = top_product(product_id)
    candidate_df = view_image[view_image['product'].isin(candidate)]
    test_view = candidate_df['file']
    
    fig,axes = plt.subplots(1, len(test_view))

    for i in range(len(test_view)):
        img = image.load_img(test_view.iloc[i], target_size=(224, 224))
        # images
        axes[i].imshow(img)
        axes[i].set_xticklabels([])
        #axes[0,i].get_xaxis().set_visible(False)
        axes[i].get_xaxis().set_ticks([])
        axes[i].get_yaxis().set_visible(False)

def plot_sim_rank(product_id):
    candidate = similar_product(product_id)
    candidate_df = view_image[view_image['product'].isin(candidate)]
    test_view = candidate_df['file']
    
    fig,axes = plt.subplots(1, len(test_view))

    for i in range(len(test_view)):
        img = image.load_img(test_view.iloc[i], target_size=(224, 224))
        # images
        axes[i].imshow(img)
        axes[i].set_xticklabels([])
        #axes[0,i].get_xaxis().set_visible(False)
        axes[i].get_xaxis().set_ticks([])
        axes[i].get_yaxis().set_visible(False)



In [417]:

    
df_spu[df_spu['spu'] == 458036191955415221]









    Out[417]:






  
    
      
      spu
      CF_item
      spu_features
      CF_features
      ave_CF_fea
      sim
      rank
    
  
  
    
      1099
      458036191955415221
      [84800400172249093, 297314006163628534, 436644...
      [0.084, 0.306, 0.0, 0.2, 0.088, 0.029, 0.166, ...
      [[[0.449, 0.247, 0.007, 0.261, 0.25, 0.007, 0....
      [0.371, 0.7426, 0.0304, 0.5118, 0.1884, 0.0459...
      0.664724
      612.0



In [ ]:

    
top_product



In [430]:

    
plot_sim_rank(3172644484366424)



In [429]:

    
plot_sim_rank(458036191955415221)



In [370]:

    
plot_top_rank(458036191955415221)









    



Similar products to 458036191955415221 include:

No. 1: 84800400172249093
No. 2: 297314006163628534
No. 3: 436644093725405288
No. 4: 305758255464948196
No. 5: 288588281885597903
No. 6: 444525391273811972
No. 7: 1732554800473563141
No. 8: 1760983773121339411
No. 9: 93526113400463377
No. 10: 89866935898595349



In [371]:

    
plot_top_rank(3172644484366424)









    



Similar products to 3172644484366424 include:

No. 1: 315046913029713936
No. 2: 461695358101766158
No. 3: 462821279656333429
No. 4: 3172644484366424
No. 5: 439458865467551753
No. 6: 89304008517624104
No. 7: 297314002868527124
No. 8: 300128739550408715
No. 9: 432703441537921049
No. 10: 32446015921365000



In [2]:

    
os.chdir('/Users/Walkon302/Desktop/deep-learning-models-master/view2buy')



In [204]:

    
df = pd.read_pickle('view2buy_url.pkl')



In [132]:

    
df.shape









    Out[132]:





(17460, 15)



In [133]:

    
df.head()









    Out[133]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu
      url
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...



In [134]:

    
df['user_buy'] = df.apply(lambda x: '{}-{}'.format(str(x['user_id']), str(x['buy_spu'])), axis = 1)



In [135]:

    
df.head()









    Out[135]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu
      url
      user_buy
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-453532580309307392
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      529805243-103096245561765919
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      3748045464-446777176556679168
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-438895881520357521
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-74104320184119307



In [136]:

    
df_cf = df.groupby(['user_buy','view_spu' ,'view_cnt']).count()



In [137]:

    
df_cf = df_cf.reset_index()[['user_buy', 'view_spu', 'view_cnt']]
df_cf.head()









    Out[137]:






  
    
      
      user_buy
      view_spu
      view_cnt
    
  
  
    
      0
      1018047589-2885476247461195776
      293373310066720769
      2
    
    
      1
      1018047589-2885476247461195776
      302661994239094787
      2
    
    
      2
      1018047589-2885476247461195776
      447903106563379200
      1
    
    
      3
      1018047589-2885476247461195776
      972290827227131904
      1
    
    
      4
      1018047589-2885476247461195776
      2192766390940934144
      2



In [138]:

    
piv = df_cf.pivot_table(index=['user_buy'], columns=['view_spu'], values='view_cnt')
piv_norm = piv.apply(lambda x: (x/np.mean(x)), axis=1)
piv_norm.fillna(0, inplace=True)
piv_norm = piv_norm.T
piv_norm = piv_norm.loc[:, (piv_norm != 0).any(axis=0)]
piv_sparse = sp.sparse.csr_matrix(piv_norm.values)



In [139]:

    
item_similarity = cosine_similarity(piv_sparse)
user_similarity = cosine_similarity(piv_sparse.T)



In [140]:

    
item_sim_df = pd.DataFrame(item_similarity, index = piv_norm.index, columns = piv_norm.index)
user_sim_df = pd.DataFrame(user_similarity, index = piv_norm.columns, columns = piv_norm.columns)



In [428]:

    
def similar_product(product_name):
    df_spu2 = df_spu
    candi = (df_spu[df_spu['spu'] == product_name]['spu_features'].iloc[0])
    df_spu2['sim'] = df_spu2.apply(lambda x: similarity(x['spu_features'], candi), axis = 1)
    df_spu2['rank'] = df_spu2['sim'].rank(ascending=False)
    return list(df_spu2.sort_values(by = 'rank')['spu'][0:10])



In [427]:

    
df_spu[df_spu['spu'] == 458036191955415221]['spu_features'].iloc[0]









    Out[427]:





[0.084,
 0.306,
 0.0,
 0.2,
 0.088,
 0.029,
 0.166,
 0.127,
 0.257,
 0.009,
 0.358,
 0.052,
 0.0,
 0.0,
 0.059,
 0.0,
 0.059,
 0.063,
 0.357,
 0.027,
 0.665,
 0.69,
 0.0,
 0.167,
 0.097,
 0.0,
 0.005,
 0.969,
 0.016,
 0.212,
 0.0,
 0.121,
 0.384,
 0.008,
 0.048,
 0.0,
 0.0,
 0.736,
 0.0,
 0.001,
 0.21,
 0.0,
 0.276,
 0.0,
 0.035,
 0.127,
 0.133,
 0.012,
 0.269,
 0.676,
 0.005,
 0.212,
 1.042,
 0.042,
 0.159,
 0.021,
 0.102,
 0.48,
 0.105,
 1.2,
 0.346,
 0.072,
 0.023,
 0.0,
 0.719,
 0.026,
 0.495,
 0.037,
 0.37,
 0.014,
 0.0,
 0.0,
 0.0,
 0.012,
 0.001,
 0.778,
 0.294,
 0.863,
 0.455,
 0.0,
 0.421,
 1.058,
 0.081,
 0.047,
 0.164,
 1.853,
 0.0,
 0.718,
 0.082,
 0.124,
 0.184,
 0.0,
 0.15,
 0.006,
 0.0,
 0.0,
 0.058,
 0.026,
 0.995,
 1.288,
 0.208,
 3.183,
 0.274,
 0.154,
 0.99,
 0.101,
 0.0,
 0.328,
 0.874,
 2.979,
 0.2,
 0.093,
 0.238,
 0.144,
 0.0,
 0.157,
 0.182,
 0.0,
 0.0,
 0.293,
 0.069,
 0.211,
 0.058,
 0.156,
 0.629,
 0.296,
 0.111,
 0.0,
 0.083,
 2.953,
 0.049,
 0.482,
 0.031,
 0.041,
 0.017,
 0.032,
 2.279,
 0.0,
 0.0,
 0.0,
 1.778,
 0.029,
 0.431,
 0.445,
 0.01,
 0.107,
 0.006,
 0.019,
 0.169,
 0.003,
 0.0,
 0.566,
 0.03,
 0.0,
 0.007,
 0.018,
 0.52,
 0.177,
 0.381,
 1.059,
 0.0,
 0.139,
 0.326,
 0.0,
 0.401,
 0.13,
 1.363,
 0.045,
 0.514,
 1.407,
 0.758,
 0.907,
 0.0,
 0.0,
 0.076,
 0.013,
 4.054,
 0.2,
 0.555,
 1.115,
 0.0,
 0.056,
 0.0,
 0.218,
 0.271,
 0.074,
 0.0,
 0.615,
 0.007,
 0.175,
 0.145,
 0.055,
 0.762,
 0.591,
 0.178,
 0.593,
 1.042,
 0.827,
 0.18,
 0.785,
 0.394,
 0.0,
 0.089,
 0.349,
 0.321,
 0.0,
 0.038,
 0.17,
 0.0,
 2.378,
 0.291,
 0.417,
 0.08,
 0.035,
 0.294,
 0.843,
 0.06,
 0.11,
 0.101,
 0.886,
 1.076,
 0.869,
 0.023,
 0.008,
 0.053,
 0.297,
 0.034,
 0.195,
 0.017,
 1.094,
 0.456,
 0.021,
 0.0,
 0.05,
 0.0,
 0.28,
 0.0,
 0.005,
 0.078,
 0.0,
 0.122,
 0.534,
 1.314,
 0.049,
 0.0,
 0.256,
 0.05,
 0.03,
 1.044,
 0.426,
 0.0,
 0.008,
 0.057,
 0.131,
 0.249,
 0.006,
 0.333,
 0.019,
 0.149,
 0.112,
 0.324,
 0.346,
 0.247,
 0.001,
 0.32,
 0.108,
 0.004,
 0.067,
 0.523,
 0.231,
 0.0,
 0.0,
 0.067,
 0.318,
 0.0,
 0.023,
 0.006,
 0.244,
 0.074,
 2.387,
 0.397,
 0.496,
 0.221,
 0.0,
 0.0,
 0.486,
 0.0,
 0.019,
 0.048,
 0.107,
 0.054,
 0.0,
 0.036,
 0.014,
 0.006,
 1.431,
 1.23,
 0.052,
 0.0,
 0.0,
 0.46,
 0.052,
 0.0,
 0.96,
 0.189,
 0.056,
 0.021,
 0.193,
 0.166,
 0.044,
 0.143,
 1.921,
 0.577,
 0.368,
 0.0,
 0.0,
 0.031,
 2.319,
 0.179,
 0.004,
 0.105,
 0.167,
 0.008,
 0.23,
 0.005,
 0.0,
 0.598,
 0.103,
 0.0,
 0.15,
 0.024,
 0.0,
 0.029,
 0.056,
 0.004,
 1.179,
 0.28,
 1.374,
 1.81,
 0.16,
 0.163,
 1.253,
 0.119,
 0.017,
 0.335,
 0.1,
 0.0,
 0.313,
 0.235,
 0.017,
 0.001,
 0.426,
 0.072,
 0.556,
 0.0,
 0.019,
 0.01,
 0.538,
 0.0,
 0.501,
 0.026,
 0.271,
 0.399,
 0.0,
 1.205,
 0.028,
 3.248,
 0.109,
 0.0,
 0.01,
 0.035,
 0.036,
 0.682,
 0.0,
 0.09,
 0.0,
 0.0,
 0.115,
 0.187,
 0.173,
 0.114,
 0.0,
 0.0,
 0.0,
 0.037,
 0.052,
 0.142,
 0.029,
 0.005,
 1.109,
 0.147,
 0.0,
 1.586,
 0.175,
 0.549,
 1.063,
 0.082,
 0.179,
 0.752,
 0.0,
 0.321,
 0.0,
 0.556,
 0.0,
 0.124,
 0.052,
 0.16,
 0.084,
 0.252,
 0.069,
 0.049,
 0.34,
 0.009,
 0.0,
 0.0,
 0.0,
 0.101,
 1.743,
 0.058,
 0.0,
 0.0,
 0.336,
 0.089,
 1.804,
 0.056,
 0.006,
 0.095,
 0.318,
 0.146,
 0.088,
 0.009,
 2.152,
 0.0,
 0.044,
 0.0,
 0.057,
 0.373,
 0.018,
 0.128,
 1.293,
 0.676,
 0.0,
 0.043,
 0.01,
 0.038,
 0.003,
 0.005,
 0.207,
 2.47,
 0.127,
 0.162,
 0.0,
 0.012,
 0.0,
 0.44,
 0.685,
 0.189,
 0.074,
 0.0,
 0.611,
 0.151,
 1.678,
 0.18,
 0.261,
 0.05,
 0.426,
 0.193,
 0.326,
 0.18,
 0.187,
 0.045,
 2.542,
 0.037,
 0.208,
 0.215,
 0.943,
 0.047,
 0.082,
 0.247,
 0.853,
 0.106,
 0.402,
 0.491,
 0.014,
 0.245,
 0.0,
 0.0,
 0.658,
 2.221,
 0.0,
 0.071,
 2.839,
 0.123,
 0.852,
 1.838,
 0.835,
 0.0,
 0.293,
 0.048,
 0.044,
 0.475,
 0.033,
 0.089,
 0.0,
 0.29,
 0.956,
 2.701,
 2.531,
 0.449,
 0.166,
 0.242,
 0.515,
 0.434,
 0.146,
 0.238,
 0.0,
 0.038,
 0.202,
 0.0,
 0.0,
 0.379,
 0.257,
 0.095,
 0.259,
 0.0,
 0.362,
 0.104,
 0.584,
 0.0,
 1.079,
 0.021,
 0.561,
 0.0,
 0.0,
 0.01,
 0.319,
 0.003,
 0.32,
 0.392,
 0.101,
 0.252,
 0.0,
 0.041,
 0.234,
 0.102,
 4.737,
 0.2,
 0.0,
 0.0,
 0.099,
 0.689,
 0.041,
 3.696,
 0.054,
 0.076,
 0.0,
 0.892,
 0.235,
 0.12,
 0.319,
 0.687,
 0.347,
 0.452,
 0.061,
 0.024,
 0.02,
 0.844,
 0.034,
 0.644,
 0.004,
 0.043,
 0.682,
 0.236,
 0.354,
 0.209,
 0.159,
 0.2,
 0.0,
 0.615,
 0.264,
 0.375,
 0.047,
 0.296,
 0.077,
 0.488,
 0.055,
 0.032,
 0.168,
 0.471,
 0.007,
 0.017,
 0.213,
 1.324,
 0.072,
 0.007,
 0.132,
 0.056,
 0.496,
 0.054,
 0.573,
 0.051,
 0.811,
 0.0,
 0.0,
 0.0,
 0.058,
 0.0,
 0.106,
 0.037,
 0.822,
 0.058,
 0.346,
 0.204,
 0.007,
 0.446,
 0.025,
 0.0,
 0.192,
 0.247,
 0.036,
 0.02,
 0.0,
 0.044,
 0.509,
 0.061,
 0.549,
 6.572,
 0.02,
 0.127,
 0.0,
 0.052,
 0.14,
 0.489,
 0.0,
 0.013,
 0.613,
 0.0,
 0.0,
 0.0,
 0.0,
 0.003,
 0.046,
 0.489,
 0.132,
 0.315,
 1.312,
 0.755,
 0.0,
 0.322,
 0.091,
 1.003,
 0.0,
 0.028,
 0.006,
 0.148,
 0.097,
 0.003,
 1.363,
 0.223,
 0.266,
 0.011,
 0.126,
 0.078,
 0.097,
 0.0,
 0.021,
 0.009,
 0.0,
 0.036,
 0.257,
 0.006,
 0.534,
 0.0,
 1.094,
 0.344,
 0.189,
 0.016,
 1.248,
 0.0,
 0.237,
 0.03,
 0.227,
 0.086,
 0.899,
 0.0,
 0.268,
 0.205,
 0.0,
 0.119,
 0.0,
 0.013,
 0.011,
 0.0,
 0.187,
 0.02,
 0.042,
 0.284,
 0.054,
 0.0,
 0.288,
 0.012,
 0.428,
 1.034,
 0.0,
 0.0,
 0.127,
 0.111,
 0.205,
 0.214,
 0.029,
 0.0,
 0.38,
 0.547,
 0.937,
 0.342,
 0.0,
 0.131,
 0.059,
 0.0,
 0.013,
 0.053,
 0.001,
 0.464,
 0.048,
 0.064,
 0.035,
 0.008,
 0.564,
 0.0,
 0.018,
 0.19,
 0.365,
 3.314,
 0.414,
 0.817,
 0.0,
 0.279,
 0.0,
 1.552,
 0.06,
 0.316,
 0.8,
 0.841,
 0.476,
 0.324,
 0.024,
 0.229,
 0.133,
 0.0,
 0.0,
 3.043,
 0.355,
 0.28,
 0.0,
 0.013,
 0.249,
 0.529,
 0.103,
 0.017,
 0.053,
 0.009,
 0.18,
 0.0,
 0.386,
 0.276,
 0.323,
 0.0,
 0.771,
 0.27,
 0.513,
 0.476,
 0.239,
 0.063,
 0.0,
 0.807,
 0.705,
 0.025,
 0.015,
 0.008,
 1.374,
 0.0,
 0.0,
 0.045,
 0.034,
 0.0,
 0.34,
 0.13,
 0.0,
 0.215,
 0.0,
 0.075,
 0.0,
 0.691,
 0.26,
 0.043,
 0.214,
 0.096,
 0.019,
 0.332,
 0.174,
 0.089,
 0.039,
 0.0,
 0.0,
 1.721,
 0.821,
 0.199,
 0.063,
 0.874,
 0.007,
 0.0,
 0.0,
 0.104,
 0.241,
 0.0,
 1.289,
 0.263,
 0.06,
 0.45,
 0.798,
 0.104,
 0.001,
 0.223,
 0.0,
 0.008,
 0.034,
 0.191,
 0.0,
 0.178,
 0.048,
 0.034,
 0.001,
 0.017,
 0.0,
 0.0,
 0.032,
 0.37,
 0.0,
 0.07,
 0.0,
 0.599,
 0.476,
 0.222,
 0.0,
 6.315,
 0.274,
 0.621,
 0.021,
 0.037,
 0.341,
 0.053,
 4.8,
 0.086,
 0.184,
 0.014,
 0.047,
 0.355,
 0.192,
 0.176,
 0.554,
 0.0,
 0.177,
 0.112,
 0.31,
 0.0,
 0.03,
 0.0,
 0.175,
 0.0,
 0.707,
 1.375,
 0.248,
 0.098,
 0.093,
 0.317,
 0.098,
 0.059,
 0.13,
 2.406,
 0.0,
 0.0,
 1.71,
 0.0,
 0.449,
 0.275,
 0.153,
 0.019,
 0.514,
 1.551,
 0.0,
 0.0,
 0.0,
 0.057,
 0.696,
 0.0,
 0.297,
 0.03,
 0.002,
 0.146,
 0.0,
 0.311,
 0.56,
 0.429,
 0.102,
 1.062,
 0.219,
 0.03,
 0.161,
 0.426,
 0.039,
 0.175,
 0.0,
 0.884,
 0.509,
 0.052,
 0.104,
 0.0,
 0.0,
 0.0,
 0.178,
 0.241,
 0.26,
 0.128,
 0.831,
 0.045,
 0.072,
 0.0,
 0.011,
 0.0,
 0.0,
 0.022,
 0.003,
 0.04,
 0.022,
 0.0,
 0.406,
 0.315,
 0.059,
 0.332,
 0.21,
 0.377,
 0.429,
 0.0,
 0.234,
 0.123,
 0.0,
 0.154,
 3.243,
 0.904,
 2.536,
 3.8,
 0.052,
 0.0,
 0.009,
 0.439,
 0.02,
 0.211,
 0.391,
 0.03,
 0.467,
 0.181,
 0.408,
 0.036,
 0.467,
 0.0,
 0.008,
 0.0,
 0.0,
 0.044,
 0.0,
 0.262,
 0.002,
 0.277,
 0.007,
 0.348,
 0.012,
 0.815,
 0.211,
 0.047,
 0.593,
 0.547,
 0.027,
 0.155,
 0.0,
 0.0,
 0.605,
 1.441,
 0.536,
 0.389,
 0.401,
 0.355,
 0.025,
 0.42,
 0.143,
 0.127,
 0.016,
 0.102,
 0.0,
 0.316,
 0.006,
 ...]



In [ ]:

    
458036191955415221



In [408]:

    
similar_product(357872333107204)









    Out[408]:





[357872333107204,
 447058691588489219,
 7653099516274397185,
 3778596430335328256,
 4429648062768701440,
 3773248405777813504,
 440866234308272136,
 937950908773744640,
 8081222873064148999,
 463665709926023172]



In [141]:

    
def top_product(product_name):
    count = 1
    print('Similar products to {} include:\n'.format(product_name))
    for item in item_sim_df.sort_values(by = product_name, ascending = False).index[1:11]:
        print('No. {}: {}'.format(count, item))
        count +=1
    return item_sim_df.sort_values(by = product_name, ascending = False).index[1:11]



In [190]:

    
def top_product_noprint(product_name):
    return list(item_sim_df.sort_values(by = product_name, ascending = False).index[1:])



In [191]:

    
a = top_product_noprint(357875526680651)



In [385]:

    
df_spu









    Out[385]:






  
    
      
      spu
      CF_item
      spu_features
      CF_features
      ave_CF_fea
    
  
  
    
      0
      357872333107204
      [8952950888272863232, 2846351224980500480, 881...
      [0.035, 0.385, 0.112, 0.014, 0.0, 0.123, 0.438...
      [[[0.462, 0.551, 0.068, 0.833, 0.0, 0.0, 0.0, ...
      [0.3597, 0.7012, 0.0831, 1.0618, 0.2302, 0.123...
    
    
      1
      357875526680651
      [2046769978417582, 461413925257830545, 3255052...
      [0.132, 1.678, 0.061, 0.918, 0.462, 0.342, 0.4...
      [[[0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104...
      [0.4727, 0.8078, 0.0697, 0.5796, 0.3075, 0.009...
    
    
      2
      357882254983171
      [459725075493814272, 8582811288237465674, 1976...
      [0.026, 0.936, 0.056, 0.614, 0.139, 0.0, 0.302...
      [[[1.884, 0.52, 0.0, 3.98, 0.175, 0.008, 0.663...
      [0.6206, 0.8754, 0.1066, 0.7549, 0.2387, 0.186...
    
    
      3
      357901107539985
      [2466922956389351424, 7804532970923106304, 130...
      [0.229, 0.543, 0.132, 0.144, 0.295, 0.018, 0.0...
      [[[0.124, 0.819, 0.0, 0.596, 0.306, 0.043, 0.2...
      [0.449, 0.7069, 0.1971, 0.7197, 0.2461, 0.0106...
    
    
      4
      639360131194904
      [81141212316332372, 320394952166453251, 639360...
      [1.113, 0.5, 0.758, 0.218, 0.0, 0.0, 0.335, 1....
      [[[0.06, 0.15, 0.011, 0.946, 0.501, 0.0, 1.309...
      [0.2552, 0.5227, 0.0964, 0.3326, 0.1703, 0.011...
    
    
      5
      639369692328147
      [463947194068213779, 4861516576375025, 9630021...
      [1.489, 0.457, 0.0, 0.639, 0.0, 0.029, 0.656, ...
      [[[0.057, 0.172, 0.0, 0.068, 0.284, 0.0, 0.0, ...
      [0.5026, 0.6077, 0.1351, 1.0361, 0.3056, 0.098...
    
    
      6
      639371126526005
      [2166589220222894080, 444243906496860160, 4611...
      [0.28, 0.566, 0.009, 0.004, 0.119, 0.199, 0.39...
      [[[0.051, 0.253, 0.0, 0.173, 0.803, 0.002, 0.2...
      [0.2053, 0.3088, 0.0316, 0.194, 0.2859, 0.1264...
    
    
      7
      639389503180805
      [81985618826645681, 15838990034669717, 1014074...
      [0.023, 0.853, 0.11, 0.415, 0.681, 0.078, 0.50...
      [[[0.621, 0.779, 0.019, 0.708, 0.32, 0.268, 0....
      [0.4553, 0.8364, 0.0406, 0.5165, 0.2133, 0.046...
    
    
      8
      639392717246493
      [13587203813871817, 1765254792024080, 10440669...
      [0.496, 1.321, 0.014, 0.093, 0.145, 0.118, 0.1...
      [[[0.086, 0.85, 0.023, 0.019, 0.018, 0.0, 0.16...
      [0.3234, 0.9647, 0.089, 0.2659, 0.1303, 0.0571...
    
    
      9
      920816362999808
      [2457352807885774848, 8584218663084269568, 465...
      [0.375, 0.498, 0.093, 1.439, 0.482, 0.268, 0.1...
      [[[0.156, 0.49, 0.359, 0.513, 0.0, 0.066, 0.49...
      [0.5876, 0.3963, 0.194, 0.5702, 0.0595, 0.1919...
    
    
      10
      920832942268416
      [299565768102322188, 31601602323353621, 439458...
      [0.151, 0.729, 0.118, 0.091, 0.284, 0.0, 0.331...
      [[[0.804, 0.159, 0.134, 2.68, 0.272, 0.0, 0.14...
      [0.3458, 0.7266, 0.1114, 0.6795, 0.271, 0.0797...
    
    
      11
      920846404657158
      [319550492123078656, 3454096121704448, 2995657...
      [0.172, 0.284, 0.004, 0.19, 0.132, 0.0, 0.123,...
      [[[0.01, 0.928, 0.125, 0.437, 0.17, 0.009, 0.2...
      [0.3545, 0.7114, 0.0839, 0.5078, 0.3372, 0.011...
    
    
      12
      1202299096490170
      [1044348428712186010, 93526113400463372, 89532...
      [0.538, 0.997, 0.016, 0.28, 0.538, 0.436, 0.30...
      [[[0.672, 0.383, 0.297, 0.59, 0.604, 0.098, 0....
      [0.352, 0.6496, 0.0722, 0.3963, 0.3971, 0.0728...
    
    
      13
      1202310084616220
      [6550345938870290, 462821289168044046, 3329046...
      [0.897, 1.037, 0.0, 0.09, 0.027, 0.53, 0.088, ...
      [[[0.09, 1.494, 0.048, 0.0, 0.029, 0.298, 0.04...
      [0.2141, 0.5406, 0.1607, 0.9761, 0.1241, 0.055...
    
    
      14
      1202315469205505
      [1044348428712186010, 93526113400463372, 89532...
      [0.175, 0.717, 0.0, 0.445, 0.103, 0.0, 0.578, ...
      [[[0.672, 0.383, 0.297, 0.59, 0.604, 0.098, 0....
      [0.352, 0.6496, 0.0722, 0.3963, 0.3971, 0.0728...
    
    
      15
      1202326037671948
      [9041615583843246080, 8939721565444202502, 420...
      [0.268, 0.209, 0.016, 0.789, 1.177, 0.0, 0.034...
      [[[0.205, 0.614, 0.0, 0.283, 0.029, 0.006, 0.3...
      [0.5225, 0.3637, 0.0274, 0.7803, 0.2, 0.0929, ...
    
    
      16
      1202342670667978
      [8295425334878236672, 444806904121757743, 4346...
      [0.073, 0.544, 0.0, 0.228, 0.066, 0.004, 1.104...
      [[[0.736, 0.65, 0.0, 0.055, 0.027, 0.0, 0.337,...
      [0.2007, 0.8379, 0.0326, 0.3353, 0.0847, 0.009...
    
    
      17
      1202342670671910
      [13587203813871817, 1765254792024080, 10440669...
      [0.339, 2.969, 0.149, 0.335, 0.0, 0.0, 0.334, ...
      [[[0.086, 0.85, 0.023, 0.019, 0.018, 0.0, 0.16...
      [0.3234, 0.9647, 0.089, 0.2659, 0.1303, 0.0571...
    
    
      18
      1483782161825904
      [302662024581271741, 19216708624982102, 148378...
      [0.528, 1.082, 0.417, 1.969, 0.291, 0.022, 0.0...
      [[[0.207, 0.77, 0.009, 0.123, 0.631, 0.064, 0....
      [0.2882, 0.7877, 0.1187, 1.1597, 0.3005, 0.073...
    
    
      19
      1765254792024080
      [13587203813871817, 1765254792024080, 10440669...
      [0.69, 0.17, 0.0, 0.127, 0.051, 0.0, 0.462, 0....
      [[[0.086, 0.85, 0.023, 0.019, 0.018, 0.0, 0.16...
      [0.3234, 0.9647, 0.089, 0.2659, 0.1303, 0.0571...
    
    
      20
      2046724026622135
      [2046724026622135, 1386059101696032768, 164019...
      [0.095, 0.719, 0.0, 0.114, 0.0, 0.0, 0.02, 0.0...
      [[[0.095, 0.719, 0.0, 0.114, 0.0, 0.0, 0.02, 0...
      [0.2095, 0.5489, 0.1747, 0.2043, 0.0683, 0.113...
    
    
      21
      2046767967338535
      [5047767116498747392, 4067389766593323193, 204...
      [1.915, 0.723, 0.068, 0.761, 0.082, 0.0, 0.098...
      [[[0.044, 0.315, 0.017, 0.256, 0.003, 0.004, 0...
      [0.306, 0.8059, 0.1071, 0.3562, 0.0785, 0.0614...
    
    
      22
      2046769978417582
      [2046769978417582, 461413925257830545, 3255052...
      [0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104, ...
      [[[0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104...
      [0.4727, 0.8078, 0.0697, 0.5796, 0.3075, 0.009...
    
    
      23
      2609679722156042
      [31038690201997892, 81985606739279872, 4374885...
      [0.34, 0.747, 0.0, 0.036, 0.287, 0.075, 0.652,...
      [[[0.026, 2.31, 0.026, 0.65, 0.027, 0.014, 0.0...
      [0.1925, 0.8188, 0.0477, 0.1953, 0.1594, 0.033...
    
    
      24
      2891145450029056
      [8945069666075066368, 86770695957168136, 80015...
      [0.307, 0.529, 0.062, 0.137, 0.602, 0.26, 0.13...
      [[[0.047, 1.04, 0.0, 0.538, 0.273, 0.036, 0.04...
      [0.2889, 1.2939, 0.1574, 0.404, 0.1981, 0.3745...
    
    
      25
      2891152447287296
      [89866911491678214, 76074637632249877, 1111339...
      [0.156, 1.136, 0.104, 0.368, 0.199, 0.223, 0.1...
      [[[1.039, 0.054, 0.159, 1.421, 0.168, 0.496, 0...
      [0.5565, 0.5092, 0.0445, 0.8707, 0.2669, 0.111...
    
    
      26
      2891160600990330
      [453532585603989586, 14150149385499493, 901797...
      [0.011, 0.057, 0.003, 0.313, 0.017, 0.0, 0.93,...
      [[[0.166, 0.047, 0.0, 0.408, 0.044, 0.0, 1.0, ...
      [0.2168, 0.3611, 0.1358, 1.3846, 0.1856, 0.086...
    
    
      27
      2891169552208298
      [3735594482335915, 464791631716921422, 4397403...
      [0.475, 1.321, 0.009, 0.157, 0.017, 0.065, 0.4...
      [[[0.245, 0.255, 0.06, 0.593, 0.0, 0.467, 0.08...
      [0.478, 0.927, 0.2476, 0.7833, 0.392, 0.093, 0...
    
    
      28
      3172644484366424
      [315046913029713936, 461695358101766158, 46282...
      [0.706, 0.552, 0.0, 0.55, 0.241, 0.0, 0.43, 0....
      [[[1.037, 1.816, 0.067, 0.334, 0.272, 0.04, 0....
      [0.5111, 1.433, 0.0416, 0.5964, 0.2476, 0.0287...
    
    
      29
      3454095765094424
      [75230216867246653, 10491016902120013, 8582811...
      [0.158, 0.029, 0.0, 0.332, 0.369, 0.0, 0.35, 0...
      [[[0.047, 1.367, 0.01, 0.016, 0.192, 0.144, 0....
      [0.3853, 0.8521, 0.0434, 0.3653, 0.1598, 0.017...
    
    
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      2125
      9014593909249236993
      [9033734206588821512, 8459806721299259392, 131...
      [0.962, 0.83, 0.029, 0.529, 0.336, 1.437, 0.60...
      [[[1.107, 0.61, 0.0, 1.565, 0.093, 0.026, 0.19...
      [0.3268, 0.6027, 0.0596, 0.8568, 0.3677, 0.065...
    
    
      2126
      9015719808079347717
      [1403510549529337857, 4716752541135134720, 246...
      [0.599, 0.232, 0.182, 0.959, 0.013, 0.54, 0.05...
      [[[0.398, 0.12, 0.211, 0.331, 0.114, 0.129, 0....
      [0.4865, 0.5288, 0.125, 0.6937, 0.1892, 0.0139...
    
    
      2127
      9016845703713148936
      [8943099259803860992, 4214038229457264801, 656...
      [1.14, 0.264, 0.0, 0.497, 0.115, 0.04, 0.146, ...
      [[[1.193, 0.452, 0.086, 1.264, 0.026, 0.153, 0...
      [1.0527, 0.4987, 0.1385, 0.8035, 0.0896, 0.107...
    
    
      2128
      9017127181215457486
      [318143145884868618, 322365263185870869, 45212...
      [1.491, 0.487, 0.001, 0.313, 0.106, 0.0, 0.565...
      [[[0.043, 1.798, 0.06, 0.324, 0.522, 0.006, 0....
      [0.3767, 0.922, 0.0483, 0.3788, 0.1126, 0.1851...
    
    
      2129
      9017971603620016137
      [2480715230932934656, 9013468003992612872, 570...
      [0.457, 0.066, 0.125, 2.235, 0.394, 0.0, 0.921...
      [[[0.224, 2.103, 0.111, 1.814, 0.024, 0.053, 0...
      [0.2507, 0.7091, 0.0523, 1.216, 0.1013, 0.0805...
    
    
      2130
      9017971606044979200
      [453532585603989586, 314765448579829939, 90179...
      [0.08, 0.252, 0.023, 2.211, 0.304, 0.157, 0.23...
      [[[0.166, 0.047, 0.0, 0.408, 0.044, 0.0, 1.0, ...
      [0.1928, 0.4477, 0.1556, 1.1285, 0.1973, 0.141...
    
    
      2131
      9018816028550127616
      [25972089290305537, 82548606340628534, 2503076...
      [0.731, 0.577, 0.0, 0.579, 0.053, 0.0, 0.173, ...
      [[[0.223, 0.478, 0.018, 0.633, 0.081, 0.0, 0.0...
      [0.2758, 0.4644, 0.038, 0.8915, 0.1976, 0.1173...
    
    
      2132
      9022193728259383296
      [8662750265739194369, 1396755150088278017, 896...
      [0.287, 0.508, 0.083, 1.605, 0.0, 0.0, 0.161, ...
      [[[0.098, 0.791, 0.037, 1.392, 0.091, 0.0, 0.8...
      [0.3521, 0.5703, 0.164, 1.1472, 0.1509, 0.0404...
    
    
      2133
      9022475203247398916
      [8379867827911725056, 2833684851741020160, 247...
      [0.448, 0.296, 0.0, 0.289, 0.034, 0.0, 0.204, ...
      [[[0.244, 0.285, 0.014, 0.0, 0.026, 0.172, 0.0...
      [0.3138, 0.4603, 0.0615, 0.7818, 0.1203, 0.053...
    
    
      2134
      9022756682497105932
      [2889135421455757312, 8964209883068317705, 139...
      [0.424, 0.469, 0.866, 0.072, 0.17, 0.029, 0.04...
      [[[0.0, 0.407, 0.0, 0.936, 0.368, 0.0, 0.633, ...
      [0.4331, 0.5593, 0.1124, 1.3875, 0.1317, 0.037...
    
    
      2135
      9023882578131013643
      [2834529276655054848, 8944788109675335687, 247...
      [0.369, 0.951, 0.139, 0.554, 0.0, 0.057, 0.676...
      [[[0.508, 0.872, 0.053, 0.959, 0.406, 0.079, 0...
      [0.3402, 0.8657, 0.0735, 1.1642, 0.2633, 0.023...
    
    
      2136
      9024727008410832903
      [2814544552628457472, 4710841566656688129, 246...
      [0.268, 1.398, 0.048, 0.996, 0.038, 0.175, 0.0...
      [[[0.654, 0.789, 0.047, 1.587, 0.603, 0.122, 0...
      [0.4715, 0.4672, 0.0954, 0.9115, 0.173, 0.0866...
    
    
      2137
      9026415852921315334
      [8935499435443806210, 2469456231166840832, 250...
      [2.351, 0.923, 0.057, 2.389, 0.001, 0.279, 0.0...
      [[[0.151, 0.411, 0.516, 2.49, 0.478, 0.0, 0.02...
      [0.5588, 0.6993, 0.162, 1.3153, 0.3403, 0.052,...
    
    
      2138
      9026697332171030534
      [306321203330416650, 8943943684745093124, 3139...
      [0.226, 2.182, 0.349, 1.539, 0.623, 0.08, 0.55...
      [[[0.642, 0.678, 0.035, 0.179, 0.209, 0.0, 0.6...
      [0.2872, 0.5251, 0.0575, 0.6054, 0.1139, 0.077...
    
    
      2139
      9027823227804868619
      [32446013086847137, 4641598722385866752, 89650...
      [0.022, 0.249, 0.024, 1.01, 0.68, 0.342, 0.285...
      [[[0.5, 0.052, 0.004, 0.379, 1.003, 0.023, 0.1...
      [0.5151, 0.5221, 0.0721, 0.8971, 0.2982, 0.126...
    
    
      2140
      9031763960910209025
      [299565803160592409, 437207054292414662, 29084...
      [0.439, 1.185, 0.27, 0.076, 0.193, 1.313, 0.11...
      [[[0.403, 0.956, 0.007, 0.555, 0.099, 0.064, 0...
      [0.3553, 0.8389, 0.063, 1.3263, 0.2993, 0.2635...
    
    
      2141
      9033171252362444801
      [436644089099345920, 1394503350274605056, 7653...
      [0.111, 1.705, 0.287, 0.536, 0.174, 0.082, 0.3...
      [[[0.055, 0.927, 0.855, 0.292, 0.129, 0.095, 0...
      [0.3778, 0.6725, 0.1822, 0.6073, 0.1004, 0.073...
    
    
      2142
      9033734206588821512
      [1314001506935377921, 8459806721299259392, 946...
      [1.107, 0.61, 0.0, 1.565, 0.093, 0.026, 0.198,...
      [[[0.003, 0.944, 0.131, 0.601, 1.503, 0.008, 0...
      [0.6796, 0.9908, 0.0429, 1.0009, 0.341, 0.2758...
    
    
      2143
      9035141577199349769
      [8970120857579282441, 9007838504458428425, 282...
      [0.281, 0.999, 0.075, 0.693, 0.0, 0.0, 0.025, ...
      [[[0.0, 0.543, 0.01, 0.138, 0.018, 0.373, 0.12...
      [0.3044, 0.6704, 0.1144, 0.9836, 0.1997, 0.090...
    
    
      2144
      9036830509787594752
      [4418107589125877775, 2813981603359453184, 439...
      [0.046, 0.136, 0.123, 0.013, 0.5, 0.233, 0.118...
      [[[0.162, 0.766, 0.024, 0.238, 0.041, 0.134, 0...
      [0.2982, 0.8262, 0.1709, 0.6126, 0.0938, 0.073...
    
    
      2145
      9037674851989819400
      [5140090909293244416, 2910246045436305408, 889...
      [1.315, 0.858, 0.031, 2.212, 0.165, 0.041, 0.0...
      [[[0.012, 0.469, 0.0, 0.021, 0.004, 0.0, 0.149...
      [0.3437, 0.6673, 0.1118, 0.7965, 0.1679, 0.095...
    
    
      2146
      9038237806216196097
      [4063730591896084758, 320113495556218907, 2990...
      [0.916, 0.513, 0.167, 0.201, 0.284, 0.023, 0.1...
      [[[0.53, 0.945, 0.0, 0.785, 0.028, 0.161, 0.14...
      [0.3446, 0.9183, 0.0247, 0.3677, 0.213, 0.057,...
    
    
      2147
      9039645182176481286
      [1675415380238614528, 4641598722385866752, 246...
      [0.216, 0.17, 0.018, 3.05, 0.224, 0.835, 0.334...
      [[[0.067, 0.002, 0.048, 1.074, 0.542, 0.023, 0...
      [0.3266, 0.384, 0.0903, 0.7626, 0.4486, 0.1297...
    
    
      2148
      9039926651803541506
      [467887839865233418, 33571969587101699, 282664...
      [0.219, 1.177, 0.074, 1.615, 0.112, 0.207, 0.0...
      [[[0.657, 0.508, 0.436, 0.075, 0.625, 0.192, 0...
      [0.3592, 0.6364, 0.113, 0.9559, 0.1909, 0.0398...
    
    
      2149
      9041615583843246080
      [8939721565444202502, 13868682270638081, 12023...
      [0.205, 0.614, 0.0, 0.283, 0.029, 0.006, 0.328...
      [[[1.466, 0.586, 0.0, 0.439, 0.049, 0.0, 0.104...
      [0.7453, 0.8045, 0.0315, 0.8878, 0.3513, 0.138...
    
    
      2150
      9088621908743286785
      [84800386939424768, 5705920362590242, 40713304...
      [0.0, 0.502, 0.0, 0.01, 0.206, 0.031, 1.15, 0....
      [[[0.053, 0.258, 0.002, 0.0, 0.449, 0.061, 0.9...
      [0.2219, 0.8111, 0.0544, 0.2453, 0.2216, 0.046...
    
    
      2151
      9089747807251402752
      [447903087581487120, 84800366075408747, 318987...
      [0.764, 0.496, 0.486, 0.159, 0.165, 0.474, 0.8...
      [[[0.176, 1.749, 0.0, 0.185, 0.02, 0.31, 0.084...
      [0.3317, 0.7604, 0.0334, 0.7855, 0.1488, 0.231...
    
    
      2152
      9090029283626840066
      [88178053449961475, 299847247939522560, 909002...
      [0.423, 0.22, 0.083, 0.994, 0.096, 0.0, 0.048,...
      [[[0.004, 0.453, 0.0, 0.643, 0.442, 0.043, 0.0...
      [0.3801, 0.6667, 0.0895, 0.4036, 0.2618, 0.027...
    
    
      2153
      9090592232181542912
      [8306121384015122432, 2900394421224820736, 283...
      [0.25, 0.926, 0.073, 1.526, 0.386, 0.024, 0.49...
      [[[0.157, 0.964, 0.117, 0.82, 0.915, 0.016, 0....
      [0.7383, 0.6909, 0.0327, 1.0177, 0.4509, 0.134...
    
    
      2154
      9094251405871296512
      [100844442657288193, 292247467889451008, 29252...
      [0.055, 0.351, 0.0, 0.475, 0.129, 0.055, 0.185...
      [[[0.206, 1.239, 0.043, 1.42, 0.057, 0.03, 0.0...
      [0.5435, 0.9577, 0.0513, 1.5471, 0.1106, 0.312...
    
  

2155 rows × 5 columns



In [143]:

    
plot_top_rank(639371126526005)









    



Similar products to 639371126526005 include:

No. 1: 2166589220222894080
No. 2: 444243906496860160
No. 3: 461132458872606754
No. 4: 452406680821547008
No. 5: 937950908773744640
No. 6: 1586187811960238082
No. 7: 1099236096233168896
No. 8: 1102050800015937536
No. 9: 98311167513120777
No. 10: 8951824985835937792



In [172]:

    
a = top_product_noprint(639371126526005)



In [173]:

    
a









    Out[173]:





[2166589220222894080,
 444243906496860160,
 461132458872606754,
 452406680821547008,
 937950908773744640,
 1586187811960238082,
 1099236096233168896,
 1102050800015937536,
 98311167513120777,
 8951824985835937792]



In [44]:

    
#df.to_pickle('view2buy_url_CF_user_buy.pkl')



In [145]:

    
df = pd.read_pickle('view2buy_url_CF_user_buy.pkl')



In [45]:

    
df.head()









    Out[45]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu
      url
      user_buy
      CF_item
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-453532580309307392
      [82267097285177879, 12742773141631009, 8883989...
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      529805243-103096245561765919
      [82267097285177879, 12742773141631009, 8883989...
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      3748045464-446777176556679168
      [82267097285177879, 12742773141631009, 8883989...
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-438895881520357521
      [82267097285177879, 12742773141631009, 8883989...
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-74104320184119307
      [82267097285177879, 12742773141631009, 8883989...



In [146]:

    
df_spu = pd.DataFrame(df.groupby('spu').count().reset_index()['spu'])



In [147]:

    
# assign CF_item and features to each spu
df_spu['CF_item'] = df_spu.apply(lambda x: df[df['spu'] == x['spu']]['CF_item'].iloc[0], axis = 1)
df_spu['spu_features'] = df_spu.apply(lambda x: df[df['spu'] == x['spu']]['view_features'].iloc[0], axis = 1)



In [148]:

    
df_spu.head()









    Out[148]:






  
    
      
      spu
      CF_item
      spu_features
    
  
  
    
      0
      357872333107204
      [8952950888272863232, 2846351224980500480, 881...
      [0.035, 0.385, 0.112, 0.014, 0.0, 0.123, 0.438...
    
    
      1
      357875526680651
      [2046769978417582, 461413925257830545, 3255052...
      [0.132, 1.678, 0.061, 0.918, 0.462, 0.342, 0.4...
    
    
      2
      357882254983171
      [459725075493814272, 8582811288237465674, 1976...
      [0.026, 0.936, 0.056, 0.614, 0.139, 0.0, 0.302...
    
    
      3
      357901107539985
      [2466922956389351424, 7804532970923106304, 130...
      [0.229, 0.543, 0.132, 0.144, 0.295, 0.018, 0.0...
    
    
      4
      639360131194904
      [81141212316332372, 320394952166453251, 639360...
      [1.113, 0.5, 0.758, 0.218, 0.0, 0.0, 0.335, 1....



In [49]:

    
# Assign item_features for all CF_item
df_spu['CF_features'] = df_spu.apply(lambda x: [df_spu[df_spu['spu'] == i]['spu_features'] for i in x['CF_item']], axis = 1)



In [50]:

    
# Calculate the average features from 10 CF_recommended items for each spu
def CF_ave(CF_list):
    return [np.mean(i) for i in zip(*[list(x)[0] for x in CF_list])]



In [51]:

    
df_spu['ave_CF_fea'] = df_spu.apply(lambda x: CF_ave(x['CF_features']), axis = 1)



In [52]:

    
#df_spu.to_pickle('spu_CF_features_user_buy.pkl')



In [150]:

    
df_spu = pd.read_pickle('spu_CF_features_user_buy.pkl')



In [152]:

    
df.head()









    Out[152]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu
      url
      user_buy
      CF_item
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-453532580309307392
      [82267097285177879, 12742773141631009, 8883989...
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      529805243-103096245561765919
      [82267097285177879, 12742773141631009, 8883989...
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      3748045464-446777176556679168
      [82267097285177879, 12742773141631009, 8883989...
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-438895881520357521
      [82267097285177879, 12742773141631009, 8883989...
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-74104320184119307
      [82267097285177879, 12742773141631009, 8883989...



In [151]:

    
df_spu.head()









    Out[151]:






  
    
      
      spu
      CF_item
      spu_features
      CF_features
      ave_CF_fea
    
  
  
    
      0
      357872333107204
      [8952950888272863232, 2846351224980500480, 881...
      [0.035, 0.385, 0.112, 0.014, 0.0, 0.123, 0.438...
      [[[0.462, 0.551, 0.068, 0.833, 0.0, 0.0, 0.0, ...
      [0.3597, 0.7012, 0.0831, 1.0618, 0.2302, 0.123...
    
    
      1
      357875526680651
      [2046769978417582, 461413925257830545, 3255052...
      [0.132, 1.678, 0.061, 0.918, 0.462, 0.342, 0.4...
      [[[0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104...
      [0.4727, 0.8078, 0.0697, 0.5796, 0.3075, 0.009...
    
    
      2
      357882254983171
      [459725075493814272, 8582811288237465674, 1976...
      [0.026, 0.936, 0.056, 0.614, 0.139, 0.0, 0.302...
      [[[1.884, 0.52, 0.0, 3.98, 0.175, 0.008, 0.663...
      [0.6206, 0.8754, 0.1066, 0.7549, 0.2387, 0.186...
    
    
      3
      357901107539985
      [2466922956389351424, 7804532970923106304, 130...
      [0.229, 0.543, 0.132, 0.144, 0.295, 0.018, 0.0...
      [[[0.124, 0.819, 0.0, 0.596, 0.306, 0.043, 0.2...
      [0.449, 0.7069, 0.1971, 0.7197, 0.2461, 0.0106...
    
    
      4
      639360131194904
      [81141212316332372, 320394952166453251, 639360...
      [1.113, 0.5, 0.758, 0.218, 0.0, 0.0, 0.335, 1....
      [[[0.06, 0.15, 0.011, 0.946, 0.501, 0.0, 1.309...
      [0.2552, 0.5227, 0.0964, 0.3326, 0.1703, 0.011...



In [153]:

    
df_final = pd.merge(df, df_spu, left_on='view_spu', right_on='spu')



In [160]:

    
df_final.columns









    Out[160]:





Index([u'0', u'user_id', u'buy_spu', u'buy_sn', u'buy_ct3', u'view_spu',
       u'view_sn', u'view_ct3', u'time_interval', u'view_cnt',
       u'view_secondes', u'view_features', u'buy_features', u'spu_x', u'url',
       u'user_buy', u'CF_item_x', u'spu_y', u'CF_item_y', u'spu_features',
       u'CF_features', u'ave_CF_fea'],
      dtype='object')



In [162]:

    
df_final.drop(['spu_y', 'CF_item_y'], axis = 1, inplace = True)



In [164]:

    
df_final.head()









    Out[164]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu_x
      url
      user_buy
      CF_item_x
      spu_features
      CF_features
      ave_CF_fea
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-453532580309307392
      [82267097285177879, 12742773141631009, 8883989...
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [[[0.495, 1.32, 0.022, 0.126, 0.007, 0.181, 0....
      [0.447, 1.2384, 0.0129, 0.1834, 0.0854, 0.0701...
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      529805243-103096245561765919
      [82267097285177879, 12742773141631009, 8883989...
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [[[0.495, 1.32, 0.022, 0.126, 0.007, 0.181, 0....
      [0.447, 1.2384, 0.0129, 0.1834, 0.0854, 0.0701...
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      3748045464-446777176556679168
      [82267097285177879, 12742773141631009, 8883989...
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [[[0.495, 1.32, 0.022, 0.126, 0.007, 0.181, 0....
      [0.447, 1.2384, 0.0129, 0.1834, 0.0854, 0.0701...
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-438895881520357521
      [82267097285177879, 12742773141631009, 8883989...
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [[[0.495, 1.32, 0.022, 0.126, 0.007, 0.181, 0....
      [0.447, 1.2384, 0.0129, 0.1834, 0.0854, 0.0701...
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      4209887493-74104320184119307
      [82267097285177879, 12742773141631009, 8883989...
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [[[0.495, 1.32, 0.022, 0.126, 0.007, 0.181, 0....
      [0.447, 1.2384, 0.0129, 0.1834, 0.0854, 0.0701...



In [163]:

    
#df_final.to_pickle('view2buy_CF_user_buy.pkl')



In [65]:

    
CF_user_fea = df_final.groupby('user_buy')['ave_CF_fea'].apply(lambda x: average(x))
CF_user_fea = pd.DataFrame(CF_user_fea)
CF_user_fea = CF_user_fea.reset_index()
Ori_user_fea = df_final.groupby('user_buy')['spu_features'].apply(lambda x: average(x))
Ori_user_fea = pd.DataFrame(Ori_user_fea)
Ori_user_fea = Ori_user_fea.reset_index()



In [66]:

    
CF_user_fea.head()









    Out[66]:






  
    
      
      user_buy
      ave_CF_fea
    
  
  
    
      0
      1018047589-2885476247461195776
      [0.3402875, 0.632470833333, 0.1431, 0.91783333...
    
    
      1
      1074350764-20905574407417865
      [0.345218478261, 0.517051086957, 0.12234130434...
    
    
      2
      1074350764-2836218125824516096
      [0.353695, 0.54904, 0.10707, 0.827515, 0.21728...
    
    
      3
      1076790314-2893639021813923840
      [0.221729032258, 0.651, 0.106264516129, 0.5287...
    
    
      4
      1076790314-4209253154853183622
      [0.199768181818, 0.686179545455, 0.10204318181...



In [67]:

    
Ori_user_fea.head()









    Out[67]:






  
    
      
      user_buy
      spu_features
    
  
  
    
      0
      1018047589-2885476247461195776
      [0.386333333333, 0.548166666667, 0.08983333333...
    
    
      1
      1074350764-20905574407417865
      [0.36272826087, 0.396108695652, 0.108434782609...
    
    
      2
      1074350764-2836218125824516096
      [0.37505, 0.50925, 0.11335, 0.96235, 0.12985, ...
    
    
      3
      1076790314-2893639021813923840
      [0.257322580645, 0.676548387097, 0.17258064516...
    
    
      4
      1076790314-4209253154853183622
      [0.210295454545, 0.680727272727, 0.15218181818...



In [68]:

    
user_fea = pd.merge(CF_user_fea, Ori_user_fea, on='user_buy')



In [69]:

    
user_fea.head()









    Out[69]:






  
    
      
      user_buy
      ave_CF_fea
      spu_features
    
  
  
    
      0
      1018047589-2885476247461195776
      [0.3402875, 0.632470833333, 0.1431, 0.91783333...
      [0.386333333333, 0.548166666667, 0.08983333333...
    
    
      1
      1074350764-20905574407417865
      [0.345218478261, 0.517051086957, 0.12234130434...
      [0.36272826087, 0.396108695652, 0.108434782609...
    
    
      2
      1074350764-2836218125824516096
      [0.353695, 0.54904, 0.10707, 0.827515, 0.21728...
      [0.37505, 0.50925, 0.11335, 0.96235, 0.12985, ...
    
    
      3
      1076790314-2893639021813923840
      [0.221729032258, 0.651, 0.106264516129, 0.5287...
      [0.257322580645, 0.676548387097, 0.17258064516...
    
    
      4
      1076790314-4209253154853183622
      [0.199768181818, 0.686179545455, 0.10204318181...
      [0.210295454545, 0.680727272727, 0.15218181818...



In [82]:

    
#user_fea.to_pickle('user_buy_CF_Ori_fea2.pkl')



In [78]:

    
user_fea['user_id'] = user_fea.apply(lambda x: x['user_buy'].split('-')[0], axis = 1)



In [80]:

    
user_fea['buy_spu'] = user_fea.apply(lambda x: x['user_buy'].split('-')[1], axis = 1)



In [81]:

    
user_fea.head()









    Out[81]:






  
    
      
      user_buy
      ave_CF_fea
      spu_features
      user_id
      buy_spu
    
  
  
    
      0
      1018047589-2885476247461195776
      [0.3402875, 0.632470833333, 0.1431, 0.91783333...
      [0.386333333333, 0.548166666667, 0.08983333333...
      1018047589
      2885476247461195776
    
    
      1
      1074350764-20905574407417865
      [0.345218478261, 0.517051086957, 0.12234130434...
      [0.36272826087, 0.396108695652, 0.108434782609...
      1074350764
      20905574407417865
    
    
      2
      1074350764-2836218125824516096
      [0.353695, 0.54904, 0.10707, 0.827515, 0.21728...
      [0.37505, 0.50925, 0.11335, 0.96235, 0.12985, ...
      1074350764
      2836218125824516096
    
    
      3
      1076790314-2893639021813923840
      [0.221729032258, 0.651, 0.106264516129, 0.5287...
      [0.257322580645, 0.676548387097, 0.17258064516...
      1076790314
      2893639021813923840
    
    
      4
      1076790314-4209253154853183622
      [0.199768181818, 0.686179545455, 0.10204318181...
      [0.210295454545, 0.680727272727, 0.15218181818...
      1076790314
      4209253154853183622



In [83]:

    
# Calculate similarity and ranking, return the final result for each buy item.
def sim_cal(buy_item, item):
    df_spu['sim'] = df_spu.apply(lambda x: similarity(x['spu_features'], item), axis = 1)
    df_spu['rank'] = df_spu['sim'].rank(ascending=False)
    print user
    return (df_spu[df_spu['spu'] == buy_item]['sim'], df_spu[df_spu['spu'] == buy_item]['rank'])



In [372]:









    Out[372]:





(2155, 5)



In [ ]:

    
user_fea['ave_Ori_sim_rank']= user_fea.apply(lambda x: sim_cal(x['buy_spu'],x['spu_view_fea']), axis = 1)



In [199]:

    
user_fea









    Out[199]:






  
    
      
      user_buy
      ave_CF_fea
      spu_features
      user_id
      buy_spu
    
  
  
    
      0
      1018047589-2885476247461195776
      [0.3402875, 0.632470833333, 0.1431, 0.91783333...
      [0.386333333333, 0.548166666667, 0.08983333333...
      1018047589
      2885476247461195776
    
    
      1
      1074350764-20905574407417865
      [0.345218478261, 0.517051086957, 0.12234130434...
      [0.36272826087, 0.396108695652, 0.108434782609...
      1074350764
      20905574407417865
    
    
      2
      1074350764-2836218125824516096
      [0.353695, 0.54904, 0.10707, 0.827515, 0.21728...
      [0.37505, 0.50925, 0.11335, 0.96235, 0.12985, ...
      1074350764
      2836218125824516096
    
    
      3
      1076790314-2893639021813923840
      [0.221729032258, 0.651, 0.106264516129, 0.5287...
      [0.257322580645, 0.676548387097, 0.17258064516...
      1076790314
      2893639021813923840
    
    
      4
      1076790314-4209253154853183622
      [0.199768181818, 0.686179545455, 0.10204318181...
      [0.210295454545, 0.680727272727, 0.15218181818...
      1076790314
      4209253154853183622
    
    
      5
      1107309816-2474241306483101696
      [0.429824, 0.529608, 0.124608, 0.862208, 0.223...
      [0.35292, 0.52828, 0.1044, 1.07144, 0.21252, 0...
      1107309816
      2474241306483101696
    
    
      6
      1107309816-2917845869811523584
      [0.403947368421, 0.561121052632, 0.11027368421...
      [0.568526315789, 0.388315789474, 0.05884210526...
      1107309816
      2917845869811523584
    
    
      7
      1107420964-6370980984573702144
      [0.3403, 0.554653333333, 0.128223333333, 0.828...
      [0.2917, 0.592, 0.0722333333333, 1.08156666667...
      1107420964
      6370980984573702144
    
    
      8
      1145923275-2462700832436764672
      [0.352986956522, 0.620339130435, 0.14589565217...
      [0.465869565217, 0.683086956522, 0.17413043478...
      1145923275
      2462700832436764672
    
    
      9
      1158035643-2832840426724958208
      [0.361617741935, 0.558864516129, 0.12528387096...
      [0.373564516129, 0.543096774194, 0.10837096774...
      1158035643
      2832840426724958208
    
    
      10
      1170419598-2823270277605580800
      [0.3525, 0.582928571429, 0.135685714286, 0.821...
      [0.422107142857, 0.586392857143, 0.13192857142...
      1170419598
      2823270277605580800
    
    
      11
      1171987394-2835655176583352320
      [0.334142857143, 0.648964285714, 0.11824285714...
      [0.270392857143, 0.559928571429, 0.10410714285...
      1171987394
      2835655176583352320
    
    
      12
      1176141954-324335591819321344
      [0.350716, 0.564152, 0.1234, 0.803876, 0.25326...
      [0.48424, 0.408, 0.11292, 0.70516, 0.20512, 0....
      1176141954
      324335591819321344
    
    
      13
      1178987917-467606353885155328
      [0.32172173913, 1.12372173913, 0.0753782608696...
      [0.426347826087, 1.05065217391, 0.115304347826...
      1178987917
      467606353885155328
    
    
      14
      1200352288-2480715230945681408
      [0.368341025641, 0.591753846154, 0.1427, 0.901...
      [0.379615384615, 0.423564102564, 0.14179487179...
      1200352288
      2480715230945681408
    
    
      15
      1207880243-2914749645016145920
      [0.341397727273, 0.556490909091, 0.12633636363...
      [0.353363636364, 0.457181818182, 0.11293181818...
      1207880243
      2914749645016145920
    
    
      16
      121339277-24001769421647872
      [0.242223809524, 0.694738095238, 0.04935238095...
      [0.235142857143, 0.622380952381, 0.03961904761...
      121339277
      24001769421647872
    
    
      17
      1214726068-304913827234218339
      [0.410868, 0.576348, 0.109336, 0.865796, 0.228...
      [0.36972, 0.4856, 0.11368, 0.75544, 0.1798, 0....
      1214726068
      304913827234218339
    
    
      18
      1220000546-2909964570434449408
      [0.39106969697, 0.549615151515, 0.131524242424...
      [0.46003030303, 0.683909090909, 0.077181818181...
      1220000546
      2909964570434449408
    
    
      19
      1238534392-2882661497718759424
      [0.298785365854, 0.604512195122, 0.15552682926...
      [0.226195121951, 0.54787804878, 0.172926829268...
      1238534392
      2882661497718759424
    
    
      20
      1246054243-4483128308343681024
      [0.4084, 0.572531707317, 0.0971243902439, 0.81...
      [0.473585365854, 0.487609756098, 0.11287804878...
      1246054243
      4483128308343681024
    
    
      21
      1249799965-2834810751655301120
      [0.397360377358, 0.528694339623, 0.11369811320...
      [0.465056603774, 0.471433962264, 0.19145283018...
      1249799965
      2834810751655301120
    
    
      22
      1268074130-2455663958026235904
      [0.318028571429, 0.708671428571, 0.0894, 0.944...
      [0.453857142857, 0.917428571429, 0.05471428571...
      1268074130
      2455663958026235904
    
    
      23
      1268074130-2482122605837119488
      [0.335228571429, 0.712457142857, 0.08668571428...
      [0.473714285714, 0.878571428571, 0.04071428571...
      1268074130
      2482122605837119488
    
    
      24
      1268074130-2819048152931336192
      [0.3264, 0.721642857143, 0.0877714285714, 0.98...
      [0.449571428571, 0.864, 0.0467142857143, 1.107...
      1268074130
      2819048152931336192
    
    
      25
      1268074130-8939440090467495945
      [0.3309, 0.6432, 0.1045, 1.3653, 0.1829, 0.054...
      [1.995, 2.028, 0.14, 1.745, 0.09, 0.021, 0.198...
      1268074130
      8939440090467495945
    
    
      26
      1275960841-305476758874669060
      [0.298533333333, 0.561316666667, 0.09656666666...
      [0.378666666667, 0.450666666667, 0.04425, 0.34...
      1275960841
      305476758874669060
    
    
      27
      1275960841-448184566666743834
      [0.303254545455, 0.579772727273, 0.09851818181...
      [0.327, 0.464454545455, 0.0482727272727, 0.366...
      1275960841
      448184566666743834
    
    
      28
      1288091887-4641880197364293632
      [0.448871428571, 0.523752380952, 0.15198571428...
      [0.424, 0.34619047619, 0.0848095238095, 1.2161...
      1288091887
      4641880197364293632
    
    
      29
      1288109591-9023882578131013643
      [0.381041025641, 0.64971025641, 0.118297435897...
      [0.381974358974, 0.783384615385, 0.09889743589...
      1288109591
      9023882578131013643
    
    
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      472
      798308058-4057256663630299136
      [0.3336325, 0.56245, 0.122735, 0.9166075, 0.23...
      [0.2611, 0.454425, 0.119825, 1.015675, 0.26917...
      798308058
      4057256663630299136
    
    
      473
      801989759-4210379050958020608
      [0.33159047619, 0.572923809524, 0.12615, 0.846...
      [0.426404761905, 0.581928571429, 0.16192857142...
      801989759
      4210379050958020608
    
    
      474
      802164527-2450315932750196736
      [0.322765789474, 0.624960526316, 0.13622631578...
      [0.263921052632, 0.627342105263, 0.13189473684...
      802164527
      2450315932750196736
    
    
      475
      807686967-2889416897109704704
      [0.328872413793, 0.596793103448, 0.13441724137...
      [0.308310344828, 0.492103448276, 0.12075862069...
      807686967
      2889416897109704704
    
    
      476
      807743886-4209253154853183512
      [0.345247457627, 0.574888983051, 0.11897457627...
      [0.341618644068, 0.632025423729, 0.10235593220...
      807743886
      4209253154853183512
    
    
      477
      82073468-2913060795180240896
      [0.452841176471, 0.661785294118, 0.13451764705...
      [0.573147058824, 0.7745, 0.0831176470588, 0.91...
      82073468
      2913060795180240896
    
    
      478
      826980444-2891105746980835328
      [0.33855, 0.566007692308, 0.147638461538, 0.76...
      [0.269730769231, 0.644576923077, 0.15896153846...
      826980444
      2891105746980835328
    
    
      479
      831888402-2463545257346113536
      [0.331425531915, 0.511642553191, 0.14469787234...
      [0.292553191489, 0.392063829787, 0.13655319148...
      831888402
      2463545257346113536
    
    
      480
      831888402-2898705571343994880
      [0.327314893617, 0.514457446809, 0.14286382978...
      [0.300127659574, 0.394425531915, 0.13655319148...
      831888402
      2898705571343994880
    
    
      481
      85939638-2823270277605580800
      [0.4015, 0.50786, 0.10467, 0.85096, 0.23821, 0...
      [0.2711, 0.2286, 0.0741, 0.4116, 0.1769, 0.125...
      85939638
      2823270277605580800
    
    
      482
      85939638-2832277476150169600
      [0.3644, 0.5161, 0.115166666667, 0.85116666666...
      [0.256916666667, 0.241666666667, 0.12716666666...
      85939638
      2832277476150169600
    
    
      483
      860735147-3735622055772162
      [0.306009090909, 0.621713636364, 0.18600454545...
      [0.132409090909, 0.668909090909, 0.19313636363...
      860735147
      3735622055772162
    
    
      484
      871875091-2898705571343994880
      [0.358716666667, 0.629858333333, 0.11103333333...
      [0.260083333333, 0.2385, 0.154416666667, 0.585...
      871875091
      2898705571343994880
    
    
      485
      871875091-4210379050958020608
      [0.381516666667, 0.623866666667, 0.10963333333...
      [0.250916666667, 0.232666666667, 0.15441666666...
      871875091
      4210379050958020608
    
    
      486
      903283685-1608142860794818562
      [0.358162162162, 0.576337837838, 0.12680270270...
      [0.313162162162, 0.653567567568, 0.17264864864...
      903283685
      1608142860794818562
    
    
      487
      903283685-2471426556005482496
      [0.352558333333, 0.577863888889, 0.12111111111...
      [0.303583333333, 0.664638888889, 0.17741666666...
      903283685
      2471426556005482496
    
    
      488
      905305268-33290487503762307
      [0.326576, 0.670512, 0.073036, 0.45438, 0.1488...
      [0.30508, 0.47008, 0.06384, 0.2756, 0.12596, 0...
      905305268
      33290487503762307
    
    
      489
      905305268-448184566666743834
      [0.35372, 0.611026666667, 0.0763333333333, 0.4...
      [0.3444, 0.225, 0.0674, 0.179933333333, 0.1460...
      905305268
      448184566666743834
    
    
      490
      910973934-2453130682530897920
      [0.329588990826, 0.644018348624, 0.12413119266...
      [0.330926605505, 0.752889908257, 0.12066055045...
      910973934
      2453130682530897920
    
    
      491
      912273659-4641880197364293632
      [0.378358695652, 0.544334782609, 0.12040869565...
      [0.4375, 0.35697826087, 0.124739130435, 1.0582...
      912273659
      4641880197364293632
    
    
      492
      916895118-2465797056472944640
      [0.383656756757, 0.554891891892, 0.11150540540...
      [0.318135135135, 0.409432432432, 0.14237837837...
      916895118
      2465797056472944640
    
    
      493
      9254280-3925244893201649664
      [0.360215151515, 0.618839393939, 0.13717272727...
      [0.356484848485, 0.575484848485, 0.11351515151...
      9254280
      3925244893201649664
    
    
      494
      931853555-941328597468446721
      [0.291308695652, 0.587917391304, 0.12773043478...
      [0.216391304348, 0.416173913043, 0.09791304347...
      931853555
      941328597468446721
    
    
      495
      952914660-2457634282835726336
      [0.227226086957, 0.682447826087, 0.08343478260...
      [0.35547826087, 0.682391304348, 0.143, 0.51091...
      952914660
      2457634282835726336
    
    
      496
      958739744-2893639021767663616
      [0.364666666667, 0.592477777778, 0.10754444444...
      [0.32637037037, 0.717148148148, 0.171851851852...
      958739744
      2893639021767663616
    
    
      497
      960980006-2463545257346113536
      [0.347568421053, 0.509164912281, 0.14401228070...
      [0.356824561404, 0.367473684211, 0.15691228070...
      960980006
      2463545257346113536
    
    
      498
      980478665-3925244893201649664
      [0.31312745098, 0.562525490196, 0.131131372549...
      [0.246921568627, 0.650843137255, 0.13094117647...
      980478665
      3925244893201649664
    
    
      499
      981771354-33571915871158274
      [0.369025, 1.24155, 0.116075, 0.802475, 0.2408...
      [0.291875, 1.379625, 0.102, 0.980375, 0.328375...
      981771354
      33571915871158274
    
    
      500
      981771354-80015338899632133
      [0.37269375, 1.1361125, 0.1156875, 0.789725, 0...
      [0.384875, 1.037375, 0.1055625, 0.8285625, 0.2...
      981771354
      80015338899632133
    
    
      501
      996068355-1102050800015937536
      [0.249123684211, 0.465634210526, 0.04947368421...
      [0.287684210526, 0.558631578947, 0.05186842105...
      996068355
      1102050800015937536
    
  

502 rows × 5 columns

Compare the CF with/without features



In [200]:

    
user_fea = pd.read_pickle('user_fea.pkl')



In [205]:

    
df.head()









    Out[205]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu
      url
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...



In [221]:

    
item_sim_df.head()









    Out[221]:






  
    
      view_spu
      357872333107204
      357875526680651
      357882254983171
      357901107539985
      639360131194904
      639369692328147
      639371126526005
      639389503180805
      639392717246493
      920816362999808
      ...
      9037674851989819400
      9038237806216196097
      9039645182176481286
      9039926651803541506
      9041615583843246080
      9088621908743286785
      9089747807251402752
      9090029283626840066
      9090592232181542912
      9094251405871296512
    
    
      view_spu
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
      
    
  
  
    
      357872333107204
      1.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.00000
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.000000
      0.0
    
    
      357875526680651
      0.0
      1.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.00000
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.000000
      0.0
    
    
      357882254983171
      0.0
      0.0
      1.0
      0.0
      0.0
      0.0
      0.0
      0.63211
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.000000
      0.0
    
    
      357901107539985
      0.0
      0.0
      0.0
      1.0
      0.0
      0.0
      0.0
      0.00000
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.020383
      0.0
    
    
      639360131194904
      0.0
      0.0
      0.0
      0.0
      1.0
      0.0
      0.0
      0.00000
      0.0
      0.0
      ...
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.0
      0.000000
      0.0
    
  

5 rows × 2155 columns



In [235]:

    
def CF_rank(view, buy):
    try:
        return (list(item_sim_df.sort_values(by = view, ascending = False).index[1:]).index(buy) + 1)
    except:
        pass



In [273]:

    
item_sim_df.index[0]









    Out[273]:





357872333107204



In [266]:

    
random.seed(0)









    Out[266]:





2155



In [291]:

    
def ran_CF_rank():
    view = random.randint(1,len(item_sim_df)-1)
    buy = random.randint(1,len(item_sim_df)-1)
    view = item_sim_df.index[view]
    buy = item_sim_df.index[buy]
    try:
        return (list(item_sim_df.sort_values(by = view, ascending = False).index[1:]).index(buy)+1)
    except:
        pass



In [203]:

    
user_fea.head()









    Out[203]:






  
    
      
      user_id
      buy_spu
      ave_CF_fea
      ave_view_fea
      ave_CF_sim_rank
      ave_Ori_sim_rank
      ave_CF_sim
      ave_CF_rank
      ave_Ori_sim
      ave_Ori_rank
    
  
  
    
      0
      3440325
      2898705571343994880
      [0.327609375, 0.573775, 0.11804375, 0.87390625...
      [0.30521875, 0.5995625, 0.167625, 0.99259375, ...
      ([0.799214495018], [215.0])
      ([0.811977551064], [115.0])
      0.799214
      215.0
      0.811978
      115.0
    
    
      1
      7052311
      7957699990364366
      [0.307052173913, 0.738013043478, 0.06435217391...
      [0.320739130435, 0.577217391304, 0.088, 0.6661...
      ([0.745014365081], [1155.0])
      ([0.73996321102], [1112.0])
      0.745014
      1155.0
      0.739963
      1112.0
    
    
      2
      7052311
      299847271351230626
      [0.306652173913, 0.7439, 0.0624434782609, 0.60...
      [0.314217391304, 0.620695652174, 0.08865217391...
      ([0.833736325406], [173.0])
      ([0.855587371153], [66.0])
      0.833736
      173.0
      0.855587
      66.0
    
    
      3
      7052311
      448747521265074449
      [0.306817391304, 0.735182608696, 0.06435217391...
      [0.323086956522, 0.60552173913, 0.088, 0.653, ...
      ([0.854382169198], [49.0])
      ([0.853929200306], [84.0])
      0.854382
      49.0
      0.853929
      84.0
    
    
      4
      9254280
      3925244893201649664
      [0.385093939394, 0.623651515152, 0.12763030303...
      [0.356484848485, 0.575484848485, 0.11351515151...
      ([0.730978541607], [1427.0])
      ([0.752675987128], [535.0])
      0.730979
      1427.0
      0.752676
      535.0



In [225]:

    
list(item_sim_df.sort_values(by = 74104320184119307, ascending = False).index[1:]).index(448747521265074449)









    Out[225]:





1867



In [364]:

    
item_sim_df.shape









    Out[364]:





(2155, 2155)



In [236]:

    
df['CF_rank'] = df.apply(lambda x: CF_rank(x['view_spu'], x['buy_spu']), axis=1)



In [292]:

    
df['Ran_CF_rank'] = df.apply(lambda x: ran_CF_rank(), axis=1)



In [336]:

    
#df.to_pickle('view2buy_url_CF_rank.pkl')



In [299]:

    
df_CF_rank = df.groupby(['user_id', 'buy_spu']).mean().reset_index()[['user_id', 'buy_spu', 'Ran_CF_rank', 'CF_rank']]



In [362]:

    
df.head()









    Out[362]:






  
    
      
      0
      user_id
      buy_spu
      buy_sn
      buy_ct3
      view_spu
      view_sn
      view_ct3
      time_interval
      view_cnt
      view_secondes
      view_features
      buy_features
      spu
      url
      CF_rank
      Ran_CF_rank
    
  
  
    
      0
      4209887493\t453532580309307392\t10004616\t334\...
      4209887493
      453532580309307392
      10004616
      334
      14150170026959126
      10010102
      334
      21114
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      74.0
      600.0
    
    
      1
      529805243\t103096245561765919\t10010102\t334\t...
      529805243
      103096245561765919
      10010102
      334
      14150170026959126
      10010102
      334
      37794
      4
      66
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      18.0
      1196.0
    
    
      2
      3748045464\t446777176556679168\t10005711\t334\...
      3748045464
      446777176556679168
      10005711
      334
      14150170026959126
      10010102
      334
      18820
      1
      34
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      60.0
      2106.0
    
    
      3
      4209887493\t438895881520357521\t10004616\t334\...
      4209887493
      438895881520357521
      10004616
      334
      14150170026959126
      10010102
      334
      13978
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      36.0
      1761.0
    
    
      4
      4209887493\t74104320184119307\t10004616\t334\t...
      4209887493
      74104320184119307
      10004616
      334
      14150170026959126
      10010102
      334
      14313
      1
      11
      [0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...
      [0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...
      14150170026959126
      http://a.vpimg2.com/upload/merchandise/pdcvis/...
      35.0
      422.0



In [254]:

    
user_fea_CF.head()









    Out[254]:






  
    
      
      user_id
      buy_spu
      ave_CF_fea
      ave_view_fea
      ave_CF_sim_rank
      ave_Ori_sim_rank
      ave_CF_sim
      ave_CF_rank
      ave_Ori_sim
      ave_Ori_rank
      CF_rank
    
  
  
    
      0
      3440325
      2898705571343994880
      [0.327609375, 0.573775, 0.11804375, 0.87390625...
      [0.30521875, 0.5995625, 0.167625, 0.99259375, ...
      ([0.799214495018], [215.0])
      ([0.811977551064], [115.0])
      0.799214
      215.0
      0.811978
      115.0
      111.264706
    
    
      1
      7052311
      7957699990364366
      [0.307052173913, 0.738013043478, 0.06435217391...
      [0.320739130435, 0.577217391304, 0.088, 0.6661...
      ([0.745014365081], [1155.0])
      ([0.73996321102], [1112.0])
      0.745014
      1155.0
      0.739963
      1112.0
      27.870968
    
    
      2
      7052311
      299847271351230626
      [0.306652173913, 0.7439, 0.0624434782609, 0.60...
      [0.314217391304, 0.620695652174, 0.08865217391...
      ([0.833736325406], [173.0])
      ([0.855587371153], [66.0])
      0.833736
      173.0
      0.855587
      66.0
      31.548387
    
    
      3
      7052311
      448747521265074449
      [0.306817391304, 0.735182608696, 0.06435217391...
      [0.323086956522, 0.60552173913, 0.088, 0.653, ...
      ([0.854382169198], [49.0])
      ([0.853929200306], [84.0])
      0.854382
      49.0
      0.853929
      84.0
      29.612903
    
    
      4
      9254280
      3925244893201649664
      [0.385093939394, 0.623651515152, 0.12763030303...
      [0.356484848485, 0.575484848485, 0.11351515151...
      ([0.730978541607], [1427.0])
      ([0.752675987128], [535.0])
      0.730979
      1427.0
      0.752676
      535.0
      146.333333



In [300]:

    
user_fea_CF = pd.merge(user_fea, df_CF_rank, on=['user_id', 'buy_spu'])



In [326]:

    
user_fea_CF['CF_ave_fea_rank'] = (user_fea_CF['CF_rank'] + user_fea_CF['ave_Ori_rank'])/2



In [360]:

    
user_fea_CF.head()









    Out[360]:






  
    
      
      user_id
      buy_spu
      ave_CF_fea
      ave_view_fea
      ave_CF_sim_rank
      ave_Ori_sim_rank
      ave_CF_sim
      ave_CF_rank
      ave_Ori_sim
      ave_Ori_rank
      Ran_CF_rank
      CF_rank
      CF_ave_fea_rank
    
  
  
    
      0
      3440325
      2898705571343994880
      [0.327609375, 0.573775, 0.11804375, 0.87390625...
      [0.30521875, 0.5995625, 0.167625, 0.99259375, ...
      ([0.799214495018], [215.0])
      ([0.811977551064], [115.0])
      0.799214
      215.0
      0.811978
      115.0
      1225.857143
      111.264706
      113.132353
    
    
      1
      7052311
      7957699990364366
      [0.307052173913, 0.738013043478, 0.06435217391...
      [0.320739130435, 0.577217391304, 0.088, 0.6661...
      ([0.745014365081], [1155.0])
      ([0.73996321102], [1112.0])
      0.745014
      1155.0
      0.739963
      1112.0
      925.906250
      27.870968
      569.935484
    
    
      2
      7052311
      299847271351230626
      [0.306652173913, 0.7439, 0.0624434782609, 0.60...
      [0.314217391304, 0.620695652174, 0.08865217391...
      ([0.833736325406], [173.0])
      ([0.855587371153], [66.0])
      0.833736
      173.0
      0.855587
      66.0
      1138.666667
      31.548387
      48.774194
    
    
      3
      7052311
      448747521265074449
      [0.306817391304, 0.735182608696, 0.06435217391...
      [0.323086956522, 0.60552173913, 0.088, 0.653, ...
      ([0.854382169198], [49.0])
      ([0.853929200306], [84.0])
      0.854382
      49.0
      0.853929
      84.0
      1181.193548
      29.612903
      56.806452
    
    
      4
      9254280
      3925244893201649664
      [0.385093939394, 0.623651515152, 0.12763030303...
      [0.356484848485, 0.575484848485, 0.11351515151...
      ([0.730978541607], [1427.0])
      ([0.752675987128], [535.0])
      0.730979
      1427.0
      0.752676
      535.0
      971.657143
      146.333333
      340.666667



In [337]:

    
#user_fea_CF.to_pickle('user_fea_CF.pkl')



In [366]:

    
sns.set_style('whitegrid')
g = sns.distplot(user_fea_CF[['ave_CF_rank']]/2155, bins = 100,color = 'red', hist =False, label = 'CF_fea')
g = sns.distplot(user_fea_CF[['ave_Ori_rank']]/2155, bins = 100,color = 'blue', hist =False, label = 'Ori_fea')
g = sns.distplot(user_fea_CF[['CF_rank']]/2155, bins = 100,color = 'green', hist =False, label = 'CF_rank')
g = sns.distplot(user_fea_CF[['Ran_CF_rank']]/2155, bins = 100,color = 'black', hist =False, label = 'Ran_CF_rank')
g = sns.distplot(user_fea_CF[['CF_ave_fea_rank']]/2155, bins = 100,color = 'orange', hist =False, label = 'CF_fea_rank')
g.set(xlabel='Rank of prediting item / Total items', ylabel='# of items')









    Out[366]:





[<matplotlib.text.Text at 0x1430e5450>, <matplotlib.text.Text at 0x148b50e50>]

Basically, CF only gives the best recommendation compared to features_based.



In [ ]:

	0	user_id	buy_spu	buy_sn	buy_ct3	view_spu	view_sn	view_ct3	time_interval	view_cnt	view_secondes	view_features	buy_features	spu	url
0	4209887493\t453532580309307392\t10004616\t334\...	4209887493	453532580309307392	10004616	334	14150170026959126	10010102	334	21114	1	11	[0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...	[0.1, 1.804, 0.049, 0.883, 0.092, 0.053, 0.042...	14150170026959126	http://a.vpimg2.com/upload/merchandise/pdcvis/...
1	529805243\t103096245561765919\t10010102\t334\t...	529805243	103096245561765919	10010102	334	14150170026959126	10010102	334	37794	4	66	[0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...	[0.467, 0.385, 0.0, 0.043, 0.292, 0.0, 0.448, ...	14150170026959126	http://a.vpimg2.com/upload/merchandise/pdcvis/...
2	3748045464\t446777176556679168\t10005711\t334\...	3748045464	446777176556679168	10005711	334	14150170026959126	10010102	334	18820	1	34	[0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...	[0.018, 0.161, 0.088, 0.141, 0.231, 0.0, 0.036...	14150170026959126	http://a.vpimg2.com/upload/merchandise/pdcvis/...
3	4209887493\t438895881520357521\t10004616\t334\...	4209887493	438895881520357521	10004616	334	14150170026959126	10010102	334	13978	1	11	[0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...	[0.036, 0.439, 0.0, 0.074, 0.194, 0.0, 0.331, ...	14150170026959126	http://a.vpimg2.com/upload/merchandise/pdcvis/...
4	4209887493\t74104320184119307\t10004616\t334\t...	4209887493	74104320184119307	10004616	334	14150170026959126	10010102	334	14313	1	11	[0.135, 1.078, 0.06, 0.241, 0.213, 0.22, 0.039...	[0.078, 2.304, 0.132, 0.191, 0.0, 0.087, 0.341...	14150170026959126	http://a.vpimg2.com/upload/merchandise/pdcvis/...

	user_buy	view_spu	view_cnt
0	1018047589-2885476247461195776	293373310066720769	2
1	1018047589-2885476247461195776	302661994239094787	2
2	1018047589-2885476247461195776	447903106563379200	1
3	1018047589-2885476247461195776	972290827227131904	1
4	1018047589-2885476247461195776	2192766390940934144	2

	spu	CF_item	spu_features	CF_features	ave_CF_fea
0	357872333107204	[8952950888272863232, 2846351224980500480, 881...	[0.035, 0.385, 0.112, 0.014, 0.0, 0.123, 0.438...	[[[0.462, 0.551, 0.068, 0.833, 0.0, 0.0, 0.0, ...	[0.3597, 0.7012, 0.0831, 1.0618, 0.2302, 0.123...
1	357875526680651	[2046769978417582, 461413925257830545, 3255052...	[0.132, 1.678, 0.061, 0.918, 0.462, 0.342, 0.4...	[[[0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104...	[0.4727, 0.8078, 0.0697, 0.5796, 0.3075, 0.009...
2	357882254983171	[459725075493814272, 8582811288237465674, 1976...	[0.026, 0.936, 0.056, 0.614, 0.139, 0.0, 0.302...	[[[1.884, 0.52, 0.0, 3.98, 0.175, 0.008, 0.663...	[0.6206, 0.8754, 0.1066, 0.7549, 0.2387, 0.186...
3	357901107539985	[2466922956389351424, 7804532970923106304, 130...	[0.229, 0.543, 0.132, 0.144, 0.295, 0.018, 0.0...	[[[0.124, 0.819, 0.0, 0.596, 0.306, 0.043, 0.2...	[0.449, 0.7069, 0.1971, 0.7197, 0.2461, 0.0106...
4	639360131194904	[81141212316332372, 320394952166453251, 639360...	[1.113, 0.5, 0.758, 0.218, 0.0, 0.0, 0.335, 1....	[[[0.06, 0.15, 0.011, 0.946, 0.501, 0.0, 1.309...	[0.2552, 0.5227, 0.0964, 0.3326, 0.1703, 0.011...
5	639369692328147	[463947194068213779, 4861516576375025, 9630021...	[1.489, 0.457, 0.0, 0.639, 0.0, 0.029, 0.656, ...	[[[0.057, 0.172, 0.0, 0.068, 0.284, 0.0, 0.0, ...	[0.5026, 0.6077, 0.1351, 1.0361, 0.3056, 0.098...
6	639371126526005	[2166589220222894080, 444243906496860160, 4611...	[0.28, 0.566, 0.009, 0.004, 0.119, 0.199, 0.39...	[[[0.051, 0.253, 0.0, 0.173, 0.803, 0.002, 0.2...	[0.2053, 0.3088, 0.0316, 0.194, 0.2859, 0.1264...
7	639389503180805	[81985618826645681, 15838990034669717, 1014074...	[0.023, 0.853, 0.11, 0.415, 0.681, 0.078, 0.50...	[[[0.621, 0.779, 0.019, 0.708, 0.32, 0.268, 0....	[0.4553, 0.8364, 0.0406, 0.5165, 0.2133, 0.046...
8	639392717246493	[13587203813871817, 1765254792024080, 10440669...	[0.496, 1.321, 0.014, 0.093, 0.145, 0.118, 0.1...	[[[0.086, 0.85, 0.023, 0.019, 0.018, 0.0, 0.16...	[0.3234, 0.9647, 0.089, 0.2659, 0.1303, 0.0571...
9	920816362999808	[2457352807885774848, 8584218663084269568, 465...	[0.375, 0.498, 0.093, 1.439, 0.482, 0.268, 0.1...	[[[0.156, 0.49, 0.359, 0.513, 0.0, 0.066, 0.49...	[0.5876, 0.3963, 0.194, 0.5702, 0.0595, 0.1919...
10	920832942268416	[299565768102322188, 31601602323353621, 439458...	[0.151, 0.729, 0.118, 0.091, 0.284, 0.0, 0.331...	[[[0.804, 0.159, 0.134, 2.68, 0.272, 0.0, 0.14...	[0.3458, 0.7266, 0.1114, 0.6795, 0.271, 0.0797...
11	920846404657158	[319550492123078656, 3454096121704448, 2995657...	[0.172, 0.284, 0.004, 0.19, 0.132, 0.0, 0.123,...	[[[0.01, 0.928, 0.125, 0.437, 0.17, 0.009, 0.2...	[0.3545, 0.7114, 0.0839, 0.5078, 0.3372, 0.011...
12	1202299096490170	[1044348428712186010, 93526113400463372, 89532...	[0.538, 0.997, 0.016, 0.28, 0.538, 0.436, 0.30...	[[[0.672, 0.383, 0.297, 0.59, 0.604, 0.098, 0....	[0.352, 0.6496, 0.0722, 0.3963, 0.3971, 0.0728...
13	1202310084616220	[6550345938870290, 462821289168044046, 3329046...	[0.897, 1.037, 0.0, 0.09, 0.027, 0.53, 0.088, ...	[[[0.09, 1.494, 0.048, 0.0, 0.029, 0.298, 0.04...	[0.2141, 0.5406, 0.1607, 0.9761, 0.1241, 0.055...
14	1202315469205505	[1044348428712186010, 93526113400463372, 89532...	[0.175, 0.717, 0.0, 0.445, 0.103, 0.0, 0.578, ...	[[[0.672, 0.383, 0.297, 0.59, 0.604, 0.098, 0....	[0.352, 0.6496, 0.0722, 0.3963, 0.3971, 0.0728...
15	1202326037671948	[9041615583843246080, 8939721565444202502, 420...	[0.268, 0.209, 0.016, 0.789, 1.177, 0.0, 0.034...	[[[0.205, 0.614, 0.0, 0.283, 0.029, 0.006, 0.3...	[0.5225, 0.3637, 0.0274, 0.7803, 0.2, 0.0929, ...
16	1202342670667978	[8295425334878236672, 444806904121757743, 4346...	[0.073, 0.544, 0.0, 0.228, 0.066, 0.004, 1.104...	[[[0.736, 0.65, 0.0, 0.055, 0.027, 0.0, 0.337,...	[0.2007, 0.8379, 0.0326, 0.3353, 0.0847, 0.009...
17	1202342670671910	[13587203813871817, 1765254792024080, 10440669...	[0.339, 2.969, 0.149, 0.335, 0.0, 0.0, 0.334, ...	[[[0.086, 0.85, 0.023, 0.019, 0.018, 0.0, 0.16...	[0.3234, 0.9647, 0.089, 0.2659, 0.1303, 0.0571...
18	1483782161825904	[302662024581271741, 19216708624982102, 148378...	[0.528, 1.082, 0.417, 1.969, 0.291, 0.022, 0.0...	[[[0.207, 0.77, 0.009, 0.123, 0.631, 0.064, 0....	[0.2882, 0.7877, 0.1187, 1.1597, 0.3005, 0.073...
19	1765254792024080	[13587203813871817, 1765254792024080, 10440669...	[0.69, 0.17, 0.0, 0.127, 0.051, 0.0, 0.462, 0....	[[[0.086, 0.85, 0.023, 0.019, 0.018, 0.0, 0.16...	[0.3234, 0.9647, 0.089, 0.2659, 0.1303, 0.0571...
20	2046724026622135	[2046724026622135, 1386059101696032768, 164019...	[0.095, 0.719, 0.0, 0.114, 0.0, 0.0, 0.02, 0.0...	[[[0.095, 0.719, 0.0, 0.114, 0.0, 0.0, 0.02, 0...	[0.2095, 0.5489, 0.1747, 0.2043, 0.0683, 0.113...
21	2046767967338535	[5047767116498747392, 4067389766593323193, 204...	[1.915, 0.723, 0.068, 0.761, 0.082, 0.0, 0.098...	[[[0.044, 0.315, 0.017, 0.256, 0.003, 0.004, 0...	[0.306, 0.8059, 0.1071, 0.3562, 0.0785, 0.0614...
22	2046769978417582	[2046769978417582, 461413925257830545, 3255052...	[0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104, ...	[[[0.357, 2.503, 0.0, 0.641, 0.143, 0.0, 0.104...	[0.4727, 0.8078, 0.0697, 0.5796, 0.3075, 0.009...
23	2609679722156042	[31038690201997892, 81985606739279872, 4374885...	[0.34, 0.747, 0.0, 0.036, 0.287, 0.075, 0.652,...	[[[0.026, 2.31, 0.026, 0.65, 0.027, 0.014, 0.0...	[0.1925, 0.8188, 0.0477, 0.1953, 0.1594, 0.033...
24	2891145450029056	[8945069666075066368, 86770695957168136, 80015...	[0.307, 0.529, 0.062, 0.137, 0.602, 0.26, 0.13...	[[[0.047, 1.04, 0.0, 0.538, 0.273, 0.036, 0.04...	[0.2889, 1.2939, 0.1574, 0.404, 0.1981, 0.3745...
25	2891152447287296	[89866911491678214, 76074637632249877, 1111339...	[0.156, 1.136, 0.104, 0.368, 0.199, 0.223, 0.1...	[[[1.039, 0.054, 0.159, 1.421, 0.168, 0.496, 0...	[0.5565, 0.5092, 0.0445, 0.8707, 0.2669, 0.111...
26	2891160600990330	[453532585603989586, 14150149385499493, 901797...	[0.011, 0.057, 0.003, 0.313, 0.017, 0.0, 0.93,...	[[[0.166, 0.047, 0.0, 0.408, 0.044, 0.0, 1.0, ...	[0.2168, 0.3611, 0.1358, 1.3846, 0.1856, 0.086...
27	2891169552208298	[3735594482335915, 464791631716921422, 4397403...	[0.475, 1.321, 0.009, 0.157, 0.017, 0.065, 0.4...	[[[0.245, 0.255, 0.06, 0.593, 0.0, 0.467, 0.08...	[0.478, 0.927, 0.2476, 0.7833, 0.392, 0.093, 0...
28	3172644484366424	[315046913029713936, 461695358101766158, 46282...	[0.706, 0.552, 0.0, 0.55, 0.241, 0.0, 0.43, 0....	[[[1.037, 1.816, 0.067, 0.334, 0.272, 0.04, 0....	[0.5111, 1.433, 0.0416, 0.5964, 0.2476, 0.0287...
29	3454095765094424	[75230216867246653, 10491016902120013, 8582811...	[0.158, 0.029, 0.0, 0.332, 0.369, 0.0, 0.35, 0...	[[[0.047, 1.367, 0.01, 0.016, 0.192, 0.144, 0....	[0.3853, 0.8521, 0.0434, 0.3653, 0.1598, 0.017...
...	...	...	...	...	...
2125	9014593909249236993	[9033734206588821512, 8459806721299259392, 131...	[0.962, 0.83, 0.029, 0.529, 0.336, 1.437, 0.60...	[[[1.107, 0.61, 0.0, 1.565, 0.093, 0.026, 0.19...	[0.3268, 0.6027, 0.0596, 0.8568, 0.3677, 0.065...
2126	9015719808079347717	[1403510549529337857, 4716752541135134720, 246...	[0.599, 0.232, 0.182, 0.959, 0.013, 0.54, 0.05...	[[[0.398, 0.12, 0.211, 0.331, 0.114, 0.129, 0....	[0.4865, 0.5288, 0.125, 0.6937, 0.1892, 0.0139...
2127	9016845703713148936	[8943099259803860992, 4214038229457264801, 656...	[1.14, 0.264, 0.0, 0.497, 0.115, 0.04, 0.146, ...	[[[1.193, 0.452, 0.086, 1.264, 0.026, 0.153, 0...	[1.0527, 0.4987, 0.1385, 0.8035, 0.0896, 0.107...
2128	9017127181215457486	[318143145884868618, 322365263185870869, 45212...	[1.491, 0.487, 0.001, 0.313, 0.106, 0.0, 0.565...	[[[0.043, 1.798, 0.06, 0.324, 0.522, 0.006, 0....	[0.3767, 0.922, 0.0483, 0.3788, 0.1126, 0.1851...
2129	9017971603620016137	[2480715230932934656, 9013468003992612872, 570...	[0.457, 0.066, 0.125, 2.235, 0.394, 0.0, 0.921...	[[[0.224, 2.103, 0.111, 1.814, 0.024, 0.053, 0...	[0.2507, 0.7091, 0.0523, 1.216, 0.1013, 0.0805...
2130	9017971606044979200	[453532585603989586, 314765448579829939, 90179...	[0.08, 0.252, 0.023, 2.211, 0.304, 0.157, 0.23...	[[[0.166, 0.047, 0.0, 0.408, 0.044, 0.0, 1.0, ...	[0.1928, 0.4477, 0.1556, 1.1285, 0.1973, 0.141...
2131	9018816028550127616	[25972089290305537, 82548606340628534, 2503076...	[0.731, 0.577, 0.0, 0.579, 0.053, 0.0, 0.173, ...	[[[0.223, 0.478, 0.018, 0.633, 0.081, 0.0, 0.0...	[0.2758, 0.4644, 0.038, 0.8915, 0.1976, 0.1173...
2132	9022193728259383296	[8662750265739194369, 1396755150088278017, 896...	[0.287, 0.508, 0.083, 1.605, 0.0, 0.0, 0.161, ...	[[[0.098, 0.791, 0.037, 1.392, 0.091, 0.0, 0.8...	[0.3521, 0.5703, 0.164, 1.1472, 0.1509, 0.0404...
2133	9022475203247398916	[8379867827911725056, 2833684851741020160, 247...	[0.448, 0.296, 0.0, 0.289, 0.034, 0.0, 0.204, ...	[[[0.244, 0.285, 0.014, 0.0, 0.026, 0.172, 0.0...	[0.3138, 0.4603, 0.0615, 0.7818, 0.1203, 0.053...
2134	9022756682497105932	[2889135421455757312, 8964209883068317705, 139...	[0.424, 0.469, 0.866, 0.072, 0.17, 0.029, 0.04...	[[[0.0, 0.407, 0.0, 0.936, 0.368, 0.0, 0.633, ...	[0.4331, 0.5593, 0.1124, 1.3875, 0.1317, 0.037...
2135	9023882578131013643	[2834529276655054848, 8944788109675335687, 247...	[0.369, 0.951, 0.139, 0.554, 0.0, 0.057, 0.676...	[[[0.508, 0.872, 0.053, 0.959, 0.406, 0.079, 0...	[0.3402, 0.8657, 0.0735, 1.1642, 0.2633, 0.023...
2136	9024727008410832903	[2814544552628457472, 4710841566656688129, 246...	[0.268, 1.398, 0.048, 0.996, 0.038, 0.175, 0.0...	[[[0.654, 0.789, 0.047, 1.587, 0.603, 0.122, 0...	[0.4715, 0.4672, 0.0954, 0.9115, 0.173, 0.0866...
2137	9026415852921315334	[8935499435443806210, 2469456231166840832, 250...	[2.351, 0.923, 0.057, 2.389, 0.001, 0.279, 0.0...	[[[0.151, 0.411, 0.516, 2.49, 0.478, 0.0, 0.02...	[0.5588, 0.6993, 0.162, 1.3153, 0.3403, 0.052,...
2138	9026697332171030534	[306321203330416650, 8943943684745093124, 3139...	[0.226, 2.182, 0.349, 1.539, 0.623, 0.08, 0.55...	[[[0.642, 0.678, 0.035, 0.179, 0.209, 0.0, 0.6...	[0.2872, 0.5251, 0.0575, 0.6054, 0.1139, 0.077...
2139	9027823227804868619	[32446013086847137, 4641598722385866752, 89650...	[0.022, 0.249, 0.024, 1.01, 0.68, 0.342, 0.285...	[[[0.5, 0.052, 0.004, 0.379, 1.003, 0.023, 0.1...	[0.5151, 0.5221, 0.0721, 0.8971, 0.2982, 0.126...
2140	9031763960910209025	[299565803160592409, 437207054292414662, 29084...	[0.439, 1.185, 0.27, 0.076, 0.193, 1.313, 0.11...	[[[0.403, 0.956, 0.007, 0.555, 0.099, 0.064, 0...	[0.3553, 0.8389, 0.063, 1.3263, 0.2993, 0.2635...
2141	9033171252362444801	[436644089099345920, 1394503350274605056, 7653...	[0.111, 1.705, 0.287, 0.536, 0.174, 0.082, 0.3...	[[[0.055, 0.927, 0.855, 0.292, 0.129, 0.095, 0...	[0.3778, 0.6725, 0.1822, 0.6073, 0.1004, 0.073...
2142	9033734206588821512	[1314001506935377921, 8459806721299259392, 946...	[1.107, 0.61, 0.0, 1.565, 0.093, 0.026, 0.198,...	[[[0.003, 0.944, 0.131, 0.601, 1.503, 0.008, 0...	[0.6796, 0.9908, 0.0429, 1.0009, 0.341, 0.2758...
2143	9035141577199349769	[8970120857579282441, 9007838504458428425, 282...	[0.281, 0.999, 0.075, 0.693, 0.0, 0.0, 0.025, ...	[[[0.0, 0.543, 0.01, 0.138, 0.018, 0.373, 0.12...	[0.3044, 0.6704, 0.1144, 0.9836, 0.1997, 0.090...
2144	9036830509787594752	[4418107589125877775, 2813981603359453184, 439...	[0.046, 0.136, 0.123, 0.013, 0.5, 0.233, 0.118...	[[[0.162, 0.766, 0.024, 0.238, 0.041, 0.134, 0...	[0.2982, 0.8262, 0.1709, 0.6126, 0.0938, 0.073...
2145	9037674851989819400	[5140090909293244416, 2910246045436305408, 889...	[1.315, 0.858, 0.031, 2.212, 0.165, 0.041, 0.0...	[[[0.012, 0.469, 0.0, 0.021, 0.004, 0.0, 0.149...	[0.3437, 0.6673, 0.1118, 0.7965, 0.1679, 0.095...
2146	9038237806216196097	[4063730591896084758, 320113495556218907, 2990...	[0.916, 0.513, 0.167, 0.201, 0.284, 0.023, 0.1...	[[[0.53, 0.945, 0.0, 0.785, 0.028, 0.161, 0.14...	[0.3446, 0.9183, 0.0247, 0.3677, 0.213, 0.057,...
2147	9039645182176481286	[1675415380238614528, 4641598722385866752, 246...	[0.216, 0.17, 0.018, 3.05, 0.224, 0.835, 0.334...	[[[0.067, 0.002, 0.048, 1.074, 0.542, 0.023, 0...	[0.3266, 0.384, 0.0903, 0.7626, 0.4486, 0.1297...
2148	9039926651803541506	[467887839865233418, 33571969587101699, 282664...	[0.219, 1.177, 0.074, 1.615, 0.112, 0.207, 0.0...	[[[0.657, 0.508, 0.436, 0.075, 0.625, 0.192, 0...	[0.3592, 0.6364, 0.113, 0.9559, 0.1909, 0.0398...
2149	9041615583843246080	[8939721565444202502, 13868682270638081, 12023...	[0.205, 0.614, 0.0, 0.283, 0.029, 0.006, 0.328...	[[[1.466, 0.586, 0.0, 0.439, 0.049, 0.0, 0.104...	[0.7453, 0.8045, 0.0315, 0.8878, 0.3513, 0.138...
2150	9088621908743286785	[84800386939424768, 5705920362590242, 40713304...	[0.0, 0.502, 0.0, 0.01, 0.206, 0.031, 1.15, 0....	[[[0.053, 0.258, 0.002, 0.0, 0.449, 0.061, 0.9...	[0.2219, 0.8111, 0.0544, 0.2453, 0.2216, 0.046...
2151	9089747807251402752	[447903087581487120, 84800366075408747, 318987...	[0.764, 0.496, 0.486, 0.159, 0.165, 0.474, 0.8...	[[[0.176, 1.749, 0.0, 0.185, 0.02, 0.31, 0.084...	[0.3317, 0.7604, 0.0334, 0.7855, 0.1488, 0.231...
2152	9090029283626840066	[88178053449961475, 299847247939522560, 909002...	[0.423, 0.22, 0.083, 0.994, 0.096, 0.0, 0.048,...	[[[0.004, 0.453, 0.0, 0.643, 0.442, 0.043, 0.0...	[0.3801, 0.6667, 0.0895, 0.4036, 0.2618, 0.027...
2153	9090592232181542912	[8306121384015122432, 2900394421224820736, 283...	[0.25, 0.926, 0.073, 1.526, 0.386, 0.024, 0.49...	[[[0.157, 0.964, 0.117, 0.82, 0.915, 0.016, 0....	[0.7383, 0.6909, 0.0327, 1.0177, 0.4509, 0.134...
2154	9094251405871296512	[100844442657288193, 292247467889451008, 29252...	[0.055, 0.351, 0.0, 0.475, 0.129, 0.055, 0.185...	[[[0.206, 1.239, 0.043, 1.42, 0.057, 0.03, 0.0...	[0.5435, 0.9577, 0.0513, 1.5471, 0.1106, 0.312...

	user_buy	ave_CF_fea
0	1018047589-2885476247461195776	[0.3402875, 0.632470833333, 0.1431, 0.91783333...
1	1074350764-20905574407417865	[0.345218478261, 0.517051086957, 0.12234130434...
2	1074350764-2836218125824516096	[0.353695, 0.54904, 0.10707, 0.827515, 0.21728...
3	1076790314-2893639021813923840	[0.221729032258, 0.651, 0.106264516129, 0.5287...
4	1076790314-4209253154853183622	[0.199768181818, 0.686179545455, 0.10204318181...

	user_buy	spu_features
0	1018047589-2885476247461195776	[0.386333333333, 0.548166666667, 0.08983333333...
1	1074350764-20905574407417865	[0.36272826087, 0.396108695652, 0.108434782609...
2	1074350764-2836218125824516096	[0.37505, 0.50925, 0.11335, 0.96235, 0.12985, ...
3	1076790314-2893639021813923840	[0.257322580645, 0.676548387097, 0.17258064516...
4	1076790314-4209253154853183622	[0.210295454545, 0.680727272727, 0.15218181818...

view_spu	357872333107204	357875526680651	357882254983171	357901107539985	639360131194904	639369692328147	639371126526005	639389503180805	639392717246493	920816362999808	...	9037674851989819400	9038237806216196097	9039645182176481286	9039926651803541506	9041615583843246080	9088621908743286785	9089747807251402752	9090029283626840066	9090592232181542912	9094251405871296512
view_spu
357872333107204	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.00000	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000	0.0
357875526680651	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.00000	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000	0.0
357882254983171	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.63211	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000	0.0
357901107539985	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.00000	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.020383	0.0
639360131194904	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.00000	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.000000	0.0

	user_id	buy_spu	ave_CF_fea	ave_view_fea	ave_CF_sim_rank	ave_Ori_sim_rank	ave_CF_sim	ave_CF_rank	ave_Ori_sim	ave_Ori_rank
0	3440325	2898705571343994880	[0.327609375, 0.573775, 0.11804375, 0.87390625...	[0.30521875, 0.5995625, 0.167625, 0.99259375, ...	([0.799214495018], [215.0])	([0.811977551064], [115.0])	0.799214	215.0	0.811978	115.0
1	7052311	7957699990364366	[0.307052173913, 0.738013043478, 0.06435217391...	[0.320739130435, 0.577217391304, 0.088, 0.6661...	([0.745014365081], [1155.0])	([0.73996321102], [1112.0])	0.745014	1155.0	0.739963	1112.0
2	7052311	299847271351230626	[0.306652173913, 0.7439, 0.0624434782609, 0.60...	[0.314217391304, 0.620695652174, 0.08865217391...	([0.833736325406], [173.0])	([0.855587371153], [66.0])	0.833736	173.0	0.855587	66.0
3	7052311	448747521265074449	[0.306817391304, 0.735182608696, 0.06435217391...	[0.323086956522, 0.60552173913, 0.088, 0.653, ...	([0.854382169198], [49.0])	([0.853929200306], [84.0])	0.854382	49.0	0.853929	84.0
4	9254280	3925244893201649664	[0.385093939394, 0.623651515152, 0.12763030303...	[0.356484848485, 0.575484848485, 0.11351515151...	([0.730978541607], [1427.0])	([0.752675987128], [535.0])	0.730979	1427.0	0.752676	535.0