{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"Original notebook: https://www.kaggle.com/code/cdeotte/candidate-rerank-model-lb-0-575\n\n# Candidate ReRank Model using Handcrafted Rules\nIn this notebook, we present a \"candidate rerank\" model using handcrafted rules. We can improve this model by engineering features, merging them unto items and users, and training a reranker model (such as XGB) to choose our final 20. Furthermore to tune and improve this notebook, we should build a local CV scheme to experiment new logic and/or models.\n\nUPDATE: I published a notebook to compute validation score [here][10] using Radek's scheme described [here][11].\n\nNote in this competition, a \"session\" actually means a unique \"user\". So our task is to predict what each of the `1,671,803` test \"users\" (i.e. \"sessions\") will do in the future. For each test \"user\" (i.e. \"session\") we must predict what they will `click`, `cart`, and `order` during the remainder of the week long test period.\n\n### Step 1 - Generate Candidates\nFor each test user, we generate possible choices, i.e. candidates. In this notebook, we generate candidates from 5 sources:\n* User history of clicks, carts, orders\n* Most popular 20 clicks, carts, orders during test week\n* Co-visitation matrix of click/cart/order to cart/order with type weighting\n* Co-visitation matrix of cart/order to cart/order called buy2buy\n* Co-visitation matrix of click/cart/order to clicks with time weighting\n\n### Step 2 - ReRank and Choose 20\nGiven the list of candidates, we must select 20 to be our predictions. In this notebook, we do this with a set of handcrafted rules. We can improve our predictions by training an XGBoost model to select for us. Our handcrafted rules give priority to:\n* Most recent previously visited items\n* Items previously visited multiple times\n* Items previously in cart or order\n* Co-visitation matrix of cart/order to cart/order\n* Current popular items\n\n![](https://raw.githubusercontent.com/cdeotte/Kaggle_Images/main/Nov-2022/c_r_model.png)\n  \n# Credits\nWe thank many Kagglers who have shared ideas. We use co-visitation matrix idea from Vladimir [here][1]. We use groupby sort logic from Sinan in comment section [here][4]. We use duplicate prediction removal logic from Radek [here][5]. We use multiple visit logic from Pietro [here][2]. We use type weighting logic from Ingvaras [here][3]. We use leaky test data from my previous notebook [here][4]. And some ideas may have originated from Tawara [here][6] and KJ [here][7]. We use Colum2131's parquets [here][8]. Above image is from Ravi's discussion about candidate rerank models [here][9]\n\n[1]: https://www.kaggle.com/code/vslaykovsky/co-visitation-matrix\n[2]: https://www.kaggle.com/code/pietromaldini1/multiple-clicks-vs-latest-items\n[3]: https://www.kaggle.com/code/ingvarasgalinskas/item-type-vs-multiple-clicks-vs-latest-items\n[4]: https://www.kaggle.com/code/cdeotte/test-data-leak-lb-boost\n[5]: https://www.kaggle.com/code/radek1/co-visitation-matrix-simplified-imprvd-logic\n[6]: https://www.kaggle.com/code/ttahara/otto-mors-aid-frequency-baseline\n[7]: https://www.kaggle.com/code/whitelily/co-occurrence-baseline\n[8]: https://www.kaggle.com/datasets/columbia2131/otto-chunk-data-inparquet-format\n[9]: https://www.kaggle.com/competitions/otto-recommender-system/discussion/364721\n[10]: https://www.kaggle.com/cdeotte/compute-validation-score-cv-564\n[11]: https://www.kaggle.com/competitions/otto-recommender-system/discussion/364991","metadata":{"papermill":{"duration":0.005198,"end_time":"2022-11-10T16:03:20.966987","exception":false,"start_time":"2022-11-10T16:03:20.961789","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Step 1 - Candidate Generation with RAPIDS\nFor candidate generation, we build three co-visitation matrices. One computes the popularity of cart/order given a user's previous click/cart/order. We apply type weighting to this matrix. One computes the popularity of cart/order given a user's previous cart/order. We call this \"buy2buy\" matrix. One computes the popularity of clicks given a user previously click/cart/order.  We apply time weighting to this matrix. We will use RAPIDS cuDF GPU to compute these matrices quickly!","metadata":{"papermill":{"duration":0.00373,"end_time":"2022-11-10T16:03:20.9748","exception":false,"start_time":"2022-11-10T16:03:20.97107","status":"completed"},"tags":[]}},{"cell_type":"code","source":"VER = 5\n\nimport pandas as pd, numpy as np\nfrom tqdm.notebook import tqdm\nimport os, sys, pickle, glob, gc\nfrom collections import Counter\nimport cudf, itertools\nprint('We will use RAPIDS version',cudf.__version__)","metadata":{"papermill":{"duration":3.036143,"end_time":"2022-11-10T16:03:24.014816","exception":false,"start_time":"2022-11-10T16:03:20.978673","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-06-09T08:55:00.670484Z","iopub.execute_input":"2023-06-09T08:55:00.671132Z","iopub.status.idle":"2023-06-09T08:55:03.897762Z","shell.execute_reply.started":"2023-06-09T08:55:00.671020Z","shell.execute_reply":"2023-06-09T08:55:03.896640Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Compute Three Co-visitation Matrices with RAPIDS\nWe will compute 3 co-visitation matrices using RAPIDS cuDF on GPU. This is 30x faster than using Pandas CPU like other public notebooks! For maximum speed, set the variable `DISK_PIECES` to the smallest number possible based on the GPU you are using without incurring memory errors. If you run this code offline with 32GB GPU ram, then you can use `DISK_PIECES = 1` and compute each co-visitation matrix in almost 1 minute! Kaggle's GPU only has 16GB ram, so we use `DISK_PIECES = 4` and it takes an amazing 3 minutes each! Below are some of the tricks to speed up computation\n* Use RAPIDS cuDF GPU instead of Pandas CPU\n* Read disk once and save in CPU RAM for later GPU multiple use\n* Process largest amount of data possible on GPU at one time\n* Merge data in two stages. Multiple small to single medium. Multiple medium to single large.\n* Write result as parquet instead of dictionary","metadata":{"papermill":{"duration":0.00424,"end_time":"2022-11-10T16:03:24.023816","exception":false,"start_time":"2022-11-10T16:03:24.019576","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%time\n# CACHE FUNCTIONS\ndef read_file(f):\n    return cudf.DataFrame( data_cache[f] )\ndef read_file_to_cache(f):\n    df = pd.read_parquet(f)\n    df.ts = (df.ts/1000).astype('int32')\n    df['type'] = df['type'].map(type_labels).astype('int8')\n    return df\n\n# CACHE THE DATA ON CPU BEFORE PROCESSING ON GPU\ndata_cache = {}\ntype_labels = {'clicks':0, 'carts':1, 'orders':2}\nfiles = glob.glob('../input/otto-chunk-data-inparquet-format/*_parquet/*')\nfor f in files: data_cache[f] = read_file_to_cache(f)\n\n# CHUNK PARAMETERS\nREAD_CT = 5\nCHUNK = int( np.ceil( len(files)/6 ))\nprint(f'We will process {len(files)} files, in groups of {READ_CT} and chunks of {CHUNK}.')\n\nclicks_th = 15\ncarts_th  = 20\norders_th = 20 ","metadata":{"papermill":{"duration":0.063943,"end_time":"2022-11-10T16:03:24.091816","exception":false,"start_time":"2022-11-10T16:03:24.027873","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-06-09T08:59:08.513893Z","iopub.execute_input":"2023-06-09T08:59:08.514313Z","iopub.status.idle":"2023-06-09T09:00:34.743602Z","shell.execute_reply.started":"2023-06-09T08:59:08.514250Z","shell.execute_reply":"2023-06-09T09:00:34.742512Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 1) \"Carts Orders\" Co-visitation Matrix - Type Weighted","metadata":{"papermill":{"duration":0.004089,"end_time":"2022-11-10T16:03:24.100502","exception":false,"start_time":"2022-11-10T16:03:24.096413","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%time\ntype_weight = {0:0.5, 1:9, 2:0.5}\n\n# USE SMALLEST DISK_PIECES POSSIBLE WITHOUT MEMORY ERROR\nDISK_PIECES = 4\nSIZE = 1.86e6/DISK_PIECES\n\n# COMPUTE IN PARTS FOR MEMORY MANGEMENT\nfor PART in range(DISK_PIECES):\n    print()\n    print('### DISK PART',PART+1)\n    \n    # MERGE IS FASTEST PROCESSING CHUNKS WITHIN CHUNKS\n    # => OUTER CHUNKS\n    for j in range(6):\n        a = j*CHUNK\n        b = min( (j+1)*CHUNK, len(files) )\n        print(f'Processing files {a} thru {b-1} in groups of {READ_CT}...')\n        \n        # => INNER CHUNKS\n        for k in range(a,b,READ_CT):\n            # READ FILE\n            df = [read_file(files[k])]\n            for i in range(1,READ_CT): \n                if k+i<b: df.append( read_file(files[k+i]) )#after this line, df becomes a list of 5 chunks of data\n            df = cudf.concat(df,ignore_index=True,axis=0)\n            df = df.sort_values(['session','ts'],ascending=[True,False])\n            # USE TAIL OF SESSION\n            df = df.reset_index(drop=True)\n            #if k == 0: print(df)\n            df['n'] = df.groupby('session').cumcount()#n column indicate the order of action from one\n            #if k == 0: print(df)\n            df = df.loc[df.n<30].drop('n',axis=1)#eliminate all rows with n < 30. a.k.a only allow maximum 30 actions from a session\n            #if k == 0: print(df)\n            # CREATE PAIRS\n            df = df.merge(df,on='session')#some sessions with just one action will be eliminated\n            #if k == 0: print(df)\n            df = df.loc[ ((df.ts_x - df.ts_y).abs()< 24 * 60 * 60) & (df.aid_x != df.aid_y) ]#only choose lines which satisfy the condition in []\n            # in other words, this line wants to make sure the action afterwards must be within the same day and the user has to choose another product\n            #if k == 0: print(df)\n            # MEMORY MANAGEMENT COMPUTE IN PARTS\n            df = df.loc[(df.aid_x >= PART*SIZE)&(df.aid_x < (PART+1)*SIZE)]\n            #if k == 0: print(df)\n            # ASSIGN WEIGHTS\n            df = df[['session', 'aid_x', 'aid_y','type_y']].drop_duplicates(['session', 'aid_x', 'aid_y','type_y'])#eliminate lines of the same session with the same pair of behavior\n            #if k == 0: print(df)\n            df['wgt'] = df.type_y.map(type_weight)#apply the weight indicated\n            #if k == 0: print(df)\n            df = df[['aid_x','aid_y','wgt']]\n            #if k == 0: print(df)\n            df.wgt = df.wgt.astype('float32')\n            #if k == 0: print(df)\n            df = df.groupby(['aid_x','aid_y']).wgt.sum()\n            #the final df got 3 columns: aid_x and aid_y represent a pair of  action with its represented total weight\n            #if k == 0: print(df)\n            # COMBINE INNER CHUNKS\n            if k==a: tmp2 = df\n            else: tmp2 = tmp2.add(df, fill_value=0)#combine all the chunks tgt\n            print(k,', ',end='')\n        print()\n        # COMBINE OUTER CHUNKS\n        if a==0: tmp = tmp2\n        else: tmp = tmp.add(tmp2, fill_value=0)\n        del tmp2, df #this is just to save some memory\n        gc.collect()\n    # CONVERT MATRIX TO DICTIONARY\n    #print(tmp)\n    tmp = tmp.reset_index()\n    tmp = tmp.sort_values(['aid_x','wgt'],ascending=[True,False])\n    # SAVE TOP 40\n    tmp = tmp.reset_index(drop=True)\n    tmp['n'] = tmp.groupby('aid_x').aid_y.cumcount()\n    #print(tmp)\n    tmp = tmp.loc[tmp.n<carts_th].drop('n',axis=1)\n    #print(tmp)\n    # SAVE PART TO DISK (convert to pandas first uses less memory)\n    tmp.to_pandas().to_parquet(f'top_20_carts_orders_v{VER}_{PART}.pqt')","metadata":{"papermill":{"duration":566.561189,"end_time":"2022-11-10T16:12:50.666123","exception":false,"start_time":"2022-11-10T16:03:24.104934","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:20:47.071889Z","iopub.execute_input":"2023-01-23T02:20:47.072216Z","iopub.status.idle":"2023-01-23T02:24:07.630644Z","shell.execute_reply.started":"2023-01-23T02:20:47.072186Z","shell.execute_reply":"2023-01-23T02:24:07.629413Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 2) \"Buy2Buy\" Co-visitation Matrix","metadata":{"papermill":{"duration":0.03219,"end_time":"2022-11-10T16:12:50.730634","exception":false,"start_time":"2022-11-10T16:12:50.698444","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%time\n# USE SMALLEST DISK_PIECES POSSIBLE WITHOUT MEMORY ERROR\nDISK_PIECES = 1\nSIZE = 1.86e6/DISK_PIECES\n\n# COMPUTE IN PARTS FOR MEMORY MANGEMENT\nfor PART in range(DISK_PIECES):\n    print()\n    print('### DISK PART',PART+1)\n    \n    # MERGE IS FASTEST PROCESSING CHUNKS WITHIN CHUNKS\n    # => OUTER CHUNKS\n    for j in range(6):\n        a = j*CHUNK\n        b = min( (j+1)*CHUNK, len(files) )\n        print(f'Processing files {a} thru {b-1} in groups of {READ_CT}...')\n        \n        # => INNER CHUNKS\n        for k in range(a,b,READ_CT):\n            # READ FILE\n            df = [read_file(files[k])]\n            for i in range(1,READ_CT): \n                if k+i<b: df.append( read_file(files[k+i]) )\n            df = cudf.concat(df,ignore_index=True,axis=0)\n            df = df.loc[df['type'].isin([1,2])] # ONLY WANT CARTS AND ORDERS\n            df = df.sort_values(['session','ts'],ascending=[True,False])\n            # USE TAIL OF SESSION\n            df = df.reset_index(drop=True)\n            df['n'] = df.groupby('session').cumcount()\n            df = df.loc[df.n<30].drop('n',axis=1)\n            # CREATE PAIRS\n            df = df.merge(df,on='session')\n            df = df.loc[ ((df.ts_x - df.ts_y).abs()< 7 * 24 * 60 * 60) & (df.aid_x != df.aid_y) ] # 14 DAYS\n            # MEMORY MANAGEMENT COMPUTE IN PARTS\n            df = df.loc[(df.aid_x >= PART*SIZE)&(df.aid_x < (PART+1)*SIZE)]\n            # ASSIGN WEIGHTS\n            df = df[['session', 'aid_x', 'aid_y','type_y']].drop_duplicates(['session', 'aid_x', 'aid_y','type_y'])\n            #df['wgt'] = 1\n            df['wgt'] = df.type_y.map(type_weight)\n            df = df[['aid_x','aid_y','wgt']]\n            df.wgt = df.wgt.astype('float32')\n            df = df.groupby(['aid_x','aid_y']).wgt.sum()\n            # COMBINE INNER CHUNKS\n            if k==a: tmp2 = df\n            else: tmp2 = tmp2.add(df, fill_value=0)\n            print(k,', ',end='')\n        print()\n        # COMBINE OUTER CHUNKS\n        if a==0: tmp = tmp2\n        else: tmp = tmp.add(tmp2, fill_value=0)\n        del tmp2, df\n        gc.collect()\n    # CONVERT MATRIX TO DICTIONARY\n    tmp = tmp.reset_index()\n    tmp = tmp.sort_values(['aid_x','wgt'],ascending=[True,False])\n    # SAVE TOP 40\n    tmp = tmp.reset_index(drop=True)\n    tmp['n'] = tmp.groupby('aid_x').aid_y.cumcount()\n    tmp = tmp.loc[tmp.n<orders_th].drop('n',axis=1)\n    # SAVE PART TO DISK (convert to pandas first uses less memory)\n    tmp.to_pandas().to_parquet(f'top_20_buy2buy_v{VER}_{PART}.pqt')","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"papermill":{"duration":113.735315,"end_time":"2022-11-10T16:14:44.498182","exception":false,"start_time":"2022-11-10T16:12:50.762867","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:25:02.847622Z","iopub.execute_input":"2023-01-23T02:25:02.848002Z","iopub.status.idle":"2023-01-23T02:25:30.141588Z","shell.execute_reply.started":"2023-01-23T02:25:02.847964Z","shell.execute_reply":"2023-01-23T02:25:30.140245Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 3) \"Clicks\" Co-visitation Matrix - Time Weighted","metadata":{"papermill":{"duration":0.04526,"end_time":"2022-11-10T16:14:44.58589","exception":false,"start_time":"2022-11-10T16:14:44.54063","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%time\n# USE SMALLEST DISK_PIECES POSSIBLE WITHOUT MEMORY ERROR\nDISK_PIECES = 4\nSIZE = 1.86e6/DISK_PIECES\n\n# COMPUTE IN PARTS FOR MEMORY MANGEMENT\nfor PART in range(DISK_PIECES):\n    print()\n    print('### DISK PART',PART+1)\n    \n    # MERGE IS FASTEST PROCESSING CHUNKS WITHIN CHUNKS\n    # => OUTER CHUNKS\n    for j in range(6):\n        a = j*CHUNK\n        b = min( (j+1)*CHUNK, len(files) )\n        print(f'Processing files {a} thru {b-1} in groups of {READ_CT}...')\n        \n        # => INNER CHUNKS\n        for k in range(a,b,READ_CT):\n            # READ FILE\n            df = [read_file(files[k])]\n            for i in range(1,READ_CT): \n                if k+i<b: df.append( read_file(files[k+i]) )\n            df = cudf.concat(df,ignore_index=True,axis=0)\n            df = df.sort_values(['session','ts'],ascending=[True,False])\n            # USE TAIL OF SESSION\n            df = df.reset_index(drop=True)\n            df['n'] = df.groupby('session').cumcount()\n            df = df.loc[df.n<30].drop('n',axis=1)\n            # CREATE PAIRS\n            df = df.merge(df,on='session')\n            df = df.loc[ ((df.ts_x - df.ts_y).abs()< 24 * 60 * 60) & (df.aid_x != df.aid_y) ]\n            # MEMORY MANAGEMENT COMPUTE IN PARTS\n            df = df.loc[(df.aid_x >= PART*SIZE)&(df.aid_x < (PART+1)*SIZE)]\n            # ASSIGN WEIGHTS\n            df = df[['session', 'aid_x', 'aid_y','ts_x']].drop_duplicates(['session', 'aid_x', 'aid_y'])\n            #df = df[['session', 'aid_x', 'aid_y','type_y']].drop_duplicates(['session', 'aid_x', 'aid_y','type_y'])\n            #df['wgt'] = 1 + 3*(df.ts_x - 1659304800)/(1662328791-1659304800)\n            df['wgt'] = (df.ts_x - 1659304800)/(1662328791-1659304800)\n            #df['wgt'] = df.type_y.map(type_weight)\n            df = df[['aid_x','aid_y','wgt']]\n            df.wgt = df.wgt.astype('float32')\n            df = df.groupby(['aid_x','aid_y']).wgt.sum()\n            # COMBINE INNER CHUNKS\n            if k==a: tmp2 = df\n            else: tmp2 = tmp2.add(df, fill_value=0)\n            print(k,', ',end='')\n        print()\n        # COMBINE OUTER CHUNKS\n        if a==0: tmp = tmp2\n        else: tmp = tmp.add(tmp2, fill_value=0)\n        del tmp2, df\n        gc.collect()\n    # CONVERT MATRIX TO DICTIONARY\n    tmp = tmp.reset_index()\n    tmp = tmp.sort_values(['aid_x','wgt'],ascending=[True,False])\n    # SAVE TOP 40\n    tmp = tmp.reset_index(drop=True)\n    tmp['n'] = tmp.groupby('aid_x').aid_y.cumcount()\n    tmp = tmp.loc[tmp.n<clicks_th].drop('n',axis=1)\n    # SAVE PART TO DISK (convert to pandas first uses less memory)\n    tmp.to_pandas().to_parquet(f'top_20_clicks_v{VER}_{PART}.pqt')","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"papermill":{"duration":null,"end_time":null,"exception":false,"start_time":"2022-11-10T16:14:44.629032","status":"running"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:32:01.221400Z","iopub.execute_input":"2023-01-23T02:32:01.222154Z","iopub.status.idle":"2023-01-23T02:35:17.182228Z","shell.execute_reply.started":"2023-01-23T02:32:01.222117Z","shell.execute_reply":"2023-01-23T02:35:17.181228Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# FREE MEMORY\ndel data_cache, tmp\n_ = gc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-01-14T03:17:33.730272Z","iopub.execute_input":"2023-01-14T03:17:33.730649Z","iopub.status.idle":"2023-01-14T03:17:33.885796Z","shell.execute_reply.started":"2023-01-14T03:17:33.730613Z","shell.execute_reply":"2023-01-14T03:17:33.884567Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 2 - ReRank (choose 20) using handcrafted rules\nFor description of the handcrafted rules, read this notebook's intro.","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[]}},{"cell_type":"code","source":"def load_test():    \n    dfs = []\n    for e, chunk_file in enumerate(glob.glob('../input/otto-chunk-data-inparquet-format/test_parquet/*')):\n        chunk = pd.read_parquet(chunk_file)\n        chunk.ts = (chunk.ts/1000).astype('int32')\n        chunk['type'] = chunk['type'].map(type_labels).astype('int8')\n        dfs.append(chunk)\n    return pd.concat(dfs).reset_index(drop=True) #.astype({\"ts\": \"datetime64[ms]\"})\n\ntest_df = load_test()\nprint('Test data has shape',test_df.shape)\n#test_df.head()","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:35:21.694919Z","iopub.execute_input":"2023-01-23T02:35:21.695613Z","iopub.status.idle":"2023-01-23T02:35:23.420742Z","shell.execute_reply.started":"2023-01-23T02:35:21.695573Z","shell.execute_reply":"2023-01-23T02:35:23.419719Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndef pqt_to_dict(df):\n    return df.groupby('aid_x').aid_y.apply(list).to_dict()\n# LOAD THREE CO-VISITATION MATRICES\ntop_20_clicks = pqt_to_dict( pd.read_parquet(f'top_20_clicks_v{VER}_0.pqt') )\n#print(top_20_clicks[0],top_20_clicks[1],top_20_clicks[2],top_20_clicks[3],top_20_clicks[4] )\nfor k in range(1,DISK_PIECES): \n    top_20_clicks.update( pqt_to_dict( pd.read_parquet(f'top_20_clicks_v{VER}_{k}.pqt') ) )\n    #print(top_20_clicks[0],top_20_clicks[1],top_20_clicks[2],top_20_clicks[3],top_20_clicks[4] )\ntop_20_buys = pqt_to_dict( pd.read_parquet(f'top_20_carts_orders_v{VER}_0.pqt') )\nfor k in range(1,DISK_PIECES): \n    top_20_buys.update( pqt_to_dict( pd.read_parquet(f'top_20_carts_orders_v{VER}_{k}.pqt') ) )\ntop_20_buy2buy = pqt_to_dict( pd.read_parquet(f'top_20_buy2buy_v{VER}_0.pqt') )\n\n# TOP CLICKS AND ORDERS IN TEST\ntop_clicks = test_df.loc[test_df['type']==0,'aid'].value_counts().index.values[:30]\ntop_orders = test_df.loc[test_df['type']==1,'aid'].value_counts().index.values[:30]\ntop_carts = test_df.loc[test_df['type']==2,'aid'].value_counts().index.values[:30]\nprint('Here are size of our 3 co-visitation matrices:')\nprint( len( top_20_clicks ), len( top_20_buy2buy ), len( top_20_buys ) )\n#top_20_clicks","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:38:41.216074Z","iopub.execute_input":"2023-01-23T02:38:41.217948Z","iopub.status.idle":"2023-01-23T02:40:17.972034Z","shell.execute_reply.started":"2023-01-23T02:38:41.217908Z","shell.execute_reply":"2023-01-23T02:40:17.970985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#type_weight_multipliers = {'clicks': 1, 'carts': 6, 'orders': 3}\ntype_weight_multipliers = {0: 0.5, 1: 9, 2: 0.5}\n\ndef suggest_clicks(df):\n    # USER HISTORY AIDS AND TYPES\n    aids=df.aid.tolist()\n    #print(aids)\n    types = df.type.tolist()\n    #print(types)\n    unique_aids = list(dict.fromkeys(aids[::-1] ))\n    #print(unique_aids)\n    # RERANK CANDIDATES USING WEIGHTS\n    if len(unique_aids)>=20:\n        weights=np.logspace(0.1,1,len(aids),base=2, endpoint=True)-1\n        #print(weights)\n        aids_temp = Counter()\n        #print(aids_temp)\n        # RERANK BASED ON REPEAT ITEMS AND TYPE OF ITEMS\n        for aid,w,t in zip(aids,weights,types): \n            aids_temp[aid] += w * type_weight_multipliers[t]\n            #print(aids_temp)\n        sorted_aids = [k for k,v in aids_temp.most_common(20)]\n        #print(sorted_aids)\n        return sorted_aids\n    # USE \"CLICKS\" CO-VISITATION MATRIX\n    aids2 = list(itertools.chain(*[top_20_clicks[aid] for aid in unique_aids if aid in top_20_clicks]))\n    #print(aids2)\n    # RERANK CANDIDATES\n    top_aids2 = [aid2 for aid2, cnt in Counter(aids2).most_common(20) if aid2 not in unique_aids]  \n    #print(top_aids2)\n    result = unique_aids + top_aids2[:20 - len(unique_aids)]\n    #print(result)\n    # USE TOP20 TEST CLICKS\n    set_result = set(result)\n    return result + [i for i in top_clicks[:30] if i not in set_result][:20-len(result)]\n\ndef suggest_buys(df):\n    # USER HISTORY AIDS AND TYPES\n    aids=df.aid.tolist()\n    types = df.type.tolist()\n    # UNIQUE AIDS AND UNIQUE BUYS\n    unique_aids = list(dict.fromkeys(aids[::-1] ))\n    df = df.loc[(df['type']==1)|(df['type']==2)]\n    unique_buys = list(dict.fromkeys( df.aid.tolist()[::-1] ))\n    # RERANK CANDIDATES USING WEIGHTS\n    if len(unique_aids)>=20:\n        weights=np.logspace(0.5,1,len(aids),base=2, endpoint=True)-1\n        aids_temp = Counter() \n        # RERANK BASED ON REPEAT ITEMS AND TYPE OF ITEMS\n        for aid,w,t in zip(aids,weights,types): \n            aids_temp[aid] += w * type_weight_multipliers[t]\n        # RERANK CANDIDATES USING \"BUY2BUY\" CO-VISITATION MATRIX\n        aids3 = list(itertools.chain(*[top_20_buy2buy[aid] for aid in unique_buys if aid in top_20_buy2buy]))\n        for aid in aids3: aids_temp[aid] += 0.1\n        sorted_aids = [k for k,v in aids_temp.most_common(20)]\n        return sorted_aids\n    # USE \"CART ORDER\" CO-VISITATION MATRIX\n    aids2 = list(itertools.chain(*[top_20_buys[aid] for aid in unique_aids if aid in top_20_buys]))\n    # USE \"BUY2BUY\" CO-VISITATION MATRIX\n    aids3 = list(itertools.chain(*[top_20_buy2buy[aid] for aid in unique_buys if aid in top_20_buy2buy]))\n    # RERANK CANDIDATES\n    top_aids2 = [aid2 for aid2, cnt in Counter(aids2+aids3).most_common(20) if aid2 not in unique_aids] \n    result = unique_aids + top_aids2[:20 - len(unique_aids)]\n    # USE TOP20 TEST ORDERS\n    set_result = set(result)\n    return result + [i for i in top_carts[:30] if i not in set_result][:20-len(result)]\n\ndef suggest_carts(df):\n    # User history aids and types\n    aids = df.aid.tolist()\n    types = df.type.tolist()\n    \n    # UNIQUE AIDS AND UNIQUE BUYS\n    unique_aids = list(dict.fromkeys(aids[::-1] ))\n    df = df.loc[(df['type'] == 0)|(df['type'] == 1)]\n    unique_buys = list(dict.fromkeys(df.aid.tolist()[::-1]))\n    \n    # Rerank candidates using weights\n    if len(unique_aids) >= 20:\n        weights=np.logspace(0.5,1,len(aids),base=2, endpoint=True)-1\n        aids_temp = Counter() \n        \n        # Rerank based on repeat items and types of items\n        for aid,w,t in zip(aids,weights,types): \n            aids_temp[aid] += w * type_weight_multipliers[t]\n        \n        # Rerank candidates using\"top_20_carts\" co-visitation matrix\n        aids2 = list(itertools.chain(*[top_20_buys[aid] for aid in unique_buys if aid in top_20_buys]))\n        for aid in aids2: aids_temp[aid] += 0.1\n        sorted_aids = [k for k,v in aids_temp.most_common(20)]\n        return sorted_aids\n    \n    # Use \"cart order\" and \"clicks\" co-visitation matrices\n    aids1 = list(itertools.chain(*[top_20_clicks[aid] for aid in unique_aids if aid in top_20_clicks]))\n    aids2 = list(itertools.chain(*[top_20_buys[aid] for aid in unique_aids if aid in top_20_buys]))\n    \n    # RERANK CANDIDATES\n    top_aids2 = [aid2 for aid2, cnt in Counter(aids1+aids2).most_common(20) if aid2 not in unique_aids] \n    result = unique_aids + top_aids2[:20 - len(unique_aids)]\n    \n    # USE TOP20 TEST ORDERS\n    set_result = set(result)\n    return result + [i for i in top_orders[:30] if i not in set_result][:20-len(result)]","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:41:25.834052Z","iopub.execute_input":"2023-01-23T02:41:25.834517Z","iopub.status.idle":"2023-01-23T02:41:25.945500Z","shell.execute_reply.started":"2023-01-23T02:41:25.834479Z","shell.execute_reply":"2023-01-23T02:41:25.943907Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create Submission CSV\nInferring test data with Pandas groupby is slow. We need to accelerate the following code.","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[]}},{"cell_type":"code","source":"%%time\npred_df_clicks = test_df.sort_values([\"session\", \"ts\"]).groupby([\"session\"]).apply(\n    lambda x: suggest_clicks(x)\n)#grouping all aids of the same session into one and then implement the function in each session\n\npred_df_buys = test_df.sort_values([\"session\", \"ts\"]).groupby([\"session\"]).apply(\n    lambda x: suggest_buys(x)\n)\n\npred_df_carts = test_df.sort_values([\"session\", \"ts\"]).groupby([\"session\"]).apply(\n    lambda x: suggest_carts(x)\n)","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[],"execution":{"iopub.status.busy":"2023-01-23T02:40:17.973583Z","iopub.execute_input":"2023-01-23T02:40:17.973929Z","iopub.status.idle":"2023-01-23T02:40:21.838952Z","shell.execute_reply.started":"2023-01-23T02:40:17.973894Z","shell.execute_reply":"2023-01-23T02:40:21.838009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"clicks_pred_df = pd.DataFrame(pred_df_clicks.add_suffix(\"_clicks\"), columns=[\"labels\"]).reset_index()\norders_pred_df = pd.DataFrame(pred_df_buys.add_suffix(\"_orders\"), columns=[\"labels\"]).reset_index()\ncarts_pred_df = pd.DataFrame(pred_df_carts.add_suffix(\"_carts\"), columns=[\"labels\"]).reset_index()","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[],"execution":{"iopub.status.busy":"2023-01-11T12:47:18.433471Z","iopub.execute_input":"2023-01-11T12:47:18.435397Z","iopub.status.idle":"2023-01-11T12:47:19.625732Z","shell.execute_reply.started":"2023-01-11T12:47:18.435358Z","shell.execute_reply":"2023-01-11T12:47:19.624260Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_df = pd.concat([clicks_pred_df, orders_pred_df, carts_pred_df])\npred_df.columns = [\"session_type\", \"labels\"]\npred_df[\"labels\"] = pred_df.labels.apply(lambda x: \" \".join(map(str,x)))\npred_df.to_csv(\"submission_v16.csv\", index=False)\npred_df.head()","metadata":{"papermill":{"duration":null,"end_time":null,"exception":null,"start_time":null,"status":"pending"},"tags":[],"execution":{"iopub.status.busy":"2023-01-11T12:47:19.627130Z","iopub.status.idle":"2023-01-11T12:47:19.627912Z","shell.execute_reply.started":"2023-01-11T12:47:19.627637Z","shell.execute_reply":"2023-01-11T12:47:19.627664Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Afterwards, I tried to ensemble all the past prediction using this rerank model and has improved the accuracy score to 0.578","metadata":{}}]}