{"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":"code","source":"import pandas as pd, numpy as np\nfrom tqdm.notebook import tqdm\nimport os, sys, pickle, glob, gc\nfrom collections import Counter,defaultdict\nimport cudf, itertools\nimport pyarrow.parquet as pq\nimport json","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-12-22T03:48:14.799837Z","iopub.execute_input":"2022-12-22T03:48:14.800766Z","iopub.status.idle":"2022-12-22T03:48:18.071471Z","shell.execute_reply.started":"2022-12-22T03:48:14.800662Z","shell.execute_reply":"2022-12-22T03:48:18.070297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\nVER = 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}.')","metadata":{"execution":{"iopub.status.busy":"2022-12-22T03:48:18.073555Z","iopub.execute_input":"2022-12-22T03:48:18.073914Z","iopub.status.idle":"2022-12-22T03:49:17.945558Z","shell.execute_reply.started":"2022-12-22T03:48:18.073878Z","shell.execute_reply":"2022-12-22T03:49:17.944447Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ntype_weight = {0:1, 1:6, 2:3}\nVER = 5\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') # 每个session笛卡尔积\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','type_y']].drop_duplicates(['session', 'aid_x', 'aid_y'])\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<15].drop('n',axis=1)\n    # SAVE PART TO DISK (convert to pandas first uses less memory)\n    tmp.to_pandas().to_parquet(f'top_15_carts_orders_v{VER}_{PART}.pqt')","metadata":{"execution":{"iopub.status.busy":"2022-12-22T03:49:17.947377Z","iopub.execute_input":"2022-12-22T03:49:17.947823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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()< 14 * 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'])\n            df['wgt'] = 1\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<15].drop('n',axis=1)\n    # SAVE PART TO DISK (convert to pandas first uses less memory)\n    tmp.to_pandas().to_parquet(f'top_15_buy2buy_v{VER}_{PART}.pqt')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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['wgt'] = 1 + 3*(df.ts_x - 1659304800)/(1662328791-1659304800)\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<20].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":{"trusted":true},"execution_count":null,"outputs":[]}]}