{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":31254,"databundleVersionId":3103714,"sourceType":"competition"},{"sourceId":3618498,"sourceType":"datasetVersion","datasetId":1931827},{"sourceId":94922230,"sourceType":"kernelVersion"}],"dockerImageVersionId":30153,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 52nd Place Solution Notebook\n\nThis notebook is a cleaned version of my final submission.  \nSee [this post](https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion/324076/) for some details about my solution.\n\nThe notebook has minimal code in it - most of the code is imported from my [handmhelpers dataset](https://www.kaggle.com/datasets/jacob34/handmhelpers), which is synced to [this github repo](https://github.com/JacobCP/kaggle-handm-helpers) .  \nSee [this post](https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion/324078) for some details about my code development.  \n\n**Please note:**  \nI plan on continuing to update the github repo, as I try to recreate some of the strategies shared by winning teams.  \nSome of those changes may break the code usage for this notebook.  \nIn order to keep this notebook functional, I will no longer be updating the dataset to reflect the changes made to the repo - it will remain at commit 86c412e902a7692b24e15791322a8dfeb5a761eb","metadata":{}},{"cell_type":"code","source":"%%time\nimport os\nimport sys\nimport copy\nfrom datetime import datetime\nimport gc\nimport pickle as pkl\nimport shelve\n\nimport pandas as pd\nimport numpy as np\nimport cudf\n    \nsys.path.append(\"../input/\")\nfrom handmhelpers import io as h_io, sub as h_sub, cv as h_cv, fe as h_fe\nfrom handmhelpers import modeling as h_modeling, candidates as h_can, pairs as h_pairs","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:17:48.756252Z","iopub.execute_input":"2023-12-25T13:17:48.756589Z","iopub.status.idle":"2023-12-25T13:17:53.323871Z","shell.execute_reply.started":"2023-12-25T13:17:48.756502Z","shell.execute_reply":"2023-12-25T13:17:53.323121Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Load and convert data","metadata":{}},{"cell_type":"code","source":"%%time\n\nc, t, a = h_io.load_data(files=['customers.csv', 'transactions_train.csv', 'articles.csv'])        \n\nindex_to_id_dict_path = h_fe.reduce_customer_id_memory(c, [t])\nt[\"week_number\"] = h_fe.day_week_numbers(t[\"t_dat\"])\nt[\"t_dat\"] = h_fe.day_numbers(t[\"t_dat\"])","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:18:16.610939Z","iopub.execute_input":"2023-12-25T13:18:16.611254Z","iopub.status.idle":"2023-12-25T13:19:09.123292Z","shell.execute_reply.started":"2023-12-25T13:18:16.611219Z","shell.execute_reply":"2023-12-25T13:19:09.122482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Get item pairs","metadata":{}},{"cell_type":"code","source":"%%time\n\npairs_per_item = 5\n\n#  processing of a large dataset of customer transactions to identify significant pairs of articles based on customer buying patterns\n# Top 5 pair for each article(top 5 sản phẩm được mua cùng sản phẩm đang xét)\nweek_number_pairs = {}\nfor week_number in [96, 97, 98, 99, 100, 101, 102, 103, 104]:\n    print(f\"Creating pairs for week number {week_number}\")\n    week_number_pairs[week_number] = h_pairs.create_pairs(\n        t, week_number, pairs_per_item, verbose=False\n    )","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:19:13.633088Z","iopub.execute_input":"2023-12-25T13:19:13.633813Z","iopub.status.idle":"2023-12-25T13:20:23.310949Z","shell.execute_reply.started":"2023-12-25T13:19:13.633780Z","shell.execute_reply":"2023-12-25T13:20:23.310118Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Main retrieval/features function!","metadata":{}},{"cell_type":"code","source":"def create_candidates_with_features_df(t, c, a, customer_batch=None, **kwargs):\n    # splitting cv\n    # split transaction_df into train/validation\n    # use week numbers created already using fe.day_week_numbers() function\n    # label_week: tuần có data được label, cv_param[label_week] = 104, sub_params[label_week] = 105\n    # feature_df: df của các tuần < label_week(periods = kwargs[\"feature_periods\" = 105\")\n    features_df, label_df = h_cv.feature_label_split(\n        t, kwargs[\"label_week\"], kwargs[\"feature_periods\"]\n    )\n    \n    # converting relative day_number\n    # given a pd_or_cudf.series of numbers between 0 and n,\n    # returns new series with n subtracted from each element\n    # New series would be -n, -n+1, ..., -1, 0;\n    features_df[\"t_dat\"] = h_fe.how_many_ago(features_df[\"t_dat\"])\n    features_df[\"week_number\"] = h_fe.how_many_ago(features_df[\"week_number\"])\n    \n    \n    # pull out the cv week\n    # lấy tuần cross-validation(104/105)\n    article_pairs_df = week_number_pairs[kwargs[\"label_week\"]-1]\n    \n    # check if we can limit customers?\n    if len(label_df) > 0:\n        customers = label_df[\"customer_id\"].unique()\n    elif customer_batch is not None:\n        customers = customer_batch\n    else:\n        customers = None\n    \n    ############################################\n    # creating candidates (and adding features)\n    ###########################################\n    \n    features_db = shelve.open(\"features_db\") \n    \n    # creating candidate (and saving features created)\n    # chọn các customer có thực hiện mua hàng trong vòng kwargs[\"ca_num_weeks] = 3 tuần \"\n    # features: customer_id, article_id, df: recent_customer_df sắp xếp giảm dần theo \"số lần mua\" từ trước tới giờ(không phải chỉ 3 tuần)\n    recent_customer_cand, features_db[\"customer_article\"] = (\n        h_can.create_recent_customer_candidates(\n            features_df,\n            kwargs[\"ca_num_weeks\"],\n            customers=customers,\n        )\n    )\n    \n    # clw_num_pair_weeks = 2\n    # trường của article: last_ca_purchase_diff: lần cuối customer mua - lần cuối mua article này\n    #  clw_pairs_df: những article được mua trong khoảng clw_num_pair_weeks = 2 tuần cùng với article đang xét\n    # clw_df = clw_df.query(f\"last_ca_purchase_diff <= {num_weeks * 7 - 1}\").copy()\n    # Sau đấy, merge với articles_pair_df để lấy ra các cột mới của articles_pair_df: ca_count\",\"last_ca_purchase_date\",\"last_ca_purchase_diff\",\"customer_count\",\"percent_customers\",\n    # Chọn ra các pair được mua trên 2 lần\n    # candidate cho article và pair\n    (cust_last_week_cand,\n     cust_last_week_pair_cand,\n     features_db[\"clw\"],\n     features_db[\"clw_pairs\"]) = h_can.create_last_customer_weeks_and_pairs(\n        features_df,\n        article_pairs_df,\n        kwargs[\"clw_num_weeks\"],\n        kwargs[\"clw_num_pair_weeks\"],\n        customers=customers,\n    )\n    \n    # Hier_col: department_no\n    # popular: dua tren % hierachy, sau day moi xet den so luong\n    # cust_hier[\"cust_hier_portion\"] = (\n      #  cust_hier[\"cust_hier_counts\"] / cust_hier[\"total_counts\"]\n        # num_candidates=60\n        # num_articles= 12\n    # Sắp xếp candidate dựa theo độ phổ biến của cái cust_hier này so với toàn bộ sản phẩm nguwofi dùng đã mua, rồi mới đến doanh số bán hàng của sp\n    # từ 60 candidate, chọn ra 12 popular theo sắp xếp nói trên\n    _, features_db[\"popular_articles\"] = h_can.create_popular_article_cand(\n        features_df,\n        c,\n        a,\n        kwargs[\"pa_num_weeks\"],\n        kwargs[\"hier_col\"],\n        num_candidates=kwargs[\"num_recent_candidates\"],\n        num_articles=kwargs[\"num_recent_articles\"],\n        customers=customers,\n    )\n    # 12 articles\n    # age_bucket_can: \n    \"\"\"\n    \"customer_id\": Identifier for the customer.\n    \"article_id\": Identifier for the article.\n    \"age_bucket\": The age bucket to which the customer belongs.\n    \"article_bucket_count\": The count or popularity index of the article within the specified age bucket.\n    \"\"\"\n    age_bucket_can, _, _ = h_can.create_age_bucket_candidates(\n        features_df,\n        c,\n        kwargs[\"num_age_buckets\"],\n        articles=kwargs[\"num_recent_articles\"],\n        customers=customers,\n    )\n    \n    # Tổng hợp toàn bộ candidate lại, loại bỏ duplicate\n    cand = [recent_customer_cand, cust_last_week_cand, cust_last_week_pair_cand, age_bucket_can]\n    cand = cudf.concat(cand).drop_duplicates()\n    cand = cand.sort_values([\"customer_id\", \"article_id\"]).reset_index(drop=True)\n    \n    del recent_customer_cand, cust_last_week_cand, cust_last_week_pair_cand, age_bucket_can\n    \n    # lọc ra các candidate thuộc vào các articles được giao dịch trong tuần trước đấy\n    cand = h_can.filter_candidates(cand, t, **kwargs)\n    \n    # creating other features\n    h_fe.create_cust_hier_features(features_df, a, kwargs[\"hier_cols\"], features_db)\n    h_fe.create_price_features(features_df, features_db)\n    h_fe.create_cust_features(c, features_db)\n    h_fe.create_article_cust_features(features_df, c, features_db)\n    h_fe.create_lag_features(features_df, a, kwargs[\"lag_days\"], features_db)\n    h_fe.create_rebuy_features(features_df, features_db)\n    h_fe.create_cust_t_features(features_df, a, features_db)\n    h_fe.create_art_t_features(features_df, features_db)\n    \n    del features_df\n\n    # another filter at the end, for the ones that didn't get filtered earlier\n    if customers is not None:\n        cand = cand[cand[\"customer_id\"].isin(customers)]\n    \n    # report on recall/precision of candidates\n    if kwargs[\"cv\"]:\n        ground_truth_candidates = label_df[[\"customer_id\", \"article_id\"]].drop_duplicates()\n        h_cv.report_candidates(cand, ground_truth_candidates)\n        del ground_truth_candidates        \n    \n    # adding features to candidates\n    cand_with_f_df = h_can.add_features_to_candidates(\n        cand, features_db, c, a\n    )\n    \n    # manually adding article features (couldn't use shelve for some reason)\n    for article_col in kwargs[\"article_columns\"]:\n        art_col_map = a.set_index(\"article_id\")[article_col]\n        cand_with_f_df[article_col] = cand_with_f_df[\"article_id\"].map(art_col_map)\n    \n    # limiting features\n    if kwargs[\"selected_features\"] is not None:\n        cand_with_f_df = cand_with_f_df[\n            [\"customer_id\", \"article_id\"] + kwargs[\"selected_features\"]\n        ]\n        \n    features_db.close()\n    os.remove(\"features_db.bak\"), os.remove(\"features_db.dir\"), os.remove(\"features_db.dat\")\n    \n    assert len(cand) == len(cand_with_f_df), \"seem to have duplicates in the feature dfs\"\n    del cand\n    \n    return cand_with_f_df, label_df","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:20:27.032431Z","iopub.execute_input":"2023-12-25T13:20:27.032703Z","iopub.status.idle":"2023-12-25T13:20:27.056936Z","shell.execute_reply.started":"2023-12-25T13:20:27.032673Z","shell.execute_reply":"2023-12-25T13:20:27.056082Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def calculate_model_score(ids_df, preds, truth_df):\n    predictions = h_modeling.create_predictions(ids_df, preds)\n    true_labels = h_cv.ground_truth(truth_df).set_index(\"customer_id\")[\"prediction\"]\n    score = round(h_cv.comp_average_precision(true_labels, predictions),5)\n    \n    return score","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:20:51.002485Z","iopub.execute_input":"2023-12-25T13:20:51.003282Z","iopub.status.idle":"2023-12-25T13:20:51.008363Z","shell.execute_reply.started":"2023-12-25T13:20:51.003235Z","shell.execute_reply":"2023-12-25T13:20:51.007430Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Parameters - one place for all!","metadata":{}},{"cell_type":"code","source":"cv_params = {\n    \"cv\": True,\n    \"feature_periods\": 105,\n    \"label_week\": 104,\n    \"index_to_id_dict_path\": index_to_id_dict_path,\n    \"pairs_file_version\": \"_v3_5_ex\",\n    \"num_recent_candidates\": 36,\n    \"num_recent_articles\": 12,\n    \"hier_col\": \"department_no\",\n    \"ca_num_weeks\": 3,\n    \"clw_num_weeks\": 12,\n    \"clw_num_pair_weeks\": 2,\n    \"pa_num_weeks\": 1,\n    \"num_age_buckets\": 4,\n    \"filter_recent_art_weeks\": 1,\n    \"filter_num_articles\": None,\n    \"lag_days\": [1, 3, 14, 30],\n    \"article_columns\": [\"index_code\"],\n    \"hier_cols\": [\n        \"department_no\", \"section_no\", \"index_group_no\", \"index_code\",\n        \"product_type_no\", \"product_group_name\"\n    ],\n    \"selected_features\": None,\n    \"lgbm_params\": {\"n_estimators\": 200, \"num_leaves\": 20},\n    \"log_evaluation\": 10,\n    \"early_stopping\": 20,\n    \"eval_at\": 12,\n    \"save_model\": True,\n    \"num_concats\": 5,\n}\nsub_params = {\n    \"cv\": False,\n    \"feature_periods\": 105,\n    \"label_week\": 105,\n    \"index_to_id_dict_path\": index_to_id_dict_path,\n    \"pairs_file_version\": \"_v3_5_ex\",\n    \"num_recent_candidates\": 60,\n    \"num_recent_articles\": 12,\n    \"hier_col\": \"department_no\",\n    \"ca_num_weeks\": 3,\n    \"clw_num_weeks\": 12,\n    \"clw_num_pair_weeks\": 2,\n    \"pa_num_weeks\": 1,\n    \"num_age_buckets\": 4,\n    \"filter_recent_art_weeks\": 1,\n    \"filter_num_articles\": None,\n    \"lag_days\": [1, 3, 14, 30],\n    \"article_columns\": [\"index_code\"],\n    \"hier_cols\": [\n        \"department_no\", \"section_no\", \"index_group_no\", \"index_code\",\n        \"product_type_no\", \"product_group_name\"\n    ],\n    \"selected_features\": None,\n    \"lgbm_params\": {\n        \"n_estimators\": 150,\n        \"num_leaves\": 20,    \n    },\n    \"log_evaluation\": 10,\n    \"eval_at\": 12,\n    \"prediction_models\": [\"model_104\", \"model_105\"],\n    \"save_model\": True,\n    \"num_concats\": 5,\n}","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:22:43.249084Z","iopub.execute_input":"2023-12-25T13:22:43.249853Z","iopub.status.idle":"2023-12-25T13:22:43.260390Z","shell.execute_reply.started":"2023-12-25T13:22:43.249818Z","shell.execute_reply":"2023-12-25T13:22:43.259632Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cand_features_func = create_candidates_with_features_df\nscoring_func = calculate_model_score","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:22:47.299394Z","iopub.execute_input":"2023-12-25T13:22:47.299679Z","iopub.status.idle":"2023-12-25T13:22:47.303595Z","shell.execute_reply.started":"2023-12-25T13:22:47.299639Z","shell.execute_reply":"2023-12-25T13:22:47.302732Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ncv_weeks = [104]\nresults = h_modeling.run_all_cvs(\n    t, c, a, cand_features_func, scoring_func, \n    cv_weeks=cv_weeks, **cv_params\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:22:48.713721Z","iopub.execute_input":"2023-12-25T13:22:48.714002Z","iopub.status.idle":"2023-12-25T13:26:04.962737Z","shell.execute_reply.started":"2023-12-25T13:22:48.713972Z","shell.execute_reply":"2023-12-25T13:26:04.961955Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ngc.collect()\nh_modeling.full_sub_train_run(t, c, a, cand_features_func, scoring_func, **sub_params)\npredictions = h_modeling.full_sub_predict_run(\n    t, c, a, cand_features_func, **sub_params\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:32:09.776011Z","iopub.execute_input":"2023-12-25T13:32:09.776696Z","iopub.status.idle":"2023-12-25T13:40:08.714574Z","shell.execute_reply.started":"2023-12-25T13:32:09.776661Z","shell.execute_reply":"2023-12-25T13:40:08.713828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = h_sub.create_sub(c[\"customer_id\"], predictions, index_to_id_dict_path)\nsub.to_csv('dev_submission.csv', index=False)\n\ndisplay(sub.head())\nprint(sub.shape)","metadata":{"execution":{"iopub.status.busy":"2023-12-25T13:40:20.998658Z","iopub.execute_input":"2023-12-25T13:40:20.998957Z","iopub.status.idle":"2023-12-25T13:42:15.680589Z","shell.execute_reply.started":"2023-12-25T13:40:20.998924Z","shell.execute_reply":"2023-12-25T13:42:15.679879Z"},"trusted":true},"execution_count":null,"outputs":[]}]}