def main(params: dict, output_dir: str): import mlflow print("start params={}".format(params)) logger = get_logger() df = pd.read_pickle("../input/riiid-test-answer-prediction/train_merged.pickle") # df = pd.read_pickle("../input/riiid-test-answer-prediction/split10/train_0.pickle").sort_values(["user_id", "timestamp"]).reset_index(drop=True) if is_debug: df = df.head(30000) df["prior_question_had_explanation"] = df["prior_question_had_explanation"].fillna(-1) column_config = { ("content_id", "content_type_id"): {"type": "category"}, "user_answer": {"type": "leakage_feature"}, "answered_correctly": {"type": "leakage_feature"}, "part": {"type": "category"}, "prior_question_elapsed_time_bin300": {"type": "category"}, "duration_previous_content_bin300": {"type": "category"}, "prior_question_had_explanation": {"type": "category"}, "rating_diff_content_user_id": {"type": "numeric"} } with open(f"{output_dir}/transformer_param.json", "w") as f: json.dump(params, f) if is_make_feature_factory: # feature factory feature_factory_dict = {"user_id": {}} feature_factory_dict["user_id"]["DurationPreviousContent"] = DurationPreviousContent(is_partial_fit=True) feature_factory_dict["user_id"]["ElapsedTimeBinningEncoder"] = ElapsedTimeBinningEncoder() feature_factory_dict["user_id"]["UserContentRateEncoder"] = UserContentRateEncoder(rate_func="elo", column="user_id") feature_factory_manager = FeatureFactoryManager(feature_factory_dict=feature_factory_dict, logger=logger, split_num=1, model_id=model_id, load_feature=not is_debug, save_feature=not is_debug) ff_for_transformer = FeatureFactoryForTransformer(column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) ff_for_transformer.make_dict(df=df) if is_debug: df = df.head(10000) df = df.sort_values(["user_id", "timestamp"]).reset_index(drop=True) feature_factory_manager.fit(df) df = feature_factory_manager.all_predict(df) for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = None feature_factory_manager.logger = None with open(f"{output_dir}/feature_factory_manager.pickle", "wb") as f: pickle.dump(feature_factory_manager, f) ff_for_transformer.fit(df) ff_for_transformer.logger = None with open(f"{output_dir}/feature_factory_manager_for_transformer.pickle", "wb") as f: pickle.dump(ff_for_transformer, f)
def main(params: dict, output_dir: str): import mlflow print("start params={}".format(params)) model_id = "train_0" logger = get_logger() # df = pd.read_pickle("../input/riiid-test-answer-prediction/train_merged.pickle") df = pd.read_pickle( "../input/riiid-test-answer-prediction/split10/train_0.pickle" ).sort_values(["user_id", "timestamp"]).reset_index(drop=True) if is_debug: df = df.head(30000) df["prior_question_had_explanation"] = df[ "prior_question_had_explanation"].fillna(-1) df["answered_correctly"] = df["answered_correctly"].replace(-1, np.nan) column_config = { ("content_id", "content_type_id"): { "type": "category" }, "user_answer": { "type": "leakage_feature" }, "answered_correctly": { "type": "leakage_feature" }, "part": { "type": "category" }, "prior_question_elapsed_time_bin300": { "type": "category" }, "duration_previous_content_bin300": { "type": "category" }, "prior_question_had_explanation": { "type": "category" }, "rating_diff_content_user_id": { "type": "numeric" }, "task_container_id_bin300": { "type": "category" }, "previous_answer_index_content_id": { "type": "category" }, "previous_answer_content_id": { "type": "category" }, "timediff-elapsedtime_bin500": { "type": "category" }, "timedelta_log10": { "type": "category" } } if not load_pickle or is_debug: feature_factory_dict = {"user_id": {}} feature_factory_dict["user_id"][ "DurationPreviousContent"] = DurationPreviousContent( is_partial_fit=True) feature_factory_dict["user_id"][ "ElapsedTimeBinningEncoder"] = ElapsedTimeBinningEncoder() feature_factory_dict["user_id"][ "UserContentRateEncoder"] = UserContentRateEncoder( rate_func="elo", column="user_id") feature_factory_dict["user_id"]["PreviousAnswer2"] = PreviousAnswer2( groupby="user_id", column="content_id", is_debug=is_debug, model_id=model_id, n=300) feature_factory_dict["user_id"][ "StudyTermEncoder2"] = StudyTermEncoder2(is_partial_fit=True) feature_factory_dict["user_id"][ f"MeanAggregatorStudyTimebyUserId"] = MeanAggregator( column="user_id", agg_column="study_time", remove_now=False) feature_factory_dict["user_id"][ "ElapsedTimeMeanByContentIdEncoder"] = ElapsedTimeMeanByContentIdEncoder( ) feature_factory_dict["post"] = { "DurationFeaturePostProcess": DurationFeaturePostProcess() } feature_factory_manager = FeatureFactoryManager( feature_factory_dict=feature_factory_dict, logger=logger, split_num=1, model_id=model_id, load_feature=not is_debug, save_feature=not is_debug) print("all_predict") df = feature_factory_manager.all_predict(df) def f(x): x = x // 1000 if x < -100: return -100 if x > 400: return 400 return x df["task_container_id_bin300"] = [ x if x < 300 else 300 for x in df["task_container_id"] ] df["timediff-elapsedtime_bin500"] = [ f(x) for x in df["timediff-elapsedtime"].values ] df["timedelta_log10"] = np.log10( df["duration_previous_content"].values) df["timedelta_log10"] = df["timedelta_log10"].replace( -np.inf, -1).replace(np.inf, -1).fillna(-1).astype("int8") df = df[[ "user_id", "content_id", "content_type_id", "part", "user_answer", "answered_correctly", "prior_question_elapsed_time_bin300", "duration_previous_content_bin300", "prior_question_had_explanation", "rating_diff_content_user_id", "task_container_id_bin300", "previous_answer_index_content_id", "previous_answer_content_id", "row_id", "timediff-elapsedtime_bin500", "timedelta_log10" ]] print(df.head(10)) print("data preprocess") ff_for_transformer = FeatureFactoryForTransformer( column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) ff_for_transformer.make_dict(df=df) n_skill = len(ff_for_transformer.embbed_dict[("content_id", "content_type_id")]) if not load_pickle or is_debug: df_val_row = pd.read_feather( "../../riiid_takoi/notebook/fe/validation_row_id.feather").head( len(df)) if is_debug: df_val_row = df_val_row.head(3000) df_val_row["is_val"] = 1 df = pd.merge(df, df_val_row, how="left", on="row_id") df["is_val"] = df["is_val"].fillna(0) print(df["is_val"].value_counts()) w_df = df[df["is_val"] == 0] w_df["group"] = ( w_df.groupby("user_id")["user_id"].transform("count") - w_df.groupby("user_id").cumcount()) // params["max_seq"] w_df["user_id"] = w_df["user_id"].astype( str) + "_" + w_df["group"].astype(str) group = ff_for_transformer.all_predict(w_df) dataset_train = SAKTDataset(group, n_skill=n_skill, max_seq=params["max_seq"]) del w_df gc.collect() ff_for_transformer = FeatureFactoryForTransformer( column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) if not load_pickle or is_debug: group = ff_for_transformer.all_predict(df[df["content_type_id"] == 0]) dataset_val = SAKTDataset(group, is_test=True, n_skill=n_skill, max_seq=params["max_seq"]) os.makedirs("../input/feature_engineering/model256", exist_ok=True) if not is_debug and not load_pickle: with open(f"../input/feature_engineering/model256/train.pickle", "wb") as f: pickle.dump(dataset_train, f) with open(f"../input/feature_engineering/model256/val.pickle", "wb") as f: pickle.dump(dataset_val, f) if not is_debug and load_pickle: with open(f"../input/feature_engineering/model256/train.pickle", "rb") as f: dataset_train = pickle.load(f) with open(f"../input/feature_engineering/model256/val.pickle", "rb") as f: dataset_val = pickle.load(f) print("loaded!") dataloader_train = DataLoader(dataset_train, batch_size=params["batch_size"], shuffle=True) dataloader_val = DataLoader(dataset_val, batch_size=params["batch_size"], shuffle=False) model = SAKTModel(n_skill, embed_dim=params["embed_dim"], max_seq=params["max_seq"], dropout=dropout, cont_emb=params["cont_emb"]) param_optimizer = list(model.named_parameters()) no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight'] optimizer_grouped_parameters = [{ 'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01 }, { 'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0 }] optimizer = AdamW( optimizer_grouped_parameters, lr=params["lr"], weight_decay=0.01, ) num_train_optimization_steps = int(len(dataloader_train) * 20) scheduler = get_linear_schedule_with_warmup( optimizer, num_warmup_steps=params["num_warmup_steps"], num_training_steps=num_train_optimization_steps) criterion = nn.BCEWithLogitsLoss() model.to(device) criterion.to(device) for epoch in range(epochs): loss, acc, auc, auc_val = train_epoch(model, dataloader_train, dataloader_val, optimizer, criterion, scheduler, epoch, device) print("epoch - {} train_loss - {:.3f} auc - {:.4f} auc-val: {:.4f}". format(epoch, loss, auc, auc_val)) preds = [] labels = [] with torch.no_grad(): for item in tqdm(dataloader_val): label = item["label"].to(device).float() output = model(item, device) preds.extend(torch.nn.Sigmoid()( output[:, -1]).view(-1).data.cpu().numpy().tolist()) labels.extend(label[:, -1].view(-1).data.cpu().numpy().tolist()) auc_transformer = roc_auc_score(labels, preds) print("single transformer: {:.4f}".format(auc_transformer)) df_oof = pd.DataFrame() # df_oof["row_id"] = df.loc[val_idx].index print(len(dataloader_val)) print(len(preds)) df_oof["predict"] = preds df_oof["target"] = labels df_oof.to_csv(f"{output_dir}/transformers1.csv", index=False) """ df_oof2 = pd.read_csv("../output/ex_237/20201213110353/oof_train_0_lgbm.csv") df_oof2.columns = ["row_id", "predict_lgbm", "target"] df_oof2 = pd.merge(df_oof, df_oof2, how="inner") auc_lgbm = roc_auc_score(df_oof2["target"].values, df_oof2["predict_lgbm"].values) print("lgbm: {:.4f}".format(auc_lgbm)) print("ensemble") max_auc = 0 max_nn_ratio = 0 for r in np.arange(0, 1.05, 0.05): auc = roc_auc_score(df_oof2["target"].values, df_oof2["predict_lgbm"].values*(1-r) + df_oof2["predict"].values*r) print("[nn_ratio: {:.2f}] AUC: {:.4f}".format(r, auc)) if max_auc < auc: max_auc = auc max_nn_ratio = r print(len(df_oof2)) """ if not is_debug: mlflow.start_run(experiment_id=10, run_name=os.path.basename(__file__)) for key, value in params.items(): mlflow.log_param(key, value) mlflow.log_metric("auc_val", auc_transformer) mlflow.end_run() torch.save(model.state_dict(), f"{output_dir}/transformers.pth") del model torch.cuda.empty_cache() with open(f"{output_dir}/transformer_param.json", "w") as f: json.dump(params, f) if is_make_feature_factory: # feature factory feature_factory_dict = {"user_id": {}} feature_factory_dict["user_id"][ "DurationPreviousContent"] = DurationPreviousContent( is_partial_fit=True) feature_factory_dict["user_id"][ "ElapsedTimeBinningEncoder"] = ElapsedTimeBinningEncoder() feature_factory_manager = FeatureFactoryManager( feature_factory_dict=feature_factory_dict, logger=logger, split_num=1, model_id="all", load_feature=not is_debug, save_feature=not is_debug) ff_for_transformer = FeatureFactoryForTransformer( column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) df = pd.read_pickle( "../input/riiid-test-answer-prediction/train_merged.pickle") if is_debug: df = df.head(10000) df = df.sort_values(["user_id", "timestamp"]).reset_index(drop=True) feature_factory_manager.fit(df) df = feature_factory_manager.all_predict(df) for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = None feature_factory_manager.logger = None with open(f"{output_dir}/feature_factory_manager.pickle", "wb") as f: pickle.dump(feature_factory_manager, f) ff_for_transformer.fit(df) ff_for_transformer.logger = None with open( f"{output_dir}/feature_factory_manager_for_transformer.pickle", "wb") as f: pickle.dump(ff_for_transformer, f)
def main(params: dict, output_dir: str): import mlflow print("start params={}".format(params)) logger = get_logger() df = pd.read_pickle("../input/riiid-test-answer-prediction/train_merged.pickle") # df = pd.read_pickle("../input/riiid-test-answer-prediction/split10/train_0.pickle").sort_values(["user_id", "timestamp"]).reset_index(drop=True) if is_debug: df = df.head(30000) df["prior_question_had_explanation"] = df["prior_question_had_explanation"].fillna(-1) column_config = { ("content_id", "content_type_id"): {"type": "category"}, "user_answer": {"type": "category"}, "part": {"type": "category"}, "prior_question_elapsed_time_bin300": {"type": "category"}, "duration_previous_content_bin300": {"type": "category"}, "prior_question_had_explanation": {"type": "category"}, } if not load_pickle or is_debug: feature_factory_dict = {"user_id": {}} feature_factory_dict["user_id"]["DurationPreviousContent"] = DurationPreviousContent() feature_factory_dict["user_id"]["ElapsedTimeBinningEncoder"] = ElapsedTimeBinningEncoder() feature_factory_manager = FeatureFactoryManager(feature_factory_dict=feature_factory_dict, logger=logger, split_num=1, model_id=model_id, load_feature=not is_debug, save_feature=not is_debug) print("all_predict") df = feature_factory_manager.all_predict(df) df = df[["user_id", "content_id", "content_type_id", "part", "user_answer", "answered_correctly", "prior_question_elapsed_time_bin300", "duration_previous_content_bin300", "prior_question_had_explanation"]].replace(-99, -1) print(df.head(10)) print("data preprocess") train_idx = [] val_idx = [] np.random.seed(0) for _, w_df in df[df["content_type_id"] == 0].groupby("user_id"): if np.random.random() < 0.01: # all val val_idx.extend(w_df.index.tolist()) else: train_num = int(len(w_df) * 0.95) train_idx.extend(w_df[:train_num].index.tolist()) val_idx.extend(w_df[train_num:].index.tolist()) ff_for_transformer = FeatureFactoryForTransformer(column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) ff_for_transformer.make_dict(df=df) n_skill = len(ff_for_transformer.embbed_dict[("content_id", "content_type_id")]) if not load_pickle or is_debug: df["is_val"] = 0 df["is_val"].loc[val_idx] = 1 w_df = df[df["is_val"] == 0] w_df["group"] = (w_df.groupby("user_id")["user_id"].transform("count") - w_df.groupby("user_id").cumcount()) // params["max_seq"] w_df["user_id"] = w_df["user_id"].astype(str) + "_" + w_df["group"].astype(str) group = ff_for_transformer.all_predict(w_df) dataset_train = SAKTDataset(group, n_skill=n_skill, max_seq=params["max_seq"]) del w_df gc.collect() ff_for_transformer = FeatureFactoryForTransformer(column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) if not load_pickle or is_debug: group = ff_for_transformer.all_predict(df[df["content_type_id"] == 0]) dataset_val = SAKTDataset(group, is_test=True, n_skill=n_skill, max_seq=params["max_seq"]) os.makedirs("../input/feature_engineering/model106_all", exist_ok=True) if not is_debug and not load_pickle: with open(f"../input/feature_engineering/model106_all/train.pickle", "wb") as f: pickle.dump(dataset_train, f) with open(f"../input/feature_engineering/model106_all/val.pickle", "wb") as f: pickle.dump(dataset_val, f) if not is_debug and load_pickle: with open(f"../input/feature_engineering/model106_all/train.pickle", "rb") as f: dataset_train = pickle.load(f) with open(f"../input/feature_engineering/model106_all/val.pickle", "rb") as f: dataset_val = pickle.load(f) print("loaded!") dataloader_train = DataLoader(dataset_train, batch_size=params["batch_size"], shuffle=True, num_workers=1) dataloader_val = DataLoader(dataset_val, batch_size=params["batch_size"], shuffle=False, num_workers=1) model = SAKTModel(n_skill, embed_dim=params["embed_dim"], max_seq=params["max_seq"], dropout=dropout) param_optimizer = list(model.named_parameters()) no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight'] optimizer_grouped_parameters = [ {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01}, {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0} ] optimizer = AdamW(optimizer_grouped_parameters, lr=params["lr"], weight_decay=0.01, ) num_train_optimization_steps = int(len(dataloader_train) * epochs) scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=params["num_warmup_steps"], num_training_steps=num_train_optimization_steps) criterion = nn.BCEWithLogitsLoss() model.to(device) criterion.to(device) for epoch in range(epochs): loss, acc, auc, auc_val = train_epoch(model, dataloader_train, dataloader_val, optimizer, criterion, scheduler, device) print("epoch - {} train_loss - {:.3f} auc - {:.4f} auc-val: {:.4f}".format(epoch, loss, auc, auc_val)) preds = [] labels = [] with torch.no_grad(): for item in tqdm(dataloader_val): x = item["x"].to(device).long() target_id = item["target_id"].to(device).long() part = item["part"].to(device).long() label = item["label"].to(device).float() elapsed_time = item["elapsed_time"].to(device).long() duration_previous_content = item["duration_previous_content"].to(device).long() prior_question_had_explanation = item["prior_q"].to(device).long() user_answer = item["user_answer"].to(device).long() output = model(x, target_id, part, elapsed_time, duration_previous_content, prior_question_had_explanation, user_answer) preds.extend(torch.nn.Sigmoid()(output[:, -1]).view(-1).data.cpu().numpy().tolist()) labels.extend(label[:, -1].view(-1).data.cpu().numpy().tolist()) auc_transformer = roc_auc_score(labels, preds) print("single transformer: {:.4f}".format(auc_transformer)) df_oof = pd.DataFrame() # df_oof["row_id"] = df.loc[val_idx].index print(len(dataloader_val)) print(len(preds)) df_oof["predict"] = preds df_oof["target"] = labels df_oof.to_csv(f"{output_dir}/transformers1.csv", index=False) """ df_oof2 = pd.read_csv("../output/ex_237/20201213110353/oof_train_0_lgbm.csv") df_oof2.columns = ["row_id", "predict_lgbm", "target"] df_oof2 = pd.merge(df_oof, df_oof2, how="inner") auc_lgbm = roc_auc_score(df_oof2["target"].values, df_oof2["predict_lgbm"].values) print("lgbm: {:.4f}".format(auc_lgbm)) print("ensemble") max_auc = 0 max_nn_ratio = 0 for r in np.arange(0, 1.05, 0.05): auc = roc_auc_score(df_oof2["target"].values, df_oof2["predict_lgbm"].values*(1-r) + df_oof2["predict"].values*r) print("[nn_ratio: {:.2f}] AUC: {:.4f}".format(r, auc)) if max_auc < auc: max_auc = auc max_nn_ratio = r print(len(df_oof2)) """ if not is_debug: mlflow.start_run(experiment_id=10, run_name=os.path.basename(__file__)) for key, value in params.items(): mlflow.log_param(key, value) mlflow.log_metric("auc_val", auc_transformer) mlflow.end_run() torch.save(model.state_dict(), f"{output_dir}/transformers.pth") del model torch.cuda.empty_cache() with open(f"{output_dir}/transformer_param.json", "w") as f: json.dump(params, f) if is_make_feature_factory: # feature factory feature_factory_dict = {"user_id": {}} feature_factory_dict["user_id"]["DurationPreviousContent"] = DurationPreviousContent(is_partial_fit=True) feature_factory_dict["user_id"]["ElapsedTimeBinningEncoder"] = ElapsedTimeBinningEncoder() feature_factory_manager = FeatureFactoryManager(feature_factory_dict=feature_factory_dict, logger=logger, split_num=1, model_id="all", load_feature=not is_debug, save_feature=not is_debug) ff_for_transformer = FeatureFactoryForTransformer(column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) df = pd.read_pickle("../input/riiid-test-answer-prediction/train_merged.pickle") if is_debug: df = df.head(10000) df = df.sort_values(["user_id", "timestamp"]).reset_index(drop=True) feature_factory_manager.fit(df) df = feature_factory_manager.all_predict(df) for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = None feature_factory_manager.logger = None with open(f"{output_dir}/feature_factory_manager.pickle", "wb") as f: pickle.dump(feature_factory_manager, f) ff_for_transformer.fit(df) ff_for_transformer.logger = None with open(f"{output_dir}/feature_factory_manager_for_transformer.pickle", "wb") as f: pickle.dump(ff_for_transformer, f)
def main(params: dict, output_dir: str): import mlflow print("start params={}".format(params)) model_id = "all" logger = get_logger() column_config = { ("content_id", "content_type_id"): {"type": "category", "dtype": np.int16}, "user_answer": {"type": "leakage_feature", "dtype": np.int8}, "answered_correctly": {"type": "leakage_feature", "dtype": np.int8}, "part": {"type": "category", "dtype": np.int8}, "prior_question_elapsed_time_bin300": {"type": "category", "dtype": np.int16}, "duration_previous_content_bin300": {"type": "category", "dtype": np.int16}, "prior_question_had_explanation": {"type": "category", "dtype": np.int8}, "rating_diff_content_user_id": {"type": "numeric", "dtype": np.float16}, "task_container_id_bin300": {"type": "category", "dtype": np.int16}, "previous_answer_index_content_id": {"type": "category", "dtype": np.int16}, "previous_answer_content_id": {"type": "category", "dtype": np.int8}, "timediff-elapsedtime_bin500": {"type": "category", "dtype": np.int16} } if is_make_feature_factory: # feature factory feature_factory_dict = {"user_id": {}} feature_factory_dict["user_id"]["DurationPreviousContent"] = DurationPreviousContent(is_partial_fit=True) feature_factory_dict["user_id"]["ElapsedTimeBinningEncoder"] = ElapsedTimeBinningEncoder() feature_factory_dict["user_id"]["UserContentRateEncoder"] = UserContentRateEncoder(rate_func="elo", column="user_id") feature_factory_dict["user_id"]["PreviousAnswer2"] = PreviousAnswer2(groupby="user_id", column="content_id", is_debug=is_debug, model_id=model_id, n=300) feature_factory_dict["user_id"]["StudyTermEncoder2"] = StudyTermEncoder2(is_partial_fit=True) feature_factory_dict["user_id"][f"MeanAggregatorStudyTimebyUserId"] = MeanAggregator(column="user_id", agg_column="study_time", remove_now=False) feature_factory_dict["user_id"]["ElapsedTimeMeanByContentIdEncoder"] = ElapsedTimeMeanByContentIdEncoder() feature_factory_dict["post"] = { "DurationFeaturePostProcess": DurationFeaturePostProcess() } feature_factory_manager = FeatureFactoryManager(feature_factory_dict=feature_factory_dict, logger=logger, split_num=1, model_id="all", load_feature=not is_debug, save_feature=not is_debug) ff_for_transformer = FeatureFactoryForTransformer(column_config=column_config, dict_path="../feature_engineering/", sequence_length=params["max_seq"], logger=logger) df = pd.read_pickle("../input/riiid-test-answer-prediction/train_merged.pickle") df["prior_question_had_explanation"] = df["prior_question_had_explanation"].fillna(-1) df["answered_correctly"] = df["answered_correctly"].replace(-1, np.nan) if is_debug: df = df.head(10000) df = df.sort_values(["user_id", "timestamp"]).reset_index(drop=True) ff_for_transformer.make_dict(df=df) feature_factory_manager.fit(df) df = feature_factory_manager.all_predict(df) def f(x): x = x // 1000 if x < -90: return -90 if x > 90: return 90 return x df["task_container_id_bin300"] = [x if x < 300 else 300 for x in df["task_container_id"].values] df["timediff-elapsedtime_bin500"] = [f(x) for x in df["timediff-elapsedtime"].values] df = df[["user_id", "content_id", "content_type_id", "part", "user_answer", "answered_correctly", "prior_question_elapsed_time_bin300", "duration_previous_content_bin300", "prior_question_had_explanation", "rating_diff_content_user_id", "task_container_id_bin300", "previous_answer_index_content_id", "previous_answer_content_id", "row_id", "timediff-elapsedtime_bin500"]] for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = None feature_factory_manager.logger = None with open(f"{output_dir}/feature_factory_manager.pickle", "wb") as f: pickle.dump(feature_factory_manager, f) ff_for_transformer.fit(df) ff_for_transformer.logger = None with open(f"{output_dir}/feature_factory_manager_for_transformer.pickle", "wb") as f: pickle.dump(ff_for_transformer, f)
def run(debug, model_dir, kaggle=False): if kaggle: files_dir = "/kaggle/input/riiid-split10/*.pickle" else: files_dir = "../input/riiid-test-answer-prediction/split10_base/*.pickle" logger = get_logger() # environment env = riiideducation.make_env() df_question = pd.read_csv( "../input/riiid-test-answer-prediction/questions.csv", dtype={ "bundle_id": "int32", "question_id": "int32", "correct_answer": "int8", "part": "int8" }) df_lecture = pd.read_csv( "../input/riiid-test-answer-prediction/lectures.csv", dtype={ "lecture_id": "int32", "tag": "int16", "part": "int8" }) # model loading models = [] for model_path in glob.glob(f"{model_dir}/*model*.pickle"): with open(model_path, "rb") as f: models.append(pickle.load(f)) # data preprocessing logger = get_logger() feature_factory_dict = {} feature_factory_dict["tags"] = {"TagsSeparator": TagsSeparator()} for column in [ "content_id", "user_id", "part", "prior_question_had_explanation", "tags1", "tags2", ("user_id", "prior_question_had_explanation"), ("user_id", "part") ]: is_partial_fit = (column == "content_id" or column == "user_id") if type(column) == str: feature_factory_dict[column] = { "CountEncoder": CountEncoder(column=column, is_partial_fit=is_partial_fit), "TargetEncoder": TargetEncoder(column=column, is_partial_fit=is_partial_fit) } else: feature_factory_dict[column] = { "CountEncoder": CountEncoder(column=list(column), is_partial_fit=is_partial_fit), "TargetEncoder": TargetEncoder(column=list(column), is_partial_fit=is_partial_fit) } feature_factory_dict["user_id"][ "ShiftDiffEncoderTimestamp"] = ShiftDiffEncoder(groupby="user_id", column="timestamp", is_partial_fit=True) feature_factory_dict["user_id"][ "ShiftDiffEncoderContentId"] = ShiftDiffEncoder(groupby="user_id", column="content_id") for column in ["user_id", "content_id"]: feature_factory_dict[column][ f"MeanAggregatorPriorQuestionElapsedTimeby{column}"] = MeanAggregator( column=column, agg_column="prior_question_elapsed_time", remove_now=True) feature_factory_dict["user_id"][ "UserLevelEncoder2ContentId"] = UserLevelEncoder2( vs_column="content_id") feature_factory_dict["user_id"][ "UserCountBinningEncoder"] = UserCountBinningEncoder( is_partial_fit=True) feature_factory_dict["user_count_bin"] = {} feature_factory_dict["user_count_bin"]["CountEncoder"] = CountEncoder( column="user_count_bin") feature_factory_dict["user_count_bin"]["TargetEncoder"] = TargetEncoder( column="user_count_bin") feature_factory_dict[("user_id", "user_count_bin")] = { "CountEncoder": CountEncoder(column=["user_id", "user_count_bin"]), "TargetEncoder": TargetEncoder(column=["user_id", "user_count_bin"]) } feature_factory_dict[("content_id", "user_count_bin")] = { "CountEncoder": CountEncoder(column=["content_id", "user_count_bin"]), "TargetEncoder": TargetEncoder(column=["content_id", "user_count_bin"]) } feature_factory_dict["user_id"][ "CategoryLevelEncoderPart"] = CategoryLevelEncoder( groupby_column="user_id", agg_column="part", categories=[1, 2, 3, 4, 5, 6, 7]) feature_factory_dict["user_count_bin"]["CategoryLevelEncoderUserCountBin"] = \ CategoryLevelEncoder(groupby_column="user_id", agg_column="user_count_bin", categories=[0, 1, 2, 3, 4, 5]) feature_factory_manager = FeatureFactoryManager( feature_factory_dict=feature_factory_dict, logger=logger) for model_id, fname in enumerate(glob.glob(files_dir)): logger.info(f"loading... {fname}") df = pd.read_pickle(fname) df = df[df["answered_correctly"] != -1] df["prior_question_had_explanation"] = df[ "prior_question_had_explanation"].fillna(-1).astype("int8") if debug: df = df.head(1000) df = pd.concat([ pd.merge(df[df["content_type_id"] == 0], df_question, how="left", left_on="content_id", right_on="question_id"), pd.merge(df[df["content_type_id"] == 1], df_lecture, how="left", left_on="content_id", right_on="lecture_id") ]).sort_values(["user_id", "timestamp"]) # df = feature_factory_manager.feature_factory_dict["content_id"]["TargetEncoder"].all_predict(df) feature_factory_manager.fit(df, is_first_fit=True) for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = None feature_factory_manager.logger = None with open(f"feature_factory_manager.pickle", "wb") as f: pickle.dump(feature_factory_manager, f) return
def run(debug, model_dir, kaggle=False): if kaggle: files_dir = "/kaggle/input/riiid-split10/*.pickle" else: files_dir = "../input/riiid-test-answer-prediction/split10_base/*.pickle" logger = get_logger() # environment env = riiideducation.make_env() df_question = pd.read_csv( "../input/riiid-test-answer-prediction/questions.csv", dtype={ "bundle_id": "int32", "question_id": "int32", "correct_answer": "int8", "part": "int8" }) df_lecture = pd.read_csv( "../input/riiid-test-answer-prediction/lectures.csv", dtype={ "lecture_id": "int32", "tag": "int16", "part": "int8" }) # model loading models = [] for model_path in glob.glob(f"{model_dir}/*model*.pickle"): with open(model_path, "rb") as f: models.append(pickle.load(f)) # data preprocessing logger = get_logger() feature_factory_dict = {} feature_factory_dict["tags"] = {"TagsSeparator": TagsSeparator()} for column in [ "content_id", "user_id", "part", "prior_question_had_explanation", "tags1", "tags2", ("user_id", "prior_question_had_explanation"), ("user_id", "part") ]: is_partial_fit = (column == "content_id" or column == "user_id") if type(column) == str: feature_factory_dict[column] = { "CountEncoder": CountEncoder(column=column, is_partial_fit=is_partial_fit), "TargetEncoder": TargetEncoder(column=column, is_partial_fit=is_partial_fit) } else: feature_factory_dict[column] = { "CountEncoder": CountEncoder(column=list(column), is_partial_fit=is_partial_fit), "TargetEncoder": TargetEncoder(column=list(column), is_partial_fit=is_partial_fit) } feature_factory_dict["user_id"][ "ShiftDiffEncoderTimestamp"] = ShiftDiffEncoder(groupby="user_id", column="timestamp", is_partial_fit=True) feature_factory_dict["user_id"][ "ShiftDiffEncoderContentId"] = ShiftDiffEncoder(groupby="user_id", column="content_id") for column in ["user_id", "content_id"]: feature_factory_dict[column][ f"MeanAggregatorPriorQuestionElapsedTimeby{column}"] = MeanAggregator( column=column, agg_column="prior_question_elapsed_time", remove_now=True) feature_factory_dict["user_id"][ "UserLevelEncoder2ContentId"] = UserLevelEncoder2( vs_column="content_id") feature_factory_dict["user_id"][ "UserCountBinningEncoder"] = UserCountBinningEncoder( is_partial_fit=True) feature_factory_dict["user_count_bin"] = {} feature_factory_dict["user_count_bin"]["CountEncoder"] = CountEncoder( column="user_count_bin") feature_factory_dict["user_count_bin"]["TargetEncoder"] = TargetEncoder( column="user_count_bin") feature_factory_dict[("user_id", "user_count_bin")] = { "CountEncoder": CountEncoder(column=["user_id", "user_count_bin"]), "TargetEncoder": TargetEncoder(column=["user_id", "user_count_bin"]) } feature_factory_dict[("content_id", "user_count_bin")] = { "CountEncoder": CountEncoder(column=["content_id", "user_count_bin"]), "TargetEncoder": TargetEncoder(column=["content_id", "user_count_bin"]) } feature_factory_dict["user_id"][ "CategoryLevelEncoderPart"] = CategoryLevelEncoder( groupby_column="user_id", agg_column="part", categories=[1, 2, 3, 4, 5, 6, 7]) feature_factory_dict["user_count_bin"]["CategoryLevelEncoderUserCountBin"] = \ CategoryLevelEncoder(groupby_column="user_id", agg_column="user_count_bin", categories=[0, 1, 2, 3, 4, 5]) feature_factory_manager = FeatureFactoryManager( feature_factory_dict=feature_factory_dict, logger=logger) """ for model_id, fname in enumerate(glob.glob(files_dir)): logger.info(f"loading... {fname}") df = pd.read_pickle(fname) df = df[df["answered_correctly"] != -1] df["prior_question_had_explanation"] = df["prior_question_had_explanation"].fillna(-1).astype("int8") if debug: df = df.head(1000) df = pd.concat([pd.merge(df[df["content_type_id"] == 0], df_question, how="left", left_on="content_id", right_on="question_id"), pd.merge(df[df["content_type_id"] == 1], df_lecture, how="left", left_on="content_id", right_on="lecture_id")]).sort_values(["user_id", "timestamp"]) # df = feature_factory_manager.feature_factory_dict["content_id"]["TargetEncoder"].all_predict(df) feature_factory_manager.fit(df, is_first_fit=True) for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = None feature_factory_manager.logger = None with open(f"feature_factory_manager.pickle", "wb") as f: pickle.dump(feature_factory_manager, f) return """ with open(f"feature_factory_manager.pickle", "rb") as f: feature_factory_manager = pickle.load(f) for dicts in feature_factory_manager.feature_factory_dict.values(): for factory in dicts.values(): factory.logger = logger feature_factory_manager.logger = logger iter_test = env.iter_test() df_test_prev = pd.DataFrame() answered_correctlies = [] user_answers = [] i = 0 t = time.time() for (df_test, df_sample_prediction) in iter_test: i += 1 logger.info( f"[time: {int(time.time() - t)}iteration {i}: data_length: {len(df_test)}" ) # 前回のデータ更新 if len(df_test_prev) > 0: # 初回のみパスするためのif answered_correctly = df_test.iloc[0]["prior_group_answers_correct"] user_answer = df_test.iloc[0]["prior_group_responses"] answered_correctlies.extend([ int(x) for x in answered_correctly.replace("[", "").replace( "'", "").replace("]", "").replace(" ", "").split(",") ]) user_answers.extend([ int(x) for x in user_answer.replace("[", "").replace("'", "").replace( "]", "").replace(" ", "").split(",") ]) if debug: update_record = 1 else: update_record = 75 if len(df_test_prev) > update_record: df_test_prev["answered_correctly"] = answered_correctlies df_test_prev["user_answer"] = user_answers # df_test_prev = df_test_prev.drop(prior_columns, axis=1) df_test_prev = df_test_prev[ df_test_prev["answered_correctly"] != -1] df_test_prev["answered_correctly"] = df_test_prev[ "answered_correctly"].replace(-1, np.nan) df_test_prev["prior_question_had_explanation"] = df_test_prev[ "prior_question_had_explanation"].fillna(-1).astype("int8") feature_factory_manager.fit(df_test_prev) df_test_prev = pd.DataFrame() answered_correctlies = [] user_answers = [] # 今回のデータ取得&計算 # logger.info(f"[time: {int(time.time() - t)}dataload") logger.info(f"merge... ") w_df1 = pd.merge(df_test[df_test["content_type_id"] == 0], df_question, how="left", left_on="content_id", right_on="question_id") w_df2 = pd.merge(df_test[df_test["content_type_id"] == 1], df_lecture, how="left", left_on="content_id", right_on="lecture_id") df_test = pd.concat([w_df1, w_df2]).sort_values(["user_id", "timestamp"]).sort_index() df_test["tag"] = df_test["tag"].fillna(-1) df_test["correct_answer"] = df_test["correct_answer"].fillna(-1) df_test["bundle_id"] = df_test["bundle_id"].fillna(-1) logger.info(f"transform... ") df_test["prior_question_had_explanation"] = df_test[ "prior_question_had_explanation"].astype("float16").fillna( -1).astype("int8") df = feature_factory_manager.partial_predict(df_test) df.columns = [x.replace(" ", "_") for x in df.columns] logger.info(f"other... ") # predict predicts = [] cols = models[0].feature_name() for model in models: predicts.append(model.predict(df[cols])) df["answered_correctly"] = np.array(predicts).transpose().mean(axis=1) df_sample_prediction = pd.merge(df_sample_prediction[["row_id"]], df[["row_id", "answered_correctly"]], how="inner") env.predict(df_sample_prediction) df_test_prev = df_test_prev.append(df[cols + ["user_id", "tags"]]) if i < 5: df_test_prev.to_csv(f"{i}.csv")