{"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\nimport numpy as np\nimport gc\nfrom sklearn.metrics import roc_auc_score\nfrom collections import defaultdict\nfrom tqdm.notebook import tqdm\nimport lightgbm as lgb\nimport riiideducation\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport random\nimport os\nimport joblib","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nSEED = 123\n\n\ndef seed_everything(seed):\n    random.seed(seed)\n    np.random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    \nseed_everything(SEED)\n\n\ndef add_features(df, answered_correctly_u_count, answered_correctly_u_sum, elapsed_time_u_sum, explanation_u_sum, timestamp_u, timestamp_u_incorrect, answered_correctly_q_count, answered_correctly_q_sum, elapsed_time_q_sum, explanation_q_sum, answered_correctly_uq, update = True):\n    answered_correctly_u_avg = np.zeros(len(df), dtype = np.float32)\n    elapsed_time_u_avg = np.zeros(len(df), dtype = np.float32)\n    explanation_u_avg = np.zeros(len(df), dtype = np.float32)\n    timestamp_u_recency_1 = np.zeros(len(df), dtype = np.float32)\n    timestamp_u_recency_2 = np.zeros(len(df), dtype = np.float32)\n    timestamp_u_recency_3 = np.zeros(len(df), dtype = np.float32)\n    timestamp_u_incorrect_recency = np.zeros(len(df), dtype = np.float32)\n   \n    answered_correctly_q_avg = np.zeros(len(df), dtype = np.float32)\n    elapsed_time_q_avg = np.zeros(len(df), dtype = np.float32)\n    explanation_q_avg = np.zeros(len(df), dtype = np.float32)\n    \n    answered_correctly_uq_count = np.zeros(len(df), dtype = np.int32)\n    \n    \n    for num, row in enumerate(df[['user_id', 'answered_correctly', 'content_id', 'prior_question_elapsed_time', 'prior_question_had_explanation', 'timestamp']].values):\n        \n    \n            if answered_correctly_u_count[row[0]] != 0:\n            answered_correctly_u_avg[num] = answered_correctly_u_sum[row[0]] / answered_correctly_u_count[row[0]]\n            elapsed_time_u_avg[num] = elapsed_time_u_sum[row[0]] / answered_correctly_u_count[row[0]]\n            explanation_u_avg[num] = explanation_u_sum[row[0]] / answered_correctly_u_count[row[0]]\n        else:\n            answered_correctly_u_avg[num] = np.nan\n            elapsed_time_u_avg[num] = np.nan\n            explanation_u_avg[num] = np.nan\n            \n        if len(timestamp_u[row[0]]) == 0:\n            timestamp_u_recency_1[num] = np.nan\n            timestamp_u_recency_2[num] = np.nan\n            timestamp_u_recency_3[num] = np.nan\n        elif len(timestamp_u[row[0]]) == 1:\n            timestamp_u_recency_1[num] = row[5] - timestamp_u[row[0]][0]\n            timestamp_u_recency_2[num] = np.nan\n            timestamp_u_recency_3[num] = np.nan\n        elif len(timestamp_u[row[0]]) == 2:\n            timestamp_u_recency_1[num] = row[5] - timestamp_u[row[0]][1]\n            timestamp_u_recency_2[num] = row[5] - timestamp_u[row[0]][0]\n            timestamp_u_recency_3[num] = np.nan\n        elif len(timestamp_u[row[0]]) == 3:\n            timestamp_u_recency_1[num] = row[5] - timestamp_u[row[0]][2]\n            timestamp_u_recency_2[num] = row[5] - timestamp_u[row[0]][1]\n            timestamp_u_recency_3[num] = row[5] - timestamp_u[row[0]][0]\n        \n        if len(timestamp_u_incorrect[row[0]]) == 0:\n            timestamp_u_incorrect_recency[num] = np.nan\n        else:\n            timestamp_u_incorrect_recency[num] = row[5] - timestamp_u_incorrect[row[0]][0]\n                \n        if answered_correctly_q_count[row[2]] != 0:\n            answered_correctly_q_avg[num] = answered_correctly_q_sum[row[2]] / answered_correctly_q_count[row[2]]\n            elapsed_time_q_avg[num] = elapsed_time_q_sum[row[2]] / answered_correctly_q_count[row[2]]\n            explanation_q_avg[num] = explanation_q_sum[row[2]] / answered_correctly_q_count[row[2]]\n        else:\n            answered_correctly_q_avg[num] = np.nan\n            elapsed_time_q_avg[num] = np.nan\n            explanation_q_avg[num] = np.nan\n\n            \n            \n        answered_correctly_uq_count[num] = answered_correctly_uq[row[0]][row[2]]\n        \n        \n        answered_correctly_u_count[row[0]] += 1\n        elapsed_time_u_sum[row[0]] += row[3]\n        explanation_u_sum[row[0]] += int(row[4])\n        if len(timestamp_u[row[0]]) == 3:\n            timestamp_u[row[0]].pop(0)\n            timestamp_u[row[0]].append(row[5])\n        else:\n            timestamp_u[row[0]].append(row[5])\n\n        answered_correctly_q_count[row[2]] += 1\n        elapsed_time_q_sum[row[2]] += row[3]\n        explanation_q_sum[row[2]] += int(row[4])\n\n        answered_correctly_uq[row[0]][row[2]] += 1\n        \n        \n        if update:\n            \n            \n            answered_correctly_u_sum[row[0]] += row[1]\n            if row[1] == 0:\n                if len(timestamp_u_incorrect[row[0]]) == 1:\n                    timestamp_u_incorrect[row[0]].pop(0)\n                    timestamp_u_incorrect[row[0]].append(row[5])\n                else:\n                    timestamp_u_incorrect[row[0]].append(row[5])\n            \n            answered_correctly_q_sum[row[2]] += row[1]\n             \n            \n    user_df = pd.DataFrame({'answered_correctly_u_avg': answered_correctly_u_avg, 'elapsed_time_u_avg': elapsed_time_u_avg, 'explanation_u_avg': explanation_u_avg, \n                            'answered_correctly_q_avg': answered_correctly_q_avg, 'elapsed_time_q_avg': elapsed_time_q_avg, 'explanation_q_avg': explanation_q_avg, \n                            'answered_correctly_uq_count': answered_correctly_uq_count, 'timestamp_u_recency_1': timestamp_u_recency_1, 'timestamp_u_recency_2': timestamp_u_recency_2,\n                            'timestamp_u_recency_3': timestamp_u_recency_3, 'timestamp_u_incorrect_recency': timestamp_u_incorrect_recency})\n    \n    df = pd.concat([df, user_df], axis = 1)\n    return df\n        \ndef update_features(df, answered_correctly_u_sum, answered_correctly_q_sum, timestamp_u_incorrect):\n    for row in df[['user_id', 'answered_correctly', 'content_id', 'content_type_id', 'timestamp']].values:\n        if row[3] == 0:\n\n            answered_correctly_u_sum[row[0]] += row[1]\n            if row[1] == 0:\n                if len(timestamp_u_incorrect[row[0]]) == 1:\n                    timestamp_u_incorrect[row[0]].pop(0)\n                    timestamp_u_incorrect[row[0]].append(row[4])\n                else:\n                    timestamp_u_incorrect[row[0]].append(row[4])\n            \n            answered_correctly_q_sum[row[2]] += row[1]\n            \n            \n    return\n\ndef read_and_preprocess(feature_engineering = False):\n    \n    train_pickle = '../input/riiid-cross-validation-files/cv1_train.pickle'\n    valid_pickle = '../input/riiid-cross-validation-files/cv1_valid.pickle'\n    question_file = '../input/riiid-test-answer-prediction/questions.csv'\n    \n    \n    feld_needed = ['timestamp', 'user_id', 'answered_correctly', 'content_id', 'content_type_id', 'prior_question_elapsed_time', 'prior_question_had_explanation']\n    train = pd.read_pickle(train_pickle)[feld_needed]\n    valid = pd.read_pickle(valid_pickle)[feld_needed]\n\n    if feature_engineering:\n        train = train.iloc[-40000000:]\n    \n    \n    train = train.loc[train.content_type_id == False].reset_index(drop = True)\n    valid = valid.loc[valid.content_type_id == False].reset_index(drop = True)\n    \n    \n    train['prior_question_had_explanation'] = train.prior_question_had_explanation.fillna(False).astype('int8')\n    valid['prior_question_had_explanation'] = valid.prior_question_had_explanation.fillna(False).astype('int8')\n    \n    \n    prior_question_elapsed_time_mean = train['prior_question_elapsed_time'].dropna().mean()\n    train['prior_question_elapsed_time'].fillna(prior_question_elapsed_time_mean, inplace = True)\n    valid['prior_question_elapsed_time'].fillna(prior_question_elapsed_time_mean, inplace = True)\n    \n    \n    questions_df = pd.read_csv(question_file)\n    questions_df['part'] = questions_df['part'].astype(np.int32)\n    questions_df['bundle_id'] = questions_df['bundle_id'].astype(np.int32)\n    \n    train = pd.merge(train, questions_df[['question_id', 'part']], left_on = 'content_id', right_on = 'question_id', how = 'left')\n    valid = pd.merge(valid, questions_df[['question_id', 'part']], left_on = 'content_id', right_on = 'question_id', how = 'left')\n    \n    \n    answered_correctly_u_count = defaultdict(int)\n    answered_correctly_u_sum = defaultdict(int)\n    elapsed_time_u_sum = defaultdict(int)\n    explanation_u_sum = defaultdict(int)\n    timestamp_u = defaultdict(list)\n    timestamp_u_incorrect = defaultdict(list)\n    \n    \n    answered_correctly_q_count = defaultdict(int)\n    answered_correctly_q_sum = defaultdict(int)\n    elapsed_time_q_sum = defaultdict(int)\n    explanation_q_sum = defaultdict(int)\n    \n    \n    answered_correctly_uq = defaultdict(lambda: defaultdict(int))\n    \n    print('User feature calculation started...')\n    print('\\n')\n    train = add_features(train, answered_correctly_u_count, answered_correctly_u_sum, elapsed_time_u_sum, explanation_u_sum, timestamp_u, timestamp_u_incorrect, answered_correctly_q_count, answered_correctly_q_sum, elapsed_time_q_sum, explanation_q_sum, answered_correctly_uq)\n    valid = add_features(valid, answered_correctly_u_count, answered_correctly_u_sum, elapsed_time_u_sum, explanation_u_sum, timestamp_u, timestamp_u_incorrect, answered_correctly_q_count, answered_correctly_q_sum, elapsed_time_q_sum, explanation_q_sum, answered_correctly_uq)\n    gc.collect()\n    print('User feature calculation completed...')\n    print('\\n')\n    \n    features_dicts = {\n        'answered_correctly_u_count': answered_correctly_u_count,\n        'answered_correctly_u_sum': answered_correctly_u_sum,\n        'elapsed_time_u_sum': elapsed_time_u_sum,\n        'explanation_u_sum': explanation_u_sum,\n        'answered_correctly_q_count': answered_correctly_q_count,\n        'answered_correctly_q_sum': answered_correctly_q_sum,\n        'elapsed_time_q_sum': elapsed_time_q_sum,\n        'explanation_q_sum': explanation_q_sum,\n        'answered_correctly_uq': answered_correctly_uq,\n        'timestamp_u': timestamp_u,\n        'timestamp_u_incorrect': timestamp_u_incorrect\n    }\n    \n    return train, valid, questions_df, prior_question_elapsed_time_mean, features_dicts\n\n\n\ndef train_and_evaluate(train, valid, feature_engineering = False):\n    \n    TARGET = 'answered_correctly'\n    \n    \n    \n    FEATURES = ['timestamp', 'user_id', \n        'prior_question_elapsed_time',\n        'question_id', 'part',\n       'answered_correctly_u_avg', 'elapsed_time_u_avg', 'explanation_u_avg',\n       'answered_correctly_q_avg', 'elapsed_time_q_avg', 'explanation_q_avg',\n       'answered_correctly_uq_count', 'timestamp_u_recency_1',\n       'timestamp_u_recency_2', 'timestamp_u_recency_3',\n       'timestamp_u_incorrect_recency']\n    \n    # Delete some training data to experiment faster\n    if feature_engineering:\n        train = train.sample(24000000, random_state = SEED)\n    gc.collect()\n    print(f'Traning with {train.shape[0]} rows and {len(FEATURES)} features')    \n    drop_cols = list(set(train.columns) - set(FEATURES))\n    y_train = train[TARGET]\n    y_val = valid[TARGET]\n    # Drop unnecessary columns\n    train.drop(drop_cols, axis = 1, inplace = True)\n    valid.drop(drop_cols, axis = 1, inplace = True)\n    gc.collect()\n    \n    lgb_train = lgb.Dataset(train[FEATURES], y_train)\n    lgb_valid = lgb.Dataset(valid[FEATURES], y_val)\n    del train, y_train\n    gc.collect()\n    \n    params = {'objective': 'binary', \n              'seed': SEED,\n              'metric': 'auc',\n              'num_leaves': 300,\n              'feature_fraction': 0.75,\n              'bagging_freq': 10,\n              'bagging_fraction': 0.80\n             }\n    \n    \n    \n    \n    model = lgb.train(\n        params = params,\n        train_set = lgb_train,\n        num_boost_round = 10000,\n        valid_sets = [lgb_train, lgb_valid],\n        early_stopping_rounds = 15,\n        verbose_eval = 50\n    )\n    \n    print('Our Roc Auc score for the validation data is:', roc_auc_score(y_val, model.predict(valid[FEATURES])))\n    \n    feature_importance = model.feature_importance()\n    feature_importance = pd.DataFrame({'Features': FEATURES, 'Importance': feature_importance}).sort_values('Importance', ascending = False)\n    \n    fig = plt.figure(figsize = (10, 10))\n    fig.suptitle('Feature Importance', fontsize = 20)\n    plt.tick_params(axis = 'x', labelsize = 12)\n    plt.tick_params(axis = 'y', labelsize = 12)\n    plt.xlabel('Importance', fontsize = 15)\n    plt.ylabel('Features', fontsize = 15)\n    sns.barplot(x = feature_importance['Importance'], y = feature_importance['Features'], orient = 'h')\n    plt.show()\n    \n    return TARGET, FEATURES, model\n\n\n\ndef inference(TARGET, FEATURES, model, questions_df, prior_question_elapsed_time_mean, features_dicts):\n    \n    \n    answered_correctly_u_count = features_dicts['answered_correctly_u_count']\n    answered_correctly_u_sum = features_dicts['answered_correctly_u_sum']\n    elapsed_time_u_sum = features_dicts['elapsed_time_u_sum']\n    explanation_u_sum = features_dicts['explanation_u_sum']\n    answered_correctly_q_count = features_dicts['answered_correctly_q_count']\n    answered_correctly_q_sum = features_dicts['answered_correctly_q_sum']\n    elapsed_time_q_sum = features_dicts['elapsed_time_q_sum']\n    explanation_q_sum = features_dicts['explanation_q_sum']\n    answered_correctly_uq = features_dicts['answered_correctly_uq']\n    timestamp_u = features_dicts['timestamp_u']\n    timestamp_u_incorrect = features_dicts['timestamp_u_incorrect']\n    \n    \n    env = riiideducation.make_env()\n    iter_test = env.iter_test()\n    set_predict = env.predict\n    \n    previous_test_df = None\n    for (test_df, sample_prediction_df) in iter_test:\n        if previous_test_df is not None:\n            previous_test_df[TARGET] = eval(test_df[\"prior_group_answers_correct\"].iloc[0])\n            update_features(previous_test_df, answered_correctly_u_sum, answered_correctly_q_sum, timestamp_u_incorrect)\n        previous_test_df = test_df.copy()\n        test_df = test_df[test_df['content_type_id'] == 0].reset_index(drop = True)\n        test_df['prior_question_had_explanation'] = test_df.prior_question_had_explanation.fillna(False).astype('int8')\n        test_df['prior_question_elapsed_time'].fillna(prior_question_elapsed_time_mean, inplace = True)\n        test_df = pd.merge(test_df, questions_df[['question_id', 'part']], left_on = 'content_id', right_on = 'question_id', how = 'left')\n        test_df[TARGET] = 0\n        test_df = add_features(test_df, answered_correctly_u_count, answered_correctly_u_sum, elapsed_time_u_sum, explanation_u_sum, timestamp_u, timestamp_u_incorrect, answered_correctly_q_count, answered_correctly_q_sum, elapsed_time_q_sum, explanation_q_sum, answered_correctly_uq, update = False)\n        test_df[TARGET] =  model.predict(test_df[FEATURES])\n        set_predict(test_df[['row_id', TARGET]])\n        \n    print('Job Done')\n    \ntrain, valid, questions_df, prior_question_elapsed_time_mean, features_dicts = read_and_preprocess(feature_engineering = True)\n","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"FEATURES = ['prior_question_elapsed_time', 'prior_question_had_explanation', 'part', 'answered_correctly_u_avg', 'elapsed_time_u_avg', 'explanation_u_avg',\n                'answered_correctly_q_avg', 'elapsed_time_q_avg', 'explanation_q_avg', 'answered_correctly_uq_count', 'timestamp_u_recency_1', 'timestamp_u_recency_2', 'timestamp_u_recency_3', \n                'timestamp_u_incorrect_recency']\n    \nmodel_lgb= lgb.Booster(model_file='../input/final-lgb-train/lgbm_33m_200_20')\n\nTARGET = 'answered_correctly'","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nTARGET = 'answered_correctly'","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nMAX_SEQ = 240 \nACCEPTED_USER_CONTENT_SIZE = 2 \nEMBED_SIZE = 256 \nBATCH_SIZE = 64+32 \nDROPOUT = 0.1 \nn_skill=joblib.load('../input/v4-fork-of-riiid-sakt-model-full/skills.pkl.zip')\nclass FFN(nn.Module):\n    def __init__(self, state_size = 200, forward_expansion = 1, bn_size = MAX_SEQ - 1, dropout=0.2):\n        super(FFN, self).__init__()\n        self.state_size = state_size\n        \n        self.lr1 = nn.Linear(state_size, forward_expansion * state_size)\n        self.relu = nn.ReLU()\n        self.bn = nn.BatchNorm1d(bn_size)\n        self.lr2 = nn.Linear(forward_expansion * state_size, state_size)\n        self.dropout = nn.Dropout(dropout)\n        \n    def forward(self, x):\n        x = self.relu(self.lr1(x))\n        x = self.bn(x)\n        x = self.lr2(x)\n        return self.dropout(x)\n    \nclass FFN0(nn.Module):\n    def __init__(self, state_size = 200, forward_expansion = 1, bn_size = MAX_SEQ - 1, dropout=0.2):\n        super(FFN0, self).__init__()\n        self.state_size = state_size\n\n        self.lr1 = nn.Linear(state_size, forward_expansion * state_size)\n        self.relu = nn.ReLU()\n        self.lr2 = nn.Linear(forward_expansion * state_size, state_size)\n        self.layer_normal = nn.LayerNorm(state_size) \n        self.dropout = nn.Dropout(0.2)\n    \n    def forward(self, x):\n        x = self.lr1(x)\n        x = self.relu(x)\n        x = self.lr2(x)\n        x=self.layer_normal(x)\n        return self.dropout(x)\n    \ndef future_mask(seq_length):\n    future_mask = (np.triu(np.ones([seq_length, seq_length]), k = 1)).astype('bool')\n    return torch.from_numpy(future_mask)\n\nfuture_mask(5)\n\nclass TransformerBlock(nn.Module):\n    def __init__(self, embed_dim, heads = 8, dropout = DROPOUT, forward_expansion = 1):\n        super(TransformerBlock, self).__init__()\n        self.multi_att = nn.MultiheadAttention(embed_dim=embed_dim, num_heads=heads, dropout=dropout)\n        self.dropout = nn.Dropout(dropout)\n        self.layer_normal = nn.LayerNorm(embed_dim)\n        self.ffn = FFN(embed_dim, forward_expansion = forward_expansion, dropout=dropout)\n        self.ffn0  = FFN0(embed_dim, forward_expansion = forward_expansion, dropout=dropout)\n        self.layer_normal_2 = nn.LayerNorm(embed_dim)\n\n    def forward(self, value, key, query, att_mask):\n        att_output, att_weight = self.multi_att(value, key, query, attn_mask=att_mask)\n        att_output = self.dropout(self.layer_normal(att_output + value))\n        att_output = att_output.permute(1, 0, 2) # att_output: [s_len, bs, embed] => [bs, s_len, embed]\n        x = self.ffn(att_output)\n        x1 = self.ffn0(att_output)\n        x = self.dropout(self.layer_normal_2(x + x1 + att_output))\n        return x.squeeze(-1), att_weight\n    \nclass Encoder(nn.Module):\n    def __init__(self, n_skill, max_seq=100, embed_dim=128, dropout = DROPOUT, forward_expansion = 1, num_layers=1, heads = 8):\n        super(Encoder, self).__init__()\n        self.n_skill, self.embed_dim = n_skill, embed_dim\n        self.embedding = nn.Embedding(2 * n_skill + 1, embed_dim)\n        self.pos_embedding = nn.Embedding(max_seq - 1, embed_dim)\n        self.e_embedding = nn.Embedding(n_skill+1, embed_dim)\n        self.layers = nn.ModuleList([TransformerBlock(embed_dim, forward_expansion = forward_expansion) for _ in range(num_layers)])\n        self.dropout = nn.Dropout(dropout)\n        \n    def forward(self, x, question_ids):\n        device = x.device\n        x = self.embedding(x)\n        pos_id = torch.arange(x.size(1)).unsqueeze(0).to(device)\n        pos_x = self.pos_embedding(pos_id)\n        x = self.dropout(x + pos_x)\n        x = x.permute(1, 0, 2) \n        e = self.e_embedding(question_ids)\n        e = e.permute(1, 0, 2)\n        for layer in self.layers:\n            att_mask = future_mask(e.size(0)).to(device)\n            x, att_weight = layer(e, x, x, att_mask=att_mask)\n            x = x.permute(1, 0, 2)\n        x = x.permute(1, 0, 2)\n        return x, att_weight\n\nclass SAKTModel(nn.Module):\n    def __init__(self, n_skill, max_seq=100, embed_dim=128, dropout = DROPOUT, forward_expansion = 1, enc_layers=1, heads = 8):\n        super(SAKTModel, self).__init__()\n        self.encoder = Encoder(n_skill, max_seq, embed_dim, dropout, forward_expansion, num_layers=enc_layers)\n        self.pred = nn.Linear(embed_dim, 1)\n        \n    def forward(self, x, question_ids):\n        x, att_weight = self.encoder(x, question_ids)\n        x = self.pred(x)\n        return x.squeeze(-1), att_weight\n    \ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\ndef create_model():\n    return SAKTModel(n_skill, max_seq=MAX_SEQ, embed_dim=EMBED_SIZE, forward_expansion=1, enc_layers=1, heads=4, dropout=0.1)\n\nmodel = create_model()\nmodel.load_state_dict(torch.load('../input/v4-fork-of-riiid-sakt-model-full/sakt_model.pt',map_location='cpu'))\nmodel.to(device)\ngroup = joblib.load('../input/v4-fork-of-riiid-sakt-model-full/group.pkl.zip')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TestDataset(Dataset):\n    def __init__(self, samples, test_df, n_skill, max_seq=100):\n        super(TestDataset, self).__init__()\n        self.samples, self.user_ids, self.test_df = samples, [x for x in test_df[\"user_id\"].unique()], test_df\n        self.n_skill, self.max_seq = n_skill, max_seq\n\n    def __len__(self):\n        return self.test_df.shape[0]\n    \n    def __getitem__(self, index):\n        test_info = self.test_df.iloc[index]\n        \n        user_id = test_info['user_id']\n        target_id = test_info['content_id']\n        \n        content_id_seq = np.zeros(self.max_seq, dtype=int)\n        answered_correctly_seq = np.zeros(self.max_seq, dtype=int)\n        \n        if user_id in self.samples.index:\n            content_id, answered_correctly = self.samples[user_id]\n            \n            seq_len = len(content_id)\n            \n            if seq_len >= self.max_seq:\n                content_id_seq = content_id[-self.max_seq:]\n                answered_correctly_seq = answered_correctly[-self.max_seq:]\n            else:\n                content_id_seq[-seq_len:] = content_id\n                answered_correctly_seq[-seq_len:] = answered_correctly\n                \n        x = content_id_seq[1:].copy()\n        x += (answered_correctly_seq[1:] == 1) * self.n_skill\n        \n        questions = np.append(content_id_seq[2:], [target_id])\n        \n        return x, questions","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"answered_correctly_u_count = features_dicts['answered_correctly_u_count']\nanswered_correctly_u_sum = features_dicts['answered_correctly_u_sum']\nelapsed_time_u_sum = features_dicts['elapsed_time_u_sum']\nexplanation_u_sum = features_dicts['explanation_u_sum']\nanswered_correctly_q_count = features_dicts['answered_correctly_q_count']\nanswered_correctly_q_sum = features_dicts['answered_correctly_q_sum']\nelapsed_time_q_sum = features_dicts['elapsed_time_q_sum']\nexplanation_q_sum = features_dicts['explanation_q_sum']\nanswered_correctly_uq = features_dicts['answered_correctly_uq']\ntimestamp_u = features_dicts['timestamp_u']\ntimestamp_u_incorrect = features_dicts['timestamp_u_incorrect']\n\nN=[0.4,0.6]\nTARGET = 'answered_correctly'\n\n\nimport psutil\n\nmodel.eval()\n\nprev_test_df = None\n\n\nenv = riiideducation.make_env()\niter_test = env.iter_test()\nset_predict = env.predict\n\nprevious_test_df = None\nprev_test_df1 = None\nfor (test_df, sample_prediction_df) in iter_test:\n    \n    \n    test_df1=test_df.copy()\n    \n    if (prev_test_df is not None) & (psutil.virtual_memory().percent<90):\n        print(psutil.virtual_memory().percent)\n        prev_test_df['answered_correctly'] = eval(test_df1['prior_group_answers_correct'].iloc[0])\n        prev_test_df = prev_test_df[prev_test_df.content_type_id == False]\n        prev_group = prev_test_df[['user_id', 'content_id', 'answered_correctly']].groupby('user_id').apply(lambda r: (\n            r['content_id'].values,\n            r['answered_correctly'].values))\n        for prev_user_id in prev_group.index:\n            prev_group_content = prev_group[prev_user_id][0]\n            prev_group_answered_correctly = prev_group[prev_user_id][1]\n            if prev_user_id in group.index:\n                group[prev_user_id] = (np.append(group[prev_user_id][0], prev_group_content), \n                                       np.append(group[prev_user_id][1], prev_group_answered_correctly))\n            else:\n                group[prev_user_id] = (prev_group_content, prev_group_answered_correctly)\n            \n            if len(group[prev_user_id][0]) > MAX_SEQ:\n                new_group_content = group[prev_user_id][0][-MAX_SEQ:]\n                new_group_answered_correctly = group[prev_user_id][1][-MAX_SEQ:]\n                group[prev_user_id] = (new_group_content, new_group_answered_correctly)\n                \n    prev_test_df = test_df1.copy()\n    test_df1 = test_df1[test_df1.content_type_id == False]\n    \n    test_dataset = TestDataset(group, test_df1, n_skill, max_seq=MAX_SEQ)\n    test_dataloader = DataLoader(test_dataset, batch_size=len(test_df), shuffle=False)\n    \n    item = next(iter(test_dataloader))\n    x = item[0].to(device).long()\n    target_id = item[1].to(device).long()\n    \n    with torch.no_grad():\n        output, _ = model(x, target_id)\n        \n    output = torch.sigmoid(output)\n    output = output[:, -1]\n    outs = output.cpu().numpy()\n\n    \n    \n    \n\n    \n    \n    \n    \n    \n    \n    \n    \n    \n    \n    \n    if previous_test_df is not None:\n        previous_test_df[TARGET] = eval(test_df[\"prior_group_answers_correct\"].iloc[0])\n        update_features(previous_test_df, answered_correctly_u_sum, answered_correctly_q_sum, timestamp_u_incorrect)\n    previous_test_df = test_df.copy()\n    test_df = test_df[test_df['content_type_id'] == 0].reset_index(drop = True)\n    test_df['prior_question_had_explanation'] = test_df.prior_question_had_explanation.fillna(False).astype('int8')\n    test_df['prior_question_elapsed_time'].fillna(prior_question_elapsed_time_mean, inplace = True)\n    test_df = pd.merge(test_df, questions_df[['question_id', 'part']], left_on = 'content_id', right_on = 'question_id', how = 'left')\n    test_df[TARGET] = 0\n    test_df = add_features(test_df, answered_correctly_u_count, answered_correctly_u_sum, elapsed_time_u_sum, explanation_u_sum, timestamp_u, timestamp_u_incorrect, answered_correctly_q_count, answered_correctly_q_sum, elapsed_time_q_sum, explanation_q_sum, answered_correctly_uq, update = False)\n    \n    \n    \n    \n    \n    test_df[TARGET] =  0.5*model_lgb.predict(test_df[FEATURES]) + 0.5*outs\n    \n\n    set_predict(test_df[['row_id', TARGET]])\n\nprint('Job Done')\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('./submission.csv')\nsub","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}