{"cells":[{"metadata":{"trusted":true,"_uuid":"c3581f74ae694eb07182e2a23c9db8f01a78f1ba"},"cell_type":"code","source":"import re\nimport time\nimport gc\nimport random\nimport os\n\nimport numpy as np\nimport pandas as pd\n\nfrom tqdm import tqdm\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import metrics\nfrom sklearn.model_selection import GridSearchCV, StratifiedKFold\nfrom sklearn.metrics import f1_score, roc_auc_score\n\nfrom tensorflow.keras.preprocessing.text import Tokenizer\nfrom tensorflow.keras.preprocessing.sequence import pad_sequences\n\nimport torch\nimport torch.nn as nn\nimport torch.utils.data\ndef seed_torch(seed=1029):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\nembed_size = 300 # how big is each word vector\nmax_features = 97000 # how many unique words to use (i.e num rows in embedding vector) 97000 best\nmaxlen = 72 # max number of words in a question to use 72 best\n\nbatch_size = 1000  #1000 best\ntrain_epochs = 7\n\nSEED = 1029\npuncts = [',', '.', '\"', ':', ')', '(', '-', '!', '?', '|', ';', \"'\", '$', '&', '/', '[', ']', '>', '%', '=', '#', '*', '+', '\\\\', '•',  '~', '@', '£', \n '·', '_', '{', '}', '©', '^', '®', '`',  '<', '→', '°', '€', '™', '›',  '♥', '←', '×', '§', '″', '′', 'Â', '█', '½', 'à', '…', \n '“', '★', '”', '–', '●', 'â', '►', '−', '¢', '²', '¬', '░', '¶', '↑', '±', '¿', '▾', '═', '¦', '║', '―', '¥', '▓', '—', '‹', '─', \n '▒', '：', '¼', '⊕', '▼', '▪', '†', '■', '’', '▀', '¨', '▄', '♫', '☆', 'é', '¯', '♦', '¤', '▲', 'è', '¸', '¾', 'Ã', '⋅', '‘', '∞', \n '∙', '）', '↓', '、', '│', '（', '»', '，', '♪', '╩', '╚', '³', '・', '╦', '╣', '╔', '╗', '▬', '❤', 'ï', 'Ø', '¹', '≤', '‡', '√', ]\n\ndef clean_text(x):\n    x = str(x)\n    for punct in puncts:\n        x = x.replace(punct, f' {punct} ')\n    return x\n\ndef clean_numbers(x):\n    x = re.sub('[0-9]{5,}', '#####', x)\n    x = re.sub('[0-9]{4}', '####', x)\n    x = re.sub('[0-9]{3}', '###', x)\n    x = re.sub('[0-9]{2}', '##', x)\n    return x\n\nmispell_dict = {\"aren't\" : \"are not\",\n\"can't\" : \"cannot\",\n\"couldn't\" : \"could not\",\n\"didn't\" : \"did not\",\n\"doesn't\" : \"does not\",\n\"don't\" : \"do not\",\n\"hadn't\" : \"had not\",\n\"hasn't\" : \"has not\",\n\"haven't\" : \"have not\",\n\"he'd\" : \"he would\",\n\"he'll\" : \"he will\",\n\"he's\" : \"he is\",\n\"i'd\" : \"I would\",\n\"i'd\" : \"I had\",\n\"i'll\" : \"I will\",\n\"i'm\" : \"I am\",\n\"isn't\" : \"is not\",\n\"it's\" : \"it is\",\n\"it'll\":\"it will\",\n\"i've\" : \"I have\",\n\"let's\" : \"let us\",\n\"mightn't\" : \"might not\",\n\"mustn't\" : \"must not\",\n\"shan't\" : \"shall not\",\n\"she'd\" : \"she would\",\n\"she'll\" : \"she will\",\n\"she's\" : \"she is\",\n\"shouldn't\" : \"should not\",\n\"that's\" : \"that is\",\n\"there's\" : \"there is\",\n\"they'd\" : \"they would\",\n\"they'll\" : \"they will\",\n\"they're\" : \"they are\",\n\"they've\" : \"they have\",\n\"we'd\" : \"we would\",\n\"we're\" : \"we are\",\n\"weren't\" : \"were not\",\n\"we've\" : \"we have\",\n\"what'll\" : \"what will\",\n\"what're\" : \"what are\",\n\"what's\" : \"what is\",\n\"what've\" : \"what have\",\n\"where's\" : \"where is\",\n\"who'd\" : \"who would\",\n\"who'll\" : \"who will\",\n\"who're\" : \"who are\",\n\"who's\" : \"who is\",\n\"who've\" : \"who have\",\n\"won't\" : \"will not\",\n\"wouldn't\" : \"would not\",\n\"you'd\" : \"you would\",\n\"you'll\" : \"you will\",\n\"you're\" : \"you are\",\n\"you've\" : \"you have\",\n\"'re\": \" are\",\n\"wasn't\": \"was not\",\n\"we'll\":\" will\",\n\"didn't\": \"did not\",\n\"tryin'\":\"trying\"}\n\ndef _get_mispell(mispell_dict):\n    mispell_re = re.compile('(%s)' % '|'.join(mispell_dict.keys()))\n    return mispell_dict, mispell_re\n\nmispellings, mispellings_re = _get_mispell(mispell_dict)\ndef replace_typical_misspell(text):\n    def replace(match):\n        return mispellings[match.group(0)]\n    return mispellings_re.sub(replace, text)\ndef load_and_prec():\n    train_df = pd.read_csv(\"../input/train.csv\")\n    test_df = pd.read_csv(\"../input/test.csv\")\n    print(\"Train shape : \",train_df.shape)\n    print(\"Test shape : \",test_df.shape)\n    \n    # lower\n    train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: x.lower())\n    test_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: x.lower())\n    \n    # Clean the text\n    train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: clean_text(x))\n    test_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: clean_text(x))\n    \n    # Clean numbers\n    train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: clean_numbers(x))\n    test_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: clean_numbers(x))\n    \n    # Clean speelings\n    train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: replace_typical_misspell(x))\n    test_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: replace_typical_misspell(x))\n    \n    ## fill up the missing values\n    train_X = train_df[\"question_text\"].fillna(\"_##_\").values\n    test_X = test_df[\"question_text\"].fillna(\"_##_\").values\n\n    ## Tokenize the sentences\n    tokenizer = Tokenizer(num_words=max_features)\n    tokenizer.fit_on_texts(list(train_X))\n    train_X = tokenizer.texts_to_sequences(train_X)\n    test_X = tokenizer.texts_to_sequences(test_X)\n\n    ## Pad the sentences \n    train_X = pad_sequences(train_X, maxlen=maxlen)\n    test_X = pad_sequences(test_X, maxlen=maxlen)\n\n    ## Get the target values\n    train_y = train_df['target'].values\n    \n    #shuffling the data\n    np.random.seed(SEED)\n    trn_idx = np.random.permutation(len(train_X))\n\n    train_X = train_X[trn_idx]\n    train_y = train_y[trn_idx]\n    \n    return train_X, test_X, train_y, tokenizer.word_index\ndef load_glove(word_index):\n    EMBEDDING_FILE = '../input/embeddings/glove.840B.300d/glove.840B.300d.txt'\n    def get_coefs(word,*arr): return word, np.asarray(arr, dtype='float32')\n    embeddings_index = dict(get_coefs(*o.split(\" \")) for o in open(EMBEDDING_FILE))\n\n    all_embs = np.stack(embeddings_index.values())\n    emb_mean,emb_std = all_embs.mean(), all_embs.std()\n    embed_size = all_embs.shape[1]\n\n    # word_index = tokenizer.word_index\n    nb_words = min(max_features, len(word_index))\n    embedding_matrix = np.random.normal(emb_mean, emb_std, (nb_words, embed_size))\n    for word, i in word_index.items():\n        if i >= max_features: continue\n        embedding_vector = embeddings_index.get(word)\n        if embedding_vector is not None: embedding_matrix[i] = embedding_vector\n            \n    return embedding_matrix \n\ndef load_para(word_index):\n    EMBEDDING_FILE = '../input/embeddings/paragram_300_sl999/paragram_300_sl999.txt'\n    def get_coefs(word,*arr): return word, np.asarray(arr, dtype='float32')\n    embeddings_index = dict(get_coefs(*o.split(\" \")) for o in open(EMBEDDING_FILE, encoding=\"utf8\", errors='ignore') if len(o)>100)\n\n    all_embs = np.stack(embeddings_index.values())\n    emb_mean,emb_std = all_embs.mean(), all_embs.std()\n    embed_size = all_embs.shape[1]\n\n    # word_index = tokenizer.word_index\n    nb_words = min(max_features, len(word_index))\n    embedding_matrix = np.random.normal(emb_mean, emb_std, (nb_words, embed_size))\n    for word, i in word_index.items():\n        if i >= max_features: continue\n        embedding_vector = embeddings_index.get(word)\n        if embedding_vector is not None: embedding_matrix[i] = embedding_vector\n    \n    return embedding_matrix\nfrom tqdm import tqdm\ntqdm.pandas()\n\nstart_time = time.time()\n\ntrain_X, test_X, train_y, word_index = load_and_prec()\nembedding_matrix_1 = load_glove(word_index)\nembedding_matrix_2 = load_para(word_index)\n\ntotal_time = (time.time() - start_time) / 60\nprint(\"Took {:.2f} minutes\".format(total_time))\n\nembedding_matrix = np.mean([embedding_matrix_1, embedding_matrix_2], axis=0)\n# embedding_matrix = np.concatenate((embedding_matrix_1, embedding_matrix_2), axis=1)\nprint(np.shape(embedding_matrix))\n\ndel embedding_matrix_1, embedding_matrix_2\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"02a5dc65ed687cfae0926f5c26576eab3fd19e05"},"cell_type":"code","source":"class Attention(nn.Module):\n    def __init__(self, feature_dim, step_dim, bias=True, **kwargs):\n        super(Attention, self).__init__(**kwargs)\n        \n        self.supports_masking = True\n\n        self.bias = bias\n        self.feature_dim = feature_dim\n        self.step_dim = step_dim\n        self.features_dim = 0\n        \n        weight = torch.zeros(feature_dim, 1)\n        nn.init.xavier_uniform_(weight)\n        self.weight = nn.Parameter(weight)\n        \n        if bias:\n            self.b = nn.Parameter(torch.zeros(step_dim))\n        \n    def forward(self, x, mask=None):\n        feature_dim = self.feature_dim\n        step_dim = self.step_dim\n\n        eij = torch.mm(\n            x.contiguous().view(-1, feature_dim), \n            self.weight\n        ).view(-1, step_dim)\n        \n        if self.bias:\n            eij = eij + self.b\n            \n        eij = torch.tanh(eij)\n        a = torch.exp(eij)\n        \n        if mask is not None:\n            a = a * mask\n\n        a = a / torch.sum(a, 1, keepdim=True) + 1e-10\n\n        weighted_input = x * torch.unsqueeze(a, -1)\n        return torch.sum(weighted_input, 1)\nclass NeuralNet(nn.Module):\n    def __init__(self):\n        super(NeuralNet, self).__init__()\n        \n        hidden_size = 75   #60best\n        \n        self.embedding = nn.Embedding(max_features, embed_size)\n        self.embedding.weight = nn.Parameter(torch.tensor(embedding_matrix, dtype=torch.float32))\n        self.embedding.weight.requires_grad = False\n        \n        self.embedding_dropout = nn.Dropout2d(0.1)  #0.1best\n        self.lstm = nn.LSTM(embed_size, hidden_size, bidirectional=True, batch_first=True)\n        self.gru = nn.GRU(hidden_size*2, hidden_size, bidirectional=True, batch_first=True)\n        \n        self.lstm_attention = Attention(hidden_size*2, maxlen)\n        self.gru_attention = Attention(hidden_size*2, maxlen)\n        \n        self.linear = nn.Linear(8 * hidden_size, 16)  #16best\n        self.relu = nn.ReLU()\n        self.dropout = nn.Dropout(0.1) #0.1 best\n        self.out = nn.Linear(16, 1)\n        \n    def forward(self, x):\n        h_embedding = self.embedding(x)\n        h_embedding = torch.squeeze(self.embedding_dropout(torch.unsqueeze(h_embedding, 0)))\n        \n        h_lstm, _ = self.lstm(h_embedding)\n        h_gru, _ = self.gru(h_lstm)\n        \n        h_lstm_atten = self.lstm_attention(h_lstm)\n        h_gru_atten = self.gru_attention(h_gru)\n        \n        avg_pool = torch.mean(h_gru, 1)\n        max_pool, _ = torch.max(h_gru, 1)\n        \n        conc = torch.cat((h_lstm_atten, h_gru_atten, avg_pool, max_pool), 1)\n        conc = self.relu(self.linear(conc))\n        conc = self.dropout(conc)\n        out = self.out(conc)\n        \n        return out\nsplits = list(StratifiedKFold(n_splits=5, shuffle=True, random_state=SEED).split(train_X, train_y))  #5 best\ndef sigmoid(x):\n    return 1 / (1 + np.exp(-x))\ndef threshold_search(y_true, y_proba):\n    best_threshold = 0\n    best_score = 0\n    for threshold in tqdm([i * 0.01 for i in range(100)]):\n        score = f1_score(y_true=y_true, y_pred=y_proba > threshold)\n        if score > best_score:\n            best_threshold = threshold\n            best_score = score\n    search_result = {'threshold': best_threshold, 'f1': best_score}\n    return search_result\ntrain_preds = np.zeros((len(train_X)))\ntest_preds = np.zeros((len(test_X)))\n\nseed_torch(SEED)\n\nx_test_cuda = torch.tensor(test_X, dtype=torch.long).cuda()\ntest = torch.utils.data.TensorDataset(x_test_cuda)\ntest_loader = torch.utils.data.DataLoader(test, batch_size=batch_size, shuffle=False)\n\nfor i, (train_idx, valid_idx) in enumerate(splits):\n    x_train_fold = torch.tensor(train_X[train_idx], dtype=torch.long).cuda()\n    y_train_fold = torch.tensor(train_y[train_idx, np.newaxis], dtype=torch.float32).cuda()\n    x_val_fold = torch.tensor(train_X[valid_idx], dtype=torch.long).cuda()\n    y_val_fold = torch.tensor(train_y[valid_idx, np.newaxis], dtype=torch.float32).cuda()\n    \n    model = NeuralNet()\n    model.cuda()\n    \n    loss_fn = torch.nn.BCEWithLogitsLoss(reduction=\"sum\")\n    optimizer = torch.optim.Adam(model.parameters())\n    \n    train = torch.utils.data.TensorDataset(x_train_fold, y_train_fold)\n    valid = torch.utils.data.TensorDataset(x_val_fold, y_val_fold)\n    \n    train_loader = torch.utils.data.DataLoader(train, batch_size=batch_size, shuffle=True)\n    valid_loader = torch.utils.data.DataLoader(valid, batch_size=batch_size, shuffle=False)\n    \n    print(f'Fold {i + 1}')\n    \n    for epoch in range(train_epochs):\n        start_time = time.time()\n        \n        model.train()\n        avg_loss = 0.\n        for x_batch, y_batch in tqdm(train_loader, disable=True):\n            y_pred = model(x_batch)\n            loss = loss_fn(y_pred, y_batch)\n            optimizer.zero_grad()\n            loss.backward()\n            optimizer.step()\n            avg_loss += loss.item() / len(train_loader)\n        \n        model.eval()\n        valid_preds_fold = np.zeros((x_val_fold.size(0)))\n        test_preds_fold = np.zeros(len(test_X))\n        avg_val_loss = 0.\n        for i, (x_batch, y_batch) in enumerate(valid_loader):\n            y_pred = model(x_batch).detach()\n            avg_val_loss += loss_fn(y_pred, y_batch).item() / len(valid_loader)\n            valid_preds_fold[i * batch_size:(i+1) * batch_size] = sigmoid(y_pred.cpu().numpy())[:, 0]\n        \n        elapsed_time = time.time() - start_time \n        print('Epoch {}/{} \\t loss={:.4f} \\t val_loss={:.4f} \\t time={:.2f}s'.format(\n            epoch + 1, train_epochs, avg_loss, avg_val_loss, elapsed_time))\n        \n    for i, (x_batch,) in enumerate(test_loader):\n        y_pred = model(x_batch).detach()\n\n        test_preds_fold[i * batch_size:(i+1) * batch_size] = sigmoid(y_pred.cpu().numpy())[:, 0]\n\n    train_preds[valid_idx] = valid_preds_fold\n    test_preds += test_preds_fold / len(splits) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5b47bf5d2ea260a5fff7098437d2f3e3e70b425e"},"cell_type":"code","source":"search_result = threshold_search(train_y, train_preds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ba3dac42b4de6342741e6dbb7e96d99b5a555d9b"},"cell_type":"code","source":"sub = pd.read_csv('../input/sample_submission.csv')\nsub.prediction = test_preds > search_result['threshold']\nsub.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}