{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Preface\nThis kernel contains my final submission for the Quora Insincere Questions Classification Competition.\nI came up with this model from discussions and public kernels. The model itself (loosely) resembles the 1st place solution from this discussion [thread](https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/80568) by Psi. I took the liberty to integrate Attention and GRU in an attempt to enhance the model.\n\nCurrently this kernel stands at:\n* Private LB : 0.7056 (ish)\n* Public LB : 0.699 (ish)\n\nMy initial plan was to train an off-the-shelf ULMFiT language model from FastAI and then fine tuning it for this competition. But, I found a couple of flaws in the plan:\n1. ULMFiT training was taking longer than the kernel limit.\n2. It was giving abysmal results. A simple BiLSTM with embeddings outperformed ULMFiT without embeddings.\n3. It needed major changes to the architecture to use word embeddings provided by the competition.\n4. Apparently very deep networks do not perform well in this competition.\n\nSo, I believe it is wiser to design a model from scratch."},{"metadata":{},"cell_type":"markdown","source":"## Overview\n\nThe following Figure illustrates my final model.\n![QuoraDiagram%20%281%29.jpeg](attachment:QuoraDiagram%20%281%29.jpeg)","attachments":{"QuoraDiagram%20%281%29.jpeg":{"image/jpeg":"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"}}},{"metadata":{},"cell_type":"markdown","source":"## Imports"},{"metadata":{"_uuid":"abb7e3c30b8a412a50c6b451c49939e3cf4bc11b","scrolled":true,"trusted":true},"cell_type":"code","source":"import random\nimport copy\nimport time\nimport pandas as pd\nimport numpy as np\nimport gc\nimport re\nimport torch\nfrom torchtext import data\nfrom tqdm import tqdm\nfrom tqdm import tqdm_notebook, tnrange\n\ntqdm.pandas(desc='Progress')\n\nimport torch.nn as nn\nimport torch.optim as optim\n\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence\nfrom sklearn.metrics import f1_score\nimport torchtext\nimport os\n\nfrom multiprocessing import  Pool\nfrom keras.preprocessing.text import Tokenizer\nfrom sklearn.preprocessing import StandardScaler\nfrom keras.preprocessing.sequence import pad_sequences\n\nfrom sklearn.model_selection import StratifiedKFold\nfrom torch.optim.optimizer import Optimizer\n\nfrom functools import partial\nimport numpy as np","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"9a4ff5590a6f152dc1bec5aeca79aef10218f7de"},"cell_type":"markdown","source":"## Basic Parameters"},{"metadata":{"_uuid":"deee49df5ca1c4413f71677939e26aa1ff784e44","scrolled":true,"trusted":true},"cell_type":"code","source":"embed_size = 300 # Word vector dimension number\nmax_features = 120000 # Number of unique tokens to use\nmaxlen = 80 # maximum sequence length for LSTM/GRU\nbatch_size = 512\nn_epochs = 5\nn_splits = 5 # K-Folds\n\ndebug = 0\n# debug = 0 runs full model on GPU, debug = 1 runs a part of it on CPU. Because Weekly GPU quota.\n\nnum_embeddings = 2 # number of embedding files used","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Some submissions use seeding methods for derterministic results, essentially treating them as hyperparameters, which is a bad practise. \n\nAs Psi quoted :\n> Seeing people setting the seed as a hyperparameter is weird.\n\nI decided not to use any seeds based on his recommendation."},{"metadata":{},"cell_type":"markdown","source":"## Text Preprocessing and Loading\nFirst, I needed to learn pre-processing for using word embeddings. Dieters [kernel](https://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings) was a godsend for me.\n\nI also borrowed some helper functions from this [kernel](https://www.kaggle.com/theoviel/improve-your-score-with-some-text-preprocessing)."},{"metadata":{},"cell_type":"markdown","source":"### Punctuation and Misspelled Word Dictionary"},{"metadata":{"trusted":true},"cell_type":"code","source":"puncts = [',', '.', '\"', ':', ')', '(', '-', '!', '?', '|', ';', \"'\", '$', '&', '/', '[', ']', '>', '%', '=', '#', '*', '+', '\\\\', '•',  '~', '@', '£', \n '·', '_', '{', '}', '©', '^', '®', '`',  '<', '→', '°', '€', '™', '›',  '♥', '←', '×', '§', '″', '′', 'Â', '█', '½', 'à', '…', \n '“', '★', '”', '–', '●', 'â', '►', '−', '¢', '²', '¬', '░', '¶', '↑', '±', '¿', '▾', '═', '¦', '║', '―', '¥', '▓', '—', '‹', '─', \n '▒', '：', '¼', '⊕', '▼', '▪', '†', '■', '’', '▀', '¨', '▄', '♫', '☆', 'é', '¯', '♦', '¤', '▲', 'è', '¸', '¾', 'Ã', '⋅', '‘', '∞', \n '∙', '）', '↓', '、', '│', '（', '»', '，', '♪', '╩', '╚', '³', '・', '╦', '╣', '╔', '╗', '▬', '❤', 'ï', 'Ø', '¹', '≤', '‡', '√', ]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mispell_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\"}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"first_word_mispell_dict = {\n                'whta': 'what', 'howdo': 'how do', 'Whatare': 'what are', 'howcan': 'how can', 'howmuch': 'how much', \n                'howmany': 'how many', 'whydo': 'why do', 'doi': 'do i', 'howdoes': 'how does', \"whst\": 'what', \n                'shoupd': 'should', 'whats': 'what is', \"im\": \"i am\", \"whatis\": \"what is\", \"iam\": \"i am\", \"wat\": \"what\",\n                \"wht\": \"what\",\"whts\": \"what is\", \"whtwh\": \"what\", \"whtat\": \"what\", \"whtlat\": \"what\", \"dueto to\": \"due to\",\n                \"dose\": \"does\", \"wha\": \"what\", 'hw': \"how\", \"its\": \"it is\", \"whay\": \"what\", \"ho\": \"how\", \"whart\": \"what\", \n                \"woe\": \"wow\", \"wt\": \"what\", \"ive\": \"i have\",\"wha\": \"what\", \"wich\": \"which\", \"whic\": \"which\", \"whys\": \"why\", \n                \"doe\": \"does\", \"wjy\": \"why\", \"wgat\": \"what\", \"hiw\": \"how\",\"howto\": \"how to\", \"lets\": \"let us\", \"haw\": \"how\", \n                \"witch\": \"which\", \"wy\": \"why\", \"girlfriend\": \"girl friend\", \"hows\": \"how is\",\"whyis\": \"why is\", \"whois\": \"who is\",\n                \"dont\": \"do not\", \"hat\": \"what\", \"whos\": \"who is\", \"whydoes\": \"why does\", \"whic\": \"which\",\"hy\": \"why\", \"w? hy\": \"why\",\n                \"ehat\": \"what\", \"whate\": \"what\", \"whai\": \"what\", \"whichis\": \"which is\", \"whi\": \"which\", \"isit\": \"is it\",\"ca\": \"can\", \n                \"wwhat\": \"what\", \"wil\": \"will\", \"wath\": \"what\", \"plz\": \"please\", \"ww\": \"how\", \"hou\": \"how\", \"whch\": \"which\",\n                \"ihave\": \"i have\", \"cn\": \"can\", \"doesnt\": \"does not\", \"shoul\": \"should\", \"whatdo\": \"what do\", \"isnt\": \"is not\", \n                \"whare\": \"what are\",\"whick\": \"which\", \"whatdoes\": \"what does\", \"hwo\": \"how\", \"howdid\": \"how did\", \"why dose\": \"why does\"\n}","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Helper Functions"},{"metadata":{},"cell_type":"markdown","source":"#### Cleaning Text and Numbers"},{"metadata":{"trusted":true},"cell_type":"code","source":"def clean_text(x):\n    x = str(x)\n    for punct in puncts:\n        if punct in x:\n            x = x.replace(punct, f' {punct} ')\n    return x\n\n\ndef clean_numbers(x):\n    if bool(re.search(r'\\d', 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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Fixing misspellings"},{"metadata":{"_uuid":"abeab4c80d6829cf2eae706bfa7929e2871af81f","scrolled":true,"trusted":true},"cell_type":"code","source":"def _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)\n\ndef correct_first_word(x):\n    for key in first_word_mispell_dict.keys():\n        if x.startswith(key + \" \"):\n            x = x.replace(key + \" \", first_word_mispell_dict[key] + \" \")\n            break\n    return x","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Engineering Statistical features\nI have extracted these statistical features from the train data.\n1. Total length \n2. Capitals\n3. Ratio of capitals and length\t\n4. Number of words\t\n5. Number of unique words\t\n6. Ratio of unique words and total words"},{"metadata":{"trusted":true},"cell_type":"code","source":"def add_features(df):\n    df['question_text'] = df['question_text'].progress_apply(lambda x:str(x))\n    df[\"lower_question_text\"] = df[\"question_text\"].apply(lambda x: x.lower())\n    df['total_length'] = df['question_text'].progress_apply(len)\n    df['capitals'] = df['question_text'].progress_apply(lambda comment: sum(1 for c in comment if c.isupper()))\n    df['caps_vs_length'] = df.progress_apply(lambda row: float(row['capitals'])/float(row['total_length']),\n                                axis=1)\n    df['num_words'] = df.question_text.str.count('\\S+')\n    df['num_unique_words'] = df['question_text'].progress_apply(lambda comment: len(set(w for w in comment.split())))\n    df['words_vs_unique'] = df['num_unique_words'] / df['num_words'] \n    return df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Parallel processing code for speedup"},{"metadata":{"trusted":true},"cell_type":"code","source":"def parallelize_apply(df,func,colname,num_process,newcolnames):\n    pool =Pool(processes=num_process)\n    arraydata = pool.map(func,tqdm(df[colname].values))\n    pool.close()\n    \n    newdf = pd.DataFrame(arraydata,columns = newcolnames)\n    df = pd.concat([df,newdf],axis=1)\n    return df\n\ndef parallelize_dataframe(df, func):\n    df_split = np.array_split(df, 4)\n    pool = Pool(4)\n    df = pd.concat(pool.map(func, df_split))\n    pool.close()\n    pool.join()\n    return df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Loading Text and Applying preprocessing"},{"metadata":{"trusted":true},"cell_type":"code","source":"if debug:\n    train_df = pd.read_csv(\"../input/quora-insincere-questions-classification/train.csv\")[:800]\n    test_df = pd.read_csv(\"../input/quora-insincere-questions-classification/test.csv\")[:200]\nelse:\n    train_df = pd.read_csv(\"../input/quora-insincere-questions-classification/train.csv\")\n    test_df = pd.read_csv(\"../input/quora-insincere-questions-classification/test.csv\")\nprint(\"Train shape : \",train_df.shape)\nprint(\"Test shape : \",test_df.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = parallelize_dataframe(train_df, add_features)\ntest = parallelize_dataframe(test_df, add_features)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: x.lower())\ntest_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: x.lower())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: clean_text(x))\ntest_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: clean_text(x))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: clean_numbers(x))\ntest_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: clean_numbers(x))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df[\"question_text\"] = train_df[\"question_text\"].progress_apply(lambda x: replace_typical_misspell(x))\ntest_df[\"question_text\"] = test_df[\"question_text\"].progress_apply(lambda x: replace_typical_misspell(x))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_X = train_df[\"question_text\"].fillna(\"_##_\").values\ntest_X = test_df[\"question_text\"].fillna(\"_##_\").values","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Tokenization\n\nI have used keras tokenizer here. All out of vocabulary words will be replaced with special 'xxunk' token.\nTokenizer is fit on the train data and used to make sequence of texts. Then the sequences are padded so all of them have the same length. Longer sequences are truncated and shorter ones are padded.\n\nLSTM/GRU do not like uneven sequence lengths."},{"metadata":{"_uuid":"63cb21525251b060aeb309e7be4b48772f8720f5","scrolled":true,"trusted":true},"cell_type":"code","source":"def tokenize_and_split(train_X,test_X):\n    tokenizer = Tokenizer(num_words=max_features,oov_token = 'xxunk',filters='')\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    train_X = pad_sequences(train_X, maxlen=maxlen)\n    test_X = pad_sequences(test_X, maxlen=maxlen)\n\n    train_y = train_df['target'].values\n \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    features, test_features = make_stat_features()\n    train_features = features[trn_idx]\n    \n    return train_X, test_X, train_y, train_features, test_features ,tokenizer.word_index","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Scaling Statistical Features\n\nCalculate Statistical Features will have to be scaled before putting through a neuralnet.\n\nAs because these features have different ranges for values, some features may produce vanishing gradients. For example number of words will be, on average, a way larger value than number of unique words. So, these feaures are scaled using a standard scaler."},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_stat_features():\n    \n    train_features = train[['num_unique_words','words_vs_unique','total_length','capitals',\n                      'caps_vs_length','num_words']].fillna(0)\n    test_features = test[['num_unique_words','words_vs_unique','total_length','capitals',\n                      'caps_vs_length','num_words']].fillna(0)\n    \n    ss = StandardScaler()\n    ss.fit(np.vstack((train_features, test_features)))\n    train_features = ss.transform(train_features)\n    test_features = ss.transform(test_features)\n    \n    return train_features, test_features","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3c72fcddb4f680879e231c3dbfc0c71e27fc424c","scrolled":true,"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, train_features, test_features , word_index = tokenize_and_split(train_X,test_X) ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Loading Embeddings\n\n1st place solution uses **0.7 \\* glove + 0.3 \\* paragram** matrix for its embedding layer.\n\nIn my reasoning, as these word embeddings were not trained in exactly the same system, some useful information may be lost if a weighted average is used. That is why, I have concatenated them into a **num_words \\* (embedding_dim \\* num_embedding)** matrix."},{"metadata":{"_uuid":"7026ee1d913f54dd4b560f654efdb9f833581cd3","scrolled":true,"trusted":true},"cell_type":"code","source":"def load_embedding(path, word_index,emb_mean, emb_std):\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(path, encoding=\"utf8\", errors='ignore') if len(o)>100)\n\n    all_embs = np.stack(embeddings_index.values())\n    embed_size = all_embs.shape[1]\n\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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"6a5f4502324d369ff6faa3692accee4f8a233005","scrolled":true,"trusted":true},"cell_type":"code","source":"if debug:\n    paragram_embeddings = np.random.randn(120000,300)\n    glove_embeddings = np.random.randn(120000,300)\nelse:\n    glove_embeddings = load_embedding('../input/quora-insincere-questions-classification/embeddings/glove.840B.300d/glove.840B.300d.txt',word_index,-0.005838499,0.48782197)    \n    paragram_embeddings = load_embedding('../input/quora-insincere-questions-classification/embeddings/paragram_300_sl999/paragram_300_sl999.txt',word_index,-0.0053247833,0.49346462)\n\nembedding_matrix = np.concatenate((glove_embeddings, paragram_embeddings), axis=1)          ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Model Definition"},{"metadata":{},"cell_type":"markdown","source":"### Attention Module\n\nApplying attention on LSTM and GRU outputs should boost model performance."},{"metadata":{"trusted":true},"cell_type":"code","source":"class AttentionBlock(nn.Module):\n    def __init__(self, feature_dim, step_dim, bias=True, **kwargs):\n        super(AttentionBlock, self).__init__(**kwargs)\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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Embedding and Dropout Layer\n\nMany public kernels have wrongly applied spatial droput on the batch dimension as discussed [here](https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/79911).\n\nSome reshaping was done in order to apply correct dropout on the correct dimension, i.e. feature."},{"metadata":{"trusted":true},"cell_type":"code","source":"class EmbeddingDropout(nn.Module):\n    def __init__(self, embedding_matrix, max_features = 120000, embedding_size = 300):\n        super(EmbeddingDropout,self).__init__()\n        self.embedding = nn.Embedding(max_features, embedding_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_drop = nn.Dropout2d(0.1)\n    \n    def forward(self,x):\n        h_embeddings = self.embedding(x)\n        h_embeddings = h_embeddings.unsqueeze(0)\n        h_embeddings = h_embeddings.permute(1,3,0,2)\n        h_embeddings = self.embedding_drop(h_embeddings) \n        h_embeddings = h_embeddings.permute(2,0,3,1)\n        h_embeddings = h_embeddings.squeeze(0)\n\n        return h_embeddings","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Backbone of the model\n\nThe main body of the model consists of LSTM and GRU (128).\n\nThe body returns LSTM+GRU outputs and Attention infused  LSTM+GRU outputs."},{"metadata":{"trusted":true},"cell_type":"code","source":"class Body(nn.Module):\n    def __init__ (self, embedding_size= 300, hidden_size= 128):\n        super(Body,self).__init__()\n        self.lstm = nn.LSTM(embedding_size*num_embeddings, hidden_size, bidirectional=True, batch_first=True)\n        self.gru = nn.GRU(hidden_size*2, hidden_size, bidirectional=True, batch_first=True)\n        self.hidden= hidden_size\n        \n        for name, param in self.lstm.named_parameters():\n            if 'bias' in name:\n                nn.init.constant_(param, 0.0)\n            elif 'weight_ih' in name:\n                nn.init.kaiming_normal_(param)\n            elif 'weight_hh' in name:\n                nn.init.orthogonal_(param)\n        \n        for name, param in self.gru.named_parameters():\n            if 'bias' in name:\n                nn.init.constant_(param, 0.0)\n            elif 'weight_ih' in name:\n                nn.init.kaiming_normal_(param)\n            elif 'weight_hh' in name:\n                nn.init.orthogonal_(param)\n        \n        self.lstm_attention = AttentionBlock(hidden_size*2, maxlen)\n        self.gru_attention = AttentionBlock(hidden_size*2, maxlen)\n   \n    def forward(self,x):\n        h_lstm, _ = self.lstm(x)\n        h_gru, _ = self.gru(h_lstm)\n        \n        h_lstm_att = self.lstm_attention(h_lstm)\n        h_gru_att = self.gru_attention(h_gru)\n\n        return h_lstm_att, h_gru_att, h_lstm, h_gru","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Extractor Layer\nThis layer serves as the feature extractor for lstm, gru outputs and statistical features.\n\nConv1d is applied on lstm output, which goes into a maxpool.\nGRU output is sent through avgpool.\nStatistical Features are put through a Linear layer"},{"metadata":{"trusted":true},"cell_type":"code","source":"class Extractor(nn.Module):\n    def __init__(self,maxlen= 70,hidden_size= 128,out= 64,len_feats= 6):\n        super(Extractor,self).__init__()\n        self.conv = nn.Conv1d(maxlen,out,kernel_size= 1,stride= 2)\n        self.stat = nn.Linear(len_feats,hidden_size)\n        \n    def forward(self,h_lstm,h_gru,stat_features):\n        conv_out = self.conv(h_lstm)\n        l_maxpool, _ = torch.max(conv_out,1)\n        g_avgpool = torch.mean(h_gru,1)\n        statistical_features = self.stat(stat_features)\n        \n        return l_maxpool, g_avgpool, statistical_features   ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Output Layer\n\nThis layer consists of a dropout, a relu and a batchnorm layer, sandwiched between two linear layers."},{"metadata":{"trusted":true},"cell_type":"code","source":"class Head(nn.Module):\n    def __init__(self,embedding_size= 300,intermediate_layer=64,maxlen=70,hidden_size=128):\n        super(Head,self).__init__()\n        self.linear = nn.Linear(hidden_size*8,intermediate_layer)\n        self.dropout = nn.Dropout(0.15)\n        self.bn = nn.BatchNorm1d(intermediate_layer)\n        self.output = nn.Linear(intermediate_layer, 1)\n        \n    def forward(self,x):\n        return self.output(self.bn(self.dropout(self.linear(x))))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Complete Model\n\n1. First input is sent through embedding layer, returning feature vectors.\n2. Embedding output is then passed to the Body of the model.\n3. Extractor layer is used to find features from the sequential output of the model backbone.\n4. Attention infused lstm+gru outputs and extracted features are concatenated.\n5. Concatenated features are sent to the output layer."},{"metadata":{"trusted":true},"cell_type":"code","source":"class NeuralNet(nn.Module):\n    def __init__(self, embedding_matrix,max_features=120000,embedding_size=300,\n                 maxlen=70, hidden_size=128, len_feats = 6):\n        super(NeuralNet,self).__init__()\n        self.embedding = EmbeddingDropout(embedding_matrix,max_features= max_features,embedding_size= embedding_size)\n        self.stem = Body(embedding_size,hidden_size)\n        self.extractor = Extractor(maxlen= maxlen,hidden_size= hidden_size, out= 64, len_feats= len_feats)\n        self.head = Head(embedding_size= embedding_size,maxlen= maxlen,hidden_size = hidden_size)\n    \n    def forward(self,x,stat_features):\n        embedding_output = self.embedding(x)\n        h_lstm_att, h_gru_att, h_lstm, h_gru = self.stem(embedding_output)\n        l_maxpool, g_avgpool, extracted_feats = self.extractor(h_lstm, h_gru, stat_features)\n        features = torch.cat((h_lstm_att, h_gru_att, l_maxpool, g_avgpool, extracted_feats),1)\n        out = self.head(features)\n        \n        return out","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss_fn = torch.nn.BCEWithLogitsLoss(reduction='sum')\nstep_size = 300","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Training"},{"metadata":{},"cell_type":"markdown","source":"### Custom dataset\n\nA custom dataset had to be used to keep track of the indices."},{"metadata":{"trusted":true},"cell_type":"code","source":"class MyDataset(Dataset):\n    def __init__(self,dataset):\n        self.dataset = dataset\n    def __getitem__(self,index):\n        data,target = self.dataset[index]\n        return data,target,index\n    def __len__(self):\n        return len(self.dataset)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"551ff8837a1b0899e0925c1a3801547adeddccae","trusted":true},"cell_type":"code","source":"def sigmoid(x):\n    return 1 / (1 + np.exp(-x))\nif debug :\n    x_test_cuda = torch.tensor(x_test, dtype=torch.long)\nelse :\n    x_test_cuda = torch.tensor(x_test, dtype=torch.long).cuda()\n\ntest = torch.utils.data.TensorDataset(x_test_cuda)\ntest_loader = torch.utils.data.DataLoader(test, batch_size=batch_size, shuffle=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Training Loop\n\nUsing Stratified K fold Cross Validation. Works as an ensemble."},{"metadata":{},"cell_type":"markdown","source":"#### GPU Loop"},{"metadata":{"_uuid":"b711f30cbb4b0297fec816b8102c477d9a546c80","trusted":true},"cell_type":"code","source":"def kfold_train(x_train,y_train,x_test, model_obj, train_features, test_features,clip = True):\n    avg_losses_f = []\n    avg_val_losses_f = []\n    train_preds = np.zeros((len(x_train)))\n    test_preds = np.zeros((len(x_test)))\n\n    splits = list(StratifiedKFold(n_splits=n_splits, shuffle=True).split(x_train, y_train))\n\n    for i, (train_idx, valid_idx) in tqdm(enumerate(splits)):\n        x_train = np.array(x_train)\n        y_train = np.array(y_train)\n\n        x_train_fold = torch.tensor(x_train[train_idx.astype(int)], dtype=torch.long).cuda()\n        y_train_fold = torch.tensor(y_train[train_idx.astype(int), np.newaxis], dtype=torch.float32).cuda()\n        x_val_fold = torch.tensor(x_train[valid_idx.astype(int)], dtype=torch.long).cuda()\n        y_val_fold = torch.tensor(y_train[valid_idx.astype(int), np.newaxis], dtype=torch.float32).cuda()\n        \n        feature_train_fold = train_features[train_idx.astype(int)]\n        feature_valid_fold = train_features[valid_idx.astype(int)]\n        \n        model = copy.deepcopy(model_obj)\n        model.cuda()\n\n        train_ds = MyDataset(torch.utils.data.TensorDataset(x_train_fold, y_train_fold))\n        valid_ds = MyDataset(torch.utils.data.TensorDataset(x_val_fold, y_val_fold))\n        \n        train_dl = torch.utils.data.DataLoader(train_ds, batch_size=batch_size, shuffle=True)\n        valid_dl = torch.utils.data.DataLoader(valid_ds, batch_size=batch_size, shuffle=False)\n\n        optimizer = torch.optim.Adam(model.parameters())\n        scheduler = optim.lr_scheduler.ExponentialLR(optimizer,0.01)\n\n        print('Fold %d'%i)\n        for epoch in tqdm(range(n_epochs)):\n            start_time = time.time()\n            avg_loss = 0.\n            model.train()\n\n            for i, (x_batch, y_batch, index) in enumerate(train_dl):\n                y_pred = model(x_batch,torch.FloatTensor(feature_train_fold[index]).cuda())\n\n                loss = loss_fn(y_pred, y_batch)\n                optimizer.zero_grad()\n                loss.backward()\n\n                if clip:\n                    nn.utils.clip_grad_norm_(model.parameters(),1)\n                optimizer.step()\n                avg_loss += loss.item() / len(train_dl)\n                \n            model.eval()\n            \n            valid_preds_fold = np.zeros((x_val_fold.size(0)))\n            test_preds_fold = np.zeros((len(x_test)))\n            \n            avg_val_loss = 0.\n            for i, (x_batch, y_batch,index) in enumerate(valid_dl):\n\n                y_pred = model(x_batch,torch.FloatTensor(feature_valid_fold[index]).cuda()).detach()\n                \n                avg_val_loss += loss_fn(y_pred, y_batch).item() / len(valid_dl)\n                valid_preds_fold[index] = sigmoid(y_pred.cpu().numpy())[:, 0]\n            \n            elapsed_time = time.time() - start_time \n\n            print('Epoch {}/{} \\t loss={:.4f} \\t val_loss={:.4f} \\t time={:.2f}s'\n                  .format(epoch + 1, n_epochs, avg_loss, avg_val_loss, elapsed_time))\n        \n        avg_losses_f.append(avg_loss)\n        avg_val_losses_f.append(avg_val_loss) \n\n        for i, (x_batch,) in enumerate(test_loader):\n            y_pred = model(x_batch,torch.FloatTensor(test_features[i * batch_size:(i+1) * batch_size]).cuda())\n            test_preds_fold[i * batch_size:(i+1) * batch_size] = sigmoid(y_pred.detach().cpu().numpy())[:, 0] \n        \n        train_preds[valid_idx] = valid_preds_fold\n        test_preds += test_preds_fold / len(splits)\n\n    print('All \\t loss={:.4f} \\t val_loss={:.4f} \\t '.format(np.average(avg_losses_f),np.average(avg_val_losses_f)))\n    return train_preds, test_preds","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### CPU Loop\n\nFor debugging without GPU"},{"metadata":{"trusted":true},"cell_type":"code","source":"def cpu_kfold_train(x_train,y_train,x_test, model_obj, train_features, test_features,clip = True):\n    avg_losses_f = []\n    avg_val_losses_f = []\n\n    train_preds = np.zeros((len(x_train)))\n    test_preds = np.zeros((len(x_test)))\n\n    splits = list(StratifiedKFold(n_splits=n_splits, shuffle=True).split(x_train, y_train))\n\n    for i, (train_idx, valid_idx) in tqdm(enumerate(splits)):\n        x_train = np.array(x_train)\n        y_train = np.array(y_train)\n\n        x_train_fold = torch.tensor(x_train[train_idx.astype(int)], dtype=torch.long)\n        y_train_fold = torch.tensor(y_train[train_idx.astype(int), np.newaxis], dtype=torch.float32)\n        x_val_fold = torch.tensor(x_train[valid_idx.astype(int)], dtype=torch.long)\n        y_val_fold = torch.tensor(y_train[valid_idx.astype(int), np.newaxis], dtype=torch.float32)\n        \n        feature_train_fold = train_features[train_idx.astype(int)]\n        feature_valid_fold = train_features[valid_idx.astype(int)]\n        \n        model = copy.deepcopy(model_obj)\n\n        train_ds = MyDataset(torch.utils.data.TensorDataset(x_train_fold, y_train_fold))\n        valid_ds = MyDataset(torch.utils.data.TensorDataset(x_val_fold, y_val_fold))\n        \n        train_dl = torch.utils.data.DataLoader(train_ds, batch_size=batch_size, shuffle=True)\n        valid_dl = torch.utils.data.DataLoader(valid_ds, batch_size=batch_size, shuffle=False)\n\n        optimizer = torch.optim.Adam(model.parameters())\n        scheduler = optim.lr_scheduler.ExponentialLR(optimizer,0.01)\n\n        print(f'Fold {i + 1}')\n        for epoch in tqdm(range(n_epochs)):\n            start_time = time.time()\n            avg_loss = 0.\n            model.train()\n\n            for i, (x_batch, y_batch, index) in tqdm(enumerate(train_dl)):\n                y_pred = model(x_batch,torch.FloatTensor(feature_train_fold[index]))\n\n                loss = loss_fn(y_pred, y_batch)\n                optimizer.zero_grad()\n                loss.backward()\n\n                if clip:\n                    nn.utils.clip_grad_norm_(model.parameters(),1)\n                optimizer.step()\n                avg_loss += loss.item() / len(train_dl)\n                \n            model.eval()\n            \n            valid_preds_fold = np.zeros((x_val_fold.size(0)))\n            test_preds_fold = np.zeros((len(x_test)))\n            \n            avg_val_loss = 0.\n            for i, (x_batch, y_batch,index) in tqdm(enumerate(valid_dl)):\n\n                y_pred = model(x_batch,torch.FloatTensor(feature_valid_fold[index])).detach()\n                \n                avg_val_loss += loss_fn(y_pred, y_batch).item() / len(valid_dl)\n                valid_preds_fold[index] = sigmoid(y_pred.detach().numpy())[:, 0]\n            \n            elapsed_time = time.time() - start_time \n\n            print('Epoch {}/{} \\t loss={:.4f} \\t val_loss={:.4f} \\t time={:.2f}s'.format(epoch + 1, n_epochs, avg_loss, avg_val_loss, elapsed_time))\n        \n        avg_losses_f.append(avg_loss)\n        avg_val_losses_f.append(avg_val_loss) \n\n        for i, (x_batch,) in tqdm(enumerate(test_loader)):\n            y_pred = model(x_batch,torch.FloatTensor(test_features[i * batch_size:(i+1) * batch_size]))\n            test_preds_fold[i * batch_size:(i+1) * batch_size] = sigmoid(y_pred.detach().numpy())[:, 0] \n        \n        train_preds[valid_idx] = valid_preds_fold\n        test_preds += test_preds_fold / len(splits)\n\n    print('All \\t loss={:.4f} \\t val_loss={:.4f} \\t '.format(np.average(avg_losses_f),np.average(avg_val_losses_f)))\n    return train_preds, test_preds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = NeuralNet(embedding_matrix,maxlen=maxlen,max_features=len(embedding_matrix))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3b8f851d15f3e34d40eab4146393c145886b3966","trusted":true},"cell_type":"code","source":"if debug:\n    train_preds, test_preds = cpu_kfold_train(x_train,y_train,x_test,model,train_features,test_features)\nelse :\n    train_preds, test_preds = kfold_train(x_train,y_train,x_test,model,train_features,test_features)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Choosing the best threshold for classification"},{"metadata":{"_uuid":"2ab6ac01d6d69d88ef05a542cb6f8e27cd23a8ab","trusted":true},"cell_type":"code","source":"def findthreshold (y_train, train_preds):\n    best_f1= 0\n    best_thresh= 0\n    for thresh in tqdm(np.arange(0.1,0.501,0.01)):\n        f1 = f1_score(y_train,(train_preds>thresh))\n        if f1 > best_f1:\n            best_thresh = thresh\n            best_f1 = f1\n    print('best threshold is {:.4f} with F1 score: {:.4f}'.format(best_thresh, best_f1))\n    return best_thresh, best_f1\n\nthreshold, score = findthreshold(y_train,train_preds)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submit"},{"metadata":{"_uuid":"d8bf091cac7ce485afc35bdcc50d3a9ea59f8e2a","trusted":true},"cell_type":"code","source":"if debug:\n    df_test = pd.read_csv(\"../input/quora-insincere-questions-classification/test.csv\")[:200]\nelse:\n    df_test = pd.read_csv(\"../input/quora-insincere-questions-classification/test.csv\")\nsubmission = df_test[['qid']].copy()\nsubmission['prediction'] = (test_preds > threshold).astype(int)\nsubmission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"}},"nbformat":4,"nbformat_minor":1}