{"cells":[{"metadata":{"_uuid":"710ed17d0c57bd287be0ee3b2782a53a54510561"},"cell_type":"markdown","source":"## Summary\n\nTextCNN works well for Text Classification. It takes care of words in close range. It is able to see \"new york\" together. But it still can't take care of all the context provided in a particular text sequence. It still does not learn the sequential structure of the data, where every word is dependent on the previous word. Or a word in the previous sentence. \n\nRNN help us with that. *They are able to remember previous information using hidden states and connect it to the current task.*\n\nLong Short Term Memory networks (LSTM) are a subclass of RNN, specialized in remembering information for a long period of time. More over the Bidirectional LSTM keeps the contextual information in both directions which is pretty useful in text classification task (But won't work for a time series prediction task as we don't have visibility into the future in this case).\n\n<div style=\"margin-top: 9px; margin-bottom: 10px;\">\n<center><img src=\"https://mlwhiz.com/images/birnn.png\"  height=\"400\" width=\"700\" ></center>\n</div>\n\nFor a most simplistic explanation of Bidirectional RNN, think of RNN cell as a black box taking as input a hidden state(a vector) and a word vector and giving out an output vector and the next hidden state. This box has some weights which are to be tuned using Backpropogation of the losses. Also the same cell is applied to all the words so that the weights are shared across the words in the sentence. This is called weight-sharing. \n\n            Hidden state, Word vector ->(RNN Cell) -> Output Vector , Next Hidden state\n\nFor a sequence of length 4 like 'you will never believe', The RNN cell will give 4 output vectors , which can be concatenated and then used as part of a dense feedforward architecture. \n\nIn the Bidirectional RNN the only change is that we read the text in the normal fashion as well in reverse. So we stack two RNNs in parallel and hence we get 8 output vectors to append. \n\nOnce we get the output vectors we send them through a series of dense layers and finally a softmax layer to build a text classifier.\n\nIn most cases you will just need to understand how to stack some layers in a neural network to get the best results. One can think of having multiple bidirectional GRU/LSTM layers in the network if it performs better.\n\nDue to the limitations of RNNs like not remembering long term dependencies, in practice we almost always use LSTM/GRU to model long term dependencies. In such a case you can just think of the RNN cell being replaced by a LSTM cell or a GRU cell in the above figure. An example model is provided below. You can use CuDNNGRU interchangably with CuDNNLSTM, when you build models.(CuDNNGRU/LSTM are just implementations of LSTM/GRU that are created to run faster on GPUs. In most cases always use them instead of the vanilla LSTM/GRU implementations)\n\nCheck out my [blog post](https://mlwhiz.com/blog/2019/03/09/deeplearning_architectures_text_classification/) for more information\n"},{"metadata":{"_uuid":"97b92845b85f289ba795c8c8f7117526abe073d0"},"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\n#import spacy\nfrom tqdm import tqdm_notebook, tnrange\nfrom tqdm.auto import tqdm\n\ntqdm.pandas(desc='Progress')\nfrom collections import Counter\nfrom textblob import TextBlob\nfrom nltk import word_tokenize\n\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.nn.functional as F\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence\nfrom torch.autograd import Variable\nfrom torchtext.data import Example\nfrom sklearn.metrics import f1_score\nimport torchtext\nimport os \n\nfrom keras.preprocessing.text import Tokenizer\nfrom keras.preprocessing.sequence import pad_sequences\n\n# cross validation and metrics\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.metrics import f1_score\nfrom torch.optim.optimizer import Optimizer\nfrom unidecode import unidecode\n\nfrom sklearn.preprocessing import StandardScaler\nfrom textblob import TextBlob\nfrom multiprocessing import  Pool\nfrom functools import partial\nimport numpy as np\nfrom sklearn.decomposition import PCA\nimport torch as t\nimport torch.nn as nn\nimport torch.nn.functional as F\n\n","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 # how big is each word vector\nmax_features = 120000 # how many unique words to use (i.e num rows in embedding vector)\nmaxlen = 70 # max number of words in a question to use\nbatch_size = 512 # how many samples to process at once\nn_epochs = 5 # how many times to iterate over all samples\nn_splits = 5 # Number of K-fold Splits\nSEED = 10\ndebug = 0","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b53b0ebd37575ab31361099f0538cbb0457db5b6","trusted":true},"cell_type":"code","source":"loss_fn = torch.nn.BCEWithLogitsLoss(reduction='sum')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"654cbe3c8a1f2a618a2441afe00df3b4a89e0a58"},"cell_type":"markdown","source":"### Ensure determinism in the results\n\nA common headache in this competition is the lack of determinism in the results due to cudnn. The following Kernel has a solution in Pytorch.\n\nSee https://www.kaggle.com/hengzheng/pytorch-starter. "},{"metadata":{"_uuid":"58bbf87335799247586aaed16531f4d28d10ed4a","scrolled":true,"trusted":true},"cell_type":"code","source":"def seed_everything(seed=10):\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\nseed_everything()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c890692644acce2dc4f6e2f929d6d294faca4ad2"},"cell_type":"markdown","source":"### Code for Loading Embeddings\n\nFunctions taken from the kernel:https://www.kaggle.com/gmhost/gru-capsule\n"},{"metadata":{"_uuid":"7026ee1d913f54dd4b560f654efdb9f833581cd3","scrolled":true,"trusted":true},"cell_type":"code","source":"## FUNCTIONS TAKEN FROM https://www.kaggle.com/gmhost/gru-capsule\n\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')[:300]\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 = -0.005838499,0.48782197\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        #ALLmight\n        if embedding_vector is not None: \n            embedding_matrix[i] = embedding_vector\n        else:\n            embedding_vector = embeddings_index.get(word.capitalize())\n            if embedding_vector is not None: \n                embedding_matrix[i] = embedding_vector\n    return embedding_matrix \n    \n            \ndef load_fasttext(word_index):    \n    EMBEDDING_FILE = '../input/embeddings/wiki-news-300d-1M/wiki-news-300d-1M.vec'\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) 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\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 = -0.0053247833,0.49346462\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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"07e9890ec0b490cef57565f7dff953aa56ebd3dc"},"cell_type":"markdown","source":"## Normalization\n\nBorrowed from:\n* How to: Preprocessing when using embeddings\nhttps://www.kaggle.com/christofhenkel/how-to-preprocessing-when-using-embeddings\n* Improve your Score with some Text Preprocessing https://www.kaggle.com/theoviel/improve-your-score-with-some-text-preprocessing"},{"metadata":{"_uuid":"28ebb28ba78972bb8d4fee9b53437045542d20fb","scrolled":true,"trusted":true},"cell_type":"code","source":"def build_vocab(texts):\n    sentences = texts.apply(lambda x: x.split()).values\n    vocab = {}\n    for sentence in sentences:\n        for word in sentence:\n            try:\n                vocab[word] += 1\n            except KeyError:\n                vocab[word] = 1\n    return vocab\n\ndef known_contractions(embed):\n    known = []\n    for contract in contraction_mapping:\n        if contract in embed:\n            known.append(contract)\n    return known\n\ndef clean_contractions(text, mapping):\n    specials = [\"’\", \"‘\", \"´\", \"`\"]\n    for s in specials:\n        text = text.replace(s, \"'\")\n    text = ' '.join([mapping[t] if t in mapping else t for t in text.split(\" \")])\n    return text\n\ndef correct_spelling(x, dic):\n    for word in dic.keys():\n        x = x.replace(word, dic[word])\n    return x\n\ndef unknown_punct(embed, punct):\n    unknown = ''\n    for p in punct:\n        if p not in embed:\n            unknown += p\n            unknown += ' '\n    return unknown\n\ndef clean_special_chars(text, punct, mapping):\n    for p in mapping:\n        text = text.replace(p, mapping[p])\n    \n    for p in punct:\n        text = text.replace(p, f' {p} ')\n    \n    specials = {'\\u200b': ' ', '…': ' ... ', '\\ufeff': '', 'करना': '', 'है': ''}  # Other special characters that I have to deal with in last\n    for s in specials:\n        text = text.replace(s, specials[s])\n    \n    return text\n\ndef add_lower(embedding, vocab):\n    count = 0\n    for word in vocab:\n        if word in embedding and word.lower() not in embedding:\n            embedding[word.lower()] = embedding[word]\n            count += 1\n    print(f\"Added {count} words to embedding\")    \n    ","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"abeab4c80d6829cf2eae706bfa7929e2871af81f","scrolled":true,"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\ndef 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\nmispell_dict = {\"ain't\": \"is not\", \"aren't\": \"are not\",\"can't\": \"cannot\", \"'cause\": \"because\", \"could've\": \"could have\", \"couldn't\": \"could not\", \"didn't\": \"did not\",  \"doesn't\": \"does not\", \"don't\": \"do not\", \"hadn't\": \"had not\", \"hasn't\": \"has not\", \"haven't\": \"have not\", \"he'd\": \"he would\",\"he'll\": \"he will\", \"he's\": \"he is\", \"how'd\": \"how did\", \"how'd'y\": \"how do you\", \"how'll\": \"how will\", \"how's\": \"how is\",  \"I'd\": \"I would\", \"I'd've\": \"I would have\", \"I'll\": \"I will\", \"I'll've\": \"I will have\",\"I'm\": \"I am\", \"I've\": \"I have\", \"i'd\": \"i would\", \"i'd've\": \"i would have\", \"i'll\": \"i will\",  \"i'll've\": \"i will have\",\"i'm\": \"i am\", \"i've\": \"i have\", \"isn't\": \"is not\", \"it'd\": \"it would\", \"it'd've\": \"it would have\", \"it'll\": \"it will\", \"it'll've\": \"it will have\",\"it's\": \"it is\", \"let's\": \"let us\", \"ma'am\": \"madam\", \"mayn't\": \"may not\", \"might've\": \"might have\",\"mightn't\": \"might not\",\"mightn't've\": \"might not have\", \"must've\": \"must have\", \"mustn't\": \"must not\", \"mustn't've\": \"must not have\", \"needn't\": \"need not\", \"needn't've\": \"need not have\",\"o'clock\": \"of the clock\", \"oughtn't\": \"ought not\", \"oughtn't've\": \"ought not have\", \"shan't\": \"shall not\", \"sha'n't\": \"shall not\", \"shan't've\": \"shall not have\", \"she'd\": \"she would\", \"she'd've\": \"she would have\", \"she'll\": \"she will\", \"she'll've\": \"she will have\", \"she's\": \"she is\", \"should've\": \"should have\", \"shouldn't\": \"should not\", \"shouldn't've\": \"should not have\", \"so've\": \"so have\",\"so's\": \"so as\", \"this's\": \"this is\",\"that'd\": \"that would\", \"that'd've\": \"that would have\", \"that's\": \"that is\", \"there'd\": \"there would\", \"there'd've\": \"there would have\", \"there's\": \"there is\", \"here's\": \"here is\",\"they'd\": \"they would\", \"they'd've\": \"they would have\", \"they'll\": \"they will\", \"they'll've\": \"they will have\", \"they're\": \"they are\", \"they've\": \"they have\", \"to've\": \"to have\", \"wasn't\": \"was not\", \"we'd\": \"we would\", \"we'd've\": \"we would have\", \"we'll\": \"we will\", \"we'll've\": \"we will have\", \"we're\": \"we are\", \"we've\": \"we have\", \"weren't\": \"were not\", \"what'll\": \"what will\", \"what'll've\": \"what will have\", \"what're\": \"what are\",  \"what's\": \"what is\", \"what've\": \"what have\", \"when's\": \"when is\", \"when've\": \"when have\", \"where'd\": \"where did\", \"where's\": \"where is\", \"where've\": \"where have\", \"who'll\": \"who will\", \"who'll've\": \"who will have\", \"who's\": \"who is\", \"who've\": \"who have\", \"why's\": \"why is\", \"why've\": \"why have\", \"will've\": \"will have\", \"won't\": \"will not\", \"won't've\": \"will not have\", \"would've\": \"would have\", \"wouldn't\": \"would not\", \"wouldn't've\": \"would not have\", \"y'all\": \"you all\", \"y'all'd\": \"you all would\",\"y'all'd've\": \"you all would have\",\"y'all're\": \"you all are\",\"y'all've\": \"you all have\",\"you'd\": \"you would\", \"you'd've\": \"you would have\", \"you'll\": \"you will\", \"you'll've\": \"you will have\", \"you're\": \"you are\", \"you've\": \"you have\", 'colour': 'color', 'centre': 'center', 'favourite': 'favorite', 'travelling': 'traveling', 'counselling': 'counseling', 'theatre': 'theater', 'cancelled': 'canceled', 'labour': 'labor', 'organisation': 'organization', 'wwii': 'world war 2', 'citicise': 'criticize', 'youtu ': 'youtube ', 'Qoura': 'Quora', 'sallary': 'salary', 'Whta': 'What', 'narcisist': 'narcissist', 'howdo': 'how do', 'whatare': 'what are', 'howcan': 'how can', 'howmuch': 'how much', 'howmany': 'how many', 'whydo': 'why do', 'doI': 'do I', 'theBest': 'the best', 'howdoes': 'how does', 'mastrubation': 'masturbation', 'mastrubate': 'masturbate', \"mastrubating\": 'masturbating', 'pennis': 'penis', 'Etherium': 'Ethereum', 'narcissit': 'narcissist', 'bigdata': 'big data', '2k17': '2017', '2k18': '2018', 'qouta': 'quota', 'exboyfriend': 'ex boyfriend', 'airhostess': 'air hostess', \"whst\": 'what', 'watsapp': 'whatsapp', 'demonitisation': 'demonetization', 'demonitization': 'demonetization', 'demonetisation': 'demonetization'}\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)\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3c09d981ae674e6a373189a04dba8d0932b0765b"},"cell_type":"markdown","source":"Extra feature part taken from https://github.com/wongchunghang/toxic-comment-challenge-lstm/blob/master/toxic_comment_9872_model.ipynb"},{"metadata":{"_uuid":"63cb21525251b060aeb309e7be4b48772f8720f5","scrolled":true,"trusted":true},"cell_type":"code","source":"def load_and_prec():\n    if debug:\n        train_df = pd.read_csv(\"../input/train.csv\")[:80000]\n        test_df = pd.read_csv(\"../input/test.csv\")[:20000]\n    else:\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    \n    # lower the question text\n    train_df[\"question_text\"] = train_df[\"question_text\"].apply(lambda x: x.lower())\n    test_df[\"question_text\"] = test_df[\"question_text\"].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\"].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\"].apply(lambda x: clean_numbers(x))\n    \n    # Clean spellings\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\"].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 \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    \n    return train_X, test_X, train_y, tokenizer.word_index\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3c72fcddb4f680879e231c3dbfc0c71e27fc424c","scrolled":true,"trusted":true},"cell_type":"code","source":"start = time.time()\n\nx_train, x_test, y_train, word_index = load_and_prec() \n\nprint(time.time()-start)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e5c51a8329d569d13b9f0369ebb98ca8e2e55440"},"cell_type":"markdown","source":"### Load Embeddings\n\nChanging method: first load index and then load embedding\nTwo embedding matrices have been used. Glove, and paragram. The mean of the two is used as the final embedding matrix"},{"metadata":{"_uuid":"6a5f4502324d369ff6faa3692accee4f8a233005","scrolled":true,"trusted":true},"cell_type":"code","source":"# missing entries in the embedding are set using np.random.normal so we have to seed here too\nseed_everything()\nif debug:\n    paragram_embeddings = np.random.randn(120000,300)\n    glove_embeddings = np.random.randn(120000,300)\n    embedding_matrix = np.mean([glove_embeddings, paragram_embeddings], axis=0)\nelse:\n    glove_embeddings = load_glove(word_index)    \n    paragram_embeddings = load_para(word_index)\n    embedding_matrix = np.mean([glove_embeddings, paragram_embeddings], axis=0)        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"aa6a41607b804d76a2ddc530c912b5673bcd2423"},"cell_type":"code","source":"np.shape(embedding_matrix)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0a78496e4d88d8fb351cdf26d02f1554821ed445"},"cell_type":"markdown","source":"## Running Pytorch Model"},{"metadata":{"_uuid":"0da30e2afce23b753796f3045b44ce91a07e4303"},"cell_type":"markdown","source":"### Pytorch Run Functions"},{"metadata":{"trusted":true,"_uuid":"6a5afb54f70a29808af19946ba08ef971d194e46"},"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)\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b711f30cbb4b0297fec816b8102c477d9a546c80","trusted":true},"cell_type":"code","source":"def pytorch_model_run_cv(x_train,y_train,features,x_test, model_obj, feats = False,clip = True):\n    seed_everything()\n    avg_losses_f = []\n    avg_val_losses_f = []\n    # matrix for the out-of-fold predictions\n    train_preds = np.zeros((len(x_train)))\n    # matrix for the predictions on the test set\n    test_preds = np.zeros((len(x_test)))\n    splits = list(StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED).split(x_train, y_train))\n    for i, (train_idx, valid_idx) in enumerate(splits):\n        seed_everything(i*1000+i)\n        x_train = np.array(x_train)\n        y_train = np.array(y_train)\n        if feats:\n            features = np.array(features)\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        if feats:\n            kfold_X_features = features[train_idx.astype(int)]\n            kfold_X_valid_features = features[valid_idx.astype(int)]\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        model = copy.deepcopy(model_obj)\n\n        model.cuda()\n\n        loss_fn = torch.nn.BCEWithLogitsLoss(reduction='sum')\n        optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), \n                                 lr=0.001)\n        \n        ################################################################################################\n        scheduler = False\n        ###############################################################################################\n\n        train = MyDataset(torch.utils.data.TensorDataset(x_train_fold, y_train_fold))\n        valid = MyDataset(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        for epoch in range(n_epochs):\n            start_time = time.time()\n            model.train()\n\n            avg_loss = 0.  \n            for i, (x_batch, y_batch, index) in enumerate(train_loader):\n                if feats:       \n                    f = kfold_X_features[index]\n                    y_pred = model([x_batch,f])\n                else:\n                    y_pred = model(x_batch)\n\n                if scheduler:\n                    scheduler.batch_step()\n\n                # Compute and print loss.\n                loss = loss_fn(y_pred, y_batch)\n                optimizer.zero_grad()\n                loss.backward()\n                if clip:\n                    nn.utils.clip_grad_norm_(model.parameters(),1)\n                optimizer.step()\n                avg_loss += loss.item() / len(train_loader)\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_loader):\n                if feats:\n                    f = kfold_X_valid_features[index]            \n                    y_pred = model([x_batch,f]).detach()\n                else:\n                    y_pred = model(x_batch).detach()\n                \n                avg_val_loss += loss_fn(y_pred, y_batch).item() / len(valid_loader)\n                valid_preds_fold[index] = 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, n_epochs, avg_loss, avg_val_loss, elapsed_time))\n        avg_losses_f.append(avg_loss)\n        avg_val_losses_f.append(avg_val_loss) \n        # predict all samples in the test set batch per batch\n        for i, (x_batch,) in enumerate(test_loader):\n            if feats:\n                f = test_features[i * batch_size:(i+1) * batch_size]\n                y_pred = model([x_batch,f]).detach()\n            else:\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)\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":{"_uuid":"b8caecb207a12d4a5524fe16e4524b31c7da8bac"},"cell_type":"markdown","source":"###  BiLSTM Model in Pytorch\n"},{"metadata":{"_kg_hide-input":false,"_uuid":"26e90f1839b084c126414250eac1f636b0c88937","trusted":true},"cell_type":"code","source":"class BiLSTM(nn.Module):\n    \n    def __init__(self):\n        super(BiLSTM, self).__init__()\n        self.hidden_size = 64\n        drp = 0.1\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        self.lstm = nn.LSTM(embed_size, self.hidden_size, bidirectional=True, batch_first=True)\n        self.linear = nn.Linear(self.hidden_size*4 , 64)\n        self.relu = nn.ReLU()\n        self.dropout = nn.Dropout(drp)\n        self.out = nn.Linear(64, 1)\n\n\n    def forward(self, x):\n        h_embedding = self.embedding(x)\n        h_embedding = torch.squeeze(torch.unsqueeze(h_embedding, 0))\n        \n        h_lstm, _ = self.lstm(h_embedding)\n        avg_pool = torch.mean(h_lstm, 1)\n        max_pool, _ = torch.max(h_lstm, 1)\n        #print(\"avg_pool\", avg_pool.size())\n        #print(\"max_pool\", max_pool.size())\n        conc = torch.cat(( avg_pool, max_pool), 1)\n        conc = self.relu(self.linear(conc))\n        conc = self.dropout(conc)\n        out = self.out(conc)\n        return out","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"551ff8837a1b0899e0925c1a3801547adeddccae","trusted":true},"cell_type":"code","source":"def sigmoid(x):\n    return 1 / (1 + np.exp(-x))\n\n# always call this before training for deterministic results\nseed_everything()\n\nx_test_cuda = torch.tensor(x_test, 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)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3b8f851d15f3e34d40eab4146393c145886b3966","trusted":true},"cell_type":"code","source":"train_preds , test_preds = pytorch_model_run_cv(x_train,y_train,None,x_test,BiLSTM(), feats = False, clip=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2ab6ac01d6d69d88ef05a542cb6f8e27cd23a8ab"},"cell_type":"code","source":"def bestThresshold(y_train,train_preds):\n    tmp = [0,0,0] # idx, cur, max\n    delta = 0\n    for tmp[0] in tqdm(np.arange(0.1, 0.501, 0.01)):\n        tmp[1] = f1_score(y_train, np.array(train_preds)>tmp[0])\n        if tmp[1] > tmp[2]:\n            delta = tmp[0]\n            tmp[2] = tmp[1]\n    print('best threshold is {:.4f} with F1 score: {:.4f}'.format(delta, tmp[2]))\n    return delta , tmp[2]\n\ndelta, _ = bestThresshold(y_train,train_preds)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"13dea8e1c900175db765f3fac41bcaec035d4476","trusted":true},"cell_type":"markdown","source":"## b. Runing Keras Model"},{"metadata":{"_uuid":"bf5c95169916bb4fa869eb7d14ac2b03377e486f"},"cell_type":"markdown","source":"### Keras Run Functions"},{"metadata":{"trusted":true,"_uuid":"70801ae169807ba2992348904a448c5d5490c599"},"cell_type":"code","source":"from keras.layers import Dense, Input, CuDNNLSTM, Embedding, Dropout, Activation, CuDNNGRU, Conv1D\nfrom keras.layers import Bidirectional, GlobalMaxPool1D, GlobalMaxPooling1D, GlobalAveragePooling1D\nfrom keras.layers import Input, Embedding, Dense, Conv2D, MaxPool2D, concatenate\nfrom keras.layers import Reshape, Flatten, Concatenate, Dropout, SpatialDropout1D\nfrom keras.optimizers import Adam\nfrom keras.models import Model\nfrom keras.engine.topology import Layer\nfrom keras import initializers, regularizers, constraints, optimizers, layers\n\n\nfrom keras.layers import *\nfrom keras.models import *\nfrom keras import initializers, regularizers, constraints, optimizers, layers\nfrom keras.initializers import *\nfrom keras.optimizers import *\nimport keras.backend as K\nfrom keras.callbacks import *\nimport tensorflow as tf\n\ndef model_train_cv(x_train,y_train,nfold,model_obj):\n    splits = list(StratifiedKFold(n_splits=nfold, shuffle=True, random_state=SEED).split(x_train, y_train))\n    x_train = x_train\n    y_train = np.array(y_train)\n    # matrix for the out-of-fold predictions\n    train_oof_preds = np.zeros((x_train.shape[0]))\n    for i, (train_idx, valid_idx) in enumerate(splits):\n        print(f'Fold {i + 1}')\n        x_train_fold = x_train[train_idx.astype(int)]\n        y_train_fold = y_train[train_idx.astype(int)]\n        x_val_fold = x_train[valid_idx.astype(int)]\n        y_val_fold = y_train[valid_idx.astype(int)]\n\n        clf = copy.deepcopy(model_obj)\n        clf.fit(x_train_fold, y_train_fold, batch_size=512, epochs=5, validation_data=(x_val_fold, y_val_fold))\n        \n        valid_preds_fold = clf.predict(x_val_fold)[:,0]\n\n        # storing OOF predictions\n        train_oof_preds[valid_idx] = valid_preds_fold\n    return train_oof_preds\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"9506af4bf6bec66e40536a7ffa4df58b09aca100"},"cell_type":"markdown","source":"### BiLSTM model in Keras"},{"metadata":{"trusted":true,"_uuid":"837f0f434c25cc95cf201e9a1ec06c1a735096e5"},"cell_type":"code","source":"# BiDirectional LSTM\n\ndef model_lstm_du(embedding_matrix):\n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix],trainable=False)(inp)\n    '''\n    Here 64 is the size(dim) of the hidden state vector as well as the output vector. Keeping return_sequence we want the output for the entire sequence. So what is the dimension of output for this layer?\n        64*70(maxlen)*2(bidirection concat)\n    CuDNNLSTM is fast implementation of LSTM layer in Keras which only runs on GPU\n    '''\n    x = Bidirectional(CuDNNLSTM(64, return_sequences=True))(x)\n    avg_pool = GlobalAveragePooling1D()(x)\n    max_pool = GlobalMaxPooling1D()(x)\n    conc = concatenate([avg_pool, max_pool])\n    conc = Dense(64, activation=\"relu\")(conc)\n    conc = Dropout(0.1)(conc)\n    outp = Dense(1, activation=\"sigmoid\")(conc)\n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e0cb6f64029b11d84bb901289964ee5984933740"},"cell_type":"code","source":"model = model_lstm_du(embedding_matrix)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"daaa42f4b8d503682a10ba9b0f97373a24c6fb38"},"cell_type":"code","source":"train_oof_preds = model_train_cv(x_train,y_train,5,model)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"179a6501cb7a5bcfbf0f19c42767dbafdffdca72"},"cell_type":"code","source":"delta, _ = bestThresshold(y_train,train_oof_preds)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"9d1b3fc0c8bc59f91a203adcf3dbd9d89759c8df","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"fc3e72f43d1ddba1a9d82be0cf9b642f6d5795d6","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"10c39195707e4710e11d31bafd4bde1e21ff2d6f","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"162772df446ca6ad6dda6a003d8ea2e58106192f","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"fdca46457c79c6b56409e6cfbc76d90de4d19cbe","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"717f6f2fbaa37d01db018baafcf8216fee98ce6a","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7a713658e272a3d7ec00267faa5e3d02362269ed","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7ce9e3159ce70cdaa0d706249cf80ea3157b39d0","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0fb26d857e36473fe7a458cf61692ceff5cadceb","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8dee2aefa02222d4dd5e67640708cad59285a796","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8682fc20ab59210e2aba1381232e68ce4e9519d2","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"2681fc633782d5a7005a0db95de14c6b05b88dac","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"39e764384d4073282b6a51bcd1ecf382134a33a6","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3703e549d2d8d5bb0948c2771b1e6636f0fccef2","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ee777c692947883aaa2a04349e32c6f45d5702b5"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6e8cd0bbd6cfcd4dd507f4353c29b56cd7594fe2"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f6abad47bd7c3544fc8a3ba49438afa0831131dc"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b9f763bf089050aaa711fc1e371bf83fdca515e8"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"330cc55c14571e7a88586d88676c13ec2677efed"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"eca5b5595de60fd388a4ecb4f602c89eae83d1ec"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"af8a0a6e78675868655470b4b22a8352c15933bb"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"211b2441b513ff07c13c0a5f8920728235db9507"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bc490533a242766921044c4e672e0ae76808850b"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a7c69bba55bf136310a3b890404d03e1628d985b"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"428f9cad34c6eadaf54cf316d107c9d686441fbf"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"16c92267bbbc1d611b3f7f9a1dc1eea24e009b16"},"cell_type":"code","source":"","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}