{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"## some config values \nembed_size = 300 # how big is each word vector\nmax_features = 95000 # how many unique words to use (i.e num rows in embedding vector)\nmaxlen = 70 # max number of words in a question to use","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c92fdf95bdb2bdf8df755095882544aa3ad6d221"},"cell_type":"code","source":"import os\nimport time\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom tqdm import tqdm\nimport math\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 keras.preprocessing.text import Tokenizer\nfrom keras.preprocessing.sequence import pad_sequences\nfrom 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 import backend as K\nfrom keras.engine.topology import Layer\nfrom keras import initializers, regularizers, constraints, optimizers, layers\nfrom keras.layers import concatenate\nfrom keras.callbacks import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"630d85204d2a2f495b428697140430c60e9e9664"},"cell_type":"code","source":"def 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    ## 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(2018)\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"aac23a0e88a71e6e9d1a4f8aff828ace040e3b38"},"cell_type":"code","source":"def 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_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 = 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"795e22efc9508980091314885bae8bccded52807"},"cell_type":"code","source":"class Attention(Layer):\n    def __init__(self, step_dim,\n                 W_regularizer=None, b_regularizer=None,\n                 W_constraint=None, b_constraint=None,\n                 bias=True, **kwargs):\n        self.supports_masking = True\n        self.init = initializers.get('glorot_uniform')\n\n        self.W_regularizer = regularizers.get(W_regularizer)\n        self.b_regularizer = regularizers.get(b_regularizer)\n\n        self.W_constraint = constraints.get(W_constraint)\n        self.b_constraint = constraints.get(b_constraint)\n\n        self.bias = bias\n        self.step_dim = step_dim\n        self.features_dim = 0\n        super(Attention, self).__init__(**kwargs)\n\n    def build(self, input_shape):\n        assert len(input_shape) == 3\n\n        self.W = self.add_weight((input_shape[-1],),\n                                 initializer=self.init,\n                                 name='{}_W'.format(self.name),\n                                 regularizer=self.W_regularizer,\n                                 constraint=self.W_constraint)\n        self.features_dim = input_shape[-1]\n\n        if self.bias:\n            self.b = self.add_weight((input_shape[1],),\n                                     initializer='zero',\n                                     name='{}_b'.format(self.name),\n                                     regularizer=self.b_regularizer,\n                                     constraint=self.b_constraint)\n        else:\n            self.b = None\n\n        self.built = True\n\n    def compute_mask(self, input, input_mask=None):\n        return None\n\n    def call(self, x, mask=None):\n        features_dim = self.features_dim\n        step_dim = self.step_dim\n\n        eij = K.reshape(K.dot(K.reshape(x, (-1, features_dim)),\n                        K.reshape(self.W, (features_dim, 1))), (-1, step_dim))\n\n        if self.bias:\n            eij += self.b\n\n        eij = K.tanh(eij)\n\n        a = K.exp(eij)\n\n        if mask is not None:\n            a *= K.cast(mask, K.floatx())\n\n        a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())\n\n        a = K.expand_dims(a)\n        weighted_input = x * a\n        return K.sum(weighted_input, axis=1)\n\n    def compute_output_shape(self, input_shape):\n        return input_shape[0],  self.features_dim","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f56f76bb7a994fb4034cf95fe327fb9bb2d39b19"},"cell_type":"code","source":"class CyclicLR(Callback):\n    \"\"\"This callback implements a cyclical learning rate policy (CLR).\n    The method cycles the learning rate between two boundaries with\n    some constant frequency, as detailed in this paper (https://arxiv.org/abs/1506.01186).\n    The amplitude of the cycle can be scaled on a per-iteration or \n    per-cycle basis.\n    This class has three built-in policies, as put forth in the paper.\n    \"triangular\":\n        A basic triangular cycle w/ no amplitude scaling.\n    \"triangular2\":\n        A basic triangular cycle that scales initial amplitude by half each cycle.\n    \"exp_range\":\n        A cycle that scales initial amplitude by gamma**(cycle iterations) at each \n        cycle iteration.\n    For more detail, please see paper.\n    \n    # Example\n        ```python\n            clr = CyclicLR(base_lr=0.001, max_lr=0.006,\n                                step_size=2000., mode='triangular')\n            model.fit(X_train, Y_train, callbacks=[clr])\n        ```\n    \n    Class also supports custom scaling functions:\n        ```python\n            clr_fn = lambda x: 0.5*(1+np.sin(x*np.pi/2.))\n            clr = CyclicLR(base_lr=0.001, max_lr=0.006,\n                                step_size=2000., scale_fn=clr_fn,\n                                scale_mode='cycle')\n            model.fit(X_train, Y_train, callbacks=[clr])\n        ```    \n    # Arguments\n        base_lr: initial learning rate which is the\n            lower boundary in the cycle.\n        max_lr: upper boundary in the cycle. Functionally,\n            it defines the cycle amplitude (max_lr - base_lr).\n            The lr at any cycle is the sum of base_lr\n            and some scaling of the amplitude; therefore \n            max_lr may not actually be reached depending on\n            scaling function.\n        step_size: number of training iterations per\n            half cycle. Authors suggest setting step_size\n            2-8 x training iterations in epoch.\n        mode: one of {triangular, triangular2, exp_range}.\n            Default 'triangular'.\n            Values correspond to policies detailed above.\n            If scale_fn is not None, this argument is ignored.\n        gamma: constant in 'exp_range' scaling function:\n            gamma**(cycle iterations)\n        scale_fn: Custom scaling policy defined by a single\n            argument lambda function, where \n            0 <= scale_fn(x) <= 1 for all x >= 0.\n            mode paramater is ignored \n        scale_mode: {'cycle', 'iterations'}.\n            Defines whether scale_fn is evaluated on \n            cycle number or cycle iterations (training\n            iterations since start of cycle). Default is 'cycle'.\n    \"\"\"\n\n    def __init__(self, base_lr=0.001, max_lr=0.006, step_size=2000., mode='triangular',\n                 gamma=1., scale_fn=None, scale_mode='cycle'):\n        super(CyclicLR, self).__init__()\n\n        self.base_lr = base_lr\n        self.max_lr = max_lr\n        self.step_size = step_size\n        self.mode = mode\n        self.gamma = gamma\n        if scale_fn == None:\n            if self.mode == 'triangular':\n                self.scale_fn = lambda x: 1.\n                self.scale_mode = 'cycle'\n            elif self.mode == 'triangular2':\n                self.scale_fn = lambda x: 1/(2.**(x-1))\n                self.scale_mode = 'cycle'\n            elif self.mode == 'exp_range':\n                self.scale_fn = lambda x: gamma**(x)\n                self.scale_mode = 'iterations'\n        else:\n            self.scale_fn = scale_fn\n            self.scale_mode = scale_mode\n        self.clr_iterations = 0.\n        self.trn_iterations = 0.\n        self.history = {}\n\n        self._reset()\n\n    def _reset(self, new_base_lr=None, new_max_lr=None,\n               new_step_size=None):\n        \"\"\"Resets cycle iterations.\n        Optional boundary/step size adjustment.\n        \"\"\"\n        if new_base_lr != None:\n            self.base_lr = new_base_lr\n        if new_max_lr != None:\n            self.max_lr = new_max_lr\n        if new_step_size != None:\n            self.step_size = new_step_size\n        self.clr_iterations = 0.\n        \n    def clr(self):\n        cycle = np.floor(1+self.clr_iterations/(2*self.step_size))\n        x = np.abs(self.clr_iterations/self.step_size - 2*cycle + 1)\n        if self.scale_mode == 'cycle':\n            return self.base_lr + (self.max_lr-self.base_lr)*np.maximum(0, (1-x))*self.scale_fn(cycle)\n        else:\n            return self.base_lr + (self.max_lr-self.base_lr)*np.maximum(0, (1-x))*self.scale_fn(self.clr_iterations)\n        \n    def on_train_begin(self, logs={}):\n        logs = logs or {}\n\n        if self.clr_iterations == 0:\n            K.set_value(self.model.optimizer.lr, self.base_lr)\n        else:\n            K.set_value(self.model.optimizer.lr, self.clr())        \n            \n    def on_batch_end(self, epoch, logs=None):\n        \n        logs = logs or {}\n        self.trn_iterations += 1\n        self.clr_iterations += 1\n\n        self.history.setdefault('lr', []).append(K.get_value(self.model.optimizer.lr))\n        self.history.setdefault('iterations', []).append(self.trn_iterations)\n\n        for k, v in logs.items():\n            self.history.setdefault(k, []).append(v)\n        \n        K.set_value(self.model.optimizer.lr, self.clr())\n    \n\ndef f1(y_true, y_pred):\n    '''\n    metric from here \n    https://stackoverflow.com/questions/43547402/how-to-calculate-f1-macro-in-keras\n    '''\n    def recall(y_true, y_pred):\n        \"\"\"Recall metric.\n\n        Only computes a batch-wise average of recall.\n\n        Computes the recall, a metric for multi-label classification of\n        how many relevant items are selected.\n        \"\"\"\n        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))\n        recall = true_positives / (possible_positives + K.epsilon())\n        return recall\n\n    def precision(y_true, y_pred):\n        \"\"\"Precision metric.\n\n        Only computes a batch-wise average of precision.\n\n        Computes the precision, a metric for multi-label classification of\n        how many selected items are relevant.\n        \"\"\"\n        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))\n        precision = true_positives / (predicted_positives + K.epsilon())\n        return precision\n    precision = precision(y_true, y_pred)\n    recall = recall(y_true, y_pred)\n    return 2*((precision*recall)/(precision+recall+K.epsilon()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3f90b3690d9f6dfa4de3ecaf04205c3c2ab9aa6e"},"cell_type":"code","source":"def model_lstm_atten(embedding_matrix):\n    \n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)\n    x = SpatialDropout1D(0.1)(x)\n    x = Bidirectional(CuDNNLSTM(40, return_sequences=True))(x)\n    y = Bidirectional(CuDNNGRU(40, return_sequences=True))(x)\n    \n    atten_1 = Attention(maxlen)(x) # skip connect\n    atten_2 = Attention(maxlen)(y)\n    avg_pool = GlobalAveragePooling1D()(y)\n    max_pool = GlobalMaxPooling1D()(y)\n    \n    conc = concatenate([atten_1, atten_2, avg_pool, max_pool])\n    conc = Dense(16, activation=\"relu\")(conc)\n    conc = Dropout(0.1)(conc)\n    outp = Dense(1, activation=\"sigmoid\")(conc)    \n\n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[f1])\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5e6d1dc5aa56929d4bd2a553d6e3c8a4ae629218"},"cell_type":"code","source":"def train_pred(model, train_X, train_y, val_X, val_y, epochs=2, callback=None):\n    for e in range(epochs):\n        model.fit(train_X, train_y, batch_size=512, epochs=1, validation_data=(val_X, val_y), callbacks = callback, verbose=0)\n        pred_val_y = model.predict([val_X], batch_size=1024, verbose=0)\n\n        best_score = metrics.f1_score(val_y, (pred_val_y > 0.33).astype(int))\n        print(\"Epoch: \", e, \"-    Val F1 Score: {:.4f}\".format(best_score))\n\n    pred_test_y = model.predict([test_X], batch_size=1024, verbose=0)\n    print('=' * 60)\n    return pred_val_y, pred_test_y, best_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3d3fdcabbd48f0618804cc2f2ecd5439e5e151f4"},"cell_type":"code","source":"train_X, test_X, train_y, word_index = load_and_prec()\nembedding_matrix_1 = load_glove(word_index)\n# embedding_matrix_2 = load_fasttext(word_index)\nembedding_matrix_3 = load_para(word_index)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"fa61d80831aa5b569794ae4a4a76d967735ad728"},"cell_type":"code","source":"embedding_matrix = np.mean([embedding_matrix_1, embedding_matrix_3], axis = 0)\nnp.shape(embedding_matrix)\n\ndef threshold_search(y_true, y_proba):\n    best_threshold = 0\n    best_score = 0\n    for threshold in [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\n\nDATA_SPLIT_SEED = 2018\nclr = CyclicLR(base_lr=0.001, max_lr=0.002,\n               step_size=300., mode='exp_range',\n               gamma=0.99994)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"43c17e423a09e2ad4b6e2eade77008494ffd08d3"},"cell_type":"code","source":"train_meta = np.zeros(train_y.shape)\ntest_meta = np.zeros(test_X.shape[0])\nsplits = list(StratifiedKFold(n_splits=4, shuffle=True, random_state=DATA_SPLIT_SEED).split(train_X, train_y))\nfor idx, (train_idx, valid_idx) in enumerate(splits):\n        X_train = train_X[train_idx]\n        y_train = train_y[train_idx]\n        X_val = train_X[valid_idx]\n        y_val = train_y[valid_idx]\n        model = model_lstm_atten(embedding_matrix)\n        pred_val_y, pred_test_y, best_score = train_pred(model, X_train, y_train, X_val, y_val, epochs = 8, callback = [clr,])\n        train_meta[valid_idx] = pred_val_y.reshape(-1)\n        test_meta += pred_test_y.reshape(-1) / len(splits)\n        \nsub = pd.read_csv('../input/sample_submission.csv')\nsub.prediction = test_meta > 0.33\nsub.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d3c8dff335ca4c7ee439c6624e571f4402150573"},"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}