{"cells":[{"metadata":{"_uuid":"d1c8c8a09d24612871d1ba6bf569584d8e44234d"},"cell_type":"markdown","source":"## TL;DR\n\nHi folks, this works continues **Shujian Liu**'s kernel. Combines with ** dieter**'s flippy CNNs, we have 9 models in total. \n\nThe running time of my latest attempt was **7176.5s**, which is 23.5s from getting screwed, so I doubt we can fit more models into this abomination.\n\nThe final blending coefficients were selected with Linear Regression, enjoy ensembling."},{"metadata":{"_uuid":"d65f57d963f9cbb340d5d3dcfa70b495734efc0a"},"cell_type":"markdown","source":"I was trying to clean some of my code so I can add more models. However, this can never happen without the awesome kernels from other talented Kagglers. Forgive me if I missed any.\n\n* Based on SRK's kernel: https://www.kaggle.com/sudalairajkumar/a-look-at-different-embeddings\n* Vladimir Demidov's 2DCNN textClassifier: https://www.kaggle.com/yekenot/2dcnn-textclassifier\n* Attention layer from Khoi Ngyuen: https://www.kaggle.com/suicaokhoailang/lstm-attention-baseline-0-652-lb\n* LSTM model from Strideradu: https://www.kaggle.com/strideradu/word2vec-and-gensim-go-go-go\n* https://www.kaggle.com/danofer/different-embeddings-with-attention-fork\n\nSome new things here:\n\n* Take average of embeddings (Unweighted DME) instead of blending predictions: https://arxiv.org/pdf/1804.07983.pdf\n* The original paper of this idea comes from: Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings\n* Modified the code to choose best threshold\n* Robust method for blending weights: sort the val score and give the final weight\n\nSome thoughts:\n\n* Although I pulished a kernel on Transformer, I will not use it\n* Too much randomness in CuDNN. You may get different results by just rerunning this kernel\n* Blending rocks"},{"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)\nfrom tqdm import tqdm\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":1,"outputs":[{"output_type":"stream","text":"['embeddings', 'train.csv', 'sample_submission.csv', 'test.csv']\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"e31d6e126881ee56a1de3efe02fcf309e900ef00"},"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":2,"outputs":[]},{"metadata":{"_uuid":"522d9790478f62193ea5c315372a2ab9cbe9b27f"},"cell_type":"markdown","source":"**Load packages and data**"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"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\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, Lambda\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","execution_count":3,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"}]},{"metadata":{"trusted":true,"_uuid":"5cdc95950037613c690c49b27930ae0f59eb23c3"},"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    ## split to train and val\n    train_df, val_df = train_test_split(train_df, test_size=0.08, random_state=2018)\n\n\n    ## fill up the missing values\n    train_X = train_df[\"question_text\"].fillna(\"_##_\").values\n    val_X = val_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    val_X = tokenizer.texts_to_sequences(val_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    val_X = pad_sequences(val_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    val_y = val_df['target'].values  \n    \n    #shuffling the data\n    np.random.seed(2018)\n    trn_idx = np.random.permutation(len(train_X))\n    val_idx = np.random.permutation(len(val_X))\n\n    train_X = train_X[trn_idx]\n    val_X = val_X[val_idx]\n    train_y = train_y[trn_idx]\n    val_y = val_y[val_idx]    \n    \n    return train_X, val_X, test_X, train_y, val_y, tokenizer.word_index","execution_count":4,"outputs":[]},{"metadata":{"_uuid":"dba1893c267a1e7536bbf720636647d85c7e349c"},"cell_type":"markdown","source":"**Load embeddings**"},{"metadata":{"trusted":true,"_uuid":"a662716cc5fbbcc0c84019a87c52332ed8912e8d"},"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 tqdm(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 tqdm(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 tqdm(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":5,"outputs":[]},{"metadata":{"_uuid":"73d68544af4c48bf9ee37492ecd05feb0b494351"},"cell_type":"markdown","source":"**CNN Model**"},{"metadata":{"trusted":true,"_uuid":"1f72c8c9573fb840ceb50a9cd4ac4e455e1c0ea7"},"cell_type":"code","source":"# https://www.kaggle.com/yekenot/2dcnn-textclassifier\ndef model_cnn(embedding_matrix):\n    filter_sizes = [1,2,3,5]\n    num_filters = 36\n\n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix])(inp)\n    x = Reshape((maxlen, embed_size, 1))(x)\n\n    maxpool_pool = []\n    for i in range(len(filter_sizes)):\n        conv = Conv2D(num_filters, kernel_size=(filter_sizes[i], embed_size),\n                                     kernel_initializer='he_normal', activation='elu')(x)\n        maxpool_pool.append(MaxPool2D(pool_size=(maxlen - filter_sizes[i] + 1, 1))(conv))\n\n    z = Concatenate(axis=1)(maxpool_pool)   \n    z = Flatten()(z)\n    z = Dropout(0.1)(z)\n\n    outp = Dense(1, activation=\"sigmoid\")(z)\n\n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    \n    return model\n\ndef model_cnn_flip(embedding_matrix):\n    filter_sizes = [1,2,3,5]\n    num_filters = 36\n\n    inp = Input(shape=(maxlen,))\n    x = Lambda(lambda x: K.reverse(x,axes=-1))(inp)\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix])(x)\n    x = Reshape((maxlen, embed_size, 1))(x)\n\n    maxpool_pool = []\n    for i in range(len(filter_sizes)):\n        conv = Conv2D(num_filters, kernel_size=(filter_sizes[i], embed_size),\n                                     kernel_initializer='he_normal', activation='elu')(x)\n        maxpool_pool.append(MaxPool2D(pool_size=(maxlen - filter_sizes[i] + 1, 1))(conv))\n\n    z = Concatenate(axis=1)(maxpool_pool)   \n    z = Flatten()(z)\n    z = Dropout(0.1)(z)\n\n    outp = Dense(1, activation=\"sigmoid\")(z)\n\n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    \n    return model","execution_count":6,"outputs":[]},{"metadata":{"_uuid":"5a676c3a275514a3351edf306e02d832a5f39317"},"cell_type":"markdown","source":"**Attention layer**"},{"metadata":{"trusted":true,"_uuid":"84e00df2c7b94205f5588af503f62412c48f46f3"},"cell_type":"code","source":"# https://www.kaggle.com/suicaokhoailang/lstm-attention-baseline-0-652-lb\n\nclass 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":7,"outputs":[]},{"metadata":{"_uuid":"d96793d88c22274d985436e192f62970c227c324"},"cell_type":"markdown","source":"**LSTM models**"},{"metadata":{"trusted":true,"_uuid":"05164d541a0c35cae727d0338548d156efe21427"},"cell_type":"code","source":"def model_lstm_atten(embedding_matrix):\n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)\n    x = Bidirectional(CuDNNLSTM(128, return_sequences=True))(x)\n    x = Bidirectional(CuDNNLSTM(64, return_sequences=True))(x)\n    x = Attention(maxlen)(x)\n    x = Dense(64, activation=\"relu\")(x)\n    x = Dense(1, activation=\"sigmoid\")(x)\n    model = Model(inputs=inp, outputs=x)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    \n    return model","execution_count":8,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2bf953e2b5b6d9363eda89971ecc0ac416e2ddd0"},"cell_type":"code","source":"def model_gru_srk_atten(embedding_matrix):\n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix])(inp)\n    x = Bidirectional(CuDNNGRU(64, return_sequences=True))(x)\n    x = Attention(maxlen)(x) # New\n    x = Dense(16, activation=\"relu\")(x)\n    x = Dropout(0.1)(x)\n    x = Dense(1, activation=\"sigmoid\")(x)\n    model = Model(inputs=inp, outputs=x)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    \n    return model    \n    ","execution_count":9,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"17b13ef39fbbf1919307c23efd516eddc2135023"},"cell_type":"code","source":"def model_lstm_du(embedding_matrix):\n    inp = Input(shape=(maxlen,))\n    x = Embedding(max_features, embed_size, weights=[embedding_matrix])(inp)\n    x = Bidirectional(CuDNNGRU(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    \n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    return model","execution_count":10,"outputs":[]},{"metadata":{"_uuid":"a8c857424e9c9f1703a71c1c0ade28713314dd29"},"cell_type":"markdown","source":"**Train and predict**"},{"metadata":{"trusted":true,"_uuid":"e8523d876b6eae762e673b777cc7af4d7f085792"},"cell_type":"code","source":"# https://www.kaggle.com/strideradu/word2vec-and-gensim-go-go-go\ndef train_pred(model, epochs=2):\n    for e in range(epochs):\n        model.fit(train_X, train_y, batch_size=512, epochs=1, validation_data=(val_X, val_y))\n        pred_val_y = model.predict([val_X], batch_size=1024, verbose=0)\n\n        best_thresh = 0.5\n        best_score = 0.0\n        for thresh in np.arange(0.1, 0.501, 0.01):\n            thresh = np.round(thresh, 2)\n            score = metrics.f1_score(val_y, (pred_val_y > thresh).astype(int))\n            if score > best_score:\n                best_thresh = thresh\n                best_score = score\n\n        print(\"Val F1 Score: {:.4f}\".format(best_score))\n\n    pred_test_y = model.predict([test_X], batch_size=1024, verbose=0)\n    return pred_val_y, pred_test_y, best_score","execution_count":11,"outputs":[]},{"metadata":{"_uuid":"f79081928ca032fbfe3b90c6d3ce91cf57d443d8"},"cell_type":"markdown","source":"**Main part: load, train, pred and blend**"},{"metadata":{"trusted":true,"_uuid":"99d03d2eb63600f1b222522616eab3fa35819f37"},"cell_type":"code","source":"train_X, val_X, test_X, train_y, val_y, word_index = load_and_prec()\nembedding_matrix_1 = load_glove(word_index)\nembedding_matrix_2 = load_fasttext(word_index)\nembedding_matrix_3 = load_para(word_index)","execution_count":null,"outputs":[{"output_type":"stream","text":"Train shape :  (1306122, 3)\nTest shape :  (375806, 2)\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"f0ea9b1468bd7cd3ceead2593c641900dc3a2a77"},"cell_type":"code","source":"## Simple average: http://aclweb.org/anthology/N18-2031\n\n# We have presented an argument for averaging as\n# a valid meta-embedding technique, and found experimental\n# performance to be close to, or in some cases \n# better than that of concatenation, with the\n# additional benefit of reduced dimensionality  \n\n\n## Unweighted DME in https://arxiv.org/pdf/1804.07983.pdf\n\n# “The downside of concatenating embeddings and \n#  giving that as input to an RNN encoder, however,\n#  is that the network then quickly becomes inefficient\n#  as we combine more and more embeddings.”\n  \n# embedding_matrix = np.mean([embedding_matrix_1, embedding_matrix_2, embedding_matrix_3], axis = 0)\nembedding_matrix = np.mean([embedding_matrix_1, embedding_matrix_3], axis = 0)\nnp.shape(embedding_matrix)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b12f912b6efeed36a8c8b0bc00d9e8f8ae20bb51"},"cell_type":"code","source":"outputs = []\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8335f7bd2468bad0c589934cf95f20b912cc7095"},"cell_type":"code","source":"outputs = []\npred_val_y, pred_test_y, best_score = train_pred(model_gru_srk_atten(embedding_matrix), epochs = 2)\noutputs.append([pred_val_y, pred_test_y, best_score, 'gru atten srk'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"40ec64ad93aea2eb4d303fb7c1e9fc58590885dc"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_cnn(embedding_matrix), epochs = 2)\noutputs.append([pred_val_y, pred_test_y, best_score, '2d CNN'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3a026c4e4c2112de68a68133f1a71a6585c16456"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_cnn_flip(embedding_matrix), epochs = 2)\noutputs.append([pred_val_y, pred_test_y, best_score, '2d CNN flip'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b1e92b3ab4d353c969b648b26dd992220e40fe10"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_cnn(embedding_matrix_1), epochs = 2) # GloVe only\noutputs.append([pred_val_y, pred_test_y, best_score, '2d CNN GloVe'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5ff1ff83dadb567335ee7ce6702dfec34f93b112"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_cnn_flip(embedding_matrix_1), epochs = 2) # GloVe only\noutputs.append([pred_val_y, pred_test_y, best_score, '2d CNN GloVe flip'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8a2e40120b618740f34cb78cd41e884955b193d0"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_lstm_du(embedding_matrix), epochs = 2)\noutputs.append([pred_val_y, pred_test_y, best_score, 'LSTM DU'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"53df79b205ef6caf1329ac7f75c5fc14bf741838"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_lstm_atten(embedding_matrix), epochs = 3)\noutputs.append([pred_val_y, pred_test_y, best_score, '2 LSTM w/ attention'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a1e236f0eb26d9cdd6f11d3e839709d3e931397c"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_lstm_atten(embedding_matrix_1), epochs = 3) # Only GloVe\noutputs.append([pred_val_y, pred_test_y, best_score, '2 LSTM w/ attention GloVe'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"791fc4c45a2ca80f72f9142cab625880c6dae789"},"cell_type":"code","source":"pred_val_y, pred_test_y, best_score = train_pred(model_lstm_atten(embedding_matrix_3), epochs = 3) # Only Para\noutputs.append([pred_val_y, pred_test_y, best_score, '2 LSTM w/ attention Para'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"74f090f4c169d27c6c198f8faa46ffa077029953"},"cell_type":"code","source":"outputs.sort(key=lambda x: x[2]) # Sort the output by val f1 score\nweights = [i for i in range(1, len(outputs) + 1)]\nweights = [float(i) / sum(weights) for i in weights] \nprint(weights)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"144b69d8403ef889024bf7d7bb3ace8fd5b20b9e"},"cell_type":"code","source":"for output in outputs:\n    print(output[2], output[3])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d530945ee2b5627e3907f70de3f1b3f7e42b3667"},"cell_type":"code","source":"from sklearn.linear_model import LinearRegression\nX = np.asarray([outputs[i][0] for i in range(len(outputs))])\nX = X[...,0]\nreg = LinearRegression().fit(X.T, val_y)\nprint(reg.score(X.T, val_y),reg.coef_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"47a24264a5a5fdaf4ecdfdf497b209e098369e4e"},"cell_type":"code","source":"pred_val_y = np.sum([outputs[i][0] * reg.coef_[i] for i in range(len(outputs))], axis = 0)\n# pred_val_y = np.mean([outputs[i][0] for i in range(len(outputs))], axis = 0) # to avoid overfitting, just take average\n\nthresholds = []\nfor thresh in np.arange(0.1, 0.501, 0.01):\n    thresh = np.round(thresh, 2)\n    res = metrics.f1_score(val_y, (pred_val_y > thresh).astype(int))\n    thresholds.append([thresh, res])\n    print(\"F1 score at threshold {0} is {1}\".format(thresh, res))\n    \nthresholds.sort(key=lambda x: x[1], reverse=True)\nbest_thresh = thresholds[0][0]\nprint(\"Best threshold: \", best_thresh)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"74a84952d3a6a2b265dcd72a1ba8f41e315df332"},"cell_type":"code","source":"pred_test_y = np.sum([outputs[i][1] * reg.coef_[i] for i in range(len(outputs))], axis = 0)\n# pred_test_y = np.mean([outputs[i][1] for i in range(len(outputs))], axis = 0)\n\npred_test_y = (pred_test_y > best_thresh).astype(int)\ntest_df = pd.read_csv(\"../input/test.csv\", usecols=[\"qid\"])\nout_df = pd.DataFrame({\"qid\":test_df[\"qid\"].values})\nout_df['prediction'] = pred_test_y\nout_df.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"af44b57ac7afcc8552dd0de65dcecb26538cfc2b"},"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}