{"cells":[{"metadata":{"_uuid":"d4f32337e1f085705df91bddc99e9cfaf9cd6eb0"},"cell_type":"markdown","source":"This is a very simple model - using Glove embeddings, LSTM, GlobalMaxPool layer and dropouts only. And it is generating accuracy of 0.688. It is running well under 2 hours of time limit. But the problem with this is - if I increase number of features or maximum word input length then accuracy starts reducing. My guess is that it is undergoing overfitting. I would appreciate the suggestions on reducing overfitting in this model."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.\n\n## some config values \nembed_size = 300 # how big is each word vector\nmax_features = 100000 # how many unique words to use (i.e num rows in embedding vector)\nmaxlen = 60 # max number of words in a question to use\n\nimport 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 *\n# import ptvsd\n\n# ptvsd.enable_attach(address=('0.0.0.0','5678'))\n# ptvsd.wait_for_attach()\n\ndef load_and_prec():\n    train_df = pd.read_csv(\"../input/train.csv\")\n    test_df = pd.read_csv(\"../input/test.csv\")\n    print(\"Train shape : \",train_df.shape)\n    print(\"Test shape : \",test_df.shape)\n    \n    ## fill up the missing values\n    train_X = replace_special_char(train_df).fillna(\"_##_\").values\n    test_X = replace_special_char(test_df).fillna(\"_##_\").values\n\n    ## Tokenize the sentences\n    tokenizer = Tokenizer(num_words=max_features, filters='`!\"#$%&()*+,-/:;<=>@[\\]^_{|}~')\n    tokenizer.fit_on_texts(list(train_X))\n    train_X = tokenizer.texts_to_sequences(train_X)\n    test_X = tokenizer.texts_to_sequences(test_X)\n\n    ## Pad the sentences \n    train_X = pad_sequences(train_X, maxlen=maxlen)\n    test_X = pad_sequences(test_X, maxlen=maxlen)\n\n    ## Get the target values\n    train_y = train_df['target'].values\n    \n    #shuffling the data\n    np.random.seed(2018)\n    trn_idx = np.random.permutation(len(train_X))\n\n    train_X = train_X[trn_idx]\n    train_y = train_y[trn_idx]\n    \n    return train_X, test_X, train_y, tokenizer.word_index\n\ndef replace_special_char(df):\n    return df[\"question_text\"].apply(lambda s: s.replace(\"?\", \" ?\")).apply(lambda s: s.replace(\".\", \" .\"))\n    # .apply(lambda s: s.replace(\"-\", \" - \")).apply(lambda s: s.replace(\"$\", \"$ \")).apply(lambda s: s.replace(\"/\", \" / \")).apply(lambda s: s.replace(\"@\", \"@ \")).apply(lambda s: s.replace(\":\", \" : \")).apply(lambda s: s.replace(\";\", \" ; \"))\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')\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 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(100, return_sequences=True))(x)\n    x = GlobalMaxPooling1D()(x)\n    x = Dense(32, activation=\"relu\")(x)\n    x = Dropout(0.1)(x)\n    outp = Dense(1, activation=\"sigmoid\")(x)    \n\n    model = Model(inputs=inp, outputs=outp)\n    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n    print(model.summary())\n    return model\n\n# https://www.kaggle.com/strideradu/word2vec-and-gensim-go-go-go\ndef 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\n\ntrain_X, test_X, train_y, word_index = load_and_prec()\nembedding_matrix = load_glove(word_index)\nnp.shape(embedding_matrix)\n\nDATA_SPLIT_SEED = 2018\n\ntrain_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)\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)\n\nf1_score(y_true=train_y, y_pred=train_meta > 0.33)\n","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"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}