{"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\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 read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from tqdm import tqdm\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom keras.models import Sequential\nfrom keras.layers.recurrent import GRU,SimpleRNN\nfrom keras.layers.core import Dense, Activation, Dropout\nfrom keras.layers.embeddings import Embedding\nfrom keras.layers.normalization import BatchNormalization\nfrom keras.utils import np_utils\nfrom sklearn import preprocessing, decomposition, model_selection, metrics, pipeline\nfrom keras.layers import GlobalMaxPooling1D, Conv1D, MaxPooling1D, Flatten, Bidirectional, SpatialDropout1D\nfrom keras.preprocessing import sequence, text\nfrom keras.callbacks import EarlyStopping\n\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\nfrom plotly import graph_objs as go\nimport plotly.express as px\nimport plotly.figure_factory as ff","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# TPU","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    # TPU detection. No parameters necessary if TPU_NAME environment variable is\n    # set: this is always the case on Kaggle.\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n    strategy = tf.distribute.get_strategy()\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#讀取train,valid和test的資料\ntrain = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv')\nvalidation = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/validation.csv')\ntest = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validation.drop(['lang'],axis=1,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validation","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#將train中不必要的欄位drop掉\ntrain.drop(['severe_toxic','obscene','threat','insult','identity_hate'],axis=1,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#看一下train的樣子\ntrain","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#取25000筆資料做訓練和測試\ntrain = train.loc[:19999,:]\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['comment_text'].apply(lambda x:len(str(x).split())).max()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#AUC function,若AUC越高，表示模型好\ndef roc_auc(predictions,target):\n    '''\n    This methods returns the AUC Score when given the Predictions\n    and Labels\n    '''\n    \n    fpr, tpr, thresholds = metrics.roc_curve(target, predictions)\n    roc_auc = metrics.auc(fpr, tpr)\n    return roc_auc","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#取出train和valid所需資料\nxtrain=train.comment_text.values\nytrain=train.toxic.values\nxvalid=validation.comment_text.values\nyvalid=validation.toxic.values\nxtest=test.content.values","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# tokenizer","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# using keras tokenizer here\ntoken = text.Tokenizer(num_words=None)\nmax_len = 128 #取訓練文字最大長度128\n\ntoken.fit_on_texts(list(xtrain) ) #+ list(xvalid)+list(test)\nxtrain_seq = token.texts_to_sequences(xtrain)\nxvalid_seq = token.texts_to_sequences(xvalid)\nxtest_seq = token.texts_to_sequences(xtest)\n\n#zero pad the sequences\nxtrain_pad = sequence.pad_sequences(xtrain_seq, maxlen=max_len)\nxvalid_pad = sequence.pad_sequences(xvalid_seq, maxlen=max_len)\nxtest_pad = sequence.pad_sequences(xtest_seq, maxlen=max_len)\n\n\nword_index = token.word_index\nprint(xtrain_pad.shape,xvalid_pad.shape,xtest_pad.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#看一下train做完token後的樣子\nxvalid_seq[:1]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Word Embeddings","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# load the GloVe vectors in a dictionary:\n#使用Word Embedding中的GloVe將文字轉為向量\nembeddings_index = {}\nf = open('/kaggle/input/glove840b300dtxt/glove.840B.300d.txt','r',encoding='utf-8')\nfor line in tqdm(f):\n    values = line.split(' ')\n    word = values[0]\n    coefs = np.asarray([float(val) for val in values[1:]])\n    embeddings_index[word] = coefs\nf.close()\n\nprint('Found %s word vectors.' % len(embeddings_index))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create an embedding matrix for the words we have in the dataset\n#將每一筆資料轉換為300為的向量\nembedding_matrix = np.zeros((len(word_index) + 1, 300))\nfor word, i in tqdm(word_index.items()):\n    embedding_vector = embeddings_index.get(word)\n    if embedding_vector is not None:\n        embedding_matrix[i] = embedding_vector","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# GRU","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"#GRU模型\n%time\nwith strategy.scope():\n    # GRU with glove embeddings and two dense layers\n     model = Sequential()\n     model.add(Embedding(len(word_index) + 1,\n                     300,\n                     weights=[embedding_matrix],\n                     input_length=max_len,\n                     trainable=False))\n     model.add(SpatialDropout1D(0.3))\n     model.add(GRU(300,return_sequences=True))\n     model.add(Dropout(0.2))\n     model.add(GRU(300,return_sequences=False))\n     model.add(Dropout(0.3))\n     model.add(Dense(1, activation='sigmoid'))\n\n     model.compile(loss='binary_crossentropy', optimizer='adam',metrics=['accuracy'])   \n    \nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#GRU模型訓練\nmodel.fit(xtrain_pad, ytrain, nb_epoch=1, batch_size=64*strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#使用valid測試資料的AUC結果\nscores = model.predict(xvalid_pad)\nprint(\"Auc: %.2f%%\" % (roc_auc(scores,yvalid)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/jigsaw-multilingual-toxic-comment-classification/sample_submission.csv\")\nsub['toxic'] = model.predict(xtest_pad, verbose=1)\nsub.to_csv('submission.csv', index=False)\nprint(\"finish\")","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}