{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import Dense, Input\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.callbacks import ModelCheckpoint\nfrom kaggle_datasets import KaggleDatasets\nimport transformers\n\nfrom tokenizers import BertWordPieceTokenizer\nfrom tqdm import tqdm\nimport numpy as np\n\n!pip install wandb\n\nimport os, time\nimport pandas as pd\nimport tensorflow as tf\nimport tensorflow_hub as hub\nfrom kaggle_datasets import KaggleDatasets\n\n# We'll use a tokenizer for the BERT model from the modelling demo notebook.\n!pip install bert-tensorflow\nimport bert.tokenization\n\nprint(tf.version.VERSION)","execution_count":null,"outputs":[]},{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"SEQUENCE_LENGTH = 128\n\nDATA_PATH =  KaggleDatasets().get_gcs_path('jigsaw-multilingual-toxic-comment-classification')\nBERT_PATH = KaggleDatasets().get_gcs_path('bert-multi')\nBERT_PATH_SAVEDMODEL = BERT_PATH + \"/bert_multi_from_tfhub\"\n\nOUTPUT_PATH = \"/kaggle/working\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train1 = pd.read_csv(\"/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv\")\nvalid = 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')\nsub = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/sample_submission.csv')\nsub2 = pd.read_csv('../input/ensemble/submission.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# BERT Tokenizer","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_tokenizer(bert_path=BERT_PATH_SAVEDMODEL):\n    \"\"\"Get the tokenizer for a BERT layer.\"\"\"\n    bert_layer = tf.saved_model.load(bert_path)\n    bert_layer = hub.KerasLayer(bert_layer, trainable=False)\n    vocab_file = bert_layer.resolved_object.vocab_file.asset_path.numpy()\n    cased = bert_layer.resolved_object.do_lower_case.numpy()\n    tf.gfile = tf.io.gfile  # for bert.tokenization.load_vocab in tokenizer\n    tokenizer = bert.tokenization.FullTokenizer(vocab_file, cased)\n  \n    return tokenizer\n\ntokenizer = get_tokenizer()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Preprocessing","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def fast_encode(texts, tokenizer, chunk_size=256, maxlen=512):\n    \"\"\"\n    Encoder for encoding the text into sequence of integers for BERT Input\n    \"\"\"\n    tokenizer.enable_truncation(max_length=maxlen)\n    tokenizer.enable_padding(max_length=maxlen)\n    all_ids = []\n    \n    for i in tqdm(range(0, len(texts), chunk_size)):\n        text_chunk = texts[i:i+chunk_size].tolist()\n        encs = tokenizer.encode_batch(text_chunk)\n        all_ids.extend([enc.ids for enc in encs])\n    \n    return np.array(all_ids)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#IMP DATA FOR CONFIG\n\nAUTO = tf.data.experimental.AUTOTUNE\n\n\n# Configuration\nEPOCHS = 5\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\nMAX_LEN = 192","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# First load the real tokenizer\ntokenizer = transformers.DistilBertTokenizer.from_pretrained('distilbert-base-multilingual-cased')\n# Save the loaded tokenizer locally\ntokenizer.save_pretrained('.')\n# Reload it with the huggingface tokenizers library\nfast_tokenizer = BertWordPieceTokenizer('vocab.txt', lowercase=False)\nfast_tokenizer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = fast_encode(train1.comment_text.astype(str), fast_tokenizer, maxlen=MAX_LEN)\nx_valid = fast_encode(valid.comment_text.astype(str), fast_tokenizer, maxlen=MAX_LEN)\nx_test = fast_encode(test.content.astype(str), fast_tokenizer, maxlen=MAX_LEN)\n\ny_train = train1.toxic.values\ny_valid = valid.toxic.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = (\n    tf.data.Dataset\n    .from_tensor_slices((x_train, y_train))\n    .repeat()\n    .shuffle(2048)\n    .batch(BATCH_SIZE)\n    .prefetch(AUTO)\n)\n\nvalid_dataset = (\n    tf.data.Dataset\n    .from_tensor_slices((x_valid, y_valid))\n    .batch(BATCH_SIZE)\n    .cache()\n    .prefetch(AUTO)\n)\n\ntest_dataset = (\n    tf.data.Dataset\n    .from_tensor_slices(x_test)\n    .batch(BATCH_SIZE)\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model(transformer, max_len=512):\n    \"\"\"\n    function for training the BERT model\n    \"\"\"\n    input_word_ids = Input(shape=(max_len,), dtype=tf.int32, name=\"input_word_ids\")\n    sequence_output = transformer(input_word_ids)[0]\n    \n    cls_token = sequence_output[:, 0, :]\n    out = tf.keras.layers.Dense(192, activation='relu')(cls_token)\n    out = tf.keras.layers.Dense(64, activation='relu')(out)\n    out = tf.keras.layers.Dense(64, activation='relu')(out)\n    out = Dense(1, activation='sigmoid')(out)\n    \n    model = Model(inputs=input_word_ids, outputs=out)\n    model.compile(Adam(lr=1e-5), loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nwith strategy.scope():\n    transformer_layer = (\n        transformers.TFDistilBertModel\n        .from_pretrained('distilbert-base-multilingual-cased')\n    )\n    model = build_model(transformer_layer, max_len=MAX_LEN)\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"n_steps = x_train.shape[0] // BATCH_SIZE\ntrain_history = model.fit(\n    train_dataset,\n    steps_per_epoch=n_steps,\n    validation_data=valid_dataset,\n    epochs=EPOCHS\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"n_steps = x_valid.shape[0] // BATCH_SIZE\ntrain_history_2 = model.fit(\n    valid_dataset.repeat(),\n    steps_per_epoch=n_steps,\n    epochs=EPOCHS*2\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['toxic'] = model.predict(test_dataset, verbose=1)\n#sub.to_csv('submission.csv', index=False)\n\nsub1 = sub[['id', 'toxic']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub1.rename(columns={'toxic':'toxic1'}, inplace=True)\nsub2.rename(columns={'toxic':'toxic2'}, inplace=True)\nsub3 = pd.merge(sub1, sub2, how='left', on='id')\n\nsub3['toxic'] = (sub3['toxic1'] * 0.1) + (sub3['toxic2'] * 0.9) #blend 1\nsub3['toxic'] = (sub3['toxic2'] * 0.39) + (sub3['toxic'] * 0.61) #blend 2\n\nsub3[['id', 'toxic']].to_csv('submission.csv', index=False)","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}