{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os\n\nimport numpy as np\nimport pandas as pd\nimport tensorflow as tf\nfrom 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\nfrom tqdm.notebook import tqdm\nfrom tokenizers import BertWordPieceTokenizer, SentencePieceBPETokenizer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def fast_encode(texts, tokenizer, chunk_size=256, maxlen=512):\n    \"\"\"\n    https://www.kaggle.com/xhlulu/jigsaw-tpu-distilbert-with-huggingface-and-keras\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":"# 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":"AUTO = tf.data.experimental.AUTOTUNE\n\n# Data access\nGCS_DS_PATH = KaggleDatasets().get_gcs_path()\n\n# Configuration\nEPOCHS = 3\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\nMAX_LEN = 128","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Create fast tokenizer","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# First load the real tokenizer\ntokenizer = transformers.AutoTokenizer.from_pretrained('jplu/tf-xlm-roberta-large')\n# Save the loaded tokenizer locally\ntokenizer.save_pretrained('.')\n# Reload it with the huggingface tokenizers library\n# fast_tokenizer = SentencePieceBPETokenizer('vocab.txt')\n# fast_tokenizer","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load text data into memory\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train1 = pd.read_csv(\"/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv\")\ntrain2 = pd.read_csv(\"/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-unintended-bias-train.csv\")\ntrain2.toxic = train2.toxic.round().astype(int)\n\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')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train1.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.concat([\n    train1[['comment_text', 'toxic']],\n    train2[['comment_text', 'toxic']].query('toxic==1'),\n    train2[['comment_text', 'toxic']].query('toxic==0').sample(n=150000, random_state=0)\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.toxic.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def fast_encode_xlm(texts, tokenizer, chunk_size=256, maxlen=512):\n    \"\"\"\n    https://www.kaggle.com/xhlulu/jigsaw-tpu-distilbert-with-huggingface-and-keras\n    \"\"\"\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.batch_encode_plus(text_chunk, pad_to_max_length = True, max_length = maxlen)\n        all_ids.extend(np.array(encs.input_ids))\n    \n    return np.array(all_ids)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = fast_encode_xlm(train.comment_text.astype(str), tokenizer, maxlen=MAX_LEN)\nx_valid = fast_encode_xlm(valid.comment_text.astype(str), tokenizer, maxlen=MAX_LEN)\nx_test = fast_encode_xlm(test.content.astype(str), tokenizer, maxlen=MAX_LEN)\n\ny_train = train.toxic.values\ny_valid = valid.toxic.values","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Build datasets objects","execution_count":null},{"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":{},"cell_type":"markdown","source":"# Load model into the TPU\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model(transformer, max_len=512):\n    \"\"\"\n    https://www.kaggle.com/xhlulu/jigsaw-tpu-distilbert-with-huggingface-and-keras\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    cls_token = sequence_output[:, 0, :]\n    out = Dense(1, activation='sigmoid')(cls_token)\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.TFAutoModelWithLMHead\n        .from_pretrained('jplu/tf-xlm-roberta-large')\n    )\n    model = build_model(transformer_layer, max_len=MAX_LEN)\nmodel.summary()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Train Model","execution_count":null},{"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\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['toxic'] = model.predict(test_dataset, verbose=1)\nsub.to_csv('submission.csv', index=False)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.describe()","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}