{"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 20GB 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":"import tensorflow as tf\n\n# 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":"# Loading Dependencies\nimport os\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\nfrom transformers import TFAutoModel, AutoTokenizer\nimport transformers\nfrom tokenizers import Tokenizer, models, pre_tokenizers, decoders, processors\nfrom tokenizers import BertWordPieceTokenizer\nfrom tqdm import tqdm","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load DataSet from Kaggle. Offers good TPU support\nHas a total of 4.69 GB of data"},{"metadata":{"trusted":true},"cell_type":"code","source":"# LOADING THE DATA\n\ntrain = 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')","execution_count":null,"outputs":[]},{"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    Taken from Kaggle notebooks\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":"def regular_encode(texts, tokenizer, maxlen=512):\n    enc_di = tokenizer.batch_encode_plus(\n        texts, \n        return_attention_masks=False, \n        return_token_type_ids=False,\n        pad_to_max_length=True,\n        max_length=maxlen\n    )\n    \n    return np.array(enc_di['input_ids'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# number of elements to prefetch should be greater than the number of batches consumed by a single \n# training step. Thus we use tf.data.expeirment.AUTOTUNE for runtime to tune value dynamically runtime\nAUTO = tf.data.experimental.AUTOTUNE\n# Configuration\nEPOCHS = 3\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\nMAX_LEN = 192\n\n# # Data access\nGCS_DS_PATH = KaggleDatasets().get_gcs_path()\n\nMODEL = 'jplu/tf-xlm-roberta-large'","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(train.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 = train.toxic.values\ny_valid = valid.toxic.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create data loaders\ntrain_dataset = (tf.data.Dataset.from_tensor_slices((x_train, y_train)).repeat()\n                .shuffle(2048)\n                .batch(BATCH_SIZE)\n                .prefetch(AUTO))\n\nvalid_dataset = (tf.data.Dataset.from_tensor_slices((x_valid, y_valid))\n                .batch(BATCH_SIZE).cache()\n                .prefetch(AUTO))\n\ntest_dataset = (tf.data.Dataset.from_tensor_slices(x_test).batch(BATCH_SIZE))","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    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.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)\nsub.to_csv('submission1.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hist = train_history.history\nplt.plot(list(range(3)),hist['accuracy'],label='acc')\nplt.plot(list(range(3)),hist['val_accuracy'],label='val acc')\nplt.legend()\nplt.title('Train Vs Val Accuracy')\nplt.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hist = train_history.history\nplt.plot(list(range(3)),hist['loss'],label='train loss')\nplt.plot(list(range(3)),hist['val_loss'],label='val loss')\nplt.legend()\nplt.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenizer = AutoTokenizer.from_pretrained(MODEL)","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\")\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')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Combine train1 with a subset of train2\ntrain = 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=100000, random_state=0)\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time \n\nx_train = regular_encode(train.comment_text.values, tokenizer, maxlen=MAX_LEN)\nx_valid = regular_encode(valid.comment_text.values, tokenizer, maxlen=MAX_LEN)\nx_test = regular_encode(test.content.values, tokenizer, maxlen=MAX_LEN)\n\ny_train = train.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":"%%time\nwith strategy.scope():\n    transformer_layer = TFAutoModel.from_pretrained(MODEL)\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\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['toxic'] = model.predict(test_dataset, verbose=1)\nsub.to_csv('submission2.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission1 = pd.read_csv(\"./submission1.csv\")\nsubmission2 = pd.read_csv(\"./submission2.csv\")\nsubmission1['toxic'] = submission1['toxic']*0.9 + submission2['toxic']*0.1\nsubmission1.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}