{"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\n# for 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":"import 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import transformers\n\nfrom tokenizers import BertWordPieceTokenizer\n\nfrom tqdm.notebook import tqdm\n\n\nfrom kaggle_datasets import KaggleDatasets","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":"try:\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()","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()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 2\nBATCH_SIZE = 32 * strategy.num_replicas_in_sync\n\nMAX_LEN = 192","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenizer = 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\n# fast_tokenizer = BertWordPieceTokenizer('vocab.txt', lowercase=False)\n# fast_tokenizer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DATA_PATH = \"/kaggle/input/jigsaw-multilingual-toxic-comment-classification/\"\ntrain1 = pd.read_csv(os.path.join(DATA_PATH, \"jigsaw-toxic-comment-train.csv\"))\ntrain2 = pd.read_csv(os.path.join(DATA_PATH, \"jigsaw-unintended-bias-train.csv\"))\ntrain2.toxic = train2.toxic.round().astype(int)\n\nvalid = pd.read_csv(os.path.join(DATA_PATH, 'validation.csv'))\ntest = pd.read_csv(os.path.join(DATA_PATH, 'test.csv'))\nsub = pd.read_csv(os.path.join(DATA_PATH, 'sample_submission.csv'))","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)])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = regular_encode(train.comment_text.astype(str), tokenizer, maxlen=MAX_LEN)\nx_valid = regular_encode(valid.comment_text.astype(str), tokenizer, maxlen=MAX_LEN)\nx_test = regular_encode(test.content.astype(str), 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 = (tf.data.Dataset\n    .from_tensor_slices((x_train, y_train))\n    .repeat()\n    .shuffle(2048)\n    .batch(BATCH_SIZE)\n    .prefetch(AUTO))\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 loss(y_true, y_pred):\n    return tf.keras.losses.binary_crossentropy(y_true, y_pred, from_logits=False,label_smoothing = 0.099)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model(transformer, max_len=512):\n    \"\"\"\n    Model initalization\n    Source: 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)\n    \n    x1 = tf.keras.layers.Dropout(0.1)(sequence_output[0]) \n    x1 = tf.keras.layers.Conv1D(128, 2,padding='same')(x1)\n    x1 = tf.keras.layers.LeakyReLU()(x1)\n    #x1 = tf.keras.layers.ReLU()(x1)\n    x1 = tf.keras.layers.Conv1D(64, 2,padding='same')(x1)\n    x1 = tf.keras.layers.LeakyReLU()(x1)\n    x1 = tf.keras.layers.Conv1D(32, 2,padding='same')(x1)\n    x1 = tf.keras.layers.LeakyReLU()(x1)\n    x1 = tf.keras.layers.Flatten()(x1)\n    x1 = tf.keras.layers.Dense(32,activation = 'relu')(x1)\n    out = tf.keras.layers.Dense(1,activation='sigmoid')(x1)\n    \n    model = Model(inputs=input_word_ids, outputs=out)\n    model.compile(Adam(lr=1e-5), loss=loss, metrics=['accuracy'])\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\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=5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt \n\nplt.plot(train_history.history['accuracy'])\nplt.plot(train_history.history['val_accuracy'])\nplt.title('Model accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Test'], loc='upper left')\nplt.show()","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=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(train_history_2.history['accuracy'])\nplt.title('Model accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend(['Train'], loc='upper left')\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict(test_dataset, verbose=1)\n# sub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['toxic'] = pred\nsub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save_weights('distilbert-base-multilingual-cased.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.tail(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}