{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport pandas as pd\nimport numpy as np\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"DATA_PATH = \"/kaggle/input/jigsaw-multilingual-toxic-comment-classification/\"\nos.listdir(DATA_PATH)\nTEST_PATH = DATA_PATH + \"test.csv\"\nVAL_PATH = DATA_PATH + \"validation.csv\"\nTRAIN_PATH = DATA_PATH + \"jigsaw-toxic-comment-train.csv\"\nval_data = pd.read_csv(VAL_PATH)\ntest_data = pd.read_csv(TEST_PATH)\ntrain_data = pd.read_csv(TRAIN_PATH)\n\nval = val_data\ntrain = train_data","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Preprocessing Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"def fast_encode(texts, tokenizer, chunk_size=240, maxlen=512):\n    tokenizer.enable_truncation(max_length=maxlen)\n    tokenizer.enable_padding(max_length=maxlen)\n    all_ids = []\n    \n    for i in 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":"import transformers\nfrom tokenizers import BertWordPieceTokenizer\n\ntokenizer = transformers.DistilBertTokenizer.from_pretrained('distilbert-base-multilingual-cased')\n\nsave_path = '/kaggle/working/distilbert_base_uncased/'\nif not os.path.exists(save_path):\n    os.makedirs(save_path)\ntokenizer.save_pretrained(save_path)\n\nfast_tokenizer = BertWordPieceTokenizer('distilbert_base_uncased/vocab.txt', \n                                        lowercase=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nAUTO = tf.data.experimental.AUTOTUNE\n\ntpu = tf.distribute.cluster_resolver.TPUClusterResolver()\ntf.config.experimental_connect_to_cluster(tpu)\ntf.tpu.experimental.initialize_tpu_system(tpu)\nstrategy = tf.distribute.experimental.TPUStrategy(tpu)\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('jigsaw-multilingual-toxic-comment-classification')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = fast_encode(train.comment_text.astype(str), \n                      fast_tokenizer, maxlen=512)\nx_valid = fast_encode(val_data.comment_text.astype(str).values, \n                      fast_tokenizer, maxlen=512)\nx_test = fast_encode(test_data.content.astype(str).values, \n                     fast_tokenizer, maxlen=512)\n\ny_valid = val.toxic.values\ny_train = train.toxic.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 32 * strategy.num_replicas_in_sync\n\ntrain_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":"Using CNN Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import Dense, Input, Dropout, Embedding, concatenate\nfrom tensorflow.keras.layers import LSTM, Conv1D, SpatialDropout1D, GlobalAveragePooling1D\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.models import Model\n\ndef cnn_model(transformer, max_len):\n    input_word_ids = Input(shape=(max_len,), dtype=tf.int32, name=\"input_word_ids\")\n    \n    embed = transformer.weights[0].numpy()\n    embedding = Embedding(np.shape(embed)[0], np.shape(embed)[1],\n                          input_length=max_len, weights=[embed],\n                          trainable=False)(input_word_ids)\n    \n    embedding = SpatialDropout1D(0.3)(embedding)\n    conv_1 = Conv1D(64, 2)(embedding)\n    conv_1 = SpatialDropout1D(0.4)(conv_1)\n    conv_2 = Conv1D(128, 3)(embedding)\n    conv_3 = Conv1D(256, 4)(embedding)\n    conv_3 = SpatialDropout1D(0.4)(conv_3)\n    conv_4 = Conv1D(64, 5)(embedding)\n    conv_5 = Conv1D(64, 5)(conv_1)\n    conv_6 = Conv1D(64, 5)(conv_2)\n    conv_7 = Conv1D(64, 5)(conv_3)\n    conv_8 = Conv1D(64, 5)(conv_4)\n    \n    maxpool_1 = GlobalAveragePooling1D()(conv_5)\n    maxpool_2 = GlobalAveragePooling1D()(conv_6)\n    maxpool_3 = GlobalAveragePooling1D()(conv_7)\n    maxpool_4 = GlobalAveragePooling1D()(conv_8)\n    conc = concatenate([maxpool_1, maxpool_2, maxpool_3, maxpool_4], axis=1)\n\n    conc = Dense(64, activation='relu')(conc)\n    conc = Dense(32, activation='relu')(conc)\n    conc = Dense(1, activation='sigmoid')(conc)\n    \n    model = Model(inputs=input_word_ids, outputs=conc)\n    \n    model.compile(Adam(lr=0.0001), \n                  loss='binary_crossentropy', \n                  metrics=['accuracy'])\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    transformer_layer = transformers.TFDistilBertModel.from_pretrained('distilbert-base-multilingual-cased')\n    model = cnn_model(transformer_layer, max_len=512)\n\n#model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N_STEPS = x_train.shape[0] // BATCH_SIZE\nEPOCHS = 15\n\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":{},"cell_type":"markdown","source":"*Taking tips from xhlulu notebook to retrain on validation data*"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_history_rep = model.fit(\n    valid_dataset.repeat(),\n    steps_per_epoch=N_STEPS,\n    epochs=5\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(DATA_PATH + 'sample_submission.csv')\nsub['toxic'] = model.predict(test_dataset, verbose=1)\nsub.to_csv('submission_cnn.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}