{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"!pip install transformers","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\n\nimport numpy as np\nimport pandas as pd\n\nimport tensorflow as tf\nfrom tensorflow.keras.layers import Dense, Input, BatchNormalization, Dropout\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.callbacks import ModelCheckpoint\n\nfrom kaggle_datasets import KaggleDatasets\n\nimport transformers\nfrom transformers import TFAutoModel, AutoTokenizer\nfrom tqdm.notebook import tqdm\nfrom tokenizers import Tokenizer, models, pre_tokenizers, decoders, processors\n\nfrom sklearn.metrics import accuracy_score","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":"def regular_encode(texts, tokenizer, maxlen=512):\n    \"\"\"\n    Function to encode the word\n    \"\"\"\n    # encode the word to vector of integer\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":"def build_model(transformer, max_len=512):\n    \"\"\"\n    This function to build and compile Keras model\n    \n    \"\"\"\n    #Input: for define input layer\n    #shape is vector with 512-dimensional vectors\n    input_word_ids = Input(shape=(max_len,), dtype=tf.int32, name=\"input_word_ids\") # name is optional \n    sequence_output = transformer(input_word_ids)[0]\n    # to get the vector\n    cls_token = sequence_output[:, 0, :]\n    batch_norm = BatchNormalization()(cls_token)\n    X = Dense(256, activation='relu')(batch_norm)\n    X = Dropout(0.2)(X)\n    X = Dense(32, activation='relu')(X)\n    X = Dropout(0.2)(X)\n    # define output layer\n    out = Dense(1, activation='sigmoid')(X)\n    \n    # initiate the model with inputs and outputs\n    model = Model(inputs=input_word_ids, outputs=out)\n    model.compile(Adam(lr=2e-6), loss='binary_crossentropy',metrics=[tf.keras.metrics.AUC()])\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 5\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync \nMAX_LEN = 192\nMODEL = 'bert-base-multilingual-cased'\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path()\n\nAUTO = tf.data.experimental.AUTOTUNE","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\")\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":"tokenizer = AutoTokenizer.from_pretrained(MODEL)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = regular_encode(train1.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\n#y_train,y_valid will have te target column \"toxic\"\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 # create dataset\n    .from_tensor_slices((x_train, y_train)) # Once you have a dataset, you can apply transformations \n    .repeat()\n    .shuffle(2048)\n    .batch(BATCH_SIZE)# Combines consecutive elements of this dataset into batches.\n    .prefetch(AUTO) #This allows later elements to be prepared while the current element is being processed.\n)\nvalid_dataset = (\n    tf.data.Dataset # create dataset\n    .from_tensor_slices((x_valid, y_valid)) # Once you have a dataset, you can apply transformations \n    .batch(BATCH_SIZE) #Combines consecutive elements of this dataset into batches.\n    .cache()\n    .prefetch(AUTO)#This allows later elements to be prepared while the current element is being processed.\n)\ntest_dataset = (\n    tf.data.Dataset# create dataset\n    .from_tensor_slices(x_test) # Once you have a dataset, you can apply transformations \n    .batch(BATCH_SIZE)\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    #take the encoder results of bert from transformers and use it as an input in the NN model\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(train_dataset, steps_per_epoch=n_steps, validation_data=valid_dataset,epochs=EPOCHS, shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#test the model on validation\nn_steps = x_valid.shape[0] // BATCH_SIZE\ntrain_history_2 = model.fit(valid_dataset.repeat(), steps_per_epoch=n_steps,epochs=EPOCHS*2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_valid_pre = model.predict(valid_dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.predict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_valid_pre = y_valid_pre[:,0].round().astype(int)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy_score(y_valid, y_valid_pre)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"model.evaluate(x_valid, y_valid)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(x_train, y_train)","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}