{"cells":[{"metadata":{},"cell_type":"markdown","source":"## About this notebook\nI'm interested in looking at the performance of multilingual model on various language validation data as it trains. Using [this code from Eror@StackOverflow](https://stackoverflow.com/questions/47731935/using-multiple-validation-sets-with-keras), I encountered an error while trying to add a custom callback on a model that's running on TPU. Scroll down to see the error in the training phase.\n\n\n### References\nI'm forking Xhlulu's notebook. Here's the original:\n* Original Author: [@xhlulu](https://www.kaggle.com/xhlulu/)\n* Original notebook: [Link](https://www.kaggle.com/xhlulu/jigsaw-tpu-distilbert-with-huggingface-and-keras)"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"USE_TPU = True\nimport 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 transformers import TFAutoModel, AutoTokenizer\nfrom tqdm.notebook import tqdm\nfrom tokenizers import Tokenizer, models, pre_tokenizers, decoders, processors","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Helper Functions"},{"metadata":{"trusted":true,"_kg_hide-output":true,"_kg_hide-input":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'])\n\ndef 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":"tf.keras.metrics.Accuracy.__name__","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## TPU Configs"},{"metadata":{"trusted":true},"cell_type":"code","source":"if USE_TPU:\n    # Detect hardware, return appropriate distribution strategy\n    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())\n    except ValueError:\n        tpu = None\n\n    if tpu:\n        tf.config.experimental_connect_to_cluster(tpu)\n        tf.tpu.experimental.initialize_tpu_system(tpu)\n        strategy = tf.distribute.experimental.TPUStrategy(tpu)\n    else:\n        # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n        strategy = tf.distribute.get_strategy()\n\n    print(\"REPLICAS: \", strategy.num_replicas_in_sync)\n    BATCH_SIZE = 8 * strategy.num_replicas_in_sync\n    \nelse:\n    BATCH_SIZE = 8 * 8","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 = 2\nMAX_LEN = 192\nMODEL = 'jplu/tf-xlm-roberta-large'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Create tokenizer"},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenizer = AutoTokenizer.from_pretrained(MODEL)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load text data into memory"},{"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').sample(n=200, random_state=0)\ntest = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/test.csv').sample(n=200, random_state=0)\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    train2[['comment_text', 'toxic']].query('toxic==1').sample(n=400, random_state=0),\n    train2[['comment_text', 'toxic']].query('toxic==0').sample(n=400, 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":{},"cell_type":"markdown","source":"## Build datasets objects"},{"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"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nif USE_TPU:\n    with strategy.scope():\n        transformer_layer = TFAutoModel.from_pretrained(MODEL)\n        model = build_model(transformer_layer, max_len=MAX_LEN)\n        \nelse:\n    transformer_layer = TFAutoModel.from_pretrained(MODEL)\n    model = build_model(transformer_layer, max_len=MAX_LEN)\n    \nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Train Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Code from: https://stackoverflow.com/questions/47731935/using-multiple-validation-sets-with-keras\nclass AdditionalValidationSets(tf.keras.callbacks.Callback):\n    def __init__(self, validation_sets, verbose=0, batch_size=None):\n        \"\"\"\n        :param validation_sets:\n        a list of 3-tuples (validation_data, validation_targets, validation_set_name)\n        or 4-tuples (validation_data, validation_targets, sample_weights, validation_set_name)\n        :param verbose:\n        verbosity mode, 1 or 0\n        :param batch_size:\n        batch size to be used when evaluating on the additional datasets\n        \"\"\"\n        super(AdditionalValidationSets, self).__init__()\n        self.validation_sets = validation_sets\n        for validation_set in self.validation_sets:\n            if len(validation_set) not in [2, 3]:\n                raise ValueError()\n        self.epoch = []\n        self.history = {}\n        self.verbose = verbose\n        self.batch_size = batch_size\n\n    def on_train_begin(self, logs=None):\n        self.epoch = []\n        self.history = {}\n\n    def on_epoch_end(self, epoch, logs=None):\n        logs = logs or {}\n        self.epoch.append(epoch)\n\n        # record the same values as History() as well\n        for k, v in logs.items():\n            self.history.setdefault(k, []).append(v)\n\n        # evaluate on the additional validation sets\n        for validation_set in self.validation_sets:\n            if len(validation_set) == 3:\n                validation_data, validation_targets, validation_set_name = validation_set\n                sample_weights = None\n            elif len(validation_set) == 4:\n                validation_data, validation_targets, sample_weights, validation_set_name = validation_set\n            else:\n                raise ValueError()\n\n            results = self.model.evaluate(x=validation_data,\n                                          y=validation_targets,\n                                          verbose=self.verbose,\n                                          sample_weight=sample_weights,\n                                          batch_size=self.batch_size)\n\n            for i, result in enumerate(results):\n                if i == 0:\n                    valuename = validation_set_name + '_loss'\n                else:\n                    valuename = validation_set_name + '_' + str(self.model.metrics[i-1].name)\n                self.history.setdefault(valuename, []).append(result)\n                \n                print(\" {}:{}\".format(valuename, result), end='\\t')\n                \n            print('\\n')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"n_steps = x_valid.shape[0] // BATCH_SIZE\nprint(n_steps)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntrain_history = model.fit(\n    train_dataset,\n    steps_per_epoch=n_steps,\n    validation_data=valid_dataset,\n    epochs=EPOCHS,\n    callbacks=[AdditionalValidationSets([(x_valid, y_valid, 'val_additional')])]\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['toxic'] = model.predict(test_dataset, verbose=1)\nsub.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}