{"cells":[{"metadata":{},"cell_type":"markdown","source":"This notebook makes use of a translated, cleaned dataset.","execution_count":null},{"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 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":"train = pd.read_csv(\"../input/jigsaw-toxic-comment-classification-cleaned-data/train_data.csv\")\nval = pd.read_csv(\"../input/jigsaw-toxic-comment-classification-cleaned-data/val_data.csv\")\ntest = pd.read_csv(\"../input/jigsaw-toxic-comment-classification-cleaned-data/test_data.csv\")\nprint(len(train), len(val), len(test))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dummy = train.cleaned_text.values[0]\ntest.cleaned_text[pd.isnull(test.cleaned_text)] = dummy\ntest[pd.isnull(test.cleaned_text)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(train[train.toxic == 1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"new_train = pd.DataFrame()\nnew_train = pd.concat((train[train.toxic == 1][:20000],train[train.toxic == 0][:30000]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"new_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nimport transformers\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = 'roberta-large'\ntokenizer = transformers.AutoTokenizer.from_pretrained(model)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.utils import shuffle\nfrom sklearn.model_selection import train_test_split\nnew_train = new_train[pd.notnull(new_train.cleaned_text)]\n\ntrain = train[pd.notnull(train.cleaned_text)]\ntrain, validation = train_test_split(train, test_size = 0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"max_seq_length = 200\n\ntrain_input_ids = [tokenizer.encode(i, max_length = max_seq_length , pad_to_max_length = True) for i in train.cleaned_text.values[::10]]\nval_input_ids = [tokenizer.encode(i, max_length = max_seq_length , pad_to_max_length = True) for i in validation.cleaned_text.values[::10]]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_model(): \n    input_word_ids = tf.keras.layers.Input(shape=(max_seq_length,), dtype=tf.int32,\n                                           name=\"input_word_ids\")\n    bert_layer = transformers.TFAutoModel.from_pretrained( 'roberta-large')\n    bert_outputs = bert_layer(input_word_ids)[0]\n    pred = tf.keras.layers.Conv1D(128,2,padding='same')(bert_outputs)\n    pred = tf.keras.layers.LeakyReLU()(pred)\n    pred = tf.keras.layers.Dropout(0.3)(pred)\n    pred = tf.keras.layers.Conv1D(64,2,padding='same')(pred)\n    pred = tf.keras.layers.Dense(256, activation='relu')(pred)\n    pred = tf.keras.layers.Dense(1, activation='sigmoid')(pred)\n    model = tf.keras.models.Model(inputs=input_word_ids, outputs=pred)\n    model.compile(loss='binary_crossentropy', optimizer=tf.keras.optimizers.Adam(\n    learning_rate=0.00001), metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"use_tpu = True\nif use_tpu:\n    # Create distribution strategy\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\n\n    # Create model\n    with strategy.scope():\n        model = create_model()\nelse:\n    model = create_model()\n    \nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(np.array(train_input_ids[::10]),np.array(train.toxic.values[::100]),\n          validation_data = (np.array(val_input_ids[::10]),np.array(validation.toxic.values[::100])),\n          verbose = 1, epochs = 30, batch_size = 128)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(np.array(val_input_ids[::10]),np.array(validation.toxic.values[::100]), epochs = 10, verbose = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_input_ids = [tokenizer.encode(i, max_length = max_seq_length , pad_to_max_length = True) for i in test.cleaned_text.values]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = model.predict(test_input_ids)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.where(preds > 0.5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = [max(preds[i]) for i in range(len(preds))]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"evaluation = test.id.copy().to_frame()\nevaluation['toxic'] = np.round(preds)\nevaluation","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"evaluation.to_csv(\"submission.csv\", index=False)","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}