About the Problem 📝
\nThe aprroach here that this notebook is going to solve is using multiple models based on NLP. Some of them are listed below which this notebook will cover.\n1. Using RNN's\n2. Using word embeddings like Glove\n3. LSTM's\n4. GRU\n5. Seq2seq mechanism\n6. Transformers\n7. Attention mechanism","metadata":{}},{"cell_type":"markdown","source":"Before every model development i shall be covering the basic concept and architechture behind the mechanism","metadata":{}},{"cell_type":"markdown","source":"\nEvaluation metric
\n","metadata":{}},{"cell_type":"markdown","source":"An ROC curve (receiver operating characteristic curve) is a graph showing the performance of a classification model at all classification thresholds. This curve plots two parameters:\n\nTrue Positive Rate\nFalse Positive Rate\nTrue Positive Rate (TPR) is a synonym for recall and is therefore defined as follows:\n\n\n\nFalse Positive Rate (FPR) is defined as follows:\n\n\n\nAUC: Area Under the ROC Curve\nAUC stands for \"Area under the ROC Curve.\" That is, AUC measures the entire two-dimensional area underneath the entire ROC curve (think integral calculus) from (0,0) to (1,1).\n\n\n\nAUC provides an aggregate measure of performance across all possible classification thresholds. One way of interpreting AUC is as the probability that the model ranks a random positive example more highly than a random negative example.\n\nAUC ranges in value from 0 to 1. A model whose predictions are 100% wrong has an AUC of 0.0; one whose predictions are 100% correct has an AUC of 1.0.\n\n## AUC\n\nAUC is desirable for the following two reasons:\n\nAUC is scale-invariant. It measures how well predictions are ranked, rather than their absolute values.\nAUC is classification-threshold-invariant. It measures the quality of the model's predictions irrespective of what classification threshold is chosen.\nHowever, both these reasons come with caveats, which may limit the usefulness of AUC in certain use cases:\n\nScale invariance is not always desirable. For example, sometimes we really do need well calibrated probability outputs, and AUC won’t tell us about that.\n\nClassification-threshold invariance is not always desirable. In cases where there are wide disparities in the cost of false negatives vs. false positives, it may be critical to minimize one type of classification error. For example, when doing email spam detection, you likely want to prioritize minimizing false positives (even if that results in a significant increase of false negatives). AUC isn't a useful metric for this type of optimization.\n","metadata":{},"attachments":{"b9363bf1-ed9a-4273-bfc7-11c11e5301cf.png":{"image/png":"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"},"83871910-461c-4863-aeee-fd79bad67bbb.png":{"image/png":"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"},"0ff1fc05-e966-4aa5-957f-55cc3d5eeec7.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"\nImport libraries
\n","metadata":{}},{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom tqdm import tqdm\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom keras.models import Sequential\nfrom keras.layers.recurrent import LSTM, GRU,SimpleRNN\nfrom keras.layers.core import Dense, Activation, Dropout\nfrom keras.layers.embeddings import Embedding\nfrom keras.layers.normalization import BatchNormalization\nfrom keras.utils import np_utils\nfrom sklearn import preprocessing, decomposition, model_selection, metrics, pipeline\nfrom keras.layers import GlobalMaxPooling1D, Conv1D, MaxPooling1D, Flatten, Bidirectional, SpatialDropout1D\nfrom keras.preprocessing import sequence, text\nfrom keras.callbacks import EarlyStopping\n\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\nfrom plotly import graph_objs as go\nimport plotly.express as px\nimport plotly.figure_factory as ff","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\nConfiguring TPU's
\n","metadata":{}},{"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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\nRead the dataset
\n","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv')\nvalidation = 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')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train.shape)\nprint(validation.shape)\nprint(test.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"##Take away Notes
\n\n1. This notebook is completely for the understanding purpost and hence the outputs are not shown completely for every model architechture.\n2. The number of epochs are also kept low for couple of architechtures as it is a time taking training tasks.\n3. For Bi directional LSTM and BERT models i have used GPU for training.\n4. Loading embedding from fastText is time consuming process.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}