Learn practical skills, build real-world projects, and advance your career

Natural Language Processing with RNNs - Toxic Comment Classification

Outline:

  1. Download and explore the data
  2. Prepare the data for training
  3. Build a recurrent neural network
  4. Train & evaluate the model
  5. Make predictions & submit to Kaggle

Download & Explore Data

Outline:

  1. Download the data from Kaggle
  2. Load data into Pandas dataframes
  3. Explore the dataset
import os
os.environ['KAGGLE_CONFIG_DIR'] = '.'
!kaggle competitions download -c jigsaw-toxic-comment-classification-challenge
Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 ./kaggle.json' Downloading jigsaw-toxic-comment-classification-challenge.zip to /content 36% 19.0M/52.6M [00:00<00:00, 197MB/s] 100% 52.6M/52.6M [00:00<00:00, 281MB/s]