Awesome Open Source
Awesome Open Source

Starter code: Kaggle Toxic Comment Classification Challenge

More competitions 🎇

Check collection of public projects 🎁, where you can find multiple Kaggle competitions with code, experiments and outputs.

Here, at Neptune we enjoy participating in the Kaggle competitions. Toxic Comment Classification Challenge is especially interesting because it touches important issue of online harassment.

Ensemble our predictions in the cloud!

You need to be registered to to be able to use our predictions for your ensemble models.

  • click start notebook
  • choose browse button
  • select the neptune_ensembling.ipynb file from this repository.
  • choose worker type: gcp-large is the recommended one.
  • run first few cells to load our predictions on the held out validation set along with the labels
  • grid search over many possible parameter options. The more runs you choose the longer it will run.
  • train your second level, ensemble model (it should take less than an hour once you have the parameters)
  • load our predictions on the test set
  • feed our test set predictions to your ensemble model and get final predictions
  • save your submission file
  • click on browse files and find your submission file to download it.

Running the notebook as is got 0.986+ on the LB.


In this open source solution you will find references to the It is free platform for community Users, which we use daily to keep track of our experiments. Please note that using is not necessary to proceed with this solution. You may run it as plain Python script 😉.

The idea

We are contributing starter code that is easy to use and extend. We did it before with Cdiscounts Image Classification Challenge and we believe that it is correct way to open data science to the wider community and encourage more people to participate in Challenges. This starter is ready-to-use end-to-end solution. Since all computations are organized in separate steps, it is also easy to extend. Check devbook.ipynb for more information about different pipelines.

Now we want to go one step further and invite you to participate in the development of this analysis pipeline. At the later stage of the competition (early February) we will invite top contributors to join our team on Kaggle.


You are welcome to extend this pipeline and contribute your own models or procedures. Please refer to the CONTRIBUTING for more details.


option 1: Neptune cloud

on the neptune site

  • log in: neptune accound login
  • create new project named toxic: Follow the link Projects (top bar, left side), then click New project button. This action will generate project-key TOX, which is already listed in the neptune.yaml.

run setup commands

$ git clone
$ pip3 install neptune-cli
$ neptune login

start experiment

$ neptune send --environment keras-2.0-gpu-py3 --worker gcp-gpu-medium --config best_configs/fasttext_gru.yaml -- train_evaluate_predict_cv_pipeline --pipeline_name fasttext_gru --model_level first

This should get you to 0.9852 Happy Training :)

Refer to Neptune documentation and Getting started: Neptune Cloud for more.

option 2: local install

Please refer to the Getting started: local instance for installation procedure.

Solution visualization

Below end-to-end pipeline is visualized. You can run exactly this one! pipeline_001

We have also prepared something simpler to just get you started:


User support

There are several ways to seek help:

  1. Read project's Wiki, where we publish descriptions about the code, pipelines and neptune.
  2. Kaggle discussion is our primary way of communication.
  3. You can submit an issue directly in this repo.

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (1,123,251
Python3 (32,323
Machine Learning (29,964
Deep Learning (22,240
Data Science (8,518
Nlp (7,858
Pipeline (1,886
Challenge (1,361
Kaggle (1,184
Prediction (978
Kaggle Competition (498
Competition (424
Related Projects