GitHub - qf6101/kaggle-competition-solution-avito-duplicate-ads-detection: Kaggle Competition Solution for Avito Duplicate Ads Detection competition

kaggle competition solution: avito-duplicate-ads-detection

Final leaderboard: 14/548 (qfeng in team luoq)

Please read solution.md

The base environment is linux with Anaconda3

A lot of extra libraries are needed to run this code, an incomprehensive list is

A GPU is highly recommended to run mxnet. It takes about 5 days to generate the features.

Name		Name	Last commit message	Last commit date
Latest commit History 146 Commits
data		data
feature		feature
others_code		others_code
script		script
templates		templates
README.md		README.md
__init__.py		__init__.py
auc.old.csv		auc.old.csv
avito-dup.svg		avito-dup.svg
avito-duplicate-ads-detection_public_leaderboard.csv		avito-duplicate-ads-detection_public_leaderboard.csv
config.example.json		config.example.json
config.py		config.py
data exploration.ipynb		data exploration.ipynb
image_exploration.ipynb		image_exploration.ipynb
leaderboard.ipynb		leaderboard.ipynb
leaderboard_solution.py		leaderboard_solution.py
prepare_data.sh		prepare_data.sh
review.ipynb		review.ipynb
review.slides.html		review.slides.html
simple feature.ipynb		simple feature.ipynb
solution.md		solution.md
util.py		util.py
xgboost.38.ipynb		xgboost.38.ipynb
xgboost.39.ipynb		xgboost.39.ipynb