Skip to content
Permalink
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
51 lines (39 sloc) 1.5 KB

gswid2020

Repository for the Swisstext 2020 Shared Task 2

Content

gswid2020
|
|____ 
|    data
|    |
|    | train_tweets.csv  # contains Twitter IDs of tweets in Swiss German constituting the training set
|    | train_tweets.full.csv  # generated by running download_tweets.py
|    | test_tweets.csv  # contains Twitter IDs of tweets constituting the test set
|    | test_tweets.full.csv  #  generated by running download_tweets.py
|    | sample_submission.csv  # example of how your submission should look like
|
|
|    README.md  # this readme file
|    requirements.txt  # requirements for the repo
|    download_tweets.py  # script for downloading tweets given their IDs
|    check_submission.py  # script for checking for potential problems with a submission
|    evaluation.py  # evaluation script

How to build training set:

  • First install the required dependencies:
pip install -r requirements.txt
  • Enter your Twitter Api keys into download_tweets.py
  • run python -m download_tweets, this will take around 36 minutes due to rate limiting

How to build test set:

  • run python -m download_tweets ./data/test_tweets.csv, this will take a while due to rate limiting

Checking your submission

  • run python -m check_submission /path/to/your/submission.csv to check for potential problems with your submission. It will check for parsing problems, missing entries, and similar issues.

Evaluate a submission with gold labels

  • run python -m evaluation /path/to/your/submission.csv
You can’t perform that action at this time.