mpeds
mpeds copied to clipboard
MPEDS
Machine-learning Protest Event Data System
For some reason running `docker compose up` exits immediately with no error for the `mpeds` service, and running `docker build . -f Dockerfile` while in the `mpeds` subfolder also fails...
I'm getting the following error when I try to test the example-lexisnexis.py file sh-4.2# python example-lexisnexis.py Added 348 articles, skipped 0 abstracts Loading vectorizer... Traceback (most recent call last): File...
JDK
Hi Alex, I had the same issue as zeeshansayyed when running MPEDS on a Windows system- I'm using Git Bash. From reading the previous thread, however, I can't tell if...
Need to move this puppy over to Python 3. Will probably mean reserializing the classifiers and being careful with all the string handling, especially with the open-ended classification.
Currently, SMO coding is broken because of the way that NLTK handles classpaths. Throws the following: Exception in thread "main" java.lang.NoClassDefFoundError: org/slf4j/LoggerFactory at edu.stanford.nlp.io.IOUtils.(IOUtils.java:42) at edu.stanford.nlp.ie.AbstractSequenceClassifier.loadClassifier(AbstractSequenceClassifier.java:1484) at edu.stanford.nlp.ie.AbstractSequenceClassifier.loadClassifierNoExceptions(AbstractSequenceClassifier.java:1497) at edu.stanford.nlp.ie.crf.CRFClassifier.main(CRFClassifier.java:3015)...
buildSolrQuery doesn't quite have the correct behaviour. it doesn't handle multiple values within the dict correctly.
Our location coder returns Montreal, Wisconsin (population 807 at 2010 census) when given texts about Montreal. Even adding Quebec as context doesn't help, as the coder then returns Montreal, Wisconsin...
We currently get the name of the country a city or state is in by parsing through the _countries_ entry of the CLIFF _focus_ results, matching on the field countryGeoNameId....
Our location tagger currently returns the "most specific" tags from the CLIFF results. For example, if the CLIFF results include data on cities, it will return all cities. If there...
The Stanford NER tagger tags individual words as SMO or not. For example, Occupy Wall Street is returned as `[('Occupy', 'ORGANIZATION'), ('Wall', 'ORGANIZATION'), ('Street', 'ORGANIZATION')]`. To parse this into a...