Giter VIP home page Giter VIP logo

cycontext_old's Introduction

Overview

I am a clinical data scientist and educator. As a data scientist, I apply methods including natural language processing and machine learning to support clinical research and improve patient care. As an educator, my goal is to introduce students of diverse backgrounds to Informatics and empower them to learn and apply core data science skills.

What I'm working on

Educational Work

I work as an adjunct professor at Utah Valley University, where I teach INFO-3700: Foundations of Healthcare Informatics. I've also taught at various summer schools and online workshops. Whenever possible, I try to make my materials available publicly. Here are some links to online courses or tutorials which I've contributed to.

  • Foundations of Healthcare Informatics, Fall 2020: Materials include analyzing clinical data with MIMIC, training a machine learning classifier to predict diabetes, and using NLP to extract information from clinical text
  • MIMIC34MD: A crash course in clinical data science at the University of Melbourne

cycontext_old's People

Contributors

abchapman93 avatar chapmanbe avatar turbosheep avatar

Stargazers

 avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

cycontext_old's Issues

love your work

@abchapman93
Great job here! Any chance you can tell me a bit about it. Maybe I could ask you questions regarding my own project? Perhaps via linked in? Thanks!

Exception when disabling upstream components

There is an exception in cycontext when several default components are missing. I think this is because there is no sentence. This should be handled gracefully -- perhaps with a warning to check that expected components (i.e. something that leads to sentence boundary detection) must be enabled?

nlp = spacy.load('en')

#nlp.remove_pipe('tagger')
#nlp.remove_pipe('parser')

# and then cycontext
item_data = [ConTextItem("no evidence of", "DEFINITE_NEGATED_EXISTENCE", rule="forward")]
context = ConTextComponent(nlp)
context.add(item_data)
nlp.add_pipe(context, last=True)

text = "Congestion but no evidence of pneumonia."

doc = nlp(text)

Here's the call stack:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-5-d0f024db1ca2> in <module>
      1 text = "Congestion but no evidence of pneumonia."
      2 
----> 3 doc = nlp(text)
      4 print(doc._.context_graph.edges)
      5 

~\AppData\Roaming\Python\Python36\site-packages\spacy\language.py in __call__(self, text, disable, component_cfg)
    433             if not hasattr(proc, "__call__"):
    434                 raise ValueError(Errors.E003.format(component=type(proc), name=name))
--> 435             doc = proc(doc, **component_cfg.get(name, {}))
    436             if doc is None:
    437                 raise ValueError(Errors.E005.format(name=name))

~\AppData\Roaming\Python\Python36\site-packages\cycontext\context_component.py in __call__(self, doc)
    165             # Get the ConTextItem object defining this modifier
    166             item_data = self._modifier_item_mapping[match_id]
--> 167             tag_object = TagObject(item_data, start, end, doc)
    168             context_graph.modifiers.append(tag_object)
    169 

~\AppData\Roaming\Python\Python36\site-packages\cycontext\tag_object.py in __init__(self, context_item, start, end, doc)
     19         self._scope_start = None
     20         self._scope_end = None
---> 21         self.set_scope()
     22 
     23     @property

~\AppData\Roaming\Python\Python36\site-packages\cycontext\tag_object.py in set_scope(self)
     47 
     48         if self.rule.lower() == "forward":
---> 49             self._scope_start, self._scope_end = self.end, sent.end
     50         elif self.rule.lower() == "backward":
     51             self._scope_start, self._scope_end = sent.start, self.start

AttributeError: 'NoneType' object has no attribute 'end'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.