tmadl / semisup-learn Goto Github PK
View Code? Open in Web Editor NEWSemi-supervised learning frameworks for python, which allow fitting scikit-learn classifiers to partially labeled data
License: MIT License
Semi-supervised learning frameworks for python, which allow fitting scikit-learn classifiers to partially labeled data
License: MIT License
labeled_N = 4
ys = np.array([-1]*len(ytrue)) # -1 denotes unlabeled point
Are unlabeled points a workaround for train/test data points?
Ie, model.fit(x_trn, y_trn). model.score(x_tst, y_tst)
semisup-learn/frameworks/CPLELearning.py
Line 119 in 82ad804
Traceback (most recent call last):
File "/project/peaclab-mon/pyenv/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3319, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
from frameworks.CPLELearning import CPLELearningModel
File "/usr2/collab/esencan/semisup-learn/frameworks/CPLELearning.py", line 119
except Exception, e:
^
SyntaxError: invalid syntax
It seems like
self.plattlr.predict_proba
Is called (line 63, within self.predict_proba) before self.plattlr is set on line 78.
This causes models like a generic SVC to fail:
AttributeError: 'SelfLearningModel' object has no attribute 'plattlr'
This is what I got after run the heart dataset example, seems, the semi-supervised learning does not help. I did not edit anything though, not sure where this inconsistency comes from.
supervised log.reg. score 0.555555555556
self-learning log.reg. score 0.377777777778
..n....n....n.n max_iter exceeded.
CPLE semi-supervised log.reg. score 0.555555555556
..nn..n...n..n. max_iter exceeded.
CPLE semi-supervised RBF SVM score 0.555555555556
Could you please update a new version that is compatible with Python 3? Thx!
I got a wrong of " No module named 'frameworks'", but when I used “pip” to install the "frameworks",
return the "SyntaxError: invalid syntax", is "frameworks" not a module? do everyone have some suggestions? Thanks!
Line 10 in 82ad804
I believe this should be scikit-learn instead of sklearn
I get the following error, why.....?
'QN_S3VM_Dense' object has no attribute '_QN_S3VM_Dense__kernel'
ATT, although a simple
python setup.py build
python setup.py install
seems work.
What about the robustness of 'SelfLearningModel' and 'CPLELearningModel'? when I tested them on "iris" and "leukemia" datasets, the performance of these models was much bad than the supervised model, which very confused me.
This model use the labeled samples to train , but when test the acc , this model use the labeled samples again. Is the acc would higher?
I'm a newer to machine-learning.
I think the score function can't use all data ,but should use the data which not be trained.
Looking forward for your reply.
when doing
from frameworks.CPLELearning import CPLELearningModel
I get
File "/home/MYUSERNAME/anaconda3/lib/python3.6/site-packages/semisup_learn-0.0.1-py3.6.egg/frameworks/CPLELearning.py", line 119 except Exception, e: ^ SyntaxError: invalid syntax
I am using python 3.6 and have installed the module by
python setup.py install
I find this project very interesting, and applaud the code. Though, I ended up re-writing many parts due to some typos in python 3, and have been unable to find a missing qns3vm module.
maybe this is all due to the fact that I'm in Python 3.
good work, otherwise though 👍
it has an error when running the example.py
urllib2.HTTPError: HTTP Error 404: Dataset 'lung-cancer-ontario' not found on mldata.org.
I have used the CPLELearningModel to solve the 2-class unlabled data successfully, but when I try to use it to solve multi-classes problem, I get error, so I wonder does this model support semi-supervision on multi-classes?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.