bobbyjudd / rexgen_direct Goto Github PK

View Code? Open in Web Editor NEW

This project forked from connorcoley/rexgen_direct

0.0 0.0 2.0 905.69 MB

Template-free prediction of organic reaction outcomes

License: GNU General Public License v3.0

Python 1.89% CSS 1.38% JavaScript 1.81% HTML 0.06% Jupyter Notebook 94.85%

rexgen_direct's People

Contributors

Forkers

lavroffrob13 vinylwx

rexgen_direct's Issues

Fix mol_graph.py bug when loading custom dataset

In rexgen_direct/core_wln_global/nntest_direct.py the line:
smiles2graph_batch = partial(_s2g, idxfunc=lambda x:x.GetIntProp('molAtomMapNumber') - 1)

The lambda body x.GetIntProp('molAtomMapNumber') tries to reference an integer property for and Atom object. See the RDKit docs about this property: https://www.rdkit.org/docs/RDKit_Book.html?highlight=molatommapnumber#magic-property-values

When running the custom Patent DB dataset, this code generates a KeyError:

File "nntest_direct.py", line 191, in
bindex_to_o = {val:key for key, val in bo_to_index.iteritems()}
AttributeError: 'dict' object has no attribute 'iteritems'
Exception in thread Thread-1:
Traceback (most recent call last):
File "/home/bobby/anaconda3/envs/my-rdkit-env/lib/python3.7/threading.py", line 926, in _bootstrap_inner
self.run()
File "/home/bobby/anaconda3/envs/my-rdkit-env/lib/python3.7/threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "nntest_direct.py", line 168, in read_data
src_tuple = smiles2graph_batch(src_batch)
File "/home/bobby/projects/ucla/cs260/final_proj/rexgen_direct/rexgen_direct/core_wln_global/mol_graph.py", line 143, in smiles2graph_list
res = list(map(lambda x:smiles2graph(x,idxfunc), smiles_list))
File "/home/bobby/projects/ucla/cs260/final_proj/rexgen_direct/rexgen_direct/core_wln_global/mol_graph.py", line 143, in
res = list(map(lambda x:smiles2graph(x,idxfunc), smiles_list))
File "/home/bobby/projects/ucla/cs260/final_proj/rexgen_direct/rexgen_direct/core_wln_global/mol_graph.py", line 81, in smiles2graph
idx = idxfunc(atom)
File "nntest_direct.py", line 52, in
smiles2graph_batch = partial(_s2g, idxfunc=lambda x:x.GetIntProp('molAtomMapNumber') - 1)
KeyError: 'molAtomMapNumber'

The included preprocessed datasets (train.txt.proc, test.txt.proc, valid.txt.proc) do not generate this error, however both datasets have been preprocessed by the prep_data.py script.

Need to determine what is unique to the custom dataset that is causing that is causing the error.

Report/Paper .tex file

Upload .tex file for report that will be submitted for the class

Add route to webserver for visualizing custom dataset predictions

Add another route to the Django app to host the visualization of the prediction output on the custom dataset. The route should be at http://localhost:8000/visualize/custom.

Start by adding the custom route here:

rexgen_direct/website/visualize/urls.py

Lines 5 to 8 in d40d382

 urlpatterns = [ 

 path('', views.index, name='index'), 

 path('ajax', views.display, name='display') 

 ]

Then add view functions (index and display) for custom here

rexgen_direct/website/visualize/views.py

Lines 8 to 29 in d40d382

 def index(request): 

 return render(request, 'example.html', {}) 

 def display(request): 

 print('Got request') 

 data = {'err': False} 

 index = int(request.GET.get('index', 1)) 

 showmap = json.loads(request.GET.get('showmap', 'true')) 

 highlight = int(request.GET.get('highlight', 0)) 

 print(index) 

 atts = [highlight] if highlight else [] 

 img = do_index(index - 1, showmap=showmap, atts=atts) 

 buffered = BytesIO() 

 img.save(buffered, format="png") 

 img_str = base64.b64encode(buffered.getvalue()).decode() 

 data['img_str'] = img_str 

 data['index'] = index 

 return JsonResponse(data)

The index and display functions will be pretty much the same but the display function needs to specify the correct dataset when calling do_index() and also need to add another html template to request the new custom display route.

Recommend Projects

React

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

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.

	urlpatterns = [
	path('', views.index, name='index'),
	path('ajax', views.display, name='display')
	]

	def index(request):
	return render(request, 'example.html', {})

	def display(request):
	print('Got request')

	data = {'err': False}
	index = int(request.GET.get('index', 1))
	showmap = json.loads(request.GET.get('showmap', 'true'))
	highlight = int(request.GET.get('highlight', 0))

	print(index)
	atts = [highlight] if highlight else []
	img = do_index(index - 1, showmap=showmap, atts=atts)
	buffered = BytesIO()
	img.save(buffered, format="png")
	img_str = base64.b64encode(buffered.getvalue()).decode()

	data['img_str'] = img_str
	data['index'] = index

	return JsonResponse(data)