SCNN
====
An implementation of search-convolutional neural networks [1], a new model for graph-structured data.
Installation
------------
Using pip:
pip install scnn
Usage
-----
import numpy as np
from scnn import SCNN, data
from sklearn.metrics import f1_score
# Parse the cora dataset and return an adjacency matrix, a design matrix, and a 1-hot label matrix
A, X, Y = data.parse_cora()
# Construct array indices for the training, validation, and test sets
n_nodes = A.shape[0]
indices = np.arange(n_nodes)
train_indices = indices[:n_nodes // 3]
valid_indices = indices[n_nodes // 3:(2* n_nodes) // 3]
test_indices = indices[(2* n_nodes) // 3:]
# Instantiate an SCNN and fit it to cora
scnn = SCNN()
scnn.fit(A, X, Y, train_indices=train_indices, valid_indices=valid_indices)
# Predict labels for the test set
preds = scnn.predict(X, test_indices)
actuals = np.argmax(Y[test_indices,:], axis=1)
# Display performance
print 'F score: %.4f' % (f1_score(actuals, preds))
References
----------
[1] http://arxiv.org/abs/1511.02136
====
An implementation of search-convolutional neural networks [1], a new model for graph-structured data.
Installation
------------
Using pip:
pip install scnn
Usage
-----
import numpy as np
from scnn import SCNN, data
from sklearn.metrics import f1_score
# Parse the cora dataset and return an adjacency matrix, a design matrix, and a 1-hot label matrix
A, X, Y = data.parse_cora()
# Construct array indices for the training, validation, and test sets
n_nodes = A.shape[0]
indices = np.arange(n_nodes)
train_indices = indices[:n_nodes // 3]
valid_indices = indices[n_nodes // 3:(2* n_nodes) // 3]
test_indices = indices[(2* n_nodes) // 3:]
# Instantiate an SCNN and fit it to cora
scnn = SCNN()
scnn.fit(A, X, Y, train_indices=train_indices, valid_indices=valid_indices)
# Predict labels for the test set
preds = scnn.predict(X, test_indices)
actuals = np.argmax(Y[test_indices,:], axis=1)
# Display performance
print 'F score: %.4f' % (f1_score(actuals, preds))
References
----------
[1] http://arxiv.org/abs/1511.02136
1 maintainer
Release files for scnn 1.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| scnn-1.3.1.tar.gz | 20.0 kB | Details |
Release files / scnn-1.3.1.tar.gz
| Download URL | scnn-1.3.1.tar.gz |
|---|---|
| Size | 20.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cbd28586ea75dbfa3d3f359a914f54e99bbbe6b7ce37fdd0cb88dfd67176aedd
|
|
BLAKE2b-256 checksum How to use checksums |
112f4d239db4d06abfecc4333834644d837c2724ddf72214d0c40ed7346fc826
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
