Skip to main content

Neural Network to classify short strings

Project description

Char Classifier
---------

Given a short phrase, train a neural network to classify it based on the characters that it contains.

The trainer takes in a file of phrases (separated by new line) and a file of target values (separated by new line).

To train on the sample data (parts of speech classification):

```
import chClassifier
p = chClassifier.Trainer("sample/words", "sample/parts-of-speech")
p.train([100, 100], 20, 100)
p.save("sample", "example-run")
```

This will save a trained model with the tag 'example-run' in the sample directory. To use that model, run:

```
import chClassifier
k = chClassifier.Classifier("sample", "example-run")
print k.classify("dog")
```

This will return an array of tuples of original label + likelyhood that the label is correct, like so:

```
>> print k.classify("dog")
[(u'VB', 0.050349433), (u'NN', 3.8027303)]
```

The higher the number, the more sure we are of the classification (`dog` is definitely a noun, for example, and probably not a verb).

Project details


Release history Release notifications

This version
History Node

0.6.4

History Node

0.6.3

History Node

0.6.2

History Node

0.6.1

History Node

0.6.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
chClassifier-0.6.4-py2.py3-none-any.whl (10.5 kB) Copy SHA256 hash SHA256 Wheel 2.7 Mar 11, 2016
chClassifier-0.6.4.tar.gz (5.8 kB) Copy SHA256 hash SHA256 Source None Mar 11, 2016

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page