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).
---------
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
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
chClassifier-0.6.3.tar.gz
(5.8 kB
view hashes)
Built Distribution
Close
Hashes for chClassifier-0.6.3-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 996989fcb1d1c66f5f5c6a728f4f184d7c7cb914b8f6ee1ef94ae46d2395eea9 |
|
MD5 | 68fa713c96176e870c1a851ca055ae9c |
|
BLAKE2b-256 | ea78fde63b036f2c6891608cfc5c1c9e9767a0910634a3a2ce3ec0cefb2a9bc0 |