mirror of https://github.com/gsi-upm/senpy
Add sklearn
* Add sklearn example * Fix test_case * Add SenpyClientUse docs a.k.a. The wise men editionpre-1.0
parent
3e2b8baeb2
commit
1087692de2
@ -0,0 +1,106 @@
|
||||
|
||||
Client
|
||||
======
|
||||
|
||||
Demo Endpoint
|
||||
-------------
|
||||
|
||||
Import Client and send a request
|
||||
|
||||
.. code:: python
|
||||
|
||||
from senpy.client import Client
|
||||
|
||||
c = Client('http://latest.senpy.cluster.gsi.dit.upm.es/api')
|
||||
r = c.analyse('I like Pizza', algorithm='sentiment140')
|
||||
|
||||
Print response
|
||||
|
||||
.. code:: python
|
||||
|
||||
for entry in r.entries:
|
||||
print('{} -> {}'.format(entry['text'], entry['sentiments'][0]['marl:hasPolarity']))
|
||||
|
||||
|
||||
.. parsed-literal::
|
||||
|
||||
I like Pizza -> marl:Positive
|
||||
|
||||
|
||||
Obtain a list of available plugins
|
||||
|
||||
.. code:: python
|
||||
|
||||
for plugin in c.request('/plugins')['plugins']:
|
||||
print(plugin['name'])
|
||||
|
||||
|
||||
.. parsed-literal::
|
||||
|
||||
emoRand
|
||||
rand
|
||||
sentiment140
|
||||
|
||||
|
||||
Local Endpoint
|
||||
--------------
|
||||
|
||||
Run a docker container with Senpy image and default plugins
|
||||
|
||||
.. code::
|
||||
|
||||
docker run -ti --name 'SenpyEndpoint' -d -p 5000:5000 gsiupm/senpy:0.8.6 --host 0.0.0.0 --default-plugins
|
||||
|
||||
|
||||
.. parsed-literal::
|
||||
|
||||
a0157cd98057072388bfebeed78a830da7cf0a796f4f1a3fd9188f9f2e5fe562
|
||||
|
||||
|
||||
Import client and send a request to localhost
|
||||
|
||||
.. code:: python
|
||||
|
||||
c_local = Client('http://127.0.0.1:5000/api')
|
||||
r = c_local.analyse('Hello world', algorithm='sentiment140')
|
||||
|
||||
Print response
|
||||
|
||||
.. code:: python
|
||||
|
||||
for entry in r.entries:
|
||||
print('{} -> {}'.format(entry['text'], entry['sentiments'][0]['marl:hasPolarity']))
|
||||
|
||||
|
||||
.. parsed-literal::
|
||||
|
||||
Hello world -> marl:Neutral
|
||||
|
||||
|
||||
Obtain a list of available plugins deployed locally
|
||||
|
||||
.. code:: python
|
||||
|
||||
c_local.plugins().keys()
|
||||
|
||||
|
||||
.. parsed-literal::
|
||||
|
||||
rand
|
||||
sentiment140
|
||||
emoRand
|
||||
|
||||
|
||||
Stop the docker container
|
||||
|
||||
.. code:: python
|
||||
|
||||
!docker stop SenpyEndpoint
|
||||
!docker rm SenpyEndpoint
|
||||
|
||||
|
||||
.. parsed-literal::
|
||||
|
||||
SenpyEndpoint
|
||||
SenpyEndpoint
|
||||
|
@ -0,0 +1,33 @@
|
||||
'''
|
||||
Create a dummy dataset.
|
||||
Messages with a happy emoticon are labelled positive
|
||||
Messages with a sad emoticon are labelled negative
|
||||
'''
|
||||
import random
|
||||
|
||||
dataset = []
|
||||
|
||||
vocabulary = ['hello', 'world', 'senpy', 'cool', 'goodbye', 'random', 'text']
|
||||
|
||||
emojimap = {
|
||||
1: [':)', ],
|
||||
-1: [':(', ]
|
||||
}
|
||||
|
||||
|
||||
for tag, values in emojimap.items():
|
||||
for i in range(1000):
|
||||
msg = ''
|
||||
for j in range(3):
|
||||
msg += random.choice(vocabulary)
|
||||
msg += " "
|
||||
msg += random.choice(values)
|
||||
dataset.append([msg, tag])
|
||||
|
||||
|
||||
text = []
|
||||
labels = []
|
||||
|
||||
for i in dataset:
|
||||
text.append(i[0])
|
||||
labels.append(i[1])
|
@ -0,0 +1,30 @@
|
||||
from sklearn.pipeline import Pipeline
|
||||
from sklearn.feature_extraction.text import CountVectorizer
|
||||
from sklearn.model_selection import train_test_split
|
||||
|
||||
from mydata import text, labels
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(text, labels, test_size=0.12, random_state=42)
|
||||
|
||||
from sklearn.naive_bayes import MultinomialNB
|
||||
|
||||
|
||||
count_vec = CountVectorizer(tokenizer=lambda x: x.split())
|
||||
clf3 = MultinomialNB()
|
||||
pipeline = Pipeline([('cv', count_vec),
|
||||
('clf', clf3)])
|
||||
|
||||
pipeline.fit(X_train, y_train)
|
||||
print('Feature names: {}'.format(count_vec.get_feature_names()))
|
||||
print('Class count: {}'.format(clf3.class_count_))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
print('--Results--')
|
||||
tests = [
|
||||
(['The sentiment for senpy should be positive :)', ], 1),
|
||||
(['The sentiment for anything else should be negative :()', ], -1)
|
||||
]
|
||||
for features, expected in tests:
|
||||
result = pipeline.predict(features)
|
||||
print('Input: {}\nExpected: {}\nGot: {}'.format(features[0], expected, result))
|
@ -0,0 +1,37 @@
|
||||
from senpy import SentimentBox, MappingMixin, easy_test
|
||||
|
||||
from mypipeline import pipeline
|
||||
|
||||
|
||||
class PipelineSentiment(MappingMixin, SentimentBox):
|
||||
'''
|
||||
This is a pipeline plugin that wraps a classifier defined in another module
|
||||
(mypipeline).
|
||||
'''
|
||||
author = '@balkian'
|
||||
version = 0.1
|
||||
maxPolarityValue = 1
|
||||
minPolarityValue = -1
|
||||
|
||||
mappings = {
|
||||
1: 'marl:Positive',
|
||||
-1: 'marl:Negative'
|
||||
}
|
||||
|
||||
def box(self, input, *args, **kwargs):
|
||||
return pipeline.predict([input, ])[0]
|
||||
|
||||
test_cases = [
|
||||
{
|
||||
'input': 'The sentiment for senpy should be positive :)',
|
||||
'polarity': 'marl:Positive'
|
||||
},
|
||||
{
|
||||
'input': 'The sentiment for senpy should be negative :(',
|
||||
'polarity': 'marl:Negative'
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
easy_test()
|
Loading…
Reference in New Issue