class NLClassifier(object):
def __init__(self, username, password, classifier):
# Setup Watson SDK
self.natural_language_classifier = NLC(username=username,password=password)
# Classifier information
self.classifier = {}
self.classifier['name'] = classifier['name']
self.classifier['training_file'] = classifier['training_file']
c = self.natural_language_classifier.list_classifiers()
if any(d['name'] == self.classifier['name'] for d in c['classifiers'] ):
self.classifier['id'] = [ d['classifier_id'] for d in c['classifiers'] if d['name'] == self.classifier['name'] ][0]
print 'Found classifier id %s ' % self.classifier['id']
self.classifier['status'] = self.natural_language_classifier.status(self.classifier['id'])['status']
else:
print 'No classifier found, creating new from training set'
self.classifier['id'] = self.create_classifier()
print 'New classifier id: %s ' % self.classifier['id']
### Method to train the Watson Natural Language Classifier
# The training set is delivered as a CSV file as specified in the Developer Guide
# https://www.ibm.com/watson/developercloud/doc/nl-classifier/data_format.shtml
def create_classifier(self):
training_data = open(self.classifier['training_file'], 'rb')
training_result = self.natural_language_classifier.create( training_data=training_data, name=self.classifier['name'] )
if training_result['status'] == "Training":
self.classifier['status'] = "Training"
return training_result['classifier_id']
else:
print training_result
return "Error"
def classify(self,text):
# Typically in a production system Watson NLC will be fully trained and verified by a data scientist before the system is ever
# exposed in production. However because this is a demo application where Watson NLC is trained at application deployment time,
# we will need to have a check to verify that the training is completed.
if self.classifier['status'] == "Training":
r = self.natural_language_classifier.status(self.classifier['id'])
if r['status'] == "Training":
return {"error": "Classifier still in training. Please try again in a few minutes."}
elif r['status'] == "Available":
self.classifier['status'] = 'Available'
else:
return {"error": "Unknown status for classifier", "message": r['status']}
return self.natural_language_classifier.classify(self.classifier['id'], text)
def classifier_status(url, username, password, classifier_ids):
n = NaturalLanguageClassifier(url=url,
username=username,
password=password)
for classifier_id in classifier_ids:
status = n.status(classifier_id)
print("%s: %s" % (status["status"], status["status_description"]))
class NLC(object):
def __init__(self, credential_file_path=None):
self.__nlc = None
self.__initialize(credential_file_path)
def __initialize(self, credential_file_path):
if not credential_file_path:
credential_file_path = os.path.expanduser(DEFAULT_CREDENTIAL_PATH)
with open(credential_file_path, 'r') as credential_file:
credential = json.load(credential_file)
self.__nlc = NaturalLanguageClassifier(url=credential['url'], username=credential['username'], password=credential['password'])
def create(self, traning_data, name=None, language='en'):
"""
:param traning_data: A csv file or file path representing the traning data
:param name: The optional descriptive name for the classifier
:param language: The language og the input data
:return: A instance object with the classifier_id of the newly created classifier, still in traning
"""
create_result = None
if isinstance(traning_data, file) or isinstance(traning_data, IOBase): # traning_data is file discripter
create_result = self.__nlc.create(traning_data, name=name, language=language)
elif isinstance(traning_data, str): # traning_data is file path
with open(traning_data, newline=None, mode='r', encoding='utf-8') as csv_file:
if is_valid_recode_num(csv_file):
create_result = self.__nlc.create(csv_file, name=name, language=language)
return CreateResult(create_result)
def classifiers(self):
classifiers_raw = self.__nlc.list()
classifiers_ = [Classifier(c) for c in classifiers_raw['classifiers']]
return Classifiers(classifiers_)
def status(self, classifier_id):
return Status(self.__nlc.status(classifier_id))
def classify(self, classifier_id, text):
return ClassifyResult(self.__nlc.classify(classifier_id, text))
def remove(self, classifier_id):
"""
param: classifier_id: Unique identifier for the classifier
retrun: empty dict object
raise: watson_developer_cloud.watson_developer_cloud_service.WatsonException: Not found
"""
return self.__nlc.remove(classifier_id)
def remove_all(self):
classifiers_ = self.classifiers()
return [self.remove(c.classifier_id) for c in classifiers_]
class Watson_api():
def __init__(self):
self.fname = ""
self.modelSearchList = ModelSearchList()
self.text_data = []
self.target_label = []
self.watson_crediantial = watson_key()
#self.watson_classifier = self.watson_crediantial.classifier_twitter_classfier
#self.watson_classifier = self.watson_crediantial.classifier_twitter_hash_classfier
#self.watson_classifier = self.watson_crediantial.classifier_twitter_unblance_keyword_classfier
#self.watson_classifier = self.watson_crediantial.twitter_priority_classfier
self.watson_classifier = self.watson_crediantial.twitter_category_classfier
self.natural_language_classifier = NaturalLanguageClassifier(username=self.watson_crediantial.username,
password=self.watson_crediantial.password)
#print(json.dumps(self.natural_language_classifier.list(), indent=2))
def parse_args(self):
p = ArgumentParser(description='Encoder-decoder neural machine trainslation')
p.add_argument('data', help='[in] data')
args = p.parse_args()
return args
def train(self):
# create a classifier
with open('../resources/weather_data_train.csv', 'rb') as training_data:
print(json.dumps(self.natural_language_classifier.create(training_data=training_data, name='weather2'), indent=2))
def __read_data(self):
for line in open(self.fname, "r"):
split_line = line.split(",")
self.text_data.append(split_line[0].strip())
self.target_label.append(self.modelSearchList.search_category_dictionary[split_line[1].strip()])
def predict(self, args):
# replace 47C164-nlc-243 with your classifier id
status = self.natural_language_classifier.status(self.watson_classifier)
self.fname = args.data
self.__read_data()
predict_id = []
#print (json.dumps(status, indent=2, ensure_ascii=False))
for i in range(len(self.text_data)):
classes = self.natural_language_classifier.classify(self.watson_classifier, self.text_data[i])
class_id = self.modelSearchList.search_category_dictionary[classes["classes"][0]["class_name"].replace("\"", "").replace("\"", "")]
predict_id.append(class_id)
print(self.target_label)
print(predict_id)
f1_score_twitter = f1_score(self.target_label, predict_id, average='macro')
print("----F measure-----")
print(f1_score_twitter)
import json
from os.path import join, dirname
from watson_developer_cloud import NaturalLanguageClassifierV1 as NaturalLanguageClassifier
natural_language_classifier = NaturalLanguageClassifier(
username='******', password='******')
classifiers = natural_language_classifier.list()
print(json.dumps(classifiers, indent=2))
# create a classifier
# with open('../resources/weather_data_train.csv', 'rb') as training_data:
# print(json.dumps(natural_language_classifier.create(training_data=training_data, name='weather2'), indent=2))
# replace 47C164-nlc-243 with your classifier id
status = natural_language_classifier.status('47C164-nlc-243')
print(json.dumps(status, indent=2))
classes = natural_language_classifier.classify('47C164-nlc-243',
'How hot will it be tomorrow?')
print(json.dumps(classes, indent=2))
import json
from os.path import join, dirname
from watson_developer_cloud import NaturalLanguageClassifierV1 as NaturalLanguageClassifier
natural_language_classifier = NaturalLanguageClassifier(username='******',
password='******')
print(json.dumps(natural_language_classifier.list(), indent=2))
# create a classifier
# with open('../resources/weather_data_train.csv', 'rb') as training_data:
# print(json.dumps(natural_language_classifier.create(training_data=training_data, name='weather2'), indent=2))
# replace 47C164-nlc-243 with your classifier id
status = natural_language_classifier.status('47C164-nlc-243')
print (json.dumps(status, indent=2))
classes = natural_language_classifier.classify('47C164-nlc-243', 'How hot will it be tomorrow?')
print(json.dumps(classes, indent=2))
def classifier_status(url, username, password, classifier_ids):
n = NaturalLanguageClassifier(url=url, username=username, password=password)
for classifier_id in classifier_ids:
status = n.status(classifier_id)
print("%s: %s" % (status["status"], status["status_description"]))
def classifier_status(url, username, password, classifier_ids):
n = NaturalLanguageClassifier(url=url, username=username, password=password)
for classifier_id in classifier_ids:
status = n.status(classifier_id)
print(" Instance name: %s with classifier id %s is %s; Description: %s" % (status["name"],status["classifier_id"],status["status"], status["status_description"]))
class Watson_api():
def __init__(self):
self.fname = ""
self.modelSearchList = ModelSearchList()
self.text_data = []
self.target_label = []
self.watson_crediantial = watson_key()
#self.watson_classifier = self.watson_crediantial.classifier_twitter_classfier
#self.watson_classifier = self.watson_crediantial.classifier_twitter_hash_classfier
#self.watson_classifier = self.watson_crediantial.classifier_twitter_unblance_keyword_classfier
#self.watson_classifier = self.watson_crediantial.twitter_priority_classfier
self.watson_classifier = self.watson_crediantial.twitter_category_classfier
self.natural_language_classifier = NaturalLanguageClassifier(
username=self.watson_crediantial.username,
password=self.watson_crediantial.password)
#print(json.dumps(self.natural_language_classifier.list(), indent=2))
def parse_args(self):
p = ArgumentParser(
description='Encoder-decoder neural machine trainslation')
p.add_argument('data', help='[in] data')
args = p.parse_args()
return args
def train(self):
# create a classifier
with open('../resources/weather_data_train.csv',
'rb') as training_data:
print(
json.dumps(self.natural_language_classifier.create(
training_data=training_data, name='weather2'),
indent=2))
def __read_data(self):
for line in open(self.fname, "r"):
split_line = line.split(",")
self.text_data.append(split_line[0].strip())
self.target_label.append(
self.modelSearchList.search_category_dictionary[
split_line[1].strip()])
def predict(self, args):
# replace 47C164-nlc-243 with your classifier id
status = self.natural_language_classifier.status(
self.watson_classifier)
self.fname = args.data
self.__read_data()
predict_id = []
#print (json.dumps(status, indent=2, ensure_ascii=False))
for i in range(len(self.text_data)):
classes = self.natural_language_classifier.classify(
self.watson_classifier, self.text_data[i])
class_id = self.modelSearchList.search_category_dictionary[
classes["classes"][0]["class_name"].replace("\"", "").replace(
"\"", "")]
predict_id.append(class_id)
print(self.target_label)
print(predict_id)
f1_score_twitter = f1_score(self.target_label,
predict_id,
average='macro')
print("----F measure-----")
print(f1_score_twitter)
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
usage()
sys.exit()
elif opt in ("-c", "---classifier_id"):
classifier_id = arg
elif opt == '-d':
DEBUG = True
if not classifier_id:
print('Required argument missing.')
usage()
sys.exit(2)
try:
# create classifiers with the training data
natural_language_classifier = NaturalLanguageClassifier(
url=nlcConstants.getUrl(),
username=nlcConstants.getUsername(),
password=nlcConstants.getPassword())
# get classifier information
res = natural_language_classifier.status(classifier_id)
sys.stdout.write(json.dumps(res, indent=2))
except Exception as e:
sys.stdout.write(str(e))
exit(1)
#! /usr/bin/python
from watson_developer_cloud import NaturalLanguageClassifierV1 as NLC
import json
with open('credential.json') as f_cred:
cred = json.load(f_cred)
with open('classifier_info.json') as f_cls:
cls_id = json.load(f_cls)['classifier_id']
nlc = NLC(username=cred['username'], password=cred['password'])
status = nlc.status(cls_id)
with open('classifier_info.json', 'w') as f_cls:
json.dump(status, f_cls, indent=2)
print(json.dumps(status, indent=2))
import sys
import operator
import requests
import json
import twitter
from watson_developer_cloud import NaturalLanguageClassifierV1 as NaturalLanguageClassifier
#The IBM Bluemix credentials
nlc_username = '******'
nlc_password = '******'
natural_language_classifier = NaturalLanguageClassifier(username=nlc_username,
password=nlc_password)
classifierId = 'e4be4cx148-nlc-16'
status = natural_language_classifier.status(classifierId)
print(json.dumps(status, indent=2))
#! /usr/bin/python
from watson_developer_cloud import NaturalLanguageClassifierV1 as NLC
import json
with open('credential.json') as f_cred:
cred = json.load(f_cred)
with open ('classifier_info.json') as f_cls:
cls_id = json.load(f_cls)['classifier_id']
nlc = NLC(username = cred['username'], password = cred['password'])
status = nlc.status(cls_id)
with open ('classifier_info.json', 'w') as f_cls:
json.dump(status, f_cls, indent = 2)
print (json.dumps(status, indent=2))
