def getSentimentAnalysis(url): """ Get sentiment analysis of a given URL :param: url: URL to get sentiment analysis :returns: Sentiment magnitude and emotion analysis in JSON format """ html = urllib.request.urlopen(url).read() soup = BeautifulSoup(html, 'html.parser') text = textFromHtml(html) natural_language_understanding = nl.enableWatsonNatLang() response = natural_language_understanding.analyze( text= text, features=[ # Get general sentiment of text Features.Sentiment( document=True ), # Get emotion towards relevant entities (max:3) Features.Entities( emotion=True, limit = 3 ) ] ) return json.dumps(response, indent=2)
def on_data(self, data):
try:
#json_data = status._json
tweet = json.loads(data)
textdata = tweet['text']
# print textdata
if tweet['coordinates']:
print tweet['coordinates']
#response = queue.send_message(MessageBody=tweet['text'])
# print (tweet)
producer = KafkaProducer(
value_serializer=lambda v: json.dumps(v).encode('utf-8'))
producer.send('fizzbuzz', textdata)
consumer = KafkaConsumer(bootstrap_servers='localhost:9092',
auto_offset_reset='earliest')
consumer.subscribe(['fizzbuzz'])
for message in consumer:
print(message)
nlu = watson_developer_cloud.NaturalLanguageUnderstandingV1(
version='2017-02-27', username='', password='')
nlu.analyze(text=textdata, features=[features.Sentiment()])
except Exception as e:
#print("exception: "+e)
pass
def on_error(self, status):
print(status)
return True
def run_watson_nlu():
files = glob.glob('work/bug-*.json')
(user, passwd) = get_auth()
for fname in files:
with open(fname) as f:
LOG.debug("Processing %s" % fname)
bug = json.loads(f.read())
num = bug["link"].split("/")[-1]
with open("work/res-%s.json" % num, "w") as out:
nlu = watson_developer_cloud.NaturalLanguageUnderstandingV1(
version='2017-02-27', username=user, password=passwd)
res = nlu.analyze(text=bug["comments"],
features=[
features.Concepts(),
features.Keywords(),
features.Emotion(),
features.Sentiment(),
])
output = {
"link": bug["link"],
"tags": bug["tags"],
"importance": bug["importance"],
"length": len(bug["comments"]),
"results": res
}
out.write(json.dumps(output, indent=4))
def worker_main(queue):
while True:
messages = queue.receive_messages(MessageAttributeNames=['Id', 'Tweet', 'Latitude', 'Longitude'])
print("Received messages")
if len(messages)>0:
for message in messages:
# Get the custom author message attribute if it was set
if message.message_attributes is not None:
id = message.message_attributes.get('Id').get('StringValue')
tweet = message.message_attributes.get('Tweet').get('StringValue')
lat = message.message_attributes.get('Latitude').get('StringValue')
lng = message.message_attributes.get('Longitude').get('StringValue')
try:
response = natural_language_understanding.analyze(
text=tweet, features=[features.Sentiment()])
senti = response["sentiment"]["document"]["label"]
print senti
# senti = response.get('docSentiment').get('type')
except Exception as e:
print("ERROR: "+str(e))
senti = "neutral"
# Using SNS
sns_message = {"id":id, "tweet":tweet, "lat":lat, "lng": lng, "sentiment":senti}
print("SNS messsage: "+str(sns_message))
sns.publish(TargetArn=arn, Message=json.dumps({'default':json.dumps(sns_message)}))
# print('Id: {0}; Tweet: {1}; Latitude: {2}; Longitude: {3}; sentiment: {4}'.format(id,tweet,lat,lng,senti))
# Let the queue know that the message is processed
message.delete()
else:
time.sleep(1)
def analyse(queue, sns_topic):
messages = queue.receive_messages(MessageAttributeNames=['All'],
VisibilityTimeout=30,
MaxNumberOfMessages=10)
for message in messages:
if message.body is not None and message.message_attributes is not None:
#print(message.body)
sns_message = {}
nlp = NaturalLanguageUnderstandingV1(version='2017-02-27',\
url = "https://gateway.watsonplatform.net/natural-language-understanding/api",\
username = configure.ibm_username,\
password = configure.ibm_password)
response = nlp.analyze(text=message.body,
features=[features.Sentiment()])
print(response["sentiment"]["document"]["label"])
if response["sentiment"]["document"]["label"] is not None:
username = message.message_attributes["username"]
sentiment = response["sentiment"]["document"]["label"]
lat = message.message_attributes["lat"]
long = message.message_attributes["long"]
timestamp_ms = message.message_attributes["timestamp_ms"]
sns_message["username"] = username
sns_message["content"] = message.body
sns_message["lat"] = lat
sns_message["long"] = long
sns_message["sentiment"] = sentiment
sns_message["timestamp_ms"] = timestamp_ms
message_for_send = json.dumps(sns_message)
response1 = sns_topic.publish(Message=message_for_send)
print(response1)
else:
print("sentiment analyse error!")
def on_status(self, status):
natural_language_understanding = NaturalLanguageUnderstandingV1(
version='2017-02-27',
username='******',
password='******')
twitts = status.text
coordinates = status.coordinates
language = status.user.lang
if status.place and language == 'en':
if coordinates is not None and len(coordinates) > 0:
coordinates = status.coordinates['coordinates']
print 'coordinates: ', coordinates
print 'twitts: ', twitts
try:
response = natural_language_understanding.analyze(
text=twitts, features=[features.Sentiment()])
sentiment = response['sentiment']['document']['label']
except Exception as e:
sentiment = "neutral"
print sentiment
upload_data = {
"twitts": twitts,
"coordinates": coordinates,
"sentiment": sentiment
}
print requests.post(
'https://search-trends-pnoxxtizp4zrbmwnvgsifem74y.us-east-1.es.amazonaws.com/twittmap/data',
json=upload_data)
return True
def emotionRank(url):
response = natural_language_understanding.analyze(
url=url,
features=[
Features.Sentiment()
])
return response
def get_sentiment(content): try: resp = nlp.analyze(text=content, features=[features.Sentiment()]) response = resp["sentiment"]["document"]["score"] print str(response) + ": " + content return response except: print "Error getting sentiment from Watson NLU" return None
def sentiment(tips):
# Helper function to return text sentiment analysis
# Load Watson credentials
username=os.environ.get('NLU_USERNAME')
password = os.environ.get('NLU_PASSWORD')
nlu = watson_developer_cloud.NaturalLanguageUnderstandingV1(version='2017-02-27',
username=username, password=password)
output = nlu.analyze(text=tips, features=[features.Sentiment()])
return output['sentiment']['document']['score']
def main():
load_dotenv(find_dotenv())
nlu_username = os.environ.get('NLU_USERNAME')
nlu_password = os.environ.get('NLU_PASSWORD')
nlu = NLU(username=nlu_username, password=nlu_password, version='2017-02-27')
result = nlu.analyze(text='I hate galvanize', features=[features.Sentiment()])['sentiment']['document']
print(result['label'], result['score'])
def test_analyze_throws(self):
nlu = NaturalLanguageUnderstandingV1(version='2016-01-23',
url='http://bogus.com',
username='******',
password='******')
with pytest.raises(ValueError):
nlu.analyze([features.Sentiment()])
with pytest.raises(ValueError):
nlu.analyze([], text="this will not work")
def nl_processing(reqd_text):
response = natural_language_understanding.analyze(text=reqd_text,
features=[
features.Entities(),
features.Keywords(),
features.Emotion(),
features.Concepts(),
features.Sentiment()
])
return response
def analyze(s):
response = natural_language_understanding.analyze(text=s,
features=[
Features.Keywords(
emotion=True,
sentiment=True,
limit=2),
Features.Sentiment()
])
return response
def getData(user, pw, doc):
natural_language_understanding = NaturalLanguageUnderstandingV1(
version='2017-02-27',
username=user,
password=pw)
url = 'https://gateway.watsonplatform.net/natural-language-understanding/api'
response = natural_language_understanding.analyze(
text=doc,
features=[features.Sentiment(), features.Emotion()])
return json.dumps(response)
def analyse_emotions(self, tweet):
# print('Analysis Text:',tweet)
response = natural_language_understanding.analyze(
text=tweet, features=[Features.Emotion(),
Features.Sentiment()])
list_emotion = list(
response['emotion']['document']['emotion'].values())
list_emotion.append(response['sentiment']['document']['score'])
print('List emotion is : ', list_emotion)
return list_emotion
def analyze_sentiment(self, answer):
result = self.nlu.analyze(
text=answer, features=[features.Keywords(),
features.Sentiment()])
if result['keywords']:
keywords = result['keywords'][0]
keyword = keywords['text']
else:
keyword = None
sentiment = result['sentiment']['document']['score']
return sentiment, keyword
def test_text_analyze(self):
nlu_url = "http://bogus.com/v1/analyze"
responses.add(responses.POST, nlu_url,
body="{\"resulting_key\": true}", status=200,
content_type='application/json')
nlu = NaturalLanguageUnderstandingV1(version='2016-01-23',
url='http://bogus.com',
username='******',
password='******')
nlu.analyze([features.Sentiment()], text="hello this is a test")
assert len(responses.calls) == 1
def worker():
global q
print 'Worker Initialized'
attributes = ['id', 'text', 'time', 'lat', 'lon']
while True:
responses = q.receive_messages(MessageAttributeNames=attributes)
if len(responses) != 0:
for response in responses:
if response.message_attributes is None:
response.delete()
continue
id = response.message_attributes.get('id').get('StringValue')
text = response.message_attributes.get('text').get(
'StringValue')
time = response.message_attributes.get('time').get(
'StringValue')
lat = response.message_attributes.get('lat').get('StringValue')
lon = response.message_attributes.get('lon').get('StringValue')
try:
natural_language_understanding = NaturalLanguageUnderstandingV1(\
version='2017-02-27',\
username=nlu_creds['username'],\
password=nlu_creds['password']\
)
nlu_response = natural_language_understanding.analyze(\
text=text,\
features=[features.Entities(), features.Keywords(), features.Sentiment()]\
)
sentiment = nlu_response['sentiment']['document']['label']
except Exception as e:
print 'Error:', e
sentiment = 'neutral'
# Send to AWS SNS
notification = {
'id': id,
'text': text,
'time': time,
'lat': lat,
'lon': lon,
'sentiment': sentiment
}
try:
print notification
sns.publish(TargetArn=sns_arn,
Message=json.dumps(
{'default': json.dumps(notification)}))
response.delete()
except Exception as e:
print 'Error:', e
sleep(2)
def analyze(self, content, keyword):
response = self.natural_language_understanding.analyze(
text=content,
features=[
Features.Sentiment(
# Emotion options
targets=[keyword]
)
]
)
score = response["sentiment"]["document"]["score"]
return score
def test_url_analyze(self):
nlu_url = "http://bogus.com/v1/analyze"
responses.add(responses.POST, nlu_url,
body="{\"resulting_key\": true}", status=200,
content_type='application/json')
nlu = NaturalLanguageUnderstandingV1(version='2016-01-23',
url='http://bogus.com',
username='******',
password='******')
nlu.analyze([features.Sentiment(),
features.Emotion(document=False)], url="http://cnn.com",
xpath="/bogus/xpath", language="en")
assert len(responses.calls) == 1
def open_request():
data = request.get_json()
text = data['transcription']
patient_id = data['patient_id']
if text not in watson_cache:
try:
watson_cache[text] = natural_language_understanding.analyze(
text=text,
features=[features.Keywords(), features.Sentiment()])
except WatsonException as err:
print err
enqueue(patient_id, text, watson_cache[text])
return jsonify({'result': watson_cache[text]})
def extract_sentiment_ner_trec_full(src, dst_dir):
"""
Extracts tweet overall sentiment, sentiment per NER, NERs,
keywords, sentiment per keyword for the full dataset that's read from a
.txt file.
Parameters
----------
src: str - path to dataset.
dst_dir: - directory in which results will be stored.
"""
tweets = read_txt(src)
# Since tweets are ordered according to topic, label them in a
# random order
keys = tweets.keys()
random.shuffle(keys)
for idx, tid in enumerate(keys):
fname = "{}.json".format(tid)
dst = os.path.join(dst_dir, fname)
# If file already exists, data was extracted before and due to
# rate-limiting the rest couldn't be extracted
if not os.path.isfile(dst):
try:
# Extract features for a tweet via Watson
response = natural_language_understanding.analyze(
text=tweets[tid]["text"],
# Get entities and their
features=[
# Overall tweet sentiment
Features.Sentiment(),
# NER detection and sentiment per NER
Features.Entities(sentiment=False),
Features.Keywords(sentiment=False),
])
# Store results in UTF-8 encoding
fname = "{}.json".format(tid)
dst = os.path.join(dst_dir, fname)
with codecs.open(dst, "w", encoding="utf-8") as f:
# https://stackoverflow.com/questions/18337407/saving-utf-8-texts-in-json-dumps-as-utf8-not-as-u-escape-sequence
data = json.dumps(response,
ensure_ascii=False,
encoding='utf8')
f.write(unicode(data))
# Illegal language
except watson_developer_cloud.watson_developer_cloud_service.\
WatsonException:
pass
print "Finished extraction for {} tweets".format(idx + 1)
def map_feature(name):
feature_name_mappings = {
'keywords': features.Keywords(),
'entities': features.Entities(),
'concepts': features.Concepts(),
'categories': features.Categories(),
'sentiment': features.Sentiment(),
'emotion': features.Emotion()
}
if name in feature_name_mappings:
return feature_name_mappings[name]
else:
print("Invalid feature name")
return None
def get_text_data(text,language):
username = os.environ.get("BLUEMIX-NLU-USERNAME")
password = os.environ.get("BLUEMIX-NLU-PASSWORD")
natural_language_understanding = NaturalLanguageUnderstanding(
version = "2017-02-27",
username=username,
password=password
)
return natural_language_understanding.analyze(
text = text,
features = [features.Emotion(), features.Sentiment(), features.Keywords()],
language = language
)
def nlu(text):
response = n.analyze(text=text,
features=[
features.Emotion(),
features.Concepts(),
features.Categories(),
features.Entities(),
features.Keywords(),
features.SemanticRoles(),
features.Relations(),
features.Sentiment()
],
language='en')
return json.dumps(response, indent=2)
def featureList(self, tags):
f_list = []
for tag in tags:
if tag == "sentiment":
f_list.append(features.Sentiment())
elif tag == "categories":
f_list.append(features.Categories())
elif tag == "concepts":
f_list.append(features.Concepts())
elif tag == "emotion":
f_list.append(features.Emotion())
elif tag == "entities":
f_list.append(features.Entities())
return f_list
def worker_task():
while True:
msgs = queue.receive_messages(
MessageAttributeNames=['Id', 'Tweet', 'Latitude', 'Longitude'])
sns.subscribe(
TopicArn=arn,
Protocol='http',
Endpoint=
'http://twitter-senti-env.2mvfwajxvd.us-east-1.elasticbeanstalk.com/sns_test_handler/'
)
if len(msgs) > 0:
for message in msgs:
id = message.message_attributes.get('Id').get('StringValue')
tweet = message.message_attributes.get('Tweet').get(
'StringValue')
lat = message.message_attributes.get('Latitude').get(
'StringValue')
lon = message.message_attributes.get('Longitude').get(
'StringValue')
#print(tweet)
try:
response = nlu.analyze(text=tweet,
features=[features.Sentiment()])
print(response)
s = json.dumps(response)
r = json.loads(s)
sentiment = r['sentiment']['document']['label']
senti_score = r['sentiment']['document']['score']
#sentiment = "pos"
#senti_score = 0.5
sns_message = {
'id': id,
'tweet': tweet,
'lat': lat,
'lon': lon,
'senti': sentiment,
'score': senti_score
}
print("SNS message:" + str(sns_message))
sns.publish(TopicArn=arn,
Message=json.dumps(
{'default': json.dumps(sns_message)}))
except Exception as e:
print("ERROR:" + str(e))
else:
time.sleep(1)
def IBMWatsonSentimentAnalyzer(
self, text
): # IBM Watson Sentiment Analysis. Returns score and label (float, str pair)
try:
natural_language_understanding = NaturalLanguageUnderstandingV1(
username=WATSON_USERNAME,
password=WATSON_PASSWORD,
version=WATSON_VERSION,
url=WATSON_APIURL)
response = natural_language_understanding.analyze(
text=text, features=[Features.Sentiment()])
return float(response["sentiment"]["document"]["score"]), str(
response["sentiment"]["document"]["label"])
except:
return -1000, "neutral"
def _addAnalysis(text, sentimentArray, emotionsDict):
try:
result = natural_language_understanding.analyze(
text=text, features=[Features.Sentiment(),
Features.Emotion()])
result['emotion']
except:
return
sentiment_score = result['sentiment']['document']['score']
sentimentArray.append(sentiment_score)
emotions = result['emotion']['document']['emotion']
for emo in emotions:
if emo not in emotionsDict:
emotionsDict[emo] = []
emotionsDict[emo].append(emotions[emo])
def sentimentMining():
score = 0
totalCount = 0
negativeCount = 0
positiveCount = 0
inputText = ''
natural_language_understanding = NaturalLanguageUnderstandingV1(
version='2017-04-14',
username='******',
password='******')
# the input file to be used for sentiment analysis
inputFile = ''
with open(inputFile, 'r') as f:
reader = csv.reader(f)
cnt = 0
for row in reader:
# skipping the first row which is the heading
if cnt == 0:
cnt += 1
else:
if len(row) == 0:
pass
# if empty review
else:
inputText = row[0]
cnt += 1
totalCount += 1
# sentiment analysis of every review
response = natural_language_understanding.analyze(
text=inputText,
features=[features.Sentiment(),
features.Emotion()],
language='en')
print(totalCount)
# counting the number of positive and negative review with the score
if response["sentiment"]["document"][
"label"] == 'positive':
positiveCount += 1
score += response["sentiment"]["document"]["score"]
elif response["sentiment"]["document"][
"label"] == 'negative':
negativeCount += 1
score += response["sentiment"]["document"]["score"]
return positiveCount, negativeCount, score, totalCount
