def process(self, item):
client = language.LanguageServiceClient()
doc = language.Document(content=item["tweet"],
type_=language.Document.Type.PLAIN_TEXT)
response = client.analyze_sentiment(document=doc)
item["sentiment"] = response.document_sentiment.score
return [item]
def analyze_text_entities(text):
client = language.LanguageServiceClient.from_service_account_json(
"C:\\Users\\Srinu\\Documents\\keys\\nlp.json")
document = language.Document(content=text,
type_=language.Document.Type.PLAIN_TEXT)
response = client.analyze_entities(document=document,
encoding_type='UTF32')
print(response.entities)
result = []
for entity in response.entities:
if entity.type_.name == "DATE":
# print("=" * 80)
result.append(entity.name)
# results = dict(
# name=entity.name,
# # type=entity.type_.name,
# # salience=f"{entity.salience:.1%}",
# # wikipedia_url=entity.metadata.get("wikipedia_url", "-"),
# # mid=entity.metadata.get("mid", "-"),
# )
# for k, v in results.items():
# print(f"{k:15}: {v}")
print(result)
return result
def main(inputText):
if inputText == "":
return []
dirpath = os.path.dirname(os.path.realpath(__file__))
os.environ[
"GOOGLE_APPLICATION_CREDENTIALS"] = dirpath + "/credentials.json"
# Instantiates a client
client = language.LanguageServiceClient()
# Instantiates a plain text document.
document = language.Document(content=inputText,
type=language.Document.Type.PLAIN_TEXT)
# Detects entities in the document. You can also analyze HTML with:
# document.type == enums.Document.Type.HTML
entities = client.analyze_entities(document).entities
# entity types from enums.Entity.Type
entity_type = ('UNKNOWN', 'PERSON', 'LOCATION', 'ORGANIZATION', 'EVENT',
'WORK_OF_ART', 'CONSUMER_GOOD', 'OTHER')
result = []
maxItems = 10
for i in range(min(maxItems, len(entities))):
entity = entities[i]
result.append({
'name': entity.name,
'type': entity_type[entity.type],
'salience': entity.salience
})
return result
def analyze(text):
"""Run a sentiment analysis request on text within a passed filename."""
client = language.LanguageServiceClient()
document = language.Document(content=text, type_=language.Document.Type.PLAIN_TEXT)
annotations = client.analyze_sentiment(request={'document': document})
return print_result(annotations)
def analyze_text_sentiment(text):
client = language.LanguageServiceClient.from_service_account_json(
"C:\\Users\\Srinu\\Documents\\keys\\nlp.json")
document = language.Document(content=text,
type_=language.Document.Type.PLAIN_TEXT)
response = client.analyze_sentiment(document=document)
sentiment = response.document_sentiment
return sentiment.score * 10, sentiment.magnitude * 10
def wikipedia_route(company):
# Imports the Google Cloud client library
from google.cloud import language
result = wikipedia.summary(company, sentences=10)
client = language.LanguageServiceClient()
document = language.Document(
content=result,
type_=language.Document.Type.PLAIN_TEXT)
encoding_type = language.EncodingType.UTF8
entities = client.analyze_entities(request = {'document': document, 'encoding_type': encoding_type}).entities
return str(entities)
def analyze_text_sentiment(text):
client = language.LanguageServiceClient()
document = language.Document(content=text,
type_=language.Document.Type.PLAIN_TEXT)
response = client.analyze_sentiment(document=document)
sentiment = response.document_sentiment
results = dict(
text=text,
score=f"{sentiment.score:.1%}",
magnitude=f"{sentiment.magnitude:.1%}",
)
score = sentiment.score
magnitude = sentiment.magnitude
for k, v in results.items():
print(f"{k:10}: {v}")
return (score, magnitude)
def analyze_entities(text):
'''Returns a set of detected entities, and parameters associated with those entities, such as the
entity's type, relevance of the entity to the overall text, and locations in the text that refer to the same entity.
Entities are returned in the order (highest to lowest) of their salience scores, which reflect their relevance to
the overall text.
:param text: string
:return: JSON
'''
client = language.LanguageServiceClient()
document = language.Document(content=text,
type=language.Document.Type.PLAIN_TEXT)
encoding_type = language.EncodingType.UTF8
entities = client.analyze_entities(document=document,
encoding_type=encoding_type)
return entities
def classify_text(article):
response = nl_client.classify_text(document=language.Document(
content=article, type_=language.Document.Type.PLAIN_TEXT))
return response
location = str(df.at[i, 'Location'])
date = str(df.at[i, 'Date'])
content = normalize_space(content)
location = normalize_space(location)
content = content.replace("'", "-")
content = content.replace(",", "-")
location = location.replace("'", "-")
location = location.replace(",", "-")
location.replace(" ", "_")
location.splitlines()
document = language.Document(content=content,
type_=language.Document.Type.PLAIN_TEXT)
response = client.analyze_sentiment(request={'document': document})
score_tweet = format(response.document_sentiment.score)
magnitude_tweet = format(response.document_sentiment.magnitude)
df.at[i, 'Score'] = score_tweet
df.at[i, 'Magnit'] = magnitude_tweet
content = content[:50]
sql = "INSERT " + table_id + " (number,user,location,text,magnit,score) " + \
"VALUES(" + str(i) + ",'" +str(user) + "','" + str(location) + "','" + str(content) + \
"'," + str(magnitude_tweet) + "," + str(score_tweet) + ")"
sql = str(sql)