Last active
January 17, 2018 17:19
-
-
Save anuragmishra1/4c5c05e6c02d5d31a52d59d4571a1eaf to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import boto3 | |
import time | |
from datetime import timedelta | |
import sys | |
import os | |
import argparse | |
#We need to get our API credentials in the code for authentication that we have stored as Environment Variables locally. | |
os.environ.get("AWS_ACCESS_KEY_ID") | |
os.environ.get("AWS_SECRET_ACCESS_KEY") | |
os.environ.get("AWS_REGION") | |
#Following line is used to save all the console outputs in a text file. | |
sys.stdout = open('output.txt','a') | |
start_time = time.monotonic() | |
def input_file(text_file_path): | |
global text | |
if os.path.isfile(text_file_path): | |
with open(text_file_path, 'r') as text_file: | |
text = text_file.read() | |
else: | |
print("File doesn't exist in the directory!") | |
def dominant_language_text(): | |
#Initialize amazon_comprehend client function | |
client_comprehend = boto3.client( | |
'comprehend', | |
) | |
dominant_language_response = client_comprehend.detect_dominant_language( | |
Text = text | |
) | |
#Print the Dominant Language | |
print("Language:", sorted(dominant_language_response['Languages'], key = lambda k: k['LanguageCode'])[0]['LanguageCode']) | |
def entities_text(): | |
#Initialize amazon_comprehend client function | |
client_comprehend = boto3.client( | |
'comprehend', | |
) | |
response_entities = client_comprehend.detect_entities( | |
Text = text, | |
LanguageCode = 'en' | |
) | |
entities = list(set([obj['Type'] for obj in response_entities['Entities']])) | |
#Print the Entities | |
print("Entities:",entities) | |
def key_phrases_text(): | |
#Initialize amazon_comprehend client function | |
client_comprehend = boto3.client( | |
'comprehend', | |
) | |
response_key_phrases = client_comprehend.detect_key_phrases( | |
Text = text, | |
LanguageCode = 'en' | |
) | |
key_phrases = list(set([obj['Text'] for obj in response_key_phrases['KeyPhrases']])) | |
#Print the Key Phrases | |
print("Key Phrases:", key_phrases) | |
def sentiment_text(): | |
#Initialize amazon_comprehend client function | |
client_comprehend = boto3.client( | |
'comprehend', | |
) | |
response_sentiment = client_comprehend.detect_sentiment( | |
Text = text, | |
LanguageCode = 'en' | |
) | |
sentiment = response_sentiment['Sentiment'] | |
#Print the Sentiment | |
print("Sentiment Analysis:" , sentiment) | |
if __name__ == '__main__': | |
parser = argparse.ArgumentParser( | |
description = __doc__, | |
formatter_class = argparse.RawDescriptionHelpFormatter) | |
parser.add_argument( | |
'text_file_path', | |
help = 'The complete file path of the text file you want to analyze.') | |
args = parser.parse_args() | |
input_file(args.text_file_path) | |
dominant_language_text() | |
entities_text() | |
key_phrases_text() | |
sentiment_text() | |
end_time = time.monotonic() | |
print("Execution_Time:", timedelta(seconds = end_time - start_time)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment