GabrielSGoncalves

import json
from io import StringIO
import boto3
import os
import pandas as pd


def write_dataframe_to_csv_on_s3(dataframe, filename, bucket):
    """ Write a dataframe to a CSV on S3 """

GabrielSGoncalves

import boto3
import json
import sys

BUCKET = sys.argv[1]
KEY = sys.argv[2]
OUTPUT = sys.argv[3]
GROUP = sys.argv[4]
COLUMN = sys.argv[5]
CREDENTIALS = sys.argv[6]

GabrielSGoncalves

,ID,Name,Age,Photo,Nationality,Flag,Overall,Potential,Club,Club Logo,Value,Wage,Special,Preferred Foot,International Reputation,Weak Foot,Skill Moves,Work Rate,Body Type,Real Face,Position,Jersey Number,Joined,Loaned From,Contract Valid Until,Height,Weight,LS,ST,RS,LW,LF,CF,RF,RW,LAM,CAM,RAM,LM,LCM,CM,RCM,RM,LWB,LDM,CDM,RDM,RWB,LB,LCB,CB,RCB,RB,Crossing,Finishing,HeadingAccuracy,ShortPassing,Volleys,Dribbling,Curve,FKAccuracy,LongPassing,BallControl,Acceleration,SprintSpeed,Agility,Reactions,Balance,ShotPower,Jumping,Stamina,Strength,LongShots,Aggression,Interceptions,Positioning,Vision,Penalties,Composure,Marking,StandingTackle,SlidingTackle,GKDiving,GKHandling,GKKicking,GKPositioning,GKReflexes,Release Clause
0,158023,L. Messi,31,https://cdn.sofifa.org/players/4/19/158023.png,Argentina,https://cdn.sofifa.org/flags/52.png,94,94,FC Barcelona,https://cdn.sofifa.org/teams/2/light/241.png,€110.5M,€565K,2202,Left,5,4,4,Medium/ Medium,Messi,Yes,RF,10,"Jul 1, 2004",,2021,5'7,159lbs,88+2,88+2,88+2,92+2,93+2,93+2,93+

GabrielSGoncalves

GabrielSGoncalves

from __future__ import print_function
import boto3
import os
import time
import pandas as pd
import matplotlib as plt
import logging
from botocore.exceptions import ClientError
from datetime import date
import json

GabrielSGoncalves

# 5) Creating a new S3 bucket to upload the audio files
bucket_name = 'medium-nlp-aws'
client_s3 = boto3.client('s3')
client_s3.create_bucket(Bucket=bucket_name)


# 6) Uploading the files to the created bucket
for audio_file in df_audio.filename.values:
    print(audio_file)
    client_s3.upload_file(audio_file, bucket_name,  audio_file)

GabrielSGoncalves

# 10) Function to get text from the JSON file generated using Amazon Transcribe
def get_text_from_json(bucket, key):
    s3 = boto3.client('s3')
    object = s3.get_object(Bucket=bucket, Key=key)
    serializedObject = object['Body'].read()
    data = json.loads(serializedObject)
    return data.get('results').get('transcripts')[0].get('transcript')

# 11) Reading the original transcription from the JSON file
with open('original_transcripts.json', 'r') as f:

GabrielSGoncalves

# 16) Function to call Amazon Comprehend service using boto3
def start_comprehend_job(text):
    """
    Executes sentiment analysis of a text using Amazon Comprehend.
    The text can be larger than 5000 bytes (one limitation for each job), as 
    the function will split it into multiple processes and return a 
    averaged value for each sentiment.
    
    Parameter
    - text (str): The text to be analyzed

GabrielSGoncalves

# 15) Iterate over the speakers and apply spaCy visualizer on each speech
for index, row in df_audio.iterrows():
    print(f"Rendering {index}'s texts")    
    nlp = spacy.load('en_core_web_lg')
    original_transcription = nlp(original_transcriptions.get(index))    
    transcribe_transcription = nlp(get_text_from_json(bucket_name, row.json_transcription))
    
    svg_original = spacy.displacy.render(original_transcription, style="ent",jupyter=False)
    svg_transcribe = spacy.displacy.render(transcribe_transcription, style="ent",jupyter=False)
    

GabrielSGoncalves