marcossilva

import plotly.offline as py
import plotly.graph_objs as go
import pandas as pd
import numpy as np
pd.set_option('display.max_columns', 200)
pd.set_option('display.max_rows', 500)
py.init_notebook_mode(connected=True)

#Produce two random data to plot
y0 = np.random.randn(50)-1

marcossilva

import boto3
import sagemaker
from sagemaker.amazon.amazon_estimator import get_image_uri
import json
import glob

sess = sagemaker.Session()


bucket = 'workspace-foguetes'

marcossilva

# We use the requests lib to make the HTTP GET request
import requests
r = requests.get("https://icml.cc/Conferences/2021/Schedule?type=Poster")

# And the BeautifulSoup lib to parse the HTML data
from bs4 import BeautifulSoup
soup = BeautifulSoup(r.text, 'html.parser')

# I used the select_one operator to use the CSS selector and get the element with class 'col-xs-12'
# and then the select to obtain all the divs with the onClick attribute

marcossilva

from pathlib import Path
import requests
from tqdm import tqdm

TEST_FIXTURES_DIR_PATH = "test_fixtures"
MODEL_URL = "https://grammarly-nlp-data-public.s3.amazonaws.com/gector/roberta_1_gectorv2.th"


def download_weights():
    model_path = Path("test_fixtures/roberta_model/weights.th")

marcossilva

from gector.gec_model import GecBERTModel
VOCAB_PATH = "test_fixtures/roberta_model/vocabulary"
MODEL_PATH = "test_fixtures/roberta_model/weights.th"
# Initialize model
model = GecBERTModel(
    vocab_path=VOCAB_PATH,
    model_paths=[MODEL_PATH],
    max_len=50,
    min_len=3,
    iterations=5,