sergiolucero

from transformers import AutoTokenizer, AutoModelForQuestionAnswering, Trainer, 
                         TrainingArguments, default_data_collator
import datasets

model_name = 'dccuchile/bert-base-spanish-wwm-cased'

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForQuestionAnswering.from_pretrained(model_name)

train_data = datasets.load_dataset('squad_es', 'v1.1.0', split='train[:80%]')

sergiolucero

import pydicom as dicom
import matplotlib.pylab as plt
import glob

fig=plt.figure(figsize=(20,12));rows=2;cols=2;axes=[]
for a, file in zip(range(rows*cols),glob.glob('*.dcm')):
    axes.append( fig.add_subplot(rows, cols, a+1) )
    axes[-1].set_title(file)
    axes[-1].axis('off')
    plt.imshow(dicom.dcmread(file).pixel_array)

sergiolucero

import glob
from PyPDF2 import PdfFileMerger

merger = PdfFileMerger()
for fn in glob.glob('*.pdf'):
  merger.append(fn)
  
merger.write('result.pdf')
merger.close()

sergiolucero

import glob
import cv2

images = glob.glob('Plot*.png')
print('nImages:', len(images))

height, width, layers = cv2.imread(images[0]).shape
video = cv2.VideoWriter('video.avi', 0, 1, (width,height))

for image in images:

sergiolucero

from diagrams import Diagram, Cluster
from diagrams.aws.compute import EC2
from diagrams.aws.network import ELB
from diagrams.aws.network import Route53
from diagrams.onprem.database import PostgreSQL # Would typically use RDS from aws.database
from diagrams.onprem.inmemory import Redis # Would typically use ElastiCache from aws.database

with Diagram("Simple Website Diagram", direction='LR') as diag: # It's LR by default, but you have a few options with the orientation
    dns = Route53("dns")
    load_balancer = ELB("Load Balancer")

sergiolucero

import wget, fitz, glob
import requests, time
from bs4 import BeautifulSoup

url='http://www.memoriachilena.gob.cl/602/w3-article-100795.html#documentos'
bs = BeautifulSoup(requests.get(url).text, 'lxml')

links = [link['href'] for link in bs.find_all('a')
            if '.pdf' in link.get('href','')]
print(len(links))

sergiolucero

import openaq
import pandas as pd

api = openaq.OpenAQ()   # fuente: www.openaq.org

cdf = api.cities(country='CL', df=True)
cdf = cdf[cdf.city.isin(['Quintero','Concón','Puchuncaví'])]

xdf = pd.concat([api.measurements(city=city, df=True, limit=1000) 
               for city in cdf.city])

sergiolucero

import geopandas as gp
import time

hdf=gp.read_file('Humedales', encoding='utf-8')
hdf.region.value_counts()
hdf.cut_reg.value_counts()

#hdf.set_crs(epsg=4326, inplace=True)
#hdf=hdf.to_crs(epsg=4326)  # doesn not work for every region!

sergiolucero

import tts
imagen = read('github/pecos.png')
texto = tts(imagen)

sergiolucero

  import cv2, glob
  import numpy as np
  
  fourcc = cv2.VideoWriter_fourcc(*'mp4v')   # choose codec according to needed format  
  video = cv2.VideoWriter('video.avi', fourcc, 1, (width, height))

  for fn in glob.glob('*.png'):
     img = cv2.imread(fn)
     video.write(img)