sergiolucero

import requests
from bs4 import BeautifulSoup

URL_BASE='http://www.autosrobadoschile.com/agregar-robo/9-automoviles?start=%d'

out = []
for start in range(20):   # first 400 robos
	url = URL_BASE %(20*start)
	print(url)
	page = requests.get(url)

sergiolucero

library(tm);library(wordcloud);library(memoise)

books <<- list("A Mid Summer Night's Dream" = "summer",
              "Glamorama" = "Glamorama1")     # The list of valid books

getTermMatrix <- memoise(function(book) { # Using "memoise" to automatically cache the results
  if (!(book %in% books))  stop("Unknown book")
  text <- readLines(sprintf("./%s.txt.gz", book), encoding="UTF-8")

  myCorpus = Corpus(VectorSource(text))

sergiolucero

import requests, sqlite3, pandas as pd

url='https://api.citybik.es/v2/networks/velib'
r=requests.get(url)
conn = sqlite3.connect('pybikes.db')

df = pd.DataFrame(r.json()['network']['stations'])
df = df[['id','name','free_bikes','empty_slots','timestamp']]
df.to_sql('velib', conn,if_exists='append')

sergiolucero

import json
import pandas as pd
import urllib.request

ori='75+9th+Ave+New+York,+NY'
des='MetLife+Stadium+1+MetLife+Stadium+Dr+East+Rutherford,+NJ+07073'
dep=int(datetime.datetime.now().timestamp())

URL='https://maps.googleapis.com/maps/api/directions/json?origin=%s&destination=%s&departure_time=%d' %(ori,des,dep)
URL+='&traffic_model=best_guess&key=AIzaSyB_ZS04dfON0PZVBRwhKTkeChK3rlYUgSk'

sergiolucero

# plotly polar: https://plot.ly/python/polar-chart/
# polar bokeh : https://gist.github.com/jjhelmus/10610995
# R radar discussion: https://github.com/ropensci/plotly/issues/890
# and again:  https://moderndata.plot.ly/radar-charts-in-r-using-plotly/

sergiolucero

# from http://docs.sherlockml.com/libraries/lens/getting_started.html
import lens
import pandas as pd

df=pd.read_csv('300_casas_renam.csv.gz', compression='gzip')
df=df[['id_x','text_x','hext_x','time','tint_y','hint_y','Co2_y','Ruido_y']]
df=df.rename(columns={'id_x':'casa','text_x':'TempExt','hext_x':'HumedadExt',
            'hint_y':'HumedadInt','Co2_y':'CO2',
            'Ruido_y':'Ruido','tint_y':'TempInt'})

sergiolucero

from dask.distributed import Client
# stands are a list of 50-100 objects with associated methods

def crunched(stand):
	stand.compute_stand_volume()  # aqui esta el costo del BN1
	return stand

client = Client()
y = [client.submit(crunched, stand) for stand in stands]
self.stands = client.gather(y)  # collect the results

sergiolucero

import sqlite3
import pandas as pd
db = sqlite3.connect('database.db')
tables = pd.read_sql_query("SELECT * FROM sqlite_master WHERE type='table'", db) 
print(tables)

sergiolucero

import folium

f = folium.Map(location=[-33.413, -70.6], zoom_start=15)

puntos = [(-33.41138735,-70.60239197),
	  (-33.41411257,-70.60185419),
	  (-33.41389096,-70.59258862)]

for punto in puntos:
	folium.Marker(punto).add_to(f)

sergiolucero

from pytz import timezone
from datetime import datetime

def localtime():
  santiago = timezone('America/Santiago')
  scl_time = datetime.now(santiago)
  return scl_time.strftime('%Y-%m-%d_%H-%M-%S')