| from bs4 import BeautifulSoup as bs | |
| import re, requests, time | |
| from lxml import html | |
| links = [] | |
| for date in range(1998, 2020+1): | |
| url = 'https://www.ecb.europa.eu/press/pressconf/{}/html/index_include.en.html'.format(date) | |
| r = requests.get(url) | |
| tree = html.fromstring(r.content) |
| import pandas as pd | |
| import os | |
| import matplotlib.pyplot as plt | |
| import missingno as msno | |
| ## The script merges and reshapes the data provided by https://github.com/kylemcdonald/covid-mobility-data | |
| ## Assumes all tsv files are in a folder called "archive" | |
| ## Inputs different files, outputs longform tidy data. | |
| bdf = pd.read_csv('archive/2020-03-29_ES_Mobility_Report_en.pdf.tsv', sep='\t', nrows=0) |
| graph = px.scatter(df, x="employment", y="equity", #color="country", | |
| hover_name="country", text="countrycode", | |
| range_x=[48,80], range_y=[76,93], template="plotly_dark", size="pop", | |
| animation_group="country", animation_frame="year", | |
| labels=dict(employment="Emp", equity="Eq",year="Year")) | |
| for i in graph['data']: | |
| i['name'] = i['name'].replace('Country=', '') | |
| # -*- coding: utf-8 -*- | |
| import sys, re, time, logging, requests | |
| import random | |
| import unicodecsv as csv | |
| from threading import Thread, Lock, currentThread | |
| from queue import Queue, Empty | |
| from lxml import html | |
| lock = Lock() |
| <!DOCTYPE html><html><head> | |
| <meta charset="UTF-8"> | |
| <title>prova</title> | |
| </head> | |
| <body><div><style> | |
| </style> | |
| <iframe class='viz-container' src="https://public.tableau.com/profile/actionaid.bologna#!/vizhome/dashboard2017_0/Dashboard3?:embed=y"></iframe> | |
| </div> |
Hello there! This is a sample post for gist.io, a super-lightweight writing soapbox for hackers.
Now look up. Further. Above the post title. See that grey text with the gist ID?
Now back to me. That grey text is a link! Open that sucker in a new tab to see the source for this post. Also, I'm on a horse.
| ### Beware of the Panda. | |
| ### 'You have no idea how tidy this is gonna get' | |
| from pandas import * | |
| import csv | |
| import numpy as np | |
| df = pandas.read_csv(‘data_raw.csv’, sep=” “, chunksize=5000) | |
| df | |
| appended_data = [] | |
| for chunk in df: | |
| pivot_table = chunk.pivot_table(index=[‘id’], |
| import pandas as pd | |
| import csv | |
| df = pd.read_csv('data_raw.csv') | |
| df | |
| pivot_table = df.pivot_table(index=['id'], | |
| columns=['key'], | |
| values=['value'], | |
| aggfunc=lambda x: ' '.join(str(v) for v in x)) | |
| pivot_table.to_csv('data_pivot.csv') |
| import requests | |
| from bs4 import BeautifulSoup | |
| url = ‘http://www.enricobergamini.it/trialpage.html' | |
| #load and scrape | |
| response = requests.get(url) | |
| html = response.content | |
| soup = BeautifulSoup(html, “lxml”) | |
| number = soup.find(‘h1’, id=’number’).text |