kboghe’s gists

kboghe / aggregating_googleplace_cat.csv

Created September 28, 2020 10:01

aggregating_googleplace_cat

kboghe / peakpopularityhour.py

Created September 28, 2020 08:33

peakpopularityhour

	##########################
	#check popularity by hour#
	##########################

	byhour_pop = geos_locinfo_poptimes[(geos_locinfo_poptimes['category_aggregated'] == 'restaurant')].groupby(['country', 'day list','hour list'])['percentage busy'].agg(['mean']).reset_index()
	byhour_pop = byhour_pop[~byhour_pop['hour list'].isin(['day marked as closed','not enough location data available for this day'])]
	byhour_pop = byhour_pop.pivot(index=['country','day list'], columns='hour list', values='mean')
	hours_range = [str(x) for x in range(24)]
	hours_range_night,hours_range_evening = hours_range[0:2],hours_range[17:24]
	hours_evening_night = hours_range_evening + hours_range_night

kboghe / peakpopularityplot.py

Created September 28, 2020 08:11

peakpopularityplot

	sns.set_theme(style="darkgrid")

	df_res_ov,df_res_peak = dict_pop['country_restaurant_overall'], dict_pop['country_restaurant_peak']

	df_res_ov['type'],df_res_peak['type'] = ['restaurant'] * len(df_res_ov), ['restaurant'] * len(df_res_ov)
	df_res_ov['method'],df_res_peak['method'] = ['by overall day popularity'] * len(df_res_ov),['by peak hour'] * len(df_res_peak)
	df = pd.concat([df_res_ov,df_res_peak])

	df["day list"].replace({"monday": "0", "tuesday": "1","wednesday":"2","thursday":"3","friday":"4","saturday":"5","sunday":"6"}, inplace=True)
	df['country_order'] = df["country"].replace({"NL": "0", "BE": "1","DE":"2","FR":"3","ES":"4","IT":"5"})

kboghe / summarizedata.py

Last active September 28, 2020 07:54

Summarize data

	###################################################
	#### 1. create two functions to summarize data ####
	###################################################

	## 1.1 most popular day by hour and overall popularity + number of locations per country + number of open places per country ##
	###############################################################################################################################
	def places_available(area=None,placetype=None,method=None):
	if any(parameter is None for parameter in [method,area,placetype]) :
	Exception("Please provide a value for the area, input and placetype parameters")
	if method == 'peak':

kboghe / hierarchicalclus.py

Last active September 24, 2020 14:01

hierarchicalclus

	from sklearn.cluster import AgglomerativeClustering
	from tslearn.clustering import TimeSeriesKMeans
	import pandas as pd

	#writing function to summarize cluster membership across regions
	def cluster_membership(cases=None,cluster=None):
	url_clus = pd.DataFrame({'url':cases,'cluster':cluster})
	url_clus = pd.merge(url_clus,geos_locinfo_poptimes[['url','country']].drop_duplicates(),how='left')
	url_clus['index'] = 1
	url_clus = url_clus.pivot(index=['url','cluster'], columns='country', values='index')

kboghe / plottingparis.py

Last active September 24, 2020 12:08

plotting paris

	import pandas as pd
	import geopandas

	f, axs = plt.subplots(1,1, figsize=(90, 135),sharex=False,sharey=False)
	loc = ['Paris_map.geojson'] #area to plot
	fileloc = "maps/"+ loc[0] #folder containing all maps
	map = geopandas.read_file(fileloc) #read the map
	map.plot(ax=axs,linewidth=0.1)
	axs.axis('off')

kboghe / osmcitymaps.py

Last active September 24, 2020 10:59

Retrieving city maps osm

	import json
	import numpy as np
	import geopandas
	import osmnx

	#retrieve city shapemaps and write to hard drive#

	locations = geos['search input'].unique() #creating a list of cities (e.g. "Paris,Nice,...")
	locations = ['Hamburg,Hamburg,Germany' if loc == 'Hamburg' else loc for loc in locations]
	locations = ['Saragossa' if loc == 'Zaragozza' else loc for loc in locations]

kboghe / positionstrack.py

Last active September 24, 2020 08:53

Performing Position stack requests in Python

	import re
	import pandas as pd
	import http.client, urllib.parse
	import random
	import time
	import json
	import numpy as np
	import math

	addr_city = locinfo[['id','address','country']].drop_duplicates().reset_index() #A pandas dataframe containing the id, address and country info (one row = one location)

kboghe / forcatchvpnloop.py

Last active August 11, 2020 15:48

for-catch-vpn-loop

	for i in range(2):
	try:
	current_ip = new_ip = urllib.request.urlopen('https://ident.me').read().decode('utf8')
	except urllib.error.URLError:
	print("Can't fetch current ip. Retrying...")
	time.sleep(10)
	continue
	else:
	print("\nYour current ip-address is:", current_ip)
	break

kboghe / forcatchloop.py

Last active October 6, 2022 17:33

for-catch loop

	import requests
	from bs4 import BeautifulSoup
	import random

	headers_browser = {'Connection': 'close',"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,/;q=0.8,application/signed-exchange;v=b3",
	"Accept-Encoding": "gzip","Accept-Language": "en-US,en;q=0.9,es;q=0.8", "Upgrade-Insecure-Requests": "1","User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36"}

	for i in range(3): # loop the try-part (i.e. opening the link) until it works, but only try it 4 times at most#
	try: #try the following:#
	random_sleep_link = random.uniform(10, 15) #sleep for a random chosen amount of seconds between 10 and 15 seconds#