import pandas as pd

cities = pd.DataFrame({ "name": ["Athens", "Bratislava", "Copenhagen", "Dublin"], "area": [39, 367.6, 86.2, 115], "elevation": [170, 152, 14, 20], "population": [664046, 429564, 602481, 553165] } ) cities

file = open("anscombe.json") anscombe_json = file.read() file.close() print(anscombe_json)

import requests response = requests.get('https://www.tagesschau.de/xml/rss2/') tagesschau_xml = response.text print(tagesschau_xml[:1500]) # this displays the first 1000 characters

base_url = "https://hub.culturegraph.org/entityfacts/" gnd_id = "118564943" # GND identifier found on Wikipedia page for Käthe Kollwitz (scroll to bottom) gnd_response = requests.get(base_url+gnd_id).text print(gnd_response[:1000])

kitas = pd.read_csv( "https://opendata.potsdam.de/explore/dataset/kitaboerse-20161108/download/", sep=";") kitas.head()

import json anscombe_dict = json.loads(anscombe_json) anscombe = pd.DataFrame.from_dict(anscombe_dict) anscombe

import xml.etree.ElementTree as ET

tagesschau = ET.fromstring(tagesschau_xml) tagesschau

# create two empty lists dates = [] titles = [] # go through all item elements in the tree for item in tagesschau.findall('.//item'): # extract date information and titles dates.append( item.find('.//pubDate').text ) titles.append( item.find('.//title').text ) # create a dataframe containing the two columns tagesschau_df = pd.DataFrame( {'date': dates, 'title': titles }) tagesschau_df

import bs4

permalink = "https://en.wikipedia.org/w/index.php?title=List_of_largest_cities&oldid=1219932710" wiki = requests.get(permalink).text

soup = bs4.BeautifulSoup(wiki, "html.parser") # extract the table with the class wikitable table = soup.find('table', class_='wikitable') # create some empty lists of city names and populations names = [] pops = [] # iterate over all rows, <tr> is the html element for table rows rows = table.find_all('tr') for row in rows: # the city name is in the first vertical heading cell (th) heads = row.find_all('th') # we extract the name if there is actually at least one th cell if (len(heads)>0): # extract text regardless if encapsulated with a link or not name = heads[0].get_text(strip=True) # if there is no th cell, we skip and go to the next row else: continue # we gather all regular table cells (td) cells = row.find_all('td') if (len(cells)>2): # the population number is in the 7th td cell pop = cells[6] # if there is no value, we're omitting this city if(pop is None): continue # we remove commas and any extra whitespace pop = pop.text.replace(",", "").strip() # if the content of the string is not numeric we, do not include it if (pop.isnumeric()== False): continue # finally adding city population and name pops.append(pop) names.append(name) else: continue # generate a dataframe based on the city names & populations df = pd.DataFrame({"city": names, "population": pops}) df.population = pd.to_numeric(df.population) # cast string to numeric values df

kitas.head()

kitas.describe()

kitas.info()

kitas = kitas.rename(columns={"name_der_kindertagesbetreuungseinrichtung": "name"})

kitas["name"]

kitas[["name", "betrieb_e"]]

kitas [kitas["betrieb_e"].notnull()] [["name", "betrieb_e"]]

kitas['name_copy'] = kitas['name'] kitas = kitas.set_index("name_copy")

kitas.iloc[0]

kitas.loc["Kastanienhof, Hort"]

kitas.at["Kastanienhof, Hort", "e_mail"]

kitas.iat[0, 14]

kitas[kitas['trager'].str.contains('AWO')]

import re # regular expressions module, use for a case-insensitive query kitas[kitas['name'].str.contains('Spatzen', flags=re.IGNORECASE, regex=True)] ["name"]