Code: Alles auswählen
#!/usr/bin/env python3
import pandas as pd
def main():
campaing_finance = pd.read_html(
'https://en.wikipedia.org/wiki/'
'United_States_presidential_election,_2016',
'Money raised', # Something that is just in *that* table.
skiprows=2,
)[0]
print(campaing_finance)
if __name__ == '__main__':
main()
Code: Alles auswählen
import pandas as pd
df = pd.read_html('https://en.wikipedia.org/wiki/United_States_presidential_election,_2016#Campaign_finance',
header=0)
df[25]Code: Alles auswählen
import pandas as pd
df = df.rename(columns={'Candidate': 'Candidate', 'Campaign committee (as of December 9)': 'Campaign committee Money raised', 'Outside groups (as of December 9)': 'CC Money spent', 'Total spent':'CC Cash on hand', 'Unnamed: 4': 'CC Debt', 'Unnamed: 5': 'Outside groups Money raised', 'Unnamed: 6': 'OG Money spent', 'Unnamed: 7': 'OG Cash on hand', 'Unnamed: 8': 'OG Total spent'})Code: Alles auswählen
#!/usr/bin/env python3
import pandas as pd
COLUMN_NAMES = [
'Candidate',
'Campaign committee Money raised',
'CC Money spent',
'CC Cash on hand',
'CC Debt',
'Outside groups Money raised',
'OG Money spent',
'OG Cash on hand',
'OG Total spent',
]
def convert_dollars(column):
return column.str.replace('$', '').str.replace(',', '').astype(int)
def process_campaign_finance():
campaign_finance = pd.read_html(
'https://en.wikipedia.org/wiki/'
'United_States_presidential_election,_2016',
'Money raised', # Something that is just in *that* table.
skiprows=2,
)[0]
campaign_finance.columns = COLUMN_NAMES
#
# Remove footnotes from candidates names.
#
campaign_finance['Candidate'] = (
campaign_finance['Candidate'].str.partition('[')[0]
)
campaign_finance = (
campaign_finance.set_index('Candidate').transform(convert_dollars)
)
print(campaign_finance.to_csv())
def process_student_numbers():
#
# Source of data: https://www-genesis.destatis.de/genesis/online/
# logon?sequenz=tabelleErgebnis&selectionname=21311-0014&zeitscheiben=1
#
student_numbers = pd.read_csv(
'test.csv',
encoding='iso8859-15',
sep=';',
engine='python',
skiprows=4,
skipfooter=3,
index_col=[0, 1],
header=[0, 1],
)
#
# Stata doesn't like the `MultiIndex` columns, so let's flatten the index.
#
student_numbers.columns = (
'_'.join(value) for value in student_numbers.columns.values
)
student_numbers.to_stata('test.dta')
def main():
process_campaign_finance()
process_student_numbers()
if __name__ == '__main__':
main()