We begin by importing some helper functions.
from helper import*
Now, let's get the data from the List of helicopter prison escapes Wikipedia article.
url = 'https://en.wikipedia.org/wiki/List_of_helicopter_prison_escapes'
data = data_from_url(url)
Let's print the first three rows
index = 0
for row in data:
data[index] = row[:-1]
index += 1
print(data[0:3])
[['August 19, 1971', 'Santa Martha Acatitla', 'Mexico', 'Yes', 'Joel David Kaplan Carlos Antonio Contreras Castro'], ['October 31, 1973', 'Mountjoy Jail', 'Ireland', 'Yes', "JB O'Hagan Seamus TwomeyKevin Mallon"], ['May 24, 1978', 'United States Penitentiary, Marion', 'United States', 'No', 'Garrett Brock TrapnellMartin Joseph McNallyJames Kenneth Johnson']]
for row in data:
row[0] = fetch_year(row[0])
print(data[5])
print(type(data[5][0]))
[1983, 'Pentridge (HM Prison)', 'Australia', 'No', 'David McMillan'] <class 'int'>
min_year = min(data, key=lambda x: x[0])[0]
max_year = max(data, key=lambda x: x[0])[0]
years = []
for y in range(min_year, max_year + 1):
years.append(y)
print(years)
[1971, 1972, 1973, 1974, 1975, 1976, 1977, 1978, 1979, 1980, 1981, 1982, 1983, 1984, 1985, 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020]
attempts_per_year = [[year, 0] for year in years]
print(attempts_per_year)
[[1971, 0], [1972, 0], [1973, 0], [1974, 0], [1975, 0], [1976, 0], [1977, 0], [1978, 0], [1979, 0], [1980, 0], [1981, 0], [1982, 0], [1983, 0], [1984, 0], [1985, 0], [1986, 0], [1987, 0], [1988, 0], [1989, 0], [1990, 0], [1991, 0], [1992, 0], [1993, 0], [1994, 0], [1995, 0], [1996, 0], [1997, 0], [1998, 0], [1999, 0], [2000, 0], [2001, 0], [2002, 0], [2003, 0], [2004, 0], [2005, 0], [2006, 0], [2007, 0], [2008, 0], [2009, 0], [2010, 0], [2011, 0], [2012, 0], [2013, 0], [2014, 0], [2015, 0], [2016, 0], [2017, 0], [2018, 0], [2019, 0], [2020, 0]]
# Instruction 1 - for each row in data
for row in data:
for ya in attempts_per_year: # Instruction 2 - nothing to do here
# Instruction 3 - assign the year value in ya to y
y = ya[0]
if row[0] == y:
ya[1] += 1
# Instruction 4 - print the results
print(attempts_per_year)
[[1971, 1], [1972, 0], [1973, 1], [1974, 0], [1975, 0], [1976, 0], [1977, 0], [1978, 1], [1979, 0], [1980, 0], [1981, 2], [1982, 0], [1983, 1], [1984, 0], [1985, 2], [1986, 3], [1987, 1], [1988, 1], [1989, 2], [1990, 1], [1991, 1], [1992, 2], [1993, 1], [1994, 0], [1995, 0], [1996, 1], [1997, 1], [1998, 0], [1999, 1], [2000, 2], [2001, 3], [2002, 2], [2003, 1], [2004, 0], [2005, 2], [2006, 1], [2007, 3], [2008, 0], [2009, 3], [2010, 1], [2011, 0], [2012, 1], [2013, 2], [2014, 1], [2015, 0], [2016, 1], [2017, 0], [2018, 1], [2019, 0], [2020, 1]]
%matplotlib inline
barplot(attempts_per_year)
countries_frequency = df["Country"].value_counts()
print(print_pretty_table(countries_frequency))
Country | Number of Occurrences |
---|---|
France | 15 |
United States | 8 |
Greece | 4 |
Belgium | 4 |
Canada | 4 |
Australia | 2 |
United Kingdom | 2 |
Brazil | 2 |
Mexico | 1 |
Italy | 1 |
Ireland | 1 |
Netherlands | 1 |
Chile | 1 |
Russia | 1 |
Puerto Rico | 1 |
None