#!/usr/bin/env python # coding: utf-8 # # My First Data Science Project # ## Helicopter Escapes! # We begin by importing some helper functions. # In[12]: from helper import * # ## Get the Data # Now, let's get the data from the [List of helicopter prison escapes](https://en.wikipedia.org/wiki/List_of_helicopter_prison_escapes) Wikipedia article. # In[13]: url = 'https://en.wikipedia.org/wiki/List_of_helicopter_prison_escapes' # In[14]: # Create variable data and assign it result of the url data = data_from_url(url) # Let's print the first three rows # In[19]: for row in data[:3]: print(row) # ### Removing the Details # In[20]: index = 0 for row in data: data[index] = row[:-1] index += 1 print(data[:3]) # ### Extracting the Year # In[21]: for row in data: row[0] = fetch_year(row[0]) print(data[:3]) # ### Attempts Per Year I # In[22]: 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) attempts_per_year = [] for year in years: attempts_per_year.append([year, 0]) print(attempts_per_year) # ### Attempts Per Year II # In[23]: for row in data: for ya in attempts_per_year: y = ya[0] if row[0] == y: ya[1] += 1 print(attempts_per_year) # ### Attempts Per Year III # in which year did the most attempts at breaking out of prison with a helicopter occur? # In[24]: get_ipython().run_line_magic('matplotlib', 'inline') barplot(attempts_per_year) # ### Attempts by Country # In[26]: countries_frequency = df["Country"].value_counts() print_pretty_table(countries_frequency)