#!/usr/bin/env python
# coding: utf-8

# # My First Data Science Project

# ## Helicopter Escapes

# We begin by importing some helper functions.

# In[4]:


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[5]:


url = 'https://en.wikipedia.org/wiki/List_of_helicopter_prison_escapes'
data = data_from_url(url)


# Let's print the first three rows

# In[6]:


for item in data[0:3]:
    print(item)


# Next, let's remove the column with the long text that provides the background information on the prison breaks.

# In[7]:


index = 0

for row in data:
    data[index] = row[:-1]
    index += 1
    
print(data[0:3])


# Using a provided function, change the date so that we have only the year:

# In[8]:


for row in data:
    row[0] = fetch_year(row[0])
    
print(data[0:3])


# Next, we are going to create a table that contains the year and a holder position for the number of attempts in that year.

# In[9]:


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)


# Next, we will populate the attempts per year element of the list.

# In[10]:


# 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)


# Using provided code, create a bar graph showing the number of attempts per year to better visualize the data.

# In[11]:


get_ipython().run_line_magic('matplotlib', 'inline')
barplot(attempts_per_year)


# 

# The most attempts at prison breakouts with a helicopter were 1986, 2001, 2007, and 2009.
# 
# Next, we will create a frequency table showing the number of prison break attempts by helicopter by country.

# In[12]:


countries_frequency = df["Country"].value_counts()


# In[13]:


print_pretty_table(countries_frequency)


# Next, let's try to answer the question:
# In which countries do helicopter prison breaks have a higher chance of success?

# In[14]:


# First, get a list of the countries
countries = []
for row in data:
    country = row[2]
    if country not in countries:
        countries.append(country)
        
print(countries)


# In[15]:


# Next, add empty fields for number of attempts and number 
# of successes

countries_success = []
for row in countries:
    countries_success.append([row,0,0])
    
print(countries_success)


# In[16]:


# Next, populate number of attempts and number of successes

for row in data:
    for item in countries_success: 
        country = (item[0])
        if row[2] == country:
            country_count = item[1]
            country_count += 1
            item[1] = country_count
            if row[3] == "Yes":
                count_success = item[2]
                count_success += 1
                item[2] = count_success



print(countries_success)


# From looking at the list of lists above, we can see that some countries have a 100% success rate, but these countries also have a low number of attempts.  Without the ability to make graphs, a statement for each country might be the most effective way to communicate the results: 

# In[20]:


for country in countries_success:
    print("In " + country[0] + ", there were " + str(country[1]) + 
          " attempts.  Of these, there was " + str(country[2]) + 
          " success(es).  The success rate is " + str((country[2]/country[1]) *100)+"%\n")


# In[ ]: