%load_ext retina
%pylab inline

from IPython.display import display
import pandas
pandas.set_option('display.notebook_repr_html', True)
pandas.set_option('display.precision', 2)

def plot_percent(df, limit=10):
    df['Gun Percent'][:limit].plot()
    plt.ylim(0,100)
    plt.title("% Gun Homicide")
    plt.show()


def plot_percapita(df, limit=10):
    df = df.ix[:,['Homicides', 'Gun Homicides']][:limit]
    df['Total Homicides'] = df['Homicides'] - df['Gun Homicides']
    del df['Homicides']
    df.plot(kind='bar', stacked=True, sort_columns=True)
    plt.ylabel("per 100k")
    plt.show()


def display_relevant(df, limit=10):
    display(df.ix[:,['Homicides', 'Gun Homicides', 'Gun Data Source']][:limit])

totals = pandas.read_csv('totals.csv', '\t', index_col=0)
guns = pandas.read_csv('guns.csv', '\t', index_col=0)
gdp = pandas.read_csv('gdp.csv', '\t', index_col=1)
data = totals.join(guns).join(gdp)
data['Gun Percent'] = 100 * data['Gun Homicides'] / data['Homicides']
del data['Unintentional'],data['Undetermined'],data['Gun Suicides']
data = data.dropna()

data = data.sort("Gun Homicides", ascending=False)
display_relevant(data, 15)

top = data.sort('GDP')[-30:]

top_by_guns = top.sort("Gun Homicides", ascending=False)
display_relevant(top_by_guns, 5)
plot_percapita(top_by_guns, 10)

index = (data['Region'] == 'Europe') + \
        (data.index == 'United States') + \
        (data.index == 'Canada') + \
        (data.index == 'Mexico')
selected = data[index]

print "By Total Gun Homicides"
sys.stdout.flush()

by_guns = selected.sort("Gun Homicides", ascending=False)
#by_guns['Gun Homicides'].plot(kind='bar')
plot_percapita(by_guns, limit=25)
display_relevant(selected, limit=None)


select = data.ix[['United States', 'Canada', 'United Kingdom']]
plot_percapita(select)

select['Homicides'] = select['Homicides']['United States'] / select['Homicides']
select['Gun Homicides'] = select['Gun Homicides']['United States'] / select['Gun Homicides']
display_relevant(select)

for country in data.index:
    print country