# FILL IN WITH YOUR CODE















# Testing code

def to_unicode(vals):
    return [unicode(v) for v in vals]

def test_msas_df(msas_df):

    min_set_of_columns =  set(['Asian','Black','Hispanic', 'Other', 'Total', 'White',
     'entropy4', 'entropy5', 'entropy_rice', 'gini_simpson','p_Asian', 'p_Black',
     'p_Hispanic', 'p_Other','p_White'])  
    
    assert min_set_of_columns & set(msas_df.columns) == min_set_of_columns
    
    # https://www.census.gov/geo/maps-data/data/tallies/national_geo_tallies.html
    # 366 metro areas
    # 576 micropolitan areas
    
    assert len(msas_df) == 942  
    
    # total number of people in metro/micro areas
    
    assert msas_df.Total.sum() == 289261315
    assert msas_df['White'].sum() == 180912856
    assert msas_df['Other'].sum() == 8540181
    
    # list of msas in descendng order by entropy_rice 
    # calculate the top 10 metros by population
    top_10_metros = msas_df.sort_index(by='Total', ascending=False)[:10]
    
    msa_codes_in_top_10_pop_sorted_by_entropy_rice = list(top_10_metros.sort_index(by='entropy_rice', 
                                                ascending=False).index) 
    
    assert to_unicode(msa_codes_in_top_10_pop_sorted_by_entropy_rice)== [u'26420', u'35620', u'47900', u'31100', u'19100', 
        u'33100', u'16980', u'12060', u'37980', u'14460']


    top_10_metro = msas_df.sort_index(by='Total', ascending=False)[:10]
    
    list(top_10_metro.sort_index(by='entropy_rice', ascending=False)['entropy5'])
    
    np.testing.assert_allclose(top_10_metro.sort_index(by='entropy_rice', ascending=False)['entropy5'], 
    [0.79628076626851163, 0.80528601550164602, 0.80809418318973791, 0.7980698349711991,
     0.75945930510650161, 0.74913610558765376, 0.73683277781032397, 0.72964862063970914,
     0.64082509648457675, 0.55697288400004963])
    
    np.testing.assert_allclose(top_10_metro.sort_index(by='entropy_rice', ascending=False)['entropy_rice'],
    [0.87361766576115552,
     0.87272877244078051,
     0.85931803868749834,
     0.85508015237749468,
     0.82169723530719896,
     0.81953527301129059,
     0.80589423784325431,
     0.78602596561378812,
     0.68611350427640316,
     0.56978827050565117])


# you are on the right track if test_msas_df doesn't complain
test_msas_df(msas_df)

# code to save your dataframe to a CSV
# upload the CSV to bCourses
# uncomment to run
# msas_df.to_csv("msas_2010.csv", encoding="UTF-8")

# load back the CSV and test again
# df = DataFrame.from_csv("msas_2010.csv", encoding="UTF-8")
# test_msas_df(df)