Notes

def get_medals_gb_year_country():
""" Group by edition and country and sum medals count.
"""
medals_groupedBy_yearCountry = olympics.groupby(['Edition','Code']).apply(lambda country: country['Code'].count())
return medals_groupedBy_yearCountry

def get_medals_gb_year_country_medal():
""" Group by edition, country, medal type and sum medals count.
"""
medals_groupedBy_yearCountryMedal = olympics.groupby(['Edition', 'Code', 'Medal']).apply(lambda country: country['Medal'].count())
return medals_groupedBy_yearCountryMedal

def get_medals_last_10_years(countrycode):
""" Get Gold, Silver and Bronze medals for a country for last 10 editions.
"""
last10pics = olympics['Edition'].unique()
yrs = pd.Series(last10pics).nlargest(10)
df = pd.DataFrame([], columns=['Year', 'Gold', 'Silver', 'Bronze'])
medalsdf = get_medals_gb_year_country_medal()

for yr in yrs:
medaltally = medalsdf[yr][countrycode]
gold = 0
silver = 0
bronze = 0
if 'Gold' in medaltally:
gold = medaltally['Gold']
if 'Silver' in medaltally:
silver = medaltally['Silver']
if 'Bronze' in medaltally:
bronze = medaltally['Bronze']
df1 = pd.DataFrame([[yr,gold, silver, bronze]], columns=['Year', 'Gold', 'Silver', 'Bronze'])
df = df.append(df1, ignore_index=True)
df = df.sort_values(by=['Year'], ascending=True)
df = df.reset_index()
del df['index']

return df

def get_correlation_medalstally():
""" Get correlation between the medals tally and population, GDP per capita.
"""
df = get_medals_gb_year_country()
values = get_all_olympic_years().values
size = values.size
correlations = []
for i in range(size):
year = values[i][0]
df1 = df[year].to_frame(name="Tally")
df1 = df1.reset_index()
df2 = pd.merge(df1,dictionary, on='Code')
corrpop = df2.corr().values[0][1]
corrgdp = df2.corr().values[0][2]
resp = {"Year": year, "Population":corrpop, "GDP":corrgdp}
correlations.append(resp)
return correlations

def get_medals_category(countrycode, year):
""" Get the medals count in different sports category for a country in an edition.
"""
df = olympics[olympics['Edition'] == year]
df1 = df[df['Code'] == countrycode]
df2 = df1.groupby(['Sport']).apply(lambda country: country['Medal'].count())
return df2

def get_medals_category_all(countrycode):
""" Get the medals count in different sports category for a country for last ten editions.
"""
df1 = olympics[olympics['Code'] == countrycode]
df2 = df1.groupby(['Sport']).apply(lambda country: country['Medal'].count())
return df2

def get_top_ten_gold_tally(year):
""" Get the top ten gold medal winning countries in an edition.
"""
df = olympics[olympics['Edition'] == year]
df1 = df[df['Medal'] == 'Gold']
df2 = df1.groupby(['Code']).apply(lambda country: country['Medal'].count())
return df2

def get_top_ten_total_tally(year):
""" Get the top ten total medal winning countries in an edition.
"""
df = olympics[olympics['Edition'] == year]
df1 = df.groupby(['Code']).apply(lambda country: country['Medal'].count())
return df1

def get_year_venue():
""" Get edition venue matrix.
"""
df = olympics[['Edition', 'City']]
df = df.drop_duplicates()
df = df.reset_index()
df = df.set_index('Edition')
del df['index']
return df.sort_index()

def get_all_olympic_years():
""" Get list of all olympic editions.
"""
df = olympics['Edition']
df = df.drop_duplicates()
df = df.reset_index()
del df['index']
return df.sort_index()

def get_all_countries():
""" Get list of all countries.
"""
df = olympics[['Code','Country']]
df = df.drop_duplicates()
df = df.reset_index()
del df['index']
return df.sort(['Country'],ascending=[True])

def get_country_edition_data(countrycode,edition):
""" Get data for a country and edition.
"""
df = olympics[olympics["Code"] == countrycode]
df1 = df[df["Edition"] == edition]
return df1