def test_country_alpha3_to_country_alpha2(self):
cn_a2_code = country_alpha3_to_country_alpha2('USA')
assert (cn_a2_code)
assert (cn_a2_code == 'US')
cn_a2_code = country_alpha3_to_country_alpha2('RUS')
assert (cn_a2_code)
assert (cn_a2_code == 'RU')
def gather(self, data_name):
"""Importing and cleaning OECD.
returns istat as pandas.dataframe"""
# Import, Rename, adjust values in million
oecd = pd.read_csv(f'data/OECD_{data_name}.csv')
oecd.rename(columns={
'LOCATION': 'Country',
'TIME': 'Year',
'Value': data_name
},
inplace=True)
oecd['Country'] = oecd['Country'].apply(lambda x: x.split(' ')[
0] if re.match(r'[France|Germany].*', x) else x)
oecd[data_name] = oecd[data_name].apply(
lambda value: float(value * 1000000))
# Kick out every country with the wrong code len (they're not in europe anyways) & not in europe
oecd = oecd[oecd['Country'].apply(lambda x: len(x) == 3)]
oecd = oecd[oecd['Country'].apply(
lambda x: pc.country_alpha2_to_continent_code(
country_2_code=pc.country_alpha3_to_country_alpha2(x
)) == 'EU')]
# Turn country codes to full country names
oecd['Country'] = oecd['Country'].apply(
lambda x: pc.map_country_alpha3_to_country_name()[x])
oecd.set_index(['Country', 'Year'], inplace=True)
oecd.sort_index(inplace=True)
oecd = pd.DataFrame(oecd[data_name])
self.data.append(oecd)
def alpha3_to_continent(iso_alpha3):
return {
'EU': 'Europa',
'NA': 'North America',
'SA': 'South America',
'AS': 'Asia',
'OC': 'Oceania',
'AF': 'Africa',
}[country_alpha2_to_continent_code(
country_alpha3_to_country_alpha2(iso_alpha3))]
def main():
cn_name_format = COUNTRY_NAME_FORMAT_UPPER
for key, value in sorted(map_countries(cn_name_format).items()):
pprint({key: value})
try:
cn_continent = country_alpha2_to_continent_code('AA')
pprint(cn_continent)
except KeyError as kerr:
print("Key error: {0}".format(kerr))
except:
print("Unexpected error:", sys.exc_info()[0])
try:
cn_continent = country_alpha2_to_continent_code(None)
pprint(cn_continent)
except KeyError as kerr:
print("Key error: {0}".format(kerr))
except:
print("Unexpected error:", sys.exc_info()[0])
cn_continent = country_alpha2_to_continent_code('US')
pprint(cn_continent)
cn_continent = country_alpha2_to_continent_code('AU')
pprint(cn_continent)
cn_continent = country_alpha2_to_continent_code('NZ')
pprint(cn_continent)
cn_continent = country_alpha2_to_continent_code('JP')
pprint(cn_continent)
cn_name = country_alpha2_to_country_name('JP', cn_name_format)
pprint(cn_name)
cn_a2_code = country_name_to_country_alpha2('USA', cn_name_format)
pprint(cn_a2_code)
cn_a2_code = country_name_to_country_alpha2('United States',
cn_name_format)
pprint(cn_a2_code)
cn_a2_code = country_name_to_country_alpha2('South Korea', cn_name_format)
pprint(cn_a2_code)
cn_name = country_alpha2_to_country_name(cn_a2_code, cn_name_format)
pprint(cn_name)
cn_name = country_alpha2_to_country_name('RU', cn_name_format)
pprint(cn_name)
cn_a2_code = country_name_to_country_alpha2(cn_name, cn_name_format)
pprint(cn_a2_code)
cn_a2_code = country_alpha3_to_country_alpha2('RUS')
pprint(cn_a2_code)
cn_name = country_alpha2_to_country_name('GB', cn_name_format)
pprint(cn_name)
cn_name = country_alpha2_to_country_name('US', cn_name_format)
pprint(cn_name)
def createCitiesPickleFile():
worldCitiesfile = pd.read_excel('../Docs/worldcities.xlsx',
encoding='utf-8')
worldCitiesDict = {}
worldIso2Dict = {}
worldIso3Dict = {}
worldCountriesDict = {}
index = 0
cpt = 0
continents = {
'NA': 'North America',
'SA': 'South America',
'AS': 'Asia',
'OC': 'Australia',
'AF': 'Africa',
'EU': 'Europe'
}
unsupportedCountries = []
for city in worldCitiesfile['city']:
try:
iso2CountryCode = pycountry_convert.country_alpha3_to_country_alpha2(
worldCitiesfile['iso3'][index])
continentCode = pycountry_convert.country_alpha2_to_continent_code(
iso2CountryCode)
country = worldCitiesfile['country'][index].lower()
worldCountriesDict[country] = continents[continentCode]
worldCitiesDict[city.lower()] = country
worldIso2Dict[country] = iso2CountryCode
worldIso3Dict[country] = worldCitiesfile['iso3'][index]
worldIso2Dict[iso2CountryCode.lower(
)] = country # a problem when i try to transform the iso2 code to lower case
worldIso3Dict[worldCitiesfile['iso3'][index].lower()] = country
except:
unsupportedCountries.append(worldCitiesfile['iso3'][index].lower())
cpt += 1
pass
index += 1
print(cpt)
unsupportedCountries = set(unsupportedCountries)
print("number of unsupported countries", unsupportedCountries)
print("number of countries", worldCountriesDict.__len__())
print("number of iso2", worldIso2Dict.__len__())
print("number of iso3", worldIso3Dict.__len__())
print("number of cities", worldCitiesDict.__len__())
import pickle
with open('../Docs/locations.pickle', 'wb') as file:
pickle.dump(worldCitiesDict, file)
pickle.dump(worldIso2Dict, file)
pickle.dump(worldIso3Dict, file)
pickle.dump(worldCountriesDict, file)
print("succes !")
def country_code(country_code):
if not country_code:
return ""
country = country_code # If it's no 3 letter country code it is just passed
if len(country_code) == 3:
print("3")
country = country_alpha3_to_country_alpha2(
country_alpha2_to_country_name(country_code))
elif len(country_code) == 2: # In case it is just a 2 letter code.
print("2")
country = country_alpha2_to_country_name(country_code)
return country
def update_map(picked_country, map_figure):
if picked_country:
# highlight flows from that country only
country_name = country_df.iloc[picked_country]['country']
filtered_country_flow = flow_df[flow_df['country_from'] == country_name]
map_trace = make_edge_trace(filtered_country_flow)
map_trace.append(make_point_trace(country_df))
map_figure['data'] = map_trace
# highlight country and destinations
country_to = filtered_country_flow['country_to'].tolist()
index_list = country_df[country_df['country'].isin(country_to)].index.tolist()
index_list.append(picked_country)
map_figure['data'][-1]['selectedpoints'] = index_list
# rotate map to center
country_code_iso2 = pc.country_alpha3_to_country_alpha2(country_name)
lat = centroid_df.loc[centroid_df['country']==country_code_iso2, 'latitude'].iloc[0]
lon = centroid_df.loc[centroid_df['country']==country_code_iso2, 'longitude'].iloc[0]
map_figure['layout']['geo']['projection']['rotation']['lat'] = lat
map_figure['layout']['geo']['projection']['rotation']['lon'] = lon
return map_figure
def update_info(picked_country):
if not picked_country:
return [dash_dangerously_set_inner_html.DangerouslySetInnerHTML("""<center><strong ><font color="white" font-family="Source Sans Pro" size=2 font-weight='bold'>
Currently showing countries with more than 10 connections <br>
Pick a country on the map or on the bar for to show all connections of that country.
</font></strong></center>""")]
else:
country = country_df.iloc[picked_country]['country']
filtered_country_flow = flow_df[flow_df['country_from'] == country]
n_country_to = len(filtered_country_flow)
country_code_iso2 = pc.country_alpha3_to_country_alpha2(country)
country_name = pc.country_alpha2_to_country_name(country_code_iso2)
user_count = country_df.iloc[picked_country]['user_count']
line_1 = f"""{country_name} has {user_count} active user(s)."""
html_raw_1 = f'''<center><strong ><font color="white" font-family="Source Sans Pro" size=2 font-weight="bold">{line_1}</font></strong></center>'''
line_2 = f"""{country_name} has connections with {n_country_to} other countries"""
html_raw_2 = f'''<center><strong ><font color="white" font-family="Source Sans Pro" size=2 font-weight="bold">{line_2}</font></strong></center>'''
line_3 = """To clear selections, refresh the webpage. """
html_raw_3 = f'''<center><strong ><font color="gray" font-family="Source Sans Pro" size=1 font-weight="100">{line_3}</font></strong></center>'''
# todo: make it pretty if time allows...
return [dash_dangerously_set_inner_html.DangerouslySetInnerHTML(html_raw_1),
dash_dangerously_set_inner_html.DangerouslySetInnerHTML(html_raw_2),
dash_dangerously_set_inner_html.DangerouslySetInnerHTML(html_raw_3)]
def get_continent(country_code):
'''
:param country_code: ISO 3166-1 alpha-3 country code of a country
:return: the name of the continent to which the country belongs, 'Unknown' if the country code is not valid
'''
continent_names = {
'NA': 'North America',
'SA': 'South America',
'AS': 'Asia',
'OC': 'Oceania',
'AF': 'Africa',
'AN': 'Antarctica',
'EU': 'Europe'
}
try:
continent_code = pc.country_alpha2_to_continent_code(
pc.country_alpha3_to_country_alpha2(country_code))
continent = continent_names[continent_code]
except:
continent = 'Unknown'
return continent
"URU": "URY",
"VAN": "VUT",
"VIE": "VNM",
"ZAM": "ZMB",
"ZIM": "ZWE",
}
countrynames = []
continentcodes = []
with open(sys.argv[1]) as f:
for line in f:
line = line.strip()
if line == "UNK":
countrynames.append("Kosovo")
continentcodes.append(continent_dico["EU"])
else:
try:
countrynames.append(country_alpha2_to_country_name(
country_alpha3_to_country_alpha2(line)))
except:
line = alpha3_ico[line]
countrynames.append(country_alpha2_to_country_name(
country_alpha3_to_country_alpha2(line)))
continentcodes.append(continent_dico[country_alpha2_to_continent_code(
country_alpha3_to_country_alpha2(line))])
np.savetxt("continents.csv", continentcodes, delimiter=',', fmt="%s")
np.savetxt("countrynames.csv", countrynames, delimiter=',', fmt="%s")
def medal_table(season, year):
if (int(year) > 2018):
return None
print(year)
print(getcwd())
url = "https://www.topendsports.com/events/" + season.lower(
) + "/medal-tally/" + str(year) + ".htm"
filename = "responses/medal_tables/" + str(year) + "-" + season + ".html"
if (not path.exists(filename)):
get_response(url, filename)
with open(filename, 'rb') as f:
soup = BeautifulSoup(f.read(), 'html.parser')
medals = soup.find('table', class_='list')
medals['id'] = 'medalTable'
for thtag in medals.find_all('th'):
thtag['class'] = 'th-sm'
rank = medals.find('th')
if rank.text != "Ranking":
rank.string = "Ranking"
new_tag = soup.new_tag('thead')
trow = medals.find('tr')
trow.wrap(new_tag)
for tr in medals.find_all('tr'):
tr['class'] = 'inBody'
tr_one = medals.find('tr')
del tr_one['class']
for trtag in medals.find_all('tr'):
index = 0
for tdtag in trtag.find_all('td'):
if index == 0:
if "=" in tdtag.text:
tdtag.string = tdtag.text[1:]
if index == 1:
tdtag['class'] = 'sorting_1'
if tdtag.text == 'Great Britain':
tdtag.string = 'United Kingdom'
if len(tdtag.text) == 3:
if tdtag.text == "CRO":
tdtag.string = "HRV"
elif tdtag.text == "SUI":
tdtag.string = "CHE"
elif tdtag.text == "IRI":
tdtag.string = "IRN"
elif tdtag.text == "GRE":
tdtag.string = "GRC"
elif tdtag.text == "DEN":
tdtag.string = "DNK"
elif tdtag.text == "RSA":
tdtag.string = "ZAF"
elif tdtag.text == "SLO":
tdtag.string = "SVN"
elif tdtag.text == "INA":
tdtag.string = "IDN"
elif tdtag.text == "VIE":
tdtag.string = "Vietnam"
elif tdtag.text == "TPE":
tdtag.string = "TWN"
elif tdtag.text == "BAH":
tdtag.string = "BHS"
elif tdtag.text == "IOA":
tdtag.string = "Individual Olympic Athletes"
elif tdtag.text == "FIJ":
tdtag.string = "FJI"
elif tdtag.text == "KOS":
tdtag.string = "Kosovo"
elif tdtag.text == "PUR":
tdtag.string = "PRI"
elif tdtag.text == "SIN":
tdtag.string = "SGP"
elif tdtag.text == "MAS":
tdtag.string = "MYS"
elif tdtag.text == "ALG":
tdtag.string = "DZA"
elif tdtag.text == "BUL":
tdtag.string = "BGR"
elif tdtag.text == "MGL":
tdtag.string = "MNG"
elif tdtag.text == "GRN":
tdtag.string = "GRD"
elif tdtag.text == "NIG":
tdtag.string = "NER"
elif tdtag.text == "PHI":
tdtag.string = "PHL"
elif tdtag.text == "NGR":
tdtag.string = "NGA"
elif tdtag.text == "POR":
tdtag.string = "PRT"
elif tdtag.text == "UAE":
tdtag.string = "ARE"
if (tdtag.text != "Individual Olympic Athletes") & (
tdtag.text != "Kosovo") & (tdtag.text !=
"Vietnam"):
two = concon.country_alpha3_to_country_alpha2(
tdtag.text)
tdtag.string = concon.country_alpha2_to_country_name(
two)
index = index + 1
print(medals.find_all('td', class_="sorting_1"))
for countrytag in medals.find_all('td', class_="sorting_1"):
c_link = soup.new_tag("a", href='/countries/' + countrytag.text)
c_link["class"] = "btn-link"
if len(countrytag.text) > 0:
countrytag.string.wrap(c_link)
# print(medals)
print(type(medals))
print(type(str(medals)))
medals = str(medals).replace("list", "table")
return medals
def continent_from_iso_country_code(alpha3_country_code):
alpha2_country_code = pc.country_alpha3_to_country_alpha2(alpha3_country_code)
continent_code = pc.country_alpha2_to_continent_code(alpha2_country_code)
return pc.convert_continent_code_to_continent_name(continent_code)
