def stealingEnergy(countryname):
data_dateUSC = (datetime.datetime(1971, 1, 1), datetime.datetime(2011, 1, 1))
# Data on Electricity production from renewable sources (kWh) for US
if countryname == "USA":
renewableProdUS.extend(wbdata.get_data("EG.ELC.RNEW.KH", data_date=data_dateUSC, country="USA", pandas = True))
electricityProdUS.extend(wbdata.get_data("EG.ELC.PROD.KH", data_date=data_dateUSC, country="USA", pandas = True))
else:
# Data on Electricity production from renewable sources (kWh) for CHN
renewableProdCHN.extend(wbdata.get_data("EG.ELC.RNEW.KH", data_date=data_dateUSC, country="CHN", pandas = True))
electricityProdCHN.extend(wbdata.get_data("EG.ELC.PROD.KH", data_date=data_dateUSC, country="CHN", pandas = True))
def load_indicator(con, indicator, db_column_name):
cur = con.cursor()
# add column if not exists
try:
cur.execute('''alter table country_annual_indicators
add column {} real'''.format(db_column_name))
con.commit()
except sqlite3.OperationalError:
pass
# try to update, otherwise insert
indicator_value_items = wbdata.get_data(indicator)
for item in indicator_value_items:
cur.execute('''update country_annual_indicators
set {}=?
where iso_code=? and year=?'''.format(db_column_name),
(item['value'],
item['country']['id'].lower(),
item['date']))
# If no update happened (i.e. the row didn't exist) then insert one
cur.execute('''INSERT INTO country_annual_indicators ('iso_code', 'year', {})
SELECT ?, ?, ?
WHERE (Select Changes() = 0)'''.format(db_column_name),
(item['country']['id'].lower(),
item['date'],
item['value']))
con.commit()
def test_quarterly_freq(self):
got = wbd.get_data(
"DP.DOD.DECD.CR.BC.CD",
country="chl",
data_date=dt.datetime(2013, 1, 1),
freq="Q",
)[0]["value"]
assert got == 31049138725.7794
def getWb(year):
data_date = datetime.datetime(year, 1, 1)
x = wbdata.get_data("NY.GDP.PCAP.CD", data_date=data_date, pandas=True)
y = wbdata.get_data("1.1_TOTAL.FINAL.ENERGY.CONSUM",
data_date=data_date,
pandas=True)
z = wbdata.get_data("SP.POP.TOTL", data_date=data_date, pandas=True)
data = pd.concat([x, y, z], axis=1)
data.columns = ["GDP", "Energy_Consumption", "Population"]
data = data.dropna(axis=0, how="any")
df = pd.DataFrame(data)
df.to_csv("out.csv")
x = np.transpose(np.array([data["GDP"].tolist()]))
y = np.transpose(np.array([data["Energy_Consumption"].tolist()]))
z = np.transpose(np.array([data["Population"].tolist()]))
return (x, y, z)
def get_countryList(ind, ctry, year):
raw_data = []
data_date = (datetime.datetime(year, 1, 1), datetime.datetime(year, 1, 1))
raw_data = wbdata.get_data(ind, country=ctry, data_date=data_date)
data = []
for country in raw_data:
data.append(country['country']['value'])
return data
def get_countryList(ind, ctry, year):
raw_data = []
data_date = (datetime.datetime(year, 1, 1), datetime.datetime(year, 1, 1))
raw_data = wbdata.get_data(ind, country = ctry, data_date=data_date)
data = []
for country in raw_data:
data.append(country['country']['value'])
return data
def form_to_data(myform):
country = myform.cleaned_data['my_country']
indicator = myform.cleaned_data['my_indicator']
fromyr = int(myform.cleaned_data['from_'])
toyr = myform.cleaned_data['to_']
try:
if toyr:
toyr = int(toyr)
data = wbdata.get_data(indicator, [country],
data_date=(datetime(fromyr, 1, 1),
datetime(toyr, 1, 1)))
else:
data = wbdata.get_data(indicator, [country],
data_date=datetime(fromyr, 1, 1))
return data
except IndexError('No data'):
return render(request, 'request_stats.html', {'form': myform})
def carbon():
if request.method == "POST":
country_code = request.form.get("ccheck")
emission_per_capita = w.get_data("EN.ATM.CO2E.EG.ZS",
country=country_code.upper())
for i in emission_per_capita:
if i['value'] != None:
value = i['value']
value = str(value)
return "Your Country's Carbon Dioxide Density(kg per kg of oil equivalent use): " + value
return render_template("form.html")
def get_gdp(self):
gdp_list = []
for country_code in self.loan_data.country_code.unique():
if isinstance(country_code, str):
gdp_list.append([
country_code,
pd.to_numeric(
wbdata.get_data("NY.GDP.PCAP.CD",
country=(country_code))[1]['value'])
])
return pd.DataFrame(gdp_list, columns=['country_code', 'gdp'])
def wb_query(indicator,
countries='all',
start_year=config.START_YEAR,
end_year=config.END_YEAR,
iso3=True):
"""
Retrieve data for a world bank indicator,
For all world bank indicators, see:
https://data.worldbank.org/indicator
Credit to wbdata for a wrapper around API requests: https://wbdata.readthedocs.io/en/latest/
Input
-----
indicator (str) - the world bank indicator as a string, i.e. '4.1_SHARE.RE.IN.ELECTRICITY' is share of RE in a countries generation mix.
countries (list) - Default 'all' will pull all countries, if specifying a single country or a list of countries, double check spelling w/ world bank
start_year (int) - First year to pull data from, most world bank indicators are reported on an annual basis.
end_year (int) - Last year to pull data from, most world bank indicators are reported on an annual basis.
Outputs
-------
Pandas DataFrame - Long, with columns for 'country','date', and 'value'
"""
# --- Define daterange as tuple ---
daterange = (datetime.datetime(start_year, 1,
1), datetime.datetime(end_year, 12, 31))
# --- Make api requests ---
wb_query = wb.get_data(indicator, data_date=daterange, country=countries)
# --- Package results as a df ---
country_list = [d['country']['value'] for d in wb_query]
year_list = [d['date'] for d in wb_query]
value_list = [d['value'] for d in wb_query]
df = pd.DataFrame({
'country': country_list,
'year': year_list,
'value': value_list
})
df['indicator'] = indicator
df['value'] = df['value'].astype(float)
df['year'] = df['year'].astype(int)
if iso3:
df['iso'] = df['country'].apply(helper_functions.country_name_to_iso3)
return df
def getWBDataFromWeb(self, pStockCode, pStart, pEnd):
#https://wbdata.readthedocs.io/en/latest/
wbdata.get_source()
wbdata.get_indicator(source=1)
wbdata.search_countries("united")
date = (datetime.datetime(2010, 1, 1), datetime.datetime(2011, 1, 1))
self.data = wbdata.get_data("IC.BUS.EASE.XQ",
country=("USA", "GBR"),
data_date=date)
for row in self.data:
print(row['country']['id'], row)
#indicators = {"IC.BUS.EASE.XQ": "doing_business", "NY.GDP.PCAP.PP.KD": "gdppc"}
#df = wbdata.get_dataframe(indicators, country=countries, convert_date=True)
#df.describe()
return self.data
def get_dataset_wb(indicator_id):
""" downloads the given dataset and creates a dataframe
Args:
indicator_id: World Bank indicator_id for which to retrieve the dataset
Returns:
A pandas DataFrame of the dataset
"""
if indicator_id in known_datasets_from_wb:
return known_datasets_from_wb[indicator_id]
else:
dat = wbdata.get_data(indicator=indicator_id,
convert_date=True,
pandas=True)
dat = dat.unstack(level=0) # delete MultiIndex
known_datasets_from_wb.update({indicator_id: dat})
return dat
def test_year(ind, ctry, year):
import wbdata
data = []
#### limit time frame to one year as the study only need one year data
data_date = (datetime.datetime(year, 1, 1), datetime.datetime(year, 1, 1))
data = wbdata.get_data(ind, ctry, data_date)
for c in data:
if c['value'] == None:
print 'Country:', c['country']['value']
print 'Data:', c['indicator']['value']
print 'Year:', c['date']
print 'Staus:', 'NOT available'
else:
print 'Country:', c['country']['value']
print 'Data:', c['indicator']['value']
print 'Year:', c['date']
print 'Staus:', 'Available'
def test_year(ind, ctry, year):
import wbdata
data = []
#### limit time frame to one year as the study only need one year data
data_date = (datetime.datetime(year, 1, 1), datetime.datetime(year, 1, 1))
data = wbdata.get_data(ind, ctry, data_date)
for c in data:
if c['value'] == None:
print 'Country:', c['country']['value']
print 'Data:', c['indicator']['value']
print 'Year:', c['date']
print 'Staus:', 'NOT available'
else:
print 'Country:', c['country']['value']
print 'Data:', c['indicator']['value']
print 'Year:', c['date']
print 'Staus:', 'Available'
def get_ind_preview(y1=2010, ind="FR.INR.LEND"):
if ind:
if y1:
ydt = datetime(int(y1), 1, 1)
ind_details = wbdata.get_indicator(ind, display=False)[0]
ind_details['dev'] = "Feel free to use this variable!"
try:
data = rpy2functions.get_values(wbdata.get_data(ind, data_date=(ydt, ydt), country=preview_countries))
if 'q' in data.keys()[0].split('.')[0].lower():
ind_details['dev'] = "If chosen, please make sure all variables are quarterly."
if sum(map(map_adder, data.values())) < 5: #wont add properly.
ind_details['dev'] = "Very scarce data. Avoid using this variable."
except TypeError as e:
data = {'{0}.{1}'.format(str(y1), cont):'ERROR' for cont in preview_countries}
ind_details['dev'] = "No data found for this variable. Do not use this variable."
return jsonify({'data': data, 'details': ind_details})
return {}
def update_population_data(population_df):
years = (datetime.datetime(2015, 1, 1), (datetime.datetime.now()))
new_pop = wbdata.get_data(indicator='SP.POP.TOTL',
data_date=years,
pandas=True).to_frame()
formatted_population = reformat_dataframe(new_pop)
added_years = list(formatted_population)
population_df = population_df.sort_values(by=['Country Name'])
formatted_population = formatted_population.sort_values(
by=['Country Name'])
population_df.update(formatted_population)
for year in added_years:
if year not in population_df.columns:
population_df = pd.concat(
[population_df, formatted_population[year]], axis=1, sort=True)
return population_df
def update_population_data(pop_df):
years = (datetime.datetime(2015, 1, 1), (datetime.datetime.now()))
new_pop = wbdata.get_data(indicator='SP.POP.TOTL',
data_date=years,
pandas=True).to_frame()
new_pop = new_pop['value'].to_frame().reset_index()
new_pop.rename(columns={'country': 'Country Name'}, inplace=True)
new_pop = new_pop.pivot(index='Country Name',
columns='date',
values='value')
new_pop = new_pop.apply(pd.to_numeric).fillna(value=0).reset_index()
added_years = list(new_pop)
pop_df = pop_df.sort_values(by=['Country Name'])
new_pop = new_pop.sort_values(by=['Country Name'])
pop_df.update(new_pop)
for year in added_years:
if year not in pop_df.columns:
pop_df = pd.concat([pop_df, new_pop[year]], axis=1, sort=True)
return pop_df
def get_data_spec(request):
country, data_date, source, convert_date = request.param
return GetDataSpec(
result=wbd.get_data(
"NY.GDP.MKTP.CD",
country=country,
data_date=data_date,
source=source,
convert_date=convert_date,
),
country=country,
data_date=data_date,
source=source,
convert_date=convert_date,
expected_country="Eritrea",
expected_date=dt.datetime(2010, 1, 1) if convert_date else "2010",
expected_value={
"2": 2117039512.19512,
"11": 2117008130.0813
}[source or "2"],
)
def update_co2_data(co2_df):
years = (datetime.datetime(2015, 1, 1), (datetime.datetime.now()))
new_co2 = wbdata.get_data(indicator='EN.ATM.CO2E.KT',
data_date=years,
pandas=True).to_frame()
formatted_co2 = reformat_dataframe(new_co2)
added_years = list(formatted_co2)
co2_df = co2_df.sort_values(by=['Country Name'])
formatted_co2 = formatted_co2.sort_values(by=['Country Name'])
co2_df.update(formatted_co2)
for year in added_years:
if year not in co2_df.columns:
co2_df = pd.concat([co2_df, formatted_co2[year]],
axis=1,
sort=True)
return co2_df
def get_latest_wb_indicator_by_country(name: str, indicator: str):
# Get raw data
date = (datetime.datetime(2016, 1, 1), datetime.datetime(2016, 1, 1)
) # hwo to automatically select latest date?
raw_data = wbdata.get_data(indicator=indicator, data_date=date)
# Get country and arrivals
countries = []
value = []
for x in raw_data:
countries.append(x['country']['value'])
arrivals = x['value']
if arrivals is None:
arrivals = np.nan
value.append(arrivals)
# Store as pandas data frame
data = {"country": countries, name: value}
df = pd.DataFrame(data)
return df
def run(self):
db.create_all()
# get list of all country codes
countries = wbdata.get_country()
for country in countries:
country_data = []
try:
country_data = wbdata.get_data("EG.FEC.RNEW.ZS",
country=country["id"])
# Throws a NoneType error if country doesn't exist in world bank db
except TypeError:
print(f"Could not get data for country {country['name']}")
for data_entry in country_data:
if data_entry["value"]:
db_entry = RenewableEnergyCountry(
country=data_entry["country"]["value"],
year=data_entry["date"],
renewable_energy_usage=data_entry["value"],
)
db.session.add(db_entry)
db.session.commit()
def update_co2_data(co2_df):
years = (datetime.datetime(2015, 1, 1), (datetime.datetime.now()))
new_co2 = wbdata.get_data(indicator='EN.ATM.CO2E.KT',
data_date=years,
pandas=True).to_frame()
new_co2 = new_co2['value'].to_frame().reset_index()
new_co2.rename(columns={'country': 'Country Name'}, inplace=True)
new_co2 = new_co2.pivot(index='Country Name',
columns='date',
values='value')
new_co2 = new_co2.apply(pd.to_numeric).fillna(value=0).reset_index()
added_years = list(new_co2)
co2_df = co2_df.sort_values(by=['Country Name'])
new_co2 = new_co2.sort_values(by=['Country Name'])
co2_df.update(new_co2)
for year in added_years:
if year not in co2_df.columns:
co2_df = pd.concat([co2_df, new_co2[year]], axis=1, sort=True)
return co2_df
def collect_data(self):
load_env()
if isfunction(self.provider):
if self.code:
self.data = self.provider(self.code)
else:
self.data = self.provider()
elif self.provider == 'fred':
fred = Fred(api_key=os.environ['TOKEN_FRED'])
self.data = fred.get_series(self.code,
observation_start=self.start_dt,
observation_end=self.end_dt)
elif self.provider == 'eod_hist':
url = 'https://eodhistoricaldata.com/api/eod/{0}'.format(self.code)
params = {'api_token': os.environ['TOKEN_EODHIST']}
expire_after = td(days=1).total_seconds()
session = requests_cache.CachedSession(cache_name='cache',
backend='sqlite',
expire_after=expire_after)
r = session.get(url, params=params)
if r.status_code != requests.codes.ok:
session = requests.Session()
r = session.get(url, params=params)
if r.status_code == requests.codes.ok:
df = pd.read_csv(StringIO(r.text),
skipfooter=1,
parse_dates=[0],
index_col=0,
engine='python')
self.data = df['Close']
else:
raise Exception(r.status_code, r.reason, url)
elif self.provider == 'schiller':
url = 'http://www.econ.yale.edu/~shiller/data/ie_data_with_TRCAPE.xls'
webpage = requests.get(url, stream=True)
self.data = pd.read_excel(io.BytesIO(webpage.content),
'Data',
header=7,
skipfooter=1)
self.data.index = self.data['Date'].apply(
lambda x: dt.strptime(str(x).format(x, '4.2f'), '%Y.%m'))
self.data = self.data[self.code]
print(self.data.tail(5))
elif self.provider == 'quandl':
self.data = quandl.get(self.code,
authtoken=os.environ['TOKEN_QUANDL'],
collapse="quarterly",
start_date=self.start_dt,
end_date=self.end_dt)['Value']
elif self.provider == 'bls':
self.data = bls.get_series(
[self.code],
startyear=dt.strptime(self.start_dt, '%Y-%m-%d').year,
endyear=dt.strptime(self.end_dt, '%Y-%m-%d').year,
key=os.environ['TOKEN_BLS'])
elif self.provider == 'worldbank':
self.data = wbdata.get_data(
self.code,
country='US',
data_date=(dt.strptime(self.start_dt, '%Y-%m-%d'),
dt.strptime(self.end_dt, '%Y-%m-%d')),
convert_date=True,
pandas=True,
keep_levels=False)
print(self.data.tail(5))
print("Collected data for [{0}]".format(self.code))
def get_data(from_date=datetime.datetime(2010, 1, 1), to_date=datetime.datetime.now(), variable="FR.INR.LEND"):
duration = (from_date, to_date)
variable = variable.upper()
mykey = '-'.join(map(str, [from_date.year, to_date.year, variable]))
return functions.get_values(wbdata.get_data(variable, data_date=duration))
# http://wbdata.readthedocs.org/en/latest/
# http://wbdata.readthedocs.org/en/latest/fetcher.html
import wbdata
import datetime
import pandas as pd
'''
This wbdata is an interactive console to work with World Bank's API.
You can run wbdata.get_source() to see all sources of information and the
respective numbers to run in the below code to fetch the data.
Also, using Pandas package may facilitate the task to convert the lists and dictionaries
retrieved from the API.
Total Population -> source=16
'''
#wbdata.get_source()
wbdata.get_indicator(source=16)
# Define time range to search for data
data_date = (datetime.datetime(1960, 1, 1), datetime.datetime(2014, 1, 1))
# Store the data as the variable df
df = pd.DataFrame(wbdata.get_data("SP.POP.TOTL", pandas = True, data_date=data_date))
# Write it to a CSV - Exemple in /data-pipeline
df.to_csv ("YOURPATH/population_total_1960-2014.csv", sep = ',')
import numpy as np
#print(wb.get_data("BM.KLT.DINV.CD.WD", "ARB", pandas=True))
file = pd.read_csv("ind.csv")
indicators = file["Indicator Code"]
unique_indicators = list(set(indicators))
unique_indicators.sort()
l = []
from_to = (dt.datetime(1970, 1, 1), dt.datetime(2019, 1, 1))
list_indicators = {}
c = 1
for i in unique_indicators[:10]:
print(c)
c += 1
result = wb.get_data(i, country_codes, pandas=True, data_date=from_to)
maxi = list()
counter = 0
temp_maxi = list()
for year in reversed(range(1970, 2020)):
temp = [
np.isnan(result[x]) for x in result.keys() if x[1] == str(year)
]
print(temp)
if True in temp:
if len(temp_maxi) > len(maxi):
maxi = temp_maxi[:]
temp_maxi = list()
continue
temp_maxi.append(year)
#print(temp_maxi)
def main():
'''
This wbdata package is an interactive console to work with World Bank's API.
You can run wbdata.get_source() to see all sources of information and the
respective numbers to run in the below code to fetch the data.
Also, using Pandas package may facilitate the task to convert the lists and dictionaries
retrieved from the API.
Total Population -> source=16
GDP -> source = 2, NY.GDP.MKTP.CN
GDP per capita (USD) -> source = 2, NY.GDP.PCAP.CD
GDP per capita (PPP) (USD) -> source = 2, NY.GDP.PCAP.PP.CD
GDP Growth Rate -> source = 2, NY.GDP.PCAP.KD.ZG
Unemployment Rate -> source = 2, SL.UEM.TOTL.ZS
Gini Coefficient -> source = 2, SI.POV.GINI
Monetary base (M0, M1, M2, M3) (USD) ->
M1:
M2: source = 2, FM.LBL.MQMY.CN
M3:
Total Reserves (USD) -> source = 2, FI.RES.TOTL.CD
Inflation Rate (USD) ->
FDI Inflow (USD) ->
Aid Inflow (USD) ->
'''
'''
__________________________________________________________________
The following parts are focused on retrieving data from the World Bank
'''
#-------------------- Code Exemplification -------------------------#
#wbdata.get_source()
#wbdata.get_indicator(source=16)
# Define time range to search for data
data_date = (datetime.datetime(1960, 1, 1), datetime.datetime(2014, 1, 1))
# Store the data as the variable df
population = pd.DataFrame(wbdata.get_data("SP.POP.TOTL", data_date=data_date, pandas = True))
gdp = pd.DataFrame(wbdata.get_data("NY.GDP.MKTP.CN", data_date=data_date, pandas = True))
gdp_per_capita = pd.DataFrame(wbdata.get_data("NY.GDP.PCAP.CD", data_date=data_date, pandas = True))
gdp_per_capita_ppp = pd.DataFrame(wbdata.get_data("NY.GDP.PCAP.PP.CD", data_date=data_date, pandas = True))
gdp_growth_rate = pd.DataFrame(wbdata.get_data("NY.GDP.PCAP.KD.ZG", data_date=data_date, pandas = True))
unemployment_rate = pd.DataFrame(wbdata.get_data("SL.UEM.TOTL.ZS", data_date=data_date, pandas = True))
#gini-coefficient ->
total_reserves = pd.DataFrame(wbdata.get_data("FI.RES.TOTL.CD", data_date=data_date, pandas = True))
# Write it to a CSV - Exemple in /data-pipeline
population.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/population/population_total_1960-2014.csv", sep = ',')
gdp.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/gdp.csv", sep = ",")
gdp_growth_rate.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/gdp-growth-rate.csv", sep = ",")
gdp_per_capita.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/gdp-percapita.csv", sep = ",")
gdp_per_capita_ppp.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/gdp-percapita-ppp.csv", sep = ",")
unemployment_rate.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/unemployment_rate.csv", sep =",")
# gini-coefficient.to_csv ("/gini_coefficient.csv", sep = ",")
total_reserves.to_csv ("/home/gsilvapt/Documents/repos/Econ-Factbook/database/total_reserves.csv", sep = ",")
## Script to create folders for each csv file
folder = "/home/gsilvapt/Documents/repos/Econ-Factbook/database"
for file_path in glob.glob(os.path.join(folder, "*.*")):
new_dir = file_path.rsplit(".", 1)[0]
try:
os.mkdir(os.path.join(folder, new_dir))
except WindowsError:
# Handle the case where the target dir already exist.
pass
shutil.move(file_path, os.path.join(new_dir, os.path.basename(file_path)))
'''
__________________________________________________________________
The following parts are focused on retrieving data from the United
Nations
'''
## The United Natiosn API is still under construction. It was not possible
## yet to find a proper solution that can automate this process.
'''
____________________________________________________________________________
The following parts are focused on retrieving data from the International
Labour Organization
'''
'''
____________________________________________________________________________
The following parts are focused on retrieving data from the CIA World
Factbook
'''
'''
__________________________________________________________________
The following parts are focused on retrieving data from the OECD
'''
'''
def testConvertDate(self):
wbdata.get_data("SH.XPD.PRIV.ZS", country="usa", convert_date=True)
def testPandas(self):
wbdata.get_data("SH.XPD.PRIV.ZS", country="usa", pandas=True)
# Hypothesis: there is a reverse relationship between GDP per capita and unemployment rate.
# SL.UEM.TOTL.ZS = Unemployment rate in the world (Variable 1)
# NY.GDP.PCAP.PP.CD = GDP per capita in the world (Variable 2)
# For finding whether this hypothesis is true or not, we are going to make a regression analysis and find whether there is a linear relationship between two variables.
import wbdata
import datetime
import pandas as pd
import numpy as np
import regression
import math
import matplotlib.pyplot as pyplot
from sklearn.linear_model import LinearRegression
data_date = (datetime.datetime(2010, 1, 1), datetime.datetime(2015, 1, 1))
Variable_1 = wbdata.get_data("SL.UEM.TOTL.ZS", data_date = data_date, pandas = True)
Variable_2 = wbdata.get_data("NY.GDP.PCAP.PP.CD", data_date = data_date, pandas = True)
# We need to reshape Variable 1 and adjust Variable 1 and 2 for NaN values
a = np.array(Variable_1).reshape(-1,1)
np.isnan(a)
np.where(np.isnan(a))
np.nan_to_num(a)
x = np.nan_to_num(a)
b = np.array(Variable_2)
np.isnan(b)
np.where(np.isnan(b))
np.nan_to_num(b)
y = np.nan_to_num(b)
def testColumnName(self):
wbdata.get_data("SH.XPD.PRIV.ZS", country="usa", pandas=True,
column_name="IForget")
def scrape():
df = pd.read_csv(
"../SecondProject2/Resources/Project2_idmc_disaster_all_dataset.csv")
df.head()
# In[4]:
import pycountry_convert as pc
# In[5]:
country_code = pc.country_name_to_country_alpha2("China",
cn_name_format="default")
print(country_code)
continent_name = pc.country_alpha2_to_continent_code(country_code)
print(continent_name)
# In[6]:
def country_code(name):
try:
code = pc.country_name_to_country_alpha2(name,
cn_name_format="default")
return code
except:
return "N/A"
def continent_name(name):
try:
continent = pc.country_alpha2_to_continent_code(name)
return continent
except:
return "N/A"
df["Country_2D"] = df["Country Name"].apply(country_code)
df["Continent"] = df["Country_2D"].apply(continent_name)
# In[7]:
df.head()
# In[8]:
df_Africa = df[df["Continent"] == "AF"]
df_Africa.head()
# In[9]:
df_africa = df_Africa.rename(columns={
'Country Name': 'Country',
})
df_africa.head()
# In[10]:
df_africa.columns
# In[11]:
df.groupby("Continent").count()
# In[12]:
#Import Dependencies
import os
import requests
import json
import pprint
import numpy as np
import flask
import wbdata
import datetime
# In[13]:
countries = [
'algeria', 'angola', 'benin', 'botswana', 'burkina faso', 'burundi',
'cabo verde', 'cameroon', 'central african republic', 'chad',
'comoros', 'congo', "cote d'ivoire", 'djibouti', 'egypt',
'equatorial guinea', 'esqtini', 'ethiopia', 'gabon', 'gambia', 'ghana',
'guinea', 'guinea-bissau', 'kenya', 'lesotho', 'liberia', 'libya',
'madagascar', 'malawi', 'mali', 'mauritania', 'mauritius', 'morocco',
'mozambique', 'namibia', 'niger', 'nigeria', 'rwanda',
'sao tome and principe', 'senegal', 'seychelles', 'sirre leone',
'somalia', 'south africa', 'south sudan', 'sudan', 'tanzania', 'togo',
'tunisia', 'uganda', 'zambia', 'zimbabwe'
]
country_codes = [
'AGO', 'ALB', 'ARB', 'BDI', 'BEN', 'BFA', 'BMN', 'BSS', 'BWA', 'CAA',
'CAF', 'CIV', 'CME', 'CMR', 'COG', 'COM', 'CPV', 'DJI', 'DMN', 'DSF',
'DSS', 'DZA', 'EGY', 'ETH', 'GAB', 'GHA', 'GMB', 'GNB', 'GNQ', 'KEN',
'LBR', 'LSO', 'MAR', 'MDG', 'MEA', 'MLI', 'MNA', 'MOZ', 'MRT', 'MUS',
'MWI', 'NAF', 'NAM', 'NER', 'NGA', 'NLS', 'NRS', 'RRS', 'RSO', 'RWA',
'SDN', 'SLE', 'SOM', 'SSA', 'SSD', 'SSF', 'SWZ', 'SXZ', 'SYC', 'TCD',
'TGO', 'TMN', 'TSS', 'TUN', 'TZA', 'UGA', 'XZN', 'ZAF', 'ZMB', 'ZWE'
]
indicators = "SP.POP.TOTL"
data_date = datetime.datetime(2008, 1, 1), datetime.datetime(2019, 1, 1)
wbdata.get_indicator(source=50)
# In[14]:
wbdata.search_countries('')
# In[15]:
data = wbdata.get_data(indicators,
country=country_codes,
data_date=data_date)
df_wbdata = pd.DataFrame(data)
df_wbdata = df_wbdata.rename(
columns={
"indicator": "Indicator",
"country": "Country",
"countryiso3code": "Country code",
"date": "Year",
"value": "Population",
})
df_wbdata = df_wbdata.filter(
items=['Country', 'Country code', 'Year', 'Population'])
df_wbdata.dropna(inplace=True)
df_wbdata['Country'] = df_wbdata['Country'].astype(str)
df_wbdata['Country code'] = df_wbdata['Country code'].astype(str)
df_wbdata['Year'] = df_wbdata['Year'].astype(str)
df_wbdata['Population'] = df_wbdata['Population'].astype(str)
df_wbdata['Country'] = df_wbdata['Country'].str.slice(23, -2)
df_wbdata
# In[16]:
df_africa['Year'] = df_africa['Year'].astype('int64')
df_wbdata['Year'] = df_wbdata['Year'].astype('int64')
# In[17]:
merged_df = pd.merge(left=df_africa,
right=df_wbdata,
how="left",
on=['Country code', 'Year', 'Country'])
merged_df.head()
# In[18]:
merged_df = merged_df.rename(
columns={
'Country code': 'Country_Code',
'Start Date': 'Start_Date',
'Event Name': 'Event_Name',
'Hazard Category': 'Hazard_Category',
'Hazard Type': 'Hazard_Type',
'New Displacements': 'New_Displacements',
})
merged_df.head()
merged_df = merged_df.dropna()
merged_df
merged_df[merged_df['Population'].isna()].count()
merged_df.to_csv('merged.csv', index=False)
#Create the engine and pass in Postgresql
engine = create_engine(
'postgresql://*****:*****@localhost/project2_db')
engine.table_names()
query = pd.read_sql_query('select * from merged_data', con=engine)
return (query)
print(macro_data.tail())
#We can generate a plot for all of our data as follows:
macro_data.plot(grid=True)
#We can apply functions to all columns:
#Average values of macro data during recession
macro_data[macro_data['recession'] == 1].apply(np.mean)
#Average values of macro data during expansion
macro_data[macro_data['recession'] == 0].apply(np.mean)
#Access World Bank Data
#pip install wbdata
import wbdata
#We can search for keys as follows:
wbdata.search_indicators("unemployment")
data_date = (datetime.datetime(1950, 1, 1), datetime.datetime(2019, 2, 10))
unemployment_data = wbdata.get_data("UNEMPSA_", data_date=data_date)
country_data = pd.DataFrame(unemployment_data)
#Access data from quandl
#pip install quandl
import quandl
#Please replace my key with your key
quandl.api_config.ApiConfig.api_key = '1zm1xSnnoqFeAGksg3S1'
oil_prices = quandl.get("OPEC/ORB")
oil_prices.plot(grid=True, title='OPEC Reference Basket')
## IEX exchange (A simple API)
import requests
import io
url = 'https://api.iextrading.com/1.0/stock/aapl/chart/date/20190129'
s = requests.get(url).content
#ease of business
import wbdata
wbdata.get_source()
wbdata.get_indicator(source=1)
#get country codes with a search
wbdata.search_countries('Turkey') #TUR
#get indicators with a search
wbdata.search_indicators('ease of doing business') #IC.BUS.DFRN.XQ
wbdata.get_data('IC.BUS.DFRN.XQ', country='TUR')[0]
wbdata.search_countries('united') #GBR
wbdata.get_data('IC.BUS.DFRN.XQ', country='GBR')[0]
import datetime
data_date = (datetime.datetime(2017, 1, 1), datetime.datetime(2019, 1, 1))
wbdata.get_data("IC.BUS.DFRN.XQ", country=("USA", "GBR"), data_date=data_date)
wbdata.search_indicators("gdp per capita")
wbdata.get_data('NY.GDP.PCAP.KD.ZG')
wbdata.get_data('NY.GDP.PCAP.KD.ZG', country = 'USA')
wbdata.get_data('NY.GDP.PCAP.KD.ZG', country = 'OED')
#income level filter
wbdata.get_incomelevel()
countries = [i['id'] for i in wbdata.get_country(incomelevel="HIC", display=False)]
indicators = {"IC.BUS.DFRN.XQ": "doing_business", "NY.GDP.PCAP.PP.KD": "gdppc"}
df = wbdata.get_dataframe(indicators, country=countries, convert_date=True)
df.to_csv('KocPython2020/in-classMaterial/day6/econ.csv')
df.describe()
def testDateRange(self):
wbdata.get_data("SH.XPD.PRIV.ZS", country="usa",
data_date=(datetime.datetime(2006, 1, 1),
datetime.datetime(2010, 1, 1)))
#ease of business
import wbdata
wbdata.get_source()
wbdata.get_indicator(source=1)
#get country codes with a search
wbdata.search_countries('Turkey') #TUR
wbdata.get_data('IC.REG.COST.PC.MA.ZS', country='TUR')[0]
wbdata.search_countries('united') #GBR
wbdata.get_data('IC.REG.COST.PC.MA.ZS', country='GBR')
import datetime
data_date = (datetime.datetime(2010, 1, 1), datetime.datetime(2011, 1, 1))
wbdata.get_data("IC.REG.COST.PC.MA.ZS",
country=("USA", "GBR"),
data_date=data_date)
wbdata.search_indicators("gdp per capita")
wbdata.get_data('NY.GDP.PCAP.KD.ZG')
wbdata.get_data('NY.GDP.PCAP.KD.ZG', country='USA')
wbdata.get_data('NY.GDP.PCAP.KD.ZG', country='OED')
#income level filter
wbdata.get_incomelevel()
countries = [
i['id'] for i in wbdata.get_country(incomelevel="HIC", display=False)
]
indicators = {
"IC.REG.COST.PC.MA.ZS": "doing_business",
"NY.GDP.PCAP.PP.KD": "gdppc"
}
"""
Messing around with Oliver Sherouse's wbdata, which accesses all of the
World Bank's data API's. This follows the documentation, link below.
Not sure this is ready for primetime, but it could be me...
References
* http://datacatalog.worldbank.org/
* http://blogs.worldbank.org/opendata/accessing-world-bank-data-apis-python-r-ruby-stata
* https://github.com/OliverSherouse/wbdata/blob/master/docs/source/index.rst
Prepared for the NYU Course "Global Economy"
* https://sites.google.com/site/nyusternglobal/home
* https://github.com/DaveBackus/Global_Economy
Written by Dave Backus @ NYU, September 2014
Created with Python 3.4
"""
import wbdata
wbdata.get_source()
wbdata.get_indicator(source=15)
d = wbdata.get_data('IC.BUS.EASE.XQ', country='USA')
indicators = {'IC.BUS.EASE.XQ': 'Ease', 'IRSPREAD': 'Spread'}
df1 = wbdata.get_dataframe(indicators, data_date=(2012, 2013), country='ARG')
#df2 = wbdata.get_dataframe('IRSPREAD', country='all', convert_date=True)
#%%
def home(request):
if request.method == "POST":
def coal(c1):
amount = 0.015 * c1
return amount
def lpg(lg):
amount = 0.0803 * lg
return amount
def redmeat(rm): # (per day)
amount = 2.58 * rm # metric tons of co2 per year
return amount
def clothes(cl): # cl should be in dollars(per month)
amount = 0.005 * cl
return amount
def furniture(fr): # fr should be in dollars
amount = 0.001 * fr
return amount
def laundry(ld): # ld is number of times(per week)
amount = 0.1 * ld
return amount
def treadmill(tm): # tm must be in hrs(per week)
amount = 0.0467 * tm
return amount
def vehicle(hrs):
amount = 0.0444 * hrs
return amount
def papers(number):
amount = 0.0152 * number
return amount
a = request.POST['heat']
b = request.POST['hrsofheat']
he = float(b)
if a == 'coal':
res1 = coal(he)
elif a == 'LPG':
res1 = lpg(he)
c = request.POST['transportation']
res2 = 0
d = request.POST['hrs']
hr = float(d)
print(vehicle(hr))
res3 = vehicle(hr)
e = request.POST['meat']
mt = float(e)
print(redmeat(mt))
res4 = redmeat(mt)
f = request.POST['clothes']
cl = float(f)
print(clothes(cl))
res5 = clothes(cl)
g = request.POST['ac']
print(g)
res6 = 0
h = request.POST['furniture']
ft = float(h)
print(furniture(ft))
res7 = furniture(ft)
i = request.POST['laundary']
ld = float(i)
print(laundry(ld))
res7 = laundry(ld)
j = request.POST['treadmill']
td = float(j)
print(treadmill(td))
res8 = treadmill(td)
k = request.POST['papers']
p = int(k)
print(papers(p))
res9 = papers(p)
code = request.POST['crcode']
print(code)
emission_per_capita = w.get_data("EN.ATM.CO2E.EG.ZS", country=code.upper())/3.667
for i in emission_per_capita:
if i['value'] != None:
emission_per_capita_value = i['value']
break
# print(value)
# country_code = input("Country code : ")
GDP = w.get_data("NY.GDP.MKTP.CD", country=code.upper())
GDP_val = GDP[1]['value']
# print(GDP[1]['value'])
# country_code = input("Country code : ")
energy_intensity = w.get_data("EG.EGY.PRIM.PP.KD", country=code.upper())
# print(energy_intensity)
for i in energy_intensity:
if i['value'] != None:
energy_intensity_val = i['value']
break
# print(val)
# print(emission_per_capita_value)
# print(GDP_val)
# print(energy_intensity_val)
# print()
kaya_value = (emission_per_capita_value * GDP_val * energy_intensity_val * 0.001) / 41.868
result = res1 + res2 + res3 + res4 + res5 + res6 + res7 + res8
print(result)
print(kaya_value)
return render(request, "result.html", {'getvalue': result, 'countrycode': kaya_value})
## http://blogs.worldbank.org/opendata/new-country-classifications-income-level-2017-2018
## 國家資料，收入水平
countries = wb.get_country(display=False)
df_country = pd.DataFrame(countries)
def get_income(x):
return x['value']
df_country['incomeLevel'] = df_country.incomeLevel.apply(get_income)
df_country[df_country.id == 'TWN']
## GDP (current US$)
## https://data.worldbank.org/indicator/NY.GDP.MKTP.CD
gdp = wb.get_data("NY.GDP.MKTP.CD")
list_gdp = []
for i in gdp:
if i['date'] == '2018':
list_gdp = list_gdp + [[i['country']['id'], i['country']['value'], i['value']]]
df_gdp = pd.DataFrame(list_gdp, columns = ['iso2Code','name','value'])
## GDP growth (annual %)
## GDP 成長
## https://data.worldbank.org/indicator/NY.GDP.MKTP.KD.ZG
gdp_growth = wb.get_data("NY.GDP.MKTP.KD.ZG")
list_gdp_growth = []
for i in gdp_growth:
if i['date'] == '2018':
list_gdp_growth = list_gdp_growth + [[i['country']['id'], i['country']['value'], i['value']]]
@author: johnjsyoo
"""
import wbdata
import datetime
import pandas as pd
import MySQLdb as myDB
######################### GETTING ENERGY DATA FOR ALL COUNTRIES ##############################
# Setting the date range for our data
data_date = (datetime.datetime(2011, 1, 1))
# GDP (current US$)
gdp = wbdata.get_data("NY.GDP.MKTP.CD", data_date=data_date, pandas = True)[44:]
# Data on Electricity production from renewable sources (kWh)
renewableProd = wbdata.get_data("EG.ELC.RNEW.KH", data_date=data_date, pandas = True)[44:]
electricityProd = wbdata.get_data("EG.ELC.PROD.KH", data_date=data_date, pandas = True)[44:]
# Convert the time-series data into a Data Frame
gdpDF = pd.DataFrame(gdp)
renewableProdDF = pd.DataFrame(renewableProd)
electricityProdDF = pd.DataFrame(electricityProd)
energyDF = gdpDF.join(renewableProdDF, lsuffix="GDP",rsuffix="Renewable_kWh")
energyDF = energyDF.join(electricityProdDF)
energyDF.rename(columns = {'value':'Electricity_kWh'}, inplace = True)
# Dropping all NaN values and zero values
# In[ ]:
# 1 DOing Business
wbdata.get_indicator(source=1)
# In[ ]:
wbdata.search_countries("Brazil")
# In[ ]:
#wbdata.get_data(indicator, country=u'all', data_date=None, convert_date=False, pandas=False,
#column_name=u'value', keep_levels=False)
wbdata.get_data("IC.BUS.EASE.XQ", country=u'BRA')
# In[ ]:
data_date = (datetime.datetime(2010, 1, 1), datetime.datetime(2011, 1, 1))
wbdata.get_data("IC.BUS.EASE.XQ", country=("USA", "BRA"), data_date=data_date)
# In[ ]:
wbdata.search_indicators("gdp per capita")
# In[ ]:
def testIndicator(self):
wbdata.get_data("SH.XPD.PRIV.ZS")
import wbdata
import json
import pprint
pp = pprint.PrettyPrinter(indent=4)
x = wbdata.get_data("FP.CPI.TOTL")
pp.pprint(x[0])
# sources = wbdata.get_source(display=False)
# indicators = wbdata.get_indicator(source=sources[0]['id'], display=False)
# pp.pprint(indicators[0])
# print
# sources[0]['id']
from pprint import pprint
import wbdata as w
country_code = input("Country code : ")
energy_intensity = w.get_data("EG.EGY.PRIM.PP.KD", country=country_code.upper())
#pprint(energy_intensity)
for i in energy_intensity:
if i['value'] != None :
value = i['value']
break
print(value)
```
Country codes available
ABW Aruba
AFG Afghanistan
AFR Africa
AGO Angola
ALB Albania
AND Andorra
ANR Andean Region
ARB Arab World
ARE United Arab Emirates
ARG Argentina
ARM Armenia
ASM American Samoa
ATG Antigua and Barbuda
AUS Australia
AUT Austria
AZE Azerbaijan
BDI Burundi
BEA East Asia & Pacific (IBRD-only countries)
def testOneCountry(self):
wbdata.get_data("SH.XPD.PRIV.ZS", country="USA")
# http://wbdata.readthedocs.org/en/latest/
# http://wbdata.readthedocs.org/en/latest/fetcher.html
import wbdata
import datetime
import pandas as pd
'''
This wbdata is an interactive console to work with World Bank's API.
You can run wbdata.get_source() to see all sources of information and the
respective numbers to run in the below code to fetch the data.
Also, using Pandas package may facilitate the task to convert the lists and dictionaries
retrieved from the API.
Total Population -> source=16
'''
#wbdata.get_source()
wbdata.get_indicator(source=16)
# Define time range to search for data
data_date = (datetime.datetime(1960, 1, 1), datetime.datetime(2014, 1, 1))
# Store the data as the variable df
df = pd.DataFrame(
wbdata.get_data("SP.POP.TOTL", pandas=True, data_date=data_date))
# Write it to a CSV - Exemple in /data-pipeline
df.to_csv("YOURPATH/population_total_1960-2014.csv", sep=',')
def testTwoCountries(self):
wbdata.get_data("SH.XPD.PRIV.ZS", country=("chn", "bra"))
