def test_wdi_download_error_handling(self):
cntry_codes = ['USA', 'XX']
inds = 'NY.GDP.PCAP.CD'
with tm.assertRaisesRegexp(ValueError, "Invalid Country Code\\(s\\): XX"):
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='raise')
if PANDAS_0160:
# assert_produces_warning doesn't exists in prior versions
with self.assert_produces_warning():
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='warn')
self.assertTrue(isinstance(result, pd.DataFrame))
self.assertEqual(len(result), 2)
cntry_codes = ['USA']
inds = ['NY.GDP.PCAP.CD', 'BAD_INDICATOR']
with tm.assertRaisesRegexp(ValueError, "The provided parameter value is not valid\\. Indicator: BAD_INDICATOR"):
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='raise')
if PANDAS_0160:
with self.assert_produces_warning():
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='warn')
self.assertTrue(isinstance(result, pd.DataFrame))
self.assertEqual(len(result), 2)
def test_wdi_download(self):
# Test a bad indicator with double (US), triple (USA),
# standard (CA, MX), non standard (KSV),
# duplicated (US, US, USA), and unknown (BLA) country codes
# ...but NOT a crash inducing country code (World bank strips pandas
# users of the luxury of laziness, because they create their
# own exceptions, and don't clean up legacy country codes.
# ...but NOT a retired indicator (User should want it to error.)
cntry_codes = ['CA', 'MX', 'USA', 'US', 'US', 'KSV', 'BLA']
inds = ['NY.GDP.PCAP.CD','BAD.INDICATOR']
expected = {'NY.GDP.PCAP.CD': {('Canada', '2004'): 31829.522562759001, ('Canada', '2003'): 28026.006013044702,
('Kosovo', '2004'): 2135.3328465238301, ('Kosovo', '2003'): 1969.56271307405,
('Mexico', '2004'): 7042.0247834044303, ('Mexico', '2003'): 6601.0420648056606,
('United States', '2004'): 41928.886136479705, ('United States', '2003'): 39682.472247320402}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected,decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
# Round, to ignore revisions to data.
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names=['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
# pass start and end as string
result = download(country=cntry_codes, indicator=inds,
start='2003', end='2004', errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
# Round, to ignore revisions to data.
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download(self):
# Test a bad indicator with double (US), triple (USA),
# standard (CA, MX), non standard (KSV),
# duplicated (US, US, USA), and unknown (BLA) country codes
# ...but NOT a crash inducing country code (World bank strips pandas
# users of the luxury of laziness, because they create their
# own exceptions, and don't clean up legacy country codes.
# ...but NOT a retired indicator (User should want it to error.)
cntry_codes = ['CA', 'MX', 'USA', 'US', 'US', 'KSV', 'BLA']
inds = ['NY.GDP.PCAP.CD','BAD.INDICATOR']
expected = {'NY.GDP.PCAP.CD': {('Canada', '2003'): 28026.006013044702, ('Mexico', '2003'): 6601.0420648056606, ('Canada', '2004'): 31829.522562759001, ('Kosovo', '2003'): 1969.56271307405, ('Mexico', '2004'): 7042.0247834044303, ('United States', '2004'): 41928.886136479705, ('United States', '2003'): 39682.472247320402, ('Kosovo', '2004'): 2135.3328465238301}}
expected = pandas.DataFrame(expected)
# Round, to ignore revisions to data.
expected = pandas.np.round(expected,decimals=-3)
expected.sort(inplace=True)
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='ignore')
result.sort(inplace=True)
# Round, to ignore revisions to data.
result = pandas.np.round(result,decimals=-3)
expected.index = result.index
assert_frame_equal(result, pandas.DataFrame(expected))
def get_wb_df(wb_name,colname):
"""gets a dataframe from wb data with all years and all countries, and a lot of nans"""
#return all values
wb_raw =(wb.download(indicator=wb_name,start=start_year,end=today_year,country="all"))
#sensible name for the column
# wb_raw.rename(columns={wb_raw.columns[0]: colname},inplace=True)
return wb_raw.rename(columns={wb_raw.columns[0]: colname})
def test_wdi_download_w_retired_indicator(self):
cntry_codes = ['CA', 'MX', 'US']
# Despite showing up in the search feature, and being listed online,
# the api calls to GDPPCKD don't work in their own query builder, nor
# pandas module. GDPPCKD used to be a common symbol.
# This test is written to ensure that error messages to pandas users
# continue to make sense, rather than a user getting some missing
# key error, cause their JSON message format changed. If
# World bank ever finishes the deprecation of this symbol,
# this nose test should still pass.
inds = ['GDPPCKD']
try:
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='ignore')
# If for some reason result actually ever has data, it's cause WB
# fixed the issue with this ticker. Find another bad one.
except ValueError as e:
raise nose.SkipTest("No indicators returned data: {0}".format(e))
# if it ever gets here, it means WB unretired the indicator.
# even if they dropped it completely, it would still get caught above
# or the WB API changed somehow in a really unexpected way.
if len(result) > 0:
raise nose.SkipTest("Invalid results")
def datasets(dataset):
if dataset == ('WB'):
df = wb.download(indicator='NY.GDP.PCAP.KD',
country = ['US', 'CA', 'MX'],
start = 2000,
end = 2015)
return df
elif dataset == ('Iris'):
df = pd.read_csv('https://archive.ics.uci.edu/ml/'
'machine-learning-databases/iris/iris.data', header = None)
return df
def test_wdi_download_monthly(self):
expected = {'COPPER': {('World', '2012M01'): 8040.47,
('World', '2011M12'): 7565.48,
('World', '2011M11'): 7581.02,
('World', '2011M10'): 7394.19,
('World', '2011M09'): 8300.14,
('World', '2011M08'): 9000.76,
('World', '2011M07'): 9650.46,
('World', '2011M06'): 9066.85,
('World', '2011M05'): 8959.90,
('World', '2011M04'): 9492.79,
('World', '2011M03'): 9503.36,
('World', '2011M02'): 9867.60,
('World', '2011M01'): 9555.70}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'ALL'
inds = 'COPPER'
result = download(country=cntry_codes, indicator=inds,
start=2011, end=2012, freq='M',errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds, countries=cntry_codes,
start=2011, end=2012, freq='M', errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_w_crash_inducing_countrycode(self):
cntry_codes = ['CA', 'MX', 'US', 'XXX']
inds = ['NY.GDP.PCAP.CD']
try:
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='ignore')
except ValueError as e:
raise nose.SkipTest("No indicators returned data: {0}".format(e))
# if it ever gets here, it means the country code XXX got used by WB
# or the WB API changed somehow in a really unexpected way.
if len(result) > 0:
raise nose.SkipTest("Invalid results")
def api_wb(params):
from data_params import DATABASE
country_codes = mongo_to_dataframe('utilities', 'country_code')
df = wb.download(
indicator=params['indicator'],
country=params['country'],
start=params['start'],
end=params['end']
)
df = df.reset_index()
df.rename(columns=params['col_rename'], inplace=True)
df = pd.merge(df,country_codes, left_on='country',right_on='country_name')
df = df[['GDP_cst_dollars','ISO3','population','year']]
logger.info('inserting df with shape: ' + str(df.shape))
dataframe_to_mongo(df, DATABASE,params['collection_name'], erase=True)
logger.info('insertion sucessful in db' + DATABASE + ' of collection: ' + params['collection_name'])
def test_wdi_download_str(self):
expected = {'NY.GDP.PCAP.CD': {('Japan', '2004'): 36441.50449394,
('Japan', '2003'): 33690.93772972,
('Japan', '2002'): 31235.58818439,
('Japan', '2001'): 32716.41867489,
('Japan', '2000'): 37299.64412913}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'JP'
inds = 'NY.GDP.PCAP.CD'
result = download(country=cntry_codes, indicator=inds,
start=2000, end=2004, errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds, countries=cntry_codes,
start=2000, end=2004, errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_quarterly(self):
expected = {'DT.DOD.PUBS.CD.US': {('Albania', '2012Q1'): 3240539817.18,
('Albania', '2011Q4'): 3213979715.15,
('Albania', '2011Q3'): 3187681048.95,
('Albania', '2011Q2'): 3248041513.86,
('Albania', '2011Q1'): 3137210567.92}}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
if PANDAS_0170:
expected = expected.sort_index()
else:
expected = expected.sort()
cntry_codes = 'ALB'
inds = 'DT.DOD.PUBS.CD.US'
result = download(country=cntry_codes, indicator=inds,
start=2011, end=2012, freq='Q', errors='ignore')
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-3)
if PANDAS_0140:
expected.index.names = ['country', 'year']
else:
# prior versions doesn't allow to set multiple names to MultiIndex
# Thus overwrite it with the result
expected.index = result.index
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds, countries=cntry_codes,
start=2011, end=2012, freq='Q', errors='ignore').read()
if PANDAS_0170:
result = result.sort_index()
else:
result = result.sort()
result = np.round(result, decimals=-1)
tm.assert_frame_equal(result, expected)
def __init__(self, indicator):
"""Initiates with data from 2017-today"""
self.indicator = indicator
# Build cache if it does not already exist
engine = create_engine('sqlite:///cache.db')
conn = engine.connect()
if engine.dialect.has_table(engine, self.indicator):
self.data = pandas.read_sql(self.indicator,
conn,
index_col=['country', 'year'])
else:
self.data = wb.download(indicator=self.indicator,
country='all',
start=1960,
end=2030).dropna()
self.data.to_sql(self.indicator, conn, if_exists='replace')
conn.close()
self.start_date = self.data.unstack().columns[0][1]
self.end_date = self.data.unstack().columns[-1][1]
def test_wdi_download_quarterly(self):
code = "DT.DOD.PUBS.CD.US"
expected = {
code: {
("Albania", "2012Q1"): 3240539817.18,
("Albania", "2011Q4"): 3213979715.15,
("Albania", "2011Q3"): 3187681048.95,
("Albania", "2011Q2"): 3248041513.86,
("Albania", "2011Q1"): 3137210567.92,
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
expected = expected.sort_index()
cntry_codes = "ALB"
inds = "DT.DOD.PUBS.CD.US"
result = download(
country=cntry_codes,
indicator=inds,
start=2011,
end=2012,
freq="Q",
errors="ignore",
)
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ["country", "year"]
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2011,
end=2012,
freq="Q",
errors="ignore").read()
result = result.sort_index()
result = np.round(result, decimals=-1)
tm.assert_frame_equal(result, expected)
def test_wdi_download(self):
# Test a bad indicator with double (US), triple (USA),
# standard (CA, MX), non standard (KSV),
# duplicated (US, US, USA), and unknown (BLA) country codes
# ...but NOT a crash inducing country code (World bank strips pandas
# users of the luxury of laziness, because they create their
# own exceptions, and don't clean up legacy country codes.
# ...but NOT a retired indicator (User should want it to error.)
cntry_codes = ['CA', 'MX', 'USA', 'US', 'US', 'KSV', 'BLA']
inds = ['NY.GDP.PCAP.CD', 'BAD.INDICATOR']
expected = {
'NY.GDP.PCAP.CD': {
('Canada', '2003'): 28026.006013044702,
('Mexico', '2003'): 6601.0420648056606,
('Canada', '2004'): 31829.522562759001,
('Kosovo', '2003'): 1969.56271307405,
('Mexico', '2004'): 7042.0247834044303,
('United States', '2004'): 41928.886136479705,
('United States', '2003'): 39682.472247320402,
('Kosovo', '2004'): 2135.3328465238301
}
}
expected = pandas.DataFrame(expected)
# Round, to ignore revisions to data.
expected = pandas.np.round(expected, decimals=-3)
expected.sort(inplace=True)
result = download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors='ignore')
result.sort(inplace=True)
# Round, to ignore revisions to data.
result = pandas.np.round(result, decimals=-3)
expected.index = result.index
assert_frame_equal(result, pandas.DataFrame(expected))
def featureappnd(ind,nm,ft):
clmns.append(nm)
tmpdt=wb.download(country=u"all", indicator=ind,start=strtyear, end=now.year)
tmpdt.columns=[nm]
tmpdt['Country']=[i[0] for i in tmpdt.index]
tmpdt['Year']=[i[1] for i in tmpdt.index]
tmpdt['Year']=tmpdt['Year'].apply(int)
tmpdt =tmpdt.groupby("Country").transform(lambda x: x.iloc[::-1])
tmpdt['Country']=[i[0] for i in tmpdt.index]
tmpdt=tmpdt[["Country","Year",nm]]
tmpdt=tmpdt[658:]
tmpdt[nm]=tmpdt[nm].replace(0, np.nan)
if ft=="reg":
tmpdt[nm] = tmpdt.groupby("country")[nm].transform(lambda x: x.fillna(lnreg(x,tmpdt['Year']-strtyear)))
elif ft=="mean":
tmpdt[nm] = tmpdt.groupby("country")[nm].transform(lambda x: x.fillna(x.mean()))
elif ft=="sdp":
tmpdt[nm] = tmpdt.groupby("country")[nm].transform(lambda x: x.fillna(x.mean()+(tmpdt["Year"]-2010)*0.5*np.std(x)))
elif ft=="sdn":
tmpdt[nm] = tmpdt.groupby("country")[nm].transform(lambda x: x.fillna(x.mean()-(tmpdt["Year"]-2010)*0.5*np.std(x)))
global maindata
maindata=pd.merge(maindata,tmpdt)
def test_wdi_download_quarterly(self):
code = 'DT.DOD.PUBS.CD.US'
expected = {
code: {
('Albania', '2012Q1'): 3240539817.18,
('Albania', '2011Q4'): 3213979715.15,
('Albania', '2011Q3'): 3187681048.95,
('Albania', '2011Q2'): 3248041513.86,
('Albania', '2011Q1'): 3137210567.92
}
}
expected = pd.DataFrame(expected)
# Round, to ignore revisions to data.
expected = np.round(expected, decimals=-3)
expected = expected.sort_index()
cntry_codes = 'ALB'
inds = 'DT.DOD.PUBS.CD.US'
result = download(country=cntry_codes,
indicator=inds,
start=2011,
end=2012,
freq='Q',
errors='ignore')
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ['country', 'year']
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2011,
end=2012,
freq='Q',
errors='ignore').read()
result = result.sort_index()
result = np.round(result, decimals=-1)
tm.assert_frame_equal(result, expected)
def test_wdi_download_str(self):
# These are the expected results, rounded (robust against
# data revisions in the future).
expected = {
"NY.GDP.PCAP.CD": {
("Japan", "2004"): 38000.0,
("Japan", "2003"): 35000.0,
("Japan", "2002"): 32000.0,
("Japan", "2001"): 34000.0,
("Japan", "2000"): 39000.0,
}
}
expected = pd.DataFrame(expected)
expected = expected.sort_index()
cntry_codes = "JP"
inds = "NY.GDP.PCAP.CD"
result = download(country=cntry_codes,
indicator=inds,
start=2000,
end=2004,
errors="ignore")
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ["country", "year"]
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2000,
end=2004,
errors="ignore").read()
result = result.sort_index()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def to_flourish(indicator, start_yr, end_yr, country='all', save_csv=True):
"""
Downloads data from the World Bank and converts it to the format for making bar chart races in Flourish.
Parameters:
* indicator: the world bank code available on the World Bank Page.
* country: a string if single or a list if multiple of the ISO3 codes of the locations.
* start_yr: the first year of data that you want to get.
* end_yr: the final year of data that you want to collect.
* save_csv: saves the file as a csv in your working directory.
"""
df = wb.download(indicator=indicator,
country=country,
start=start_yr,
end=end_yr)
df = df.reset_index()
df = pd.pivot_table(df, values=indicator, columns='year',
index='country').reset_index()
print("Processed the Indicator Data")
country_info = wb.get_countries()
country_info = country_info[country_info.region != 'Aggregates']
df_merged = pd.merge(country_info[['iso2c', 'name', 'region']],
df,
left_on='name',
right_on='country')
df_merged.insert(
3, 'Image URL', df_merged['iso2c'].apply(
lambda i: f"https://www.countryflags.io/{i}/flat/64.png"))
df_merged = df_merged.drop(columns=['iso2c', 'country'])
if save_csv:
df_merged.to_csv(
f"flourish_data/flourish_{indicator}_{datetime.now().strftime('%d-%m-%Y %H-%M')}.csv",
index=False)
return df_merged
def test_wdi_download_str(self):
# These are the expected results, rounded (robust against
# data revisions in the future).
expected = {
'NY.GDP.PCAP.CD': {
('Japan', '2004'): 38000.0,
('Japan', '2003'): 35000.0,
('Japan', '2002'): 32000.0,
('Japan', '2001'): 34000.0,
('Japan', '2000'): 39000.0
}
}
expected = pd.DataFrame(expected)
expected = expected.sort_index()
cntry_codes = 'JP'
inds = 'NY.GDP.PCAP.CD'
result = download(country=cntry_codes,
indicator=inds,
start=2000,
end=2004,
errors='ignore')
result = result.sort_index()
result = np.round(result, decimals=-3)
expected.index.names = ['country', 'year']
tm.assert_frame_equal(result, expected)
result = WorldBankReader(inds,
countries=cntry_codes,
start=2000,
end=2004,
errors='ignore').read()
result = result.sort_index()
result = np.round(result, decimals=-3)
tm.assert_frame_equal(result, expected)
def test_wdi_download_error_handling(self):
cntry_codes = ["USA", "XX"]
inds = "NY.GDP.PCAP.CD"
msg = "Invalid Country Code\\(s\\): XX"
with pytest.raises(ValueError, match=msg):
download(
country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors="raise",
)
with pytest.warns(Warning):
result = download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors="warn")
assert isinstance(result, pd.DataFrame)
assert len(result), 2
cntry_codes = ["USA"]
inds = ["NY.GDP.PCAP.CD", "BAD_INDICATOR"]
msg = "The provided parameter value is not valid\\. " "Indicator: BAD_INDICATOR"
with pytest.raises(ValueError, match=msg):
download(
country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors="raise",
)
with pytest.warns(Warning):
result = download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors="warn")
assert isinstance(result, pd.DataFrame)
assert len(result) == 2
def chart1(indicator1, countryCode, startY, endY):
import matplotlib
from io import BytesIO
import base64
import pandas as pd
pd.core.common.is_list_like = pd.api.types.is_list_like
from pandas_datareader import wb
matplotlib.use("agg")
import matplotlib.pyplot as plt
# mathces = wb.search('gdp.*capita.*const')
dat = wb.download(indicator=indicator1,
country=countryCode,
start=startY,
end=endY)
data = dat.unstack()
print(data)
data.plot(kind='bar')
sio = BytesIO()
plt.savefig(sio, format='png')
data = base64.encodebytes(sio.getvalue()).decode()
html = '''
<html>
<body>
<img src="data:image/png;base64,{}" />
</body>
<html>
'''
picture = "data:image/png;base64," + data
#print(picture)
plt.close()
#return html.format(data)
return render_template("home.html", picture=picture)
def get_wb_data(indicator, start_yr, end_yr, country='all', save_csv=False):
"""
Downloads and formats World Bank Data with year as index.
Parameters:
* indicator: the world bank code available on the World Bank Page.
* start_yr: the first year of data that you want to get.
* end_yr: the final year of data that you want to collect.
* country: a string if single or a list if multiple of the ISO3 codes of the locations.
* save_csv: saves the file as a csv in your working directory.
"""
global indicator_name
indicator_name = indicator
temp_df = wb.download(indicator=indicator,
country=country,
start=start_yr,
end=end_yr)
temp_df = temp_df.dropna()
temp_df.index.names = ['Region', 'Year']
temp_df = temp_df.reset_index(level=0).sort_values(by='Region')
if save_csv:
temp_df.to_csv(
f"{indicator}_{datetime.now().strftime('%d-%m-%Y %H-%M')}.csv",
index=False)
return temp_df
def test_wdi_download_error_handling(self):
cntry_codes = ['USA', 'XX']
inds = 'NY.GDP.PCAP.CD'
msg = "Invalid Country Code\\(s\\): XX"
with assert_raises_regex(ValueError, msg):
download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors='raise')
with tm.assert_produces_warning():
result = download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors='warn')
assert isinstance(result, pd.DataFrame)
assert len(result), 2
cntry_codes = ['USA']
inds = ['NY.GDP.PCAP.CD', 'BAD_INDICATOR']
msg = ("The provided parameter value is not valid\\. "
"Indicator: BAD_INDICATOR")
with assert_raises_regex(ValueError, msg):
download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors='raise')
with tm.assert_produces_warning():
result = download(country=cntry_codes,
indicator=inds,
start=2003,
end=2004,
errors='warn')
assert isinstance(result, pd.DataFrame)
assert len(result) == 2
import matplotlib.pyplot as plt
import numpy as np
from pandas_datareader import wb
path = "https://github.com/omercadopopular/cgoes/blob/master/tutorial/python/statatopython/PPI_DB_082316.dta?raw=true"
cpisauce = "https://github.com/omercadopopular/cgoes/blob/master/tutorial/python/statatopython/CPIAUCSL.xls?raw=true"
gdpsauce = "https://github.com/omercadopopular/cgoes/blob/master/tutorial/python/statatopython/gdp.xlsx?raw=true"
#####################################
# 1. Retrieve Databases #############
#####################################
## 1.1 Import GDP data from the World Bank
wbdata = (wb.download(indicator='NY.GDP.MKTP.CD', country='all', start=1994, end=2015)
.dropna()
.rename(columns={'NY.GDP.MKTP.CD': 'gdp'})
)
## 1.2 Read file from STATA dta
ppidf = pd.read_stata(path)
## 1.3 Import CPI data from excel file
## Note you have to skip 9 rows
cpi = pd.read_excel(cpisauce, skiprows=9, header=1)
#####################################
# 2. Adjust Databases ###############
#####################################
import pandas as pd, datetime
from pandas_datareader import data, wb
dat = wb.download(indicator=['SL.UEM.TOTL.ZS','NY.GDP.DEFL.KD.ZG','NE.RSB.GNFS.ZS'], country=['USA', 'TUR','GBR'], start=1970, end=2016)
dat.to_csv('data.csv')
# start=datetime.datetime(1970, 1, 1)
# end=datetime.datetime(2016, 1, 1)
# df = data.DataReader(['BPBLTT01TRA188S','LRUN64TTTRQ156S','FPCPITOTLZGTUR'], "fred", start, end)
# df.columns = ['tbal','unemploy','inf']
# df.to_csv('tr.csv')
# start=datetime.datetime(1970, 1, 1)
# end=datetime.datetime(2016, 1, 1)
# df = data.DataReader(['BPBLTT01GBQ188S','LMUNRRTTGBM156S','FPCPITOTLZGGBR'], "fred", start, end)
# df.columns = ['tbal','unemploy','inf']
# df.to_csv('uk.csv')
def download_data(year):
ind = ['SH.STA.ACSN', 'SE.PRM.CMPT.FE.ZS']
dat = wb.download(indicator=ind, country='all', start=year, end=year).dropna()
dat.columns = ['sanitation', 'completion']
return dat
from pandas_datareader import data, wb
#import wbdata
import pandas
import matplotlib.pyplot as plt
# #set up the countries I want
# countries = ["CL","UY","HU"]
#
# #set up the indicator I want (just build up the dict if you want more than one)
# indicators = {'SP.DYN.LE00.IN':'Life expectancy at birth, total (years)'}
#
# #grab indicators above for countires above and load into data frame
# df = wbdata.get_dataframe(indicators, convert_date=False)
# #wbdata.get_dataframe
# #df is "pivoted", pandas' unstack fucntion helps reshape it into something plottable
# dfu = df.unstack(level=0)
#
# # a simple matplotlib plot with legend, labels and a title
# dfu.plot();
# plt.legend(loc='best');
# plt.title("GNI Per Capita ($USD, Atlas Method)");
# plt.xlabel('Date'); plt.ylabel('GNI Per Capita ($USD, Atlas Method');
ind = ['SP.DYN.LE00.IN']
#countries = ['iso2c']
dat = wb.download(indicator=ind, country='all', start=2013, end=2013).dropna()
dat.columns = ['cellphone']
print(dat)
life = pd.read_csv('subsaharan_africa.csv', index_col=3, na_values=None)
jk = pd.read_csv('subsaharan_africa.csv')
# <codecell>
life.columns
# Get the external dataset from worldbank
# We have selected indicator, "SP.POP.TOTL"
df = wb.download(
# Specify indicator to retrieve
indicator='SP.POP.TOTL',
country=['all'],
# Start Year
start='2008',
# End Year
end=2016
)
# <codecell>
#create an array with all the years
all_year = [str(x) for x in range(1960, 2000)]
#Check what's inside all_year
print all_year.count
# <codecell>
#drop all columns with no values
#life = life.dropna(axis=0)
def p148(steps):
countries = [
'BR',
'CA',
'CN',
'FR',
'DE',
'IN',
'IL',
'JP',
'SA',
'GB',
'US',
]
dat = wb.download(indicator='NY.GDP.PCAP.KD',
country=countries,
start=1970,
end=2016)
df = dat.unstack().T
df.index = df.index.droplevel(0).astype(int)
class Net(torch.nn.Module):
def __init__(self, input_size, hidden_size):
super(Net, self).__init__()
self.rnn = torch.nn.LSTM(input_size, hidden_size)
self.fc = torch.nn.Linear(hidden_size, 1)
def forward(self, x):
x = x[:, :, None]
x, _ = self.rnn(x)
x = self.fc(x)
x = x[:, :, 0]
return x
net = Net(input_size=1, hidden_size=5)
# 数据归一化
df_scaled = df / df.loc[2000]
# 确定训练集和测试集
years = df.index
train_seq_len = sum((years >= 1971) & (years <= 2000))
test_seq_len = sum(years > 2000)
print('训练集长度 = {}, 测试集长度 = {}'.format(train_seq_len, test_seq_len))
# 确定训练使用的特征和标签
inputs = torch.tensor(df_scaled.iloc[:-1].values, dtype=torch.float32)
labels = torch.tensor(df_scaled.iloc[1:].values, dtype=torch.float32)
# 训练网络
criterion = torch.nn.MSELoss()
optimizer = torch.optim.Adam(net.parameters())
for step in range(steps):
if step:
optimizer.zero_grad()
train_loss.backward()
optimizer.step()
preds = net(inputs)
train_preds = preds[:train_seq_len]
train_labels = labels[:train_seq_len]
train_loss = criterion(train_preds, train_labels)
test_preds = preds[train_seq_len:]
test_labels = labels[train_seq_len:]
test_loss = criterion(test_preds, test_labels)
if step % 500 == 0:
print('第{}次迭代: loss (训练集) = {}, loss (测试集) = {}'.format(
step, train_loss, test_loss))
preds = net(inputs)
df_pred_scaled = pd.DataFrame(preds.detach().numpy(),
index=years[1:],
columns=df.columns)
df_pred = df_pred_scaled * df.loc[2000]
print(df_pred.loc[2001:])
from pandas_datareader import wb
import matplotlib.pyplot as plt
mathces = wb.search('gni.*capita.*const')
#grab indicator,country, period I want and load into data frame
df = wb.download(indicator='NY.GNP.PCAP.CD', country=['CL', 'UY', 'HU'], start=1990, end=2010)
#df is "pivoted", pandas' unstack fucntion helps reshape it into something plottable
dfu = df.unstack(level=0)
# a simple matplotlib plot with legend, labels and a title
dfu.plot();
plt.legend(loc='best');
plt.title("GNI Per Capita ($USD, Atlas Method)");
plt.xlabel('Date'); plt.ylabel('GNI Per Capita ($USD, Atlas Method');
plt.show();
#Import packages:
from pandas_datareader import wb
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib_venn import venn2
#Import GDP data from World bank:
gdps_wb = wb.download(indicator='NY.GDP.PCAP.KD',
country=['US'],
start=1990,
end=2018)
gdps_wb = gdps_wb.rename(columns={'NY.GDP.PCAP.KD': 'gdp'})
gdps_wb = gdps_wb.reset_index()
gdps_wb.year = gdps_wb.year.astype(int)
gdps_wb.head(10)
gdpgrowth_wb = wb.download(indicator='NY.GDP.MKTP.KD.ZG',
country=['US'],
start=1990,
end=2018)
gdpgrowth_wb = gdpgrowth_wb.rename(columns={'NY.GDP.MKTP.KD.ZG': 'gdp_growth'})
gdpgrowth_wb = gdpgrowth_wb.reset_index()
gdpgrowth_wb.year = gdpgrowth_wb.year.astype(int)
gdpgrowth_wb.head(10)
#Import unemployment data from excel file:
unempl = pd.read_excel('Data.xlsx')
print(unempl)
#Change type:
"St. Vincent and the Grenadines":"Saint Vincent and the Grenadines",
"Congo, Rep.":"Republic of the Congo",
"Bahamas, The":"The Bahamas",
"Gambia, The":"The Gambia"
}
for t in trans :
s["Country/Region"] = s["Country/Region"].replace(t, trans[t])
return(s)
if __name__ == "__main__":
dsets = datasets.load()
covid = datasets.combine(dsets)
if (os.path.isfile(WDI_FILE)) :
warnings.warn("Reading cached WDI data from disk, delete file to download updated")
wdi = pd.read_pickle(WDI_FILE)
else :
wdi = covid.drop(columns=["Date","Province/State","Lat","Long", datasets.CONFIRMED,"deaths","recoveries"]).drop_duplicates()
for id in INDICES_USED:
s = wb.download(indicator=id, country="all", start=2005, end=2019).reset_index()
# use most recent non missing value
s = s.dropna().groupby("country").last()
s = s.drop(columns="year").reset_index()
# match country names to covid data
s = s.rename(columns={"country":"Country/Region"})
s = fixcountrynames(s)
wdi = pd.merge(wdi, s, how='left', on='Country/Region', validate="one_to_one")
wdi.to_pickle(WDI_FILE)
import pandas as pd
from pandas_datareader import wb
import torch
import torch.nn
import torch.optim
countries = ['BR', 'CA', 'CN', 'FR', 'DE', 'IN', 'IL', 'JP', 'SA', 'GB', 'US',]
dat = wb.download(indicator='NY.GDP.PCAP.KD',
country=countries, start=1970, end=2016)
df = dat.unstack().T
df.index = df.index.droplevel(0).astype(int)
print(df)
class Net(torch.nn.Module):
def __init__(self, input_size, hidden_size):
super(Net, self).__init__()
self.rnn = torch.nn.LSTM(input_size, hidden_size)
self.fc = torch.nn.Linear(hidden_size, 1)
def forward(self, x):
x = x[:, :, None]
x, _ = self.rnn(x)
x = self.fc(x)
x = x[:, :, 0]
return x
net = Net(input_size=1, hidden_size=5)
print(net)
####DATA PROJECT####
###Data Cleaning and Structuring###
## Set up
import pandas as pd
import numpy as np
import pandas_datareader
import datetime
from pandas_datareader import wb
##Downloand Data from the Wold Data Bank
countries = ["CN","JP","BR","US","DK","ES","TM","IN","NG"]
indicators = {"NY.GDP.PCAP.KD":"GDP per capita", "NY.GDP.MKTP.CD":"GDP(current US $)", "SP.POP.TOTL":"Population total",
"SP.URB.TOTL.IN.ZS":"Urban Population in %", "SP.DYN.TFRT.IN":"Fertility Rate", "SE.ADT.LITR.ZS": "Literacy rate, adult total in %" }
data_wb = wb.download(indicator= indicators, country= countries, start=1990, end=2017)
data_wb = data_wb.rename(columns = {"NY.GDP.PCAP.KD":"gdp_pC","NY.GDP.MKTP.CD":"gdp", "SP.POP.TOTL":"pop", "SP.URB.TOTL.IN.ZS":"urban_pop%",
"SP.DYN.TFRT.IN":"frt", "SE.ADT.LITR.ZS":"litr"})
data_wb = data_wb.reset_index()
data_wb.head(-5)
writer = pd.ExcelWriter('pandas_simple.xlsx', engine='xlsxwriter')
data_wb.to_excel(r"./data_wb1.xlsx")
##Overview of the data
data_wb.dtypes
pd.options.display.float_format = '{:,}'.format
round(data_wb.head(),2)
data_wb['gdp_in_bil'] = data_wb['gdp']/1000000000
# In[23]:
df1.Price.mean()
# In[27]:
get_ipython().system("pip3 install --upgrade pandas_datareader")
from pandas_datareader import data, wb
df_wb = wb.download(
# Specify indicator to retrieve
indicator="SP.POP.TOTL",
country=["all"],
# Start Year
start="2008",
# End Year
end=2016,
)
# In[28]:
df_wb.shape
# In[29]:
df_wb.head()
def get_wb(wb_name):
"""return unstacked dataframe (countries, year) with WB data"""
return wb.download(indicator=wb_name,start=start_year,end=today_year,country="all").unstack("year")[wb_name].dropna(how="all").dropna(how="all",axis=1)
raw_unstacked_data = raw_data.unstack(level=0)
# printing our data object
# print(raw_data)
# print(raw_unstacked_data)
# =============================================================================
# # API method 2: using from pandas.datareader import wb, convert the data object to a DataFrame
# =============================================================================
# view all data
pd.set_option('display.max_columns', 15)
pd.set_option('display.max_rows', 15)
df1 = wb.download(indicator = indicators, country = countries, start = 2008, end = 2018)
date_period = [i for i in range(2008, 2019)]
print(df1)
# create a new DataFrame df2 for later use, not change origin values from df1 if we do some calculations for our dataframe df2
# rename the columns name
df2 = df1.rename(columns = {'SI.DST.05TH.20':'Income share held by highest 20%', 'SI.DST.FRST.20': 'Income share held by lowest 20%', \
'SL.EMP.TOTL.SP.FE.NE.ZS': 'Employment to population ratio, 15+, female (%) (national estimate)',\
'SL.EMP.TOTL.SP.MA.NE.ZS': 'Employment to population ratio, 15+, male (%) (national estimate)'}, inplace = False)
# overview our data object DataFrame
# Data manipulation: dealing with the missing value, replace them as mean(), which has less impact on our data sets
df2.mean()
df2.fillna(df2.mean(), inplace = True)
print(df2)
# -*- coding: utf-8 -*-
"""
Created on Wed Feb 24 14:07:46 2016
@author: anh
"""
import pandas as pd
from pandas_datareader import wb
from ggplot import *
dat = wb.download(
indicator=['BX.KLT.DINV.CD.WD', 'BX.KLT.DINV.WD.GD.ZS'],
country='CN', start=2005, end=2011)
dat.reset_index(inplace=True)
dat['year'] = pd.to_datetime(dat['year']) # key
print ggplot(aes(x='year', y='BX.KLT.DINV.CD.WD'),
data=dat) + \
geom_line() + theme_bw() + \
scale_x_date(labels = date_format("%m - %Y"))
cdat
ggplot(dat.loc["China"], aes(x='year', y='BX.KLT.DINV.CD.WD')) + \
geom_point()
#pip install linearmodels #Run in terminal
from linearmodels import PanelOLS
import numpy as np
import matplotlib.pyplot as plt
import pandas_datareader
from pandas_datareader import wb
import seaborn as sns
###### a. Downloading inflation and unemployment data from World Bank ######
cntr_eu = ['DK', 'SE', 'FR', 'NL', 'DE', 'GB', 'BE', 'LU', 'AT',
'FI'] # Subset of countries affected by ECB's QE
cntr_other = ['CA', 'CH', 'AU', 'NZ', 'SG', 'NO', 'US', 'JP',
'KR'] # Subset of countries not affected by ECB's QE
infl_eu = wb.download(indicator='FP.CPI.TOTL.ZG',
country=cntr_eu,
start=1991,
end=2017)
infl_other = wb.download(indicator='FP.CPI.TOTL.ZG',
country=cntr_other,
start=1991,
end=2017)
unem_eu = wb.download(indicator='SL.UEM.TOTL.ZS',
country=cntr_eu,
start=1991,
end=2017)
unem_other = wb.download(indicator='SL.UEM.TOTL.ZS',
country=cntr_other,
start=1991,
end=2017)
df1.Price
# In[23]:
df1.Price.mean()
# In[27]:
get_ipython().system('pip3 install --upgrade pandas_datareader')
from pandas_datareader import data, wb
df_wb = wb.download(
# Specify indicator to retrieve
indicator='SP.POP.TOTL',
country=['all'],
# Start Year
start='2008',
# End Year
end=2016)
# In[28]:
df_wb.shape
# In[29]:
df_wb.head()
# In[ ]:
# In[36]:
# -*- coding: utf-8 -*-
"""
Created on Fri Oct 23 12:13:00 2020
@author: howard
美国、中国、日本近二十年人均GDP对比图
"""
from pandas_datareader import wb
import matplotlib.pyplot as plt
dat = wb.download(indicator='NY.GDP.PCAP.KD',
country=['US', 'CN', 'JP'],
start=2001,
end=2021)
dat2draw = dat.unstack(level=0)
plt.figure(figsize=(10, 4))
plt.plot(dat2draw.iloc[:, 0], 'r-', label="China")
plt.plot(dat2draw.iloc[:, 1], 'b-*', label="Japan")
plt.plot(dat2draw.iloc[:, 2], 'g--', label="USA")
plt.title("PER CAPITA GDP ($)", fontsize=20)
plt.legend()
plt.pause(0)
import matplotlib.pyplot as plt
import numpy as np
from pandas_datareader import wb
path = "https://github.com/omercadopopular/cgoes/blob/master/tutorial/python/statatopython/PPI_DB_082316.dta?raw=true"
cpisauce = "https://github.com/omercadopopular/cgoes/blob/master/tutorial/python/statatopython/CPIAUCSL.xls?raw=true"
gdpsauce = "https://github.com/omercadopopular/cgoes/blob/master/tutorial/python/statatopython/gdp.xlsx?raw=true"
#####################################
# 1. Retrieve Databases #############
#####################################
## 1.1 Import GDP data from the World Bank
wbdata = (wb.download(
indicator='NY.GDP.MKTP.CD', country='all', start=1994,
end=2015).dropna().rename(columns={'NY.GDP.MKTP.CD': 'gdp'}))
## 1.2 Read file from STATA dta
ppidf = pd.read_stata(path)
## 1.3 Import CPI data from excel file
## Note you have to skip 9 rows
cpi = pd.read_excel(cpisauce, skiprows=9, header=1)
#####################################
# 2. Adjust Databases ###############
#####################################
import warnings
warnings.simplefilter('ignore', FutureWarning)
from pandas_datareader import wb
import matplotlib.pyplot as plt
df = wb.download(indicator='SP.POP.TOTL', country=['JP', 'US'],
start=1960, end=2014)
print(df)
# SP.POP.TOTL
# country year
# Japan 2014 127276000
# 2013 127445000
# 2012 127629000
# 2011 127833000
# 2010 128070000
# ... ...
# United States 1964 191889000
# 1963 189242000
# 1962 186538000
# 1961 183691000
# 1960 180671000
#
# [110 rows x 1 columns]
df2 = df.unstack(level=0)
print(df2.head())
# SP.POP.TOTL
# country Japan United States
# year
#---- ch05/pandas-fred-ma
price['ma3'] = price.inflation.rolling(3, center=True).mean()
price['ma9'] = price.inflation.rolling(9, center=True).mean()
price
#---- ch05/pandas-fred-ma-plot/plot
ax = price.inflation.plot(alpha=0.2)
price[['ma3', 'ma9']].plot(ax = ax)
plt.show()
#---- ch05/wb-gdp
from pandas_datareader import wb
gdp = wb.download(indicator='NY.GDP.PCAP.CD', country='all',
start=1960, end=2010)
gdp
#---- ch05/wb-gdp-pivot
gdp_pivot = gdp.reset_index()
gdp_pivot['NY.GDP.PCAP.CD'] = np.log(gdp_pivot['NY.GDP.PCAP.CD'])
gdp_pivot = gdp_pivot.pivot(index='year', columns='country',
values='NY.GDP.PCAP.CD')
gdp_pivot.index = gdp_pivot.index.astype('uint64')
#---- ch05/wb-gdp-pivot/dnr
gdp_pivot
start = dt.datetime(2010, 1, 1) # start date
codes = ['GDPC1', 'PCECC96'] # real GDP, real consumption
fred = data.DataReader(codes, 'fred', start)
fred = fred/1000 # convert billions to trillions
fred.plot()
#%%
# World Bank
from pandas_datareader import wb # World Bank api
var = ['NY.GDP.PCAP.PP.KD'] # GDP per capita
iso = ['USA', 'FRA', 'JPN', 'CHN', 'IND', 'BRA', 'MEX'] # country codes
year = 2013
wbdf = wb.download(indicator=var, country=iso, start=year, end=year)
#%%
wbdf = wbdf.reset_index(level='year', drop=True)
wbdf.plot(kind='barh')
#%%
# Fama-French equity returns
from pandas_datareader import data # Package to access FF
ff = data.DataReader('F-F_Research_Data_factors', 'famafrench')[0]
ff.columns = ['xsm', 'smb', 'hml', 'rf'] # rename variables
#%%
"""
Review
import pandas as pd
from pandas_datareader import wb
import matplotlib.pyplot as plt
mathces = wb.search('gdp.*capita.*const')
dat = wb.download(indicator='NY.GDP.PCAP.KD',
country='CN',
start=2010,
end=2017)
data = dat.stack()
print(data)
data.plot(kind='line')
plt.show()
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import ipywidgets as widgets
#continents = ['DK','ZA','US','GB','CN','IN','BR','CA','RU','TR','KR','VN','SE','DE','AL','FR','BG','IT','PK','ID','MX','PL']
continents = ['WLD', 'TSA', 'TMN', 'ECS', 'SSF', 'NAC', 'LCN']
from pandas_datareader import wb
pop = wb.download(indicator='SP.POP.TOTL', country=continents, start=1970, end=2015)
pop.head(3)
gdp = wb.download(indicator='NY.GDP.MKTP.KD', country=continents, start=1970, end=2015)
gdp.head(3)
# Merging data:
merged = pd.merge(gdp,pop, how='inner', on=['country','year'])
merged = merged.reset_index()
merged = merged.rename(columns = {'country' : 'continent', 'NY.GDP.MKTP.KD' : 'gdp', 'SP.POP.TOTL' : 'pop'})
merged['gdp_cap'] = merged['gdp'] / merged['pop']
# Sorting data:
merged.sort_values(by=['continent','year'], inplace=True)
merged = merged.reset_index(drop = True)
merged.head()
# Indexing:
x11.append(j)
x1=np.array(x11)
y1=np.array(y11)
if len(y1)>4:
m=((x1.mean()*y1.mean())-(x1*y1).mean())/((x1.mean()*x1.mean())-(x1*x1).mean())
b=y1.mean()-(m*x1.mean())
return (m*p)+b
else:
return y1.mean()
clmns=[] #Stores names of all the columns used
'''Initiating Dataset with ease of doing business'''
indic="Ease of Doing Business"
clmns.append(indic)
maindata=wb.download(country=u"all", indicator="IC.BUS.EASE.XQ",start=strtyear, end=now.year)
maindata.columns=[indic]
maindata['Country']=[i[0] for i in maindata.index]
maindata['Year']=[i[1] for i in maindata.index]
maindata['Year']=maindata['Year'].apply(int)
maindata = maindata.groupby("Country").transform(lambda x: x.iloc[::-1])
maindata['Country']=[i[0] for i in maindata.index]
maindata=maindata[["Country","Year",indic]]
maindata=maindata[658:]
maindata[indic]=maindata[indic].replace(0, np.nan)
maindata[indic] = maindata.groupby("country")[indic].transform(lambda x: x.fillna(x.mean()))
'''Function to append Features'''
def featureappnd(ind,nm,ft):
clmns.append(nm)
tmpdt=wb.download(country=u"all", indicator=ind,start=strtyear, end=now.year)
def country_DataFrame_to_list(country, target_data): df = wb.download(indicator = target_data, country = country, start = 2008, end = 2018) df.fillna(df.mean(), inplace = True) df_list =df[df.columns[0]].tolist() round_list = [round(i, 2) for i in df_list ] return round_list[::-1]
#import matplotlib.pyplot as plt
from pandas_datareader import wb
import quandl
##GETTING DATA FROM WEB#####
tickers = "BRJ8"
startDate = '2018-1-1'
endDate = dt.datetime.today()
mgWeb = web.DataReader(tickers, 'moex', startDate, endDate)
mgWeb.to_excel('recData/BRENT_FUTURE_from_web.xlsx')
####GETTING DATA FROM MICROSOFT####
tickers = ['^SPX']
dataSource = 'stooq'
startDate = '2018-1-1'
endDate = dt.datetime.today()
gWeb = web.DataReader(tickers, dataSource, startDate, endDate)
gWeb.to_excel('recData/SP500_from_web.xlsx')
worldBank = wb.download(indicator='NY.GDP.MKTP.CD', country=[
'RU'], start=2005, end=2008)
worldBank.to_excel('recData/WB_from_web.xlsx')
keyIndicies = quandl.get('BANKRUSSIA/KEYECIND')
keyIndicies.to_excel('recData/CB_from_web.xlsx')
mgWeb = mgWeb[['VALUE', 'OPEN', 'LOW']]
mgWeb = mgWeb.assign(LowInUSD=mgWeb['LOW']/57)
mgWeb = mgWeb.assign(Numbers=mgWeb['VALUE']/mgWeb['LOW'])
print(mgWeb)
