def _min_max_sd(self, forecast, tamconfig, data_sources):
"""Return the min, max, and standard deviation for TAM data.
Arguments:
forecast: the TAM forecast dataframe for all sources.
tamconfig: the row from self.tamconfig to use
data_sources: dict of dicts of datasources, as described in tam_ref_data_sources in
the constructor
"""
source_until_2014 = tamconfig['source_until_2014']
source_after_2014 = tamconfig['source_after_2014']
result = pd.DataFrame(np.nan, index=forecast.index.copy(), columns=['Min', 'Max', 'S.D'])
result.loc[:, 'Min'] = forecast.dropna(axis='columns', how='all').min(axis=1)
result.loc[:, 'Max'] = forecast.max(axis=1)
if forecast.empty:
# Some solutions provide no data sources for PDS
result.loc[:, 'S.D'] = np.nan
else:
columns = interpolation.matching_data_sources(data_sources=data_sources,
name=source_until_2014, groups_only=True)
# Excel STDDEV.P is a whole population stddev, ddof=0
m = forecast.loc[:2014, columns].dropna(axis='columns', how='all').std(axis=1, ddof=0)
m.name = 'S.D'
result.update(m)
columns = interpolation.matching_data_sources(data_sources=data_sources,
name=source_after_2014, groups_only=True)
m = forecast.loc[2015:, columns].dropna(axis='columns', how='all').std(axis=1, ddof=0)
m.name = 'S.D'
result.update(m)
return result
def _min_max_sd(self, forecast, tamconfig, data_sources, region):
"""Return the min, max, and standard deviation for TAM data.
Arguments:
forecast: the TAM forecast dataframe for all sources.
tamconfig: the row from self.tamconfig to use
data_sources: dict of dicts of datasources, as described in tam_ref_data_sources in
the constructor
region: the name of the region to match, like 'OECD90' or 'Latin America'. Can
be None, which will use the top level ('World') data_sources.
"""
source_until_2014 = tamconfig['source_until_2014']
source_after_2014 = tamconfig['source_after_2014']
result = pd.DataFrame(np.nan, index=forecast.index.copy(), columns=['Min', 'Max', 'S.D'])
result.loc[:, 'Min'] = forecast.dropna(axis='columns', how='all').min(axis=1)
result.loc[:, 'Max'] = forecast.max(axis=1)
if forecast.empty:
# Some solutions provide no data sources for PDS
result.loc[:, 'S.D'] = np.nan
else:
region_key = None if region is None else f'Region: {region}'
columns = interpolation.matching_data_sources(data_sources=data_sources,
name=source_until_2014, groups_only=True, region_key=region_key)
# Excel STDDEV.P is a whole population stddev, ddof=0
m = forecast.loc[:2014, columns].dropna(axis='columns', how='all').std(axis=1, ddof=0)
m.name = 'S.D'
result.update(m)
columns = interpolation.matching_data_sources(data_sources=data_sources,
name=source_after_2014, groups_only=True, region_key=region_key)
m = forecast.loc[2015:, columns].dropna(axis='columns', how='all').std(axis=1, ddof=0)
m.name = 'S.D'
result.update(m)
return result
def _low_med_high(self, forecast, min_max_sd, tamconfig, data_sources):
"""Return the selected data sources as Medium, and N stddev away as Low and High.
Arguments:
forecast: DataFrame of all of the data sources, source name as the column name.
min_max_sd: DataFrame with columns for the Minimum, Maxiumum, and Standard deviation.
tamconfig: the row from self.tamconfig to use
data_sources: dict of dicts of datasources, as described in tam_ref_data_sources in
the constructor
"""
result = pd.DataFrame(np.nan, index=forecast.index.copy(),
columns=['Low', 'Medium', 'High'])
if forecast.empty:
result.loc[:, 'Medium'] = np.nan
result.loc[:, 'Low'] = np.nan
result.loc[:, 'High'] = np.nan
return result
columns = interpolation.matching_data_sources(data_sources=data_sources,
name=tamconfig['source_until_2014'], groups_only=False)
if columns and len(columns) > 1:
# In Excel, the Mean computation is:
# SUM($C521:$Q521)/COUNTIF($C521:$Q521,">0")
#
# The intent is to skip sources which are empty, but also means that
# a source where the real data is 0.0 will not impact the Medium result.
#
# See this document for more information:
# https://docs.google.com/document/d/19sq88J_PXY-y_EnqbSJDl0v9CdJArOdFLatNNUFhjEA/edit#heading=h.yvwwsbvutw2j
#
# We're matching the Excel behavior in the initial product. This decision can
# be revisited later, when matching results from Excel is no longer required.
# To revert, use: m = forecast.loc[:2014, columns].mean(axis=1)
# and: m = forecast.loc[2015:, columns].mean(axis=1)
m = forecast.loc[:2014, columns].mask(lambda f: f == 0.0, np.nan).mean(axis=1)
m.name = 'Medium'
result.update(m)
elif columns and len(columns) == 1:
m = forecast.loc[:2014, columns].mean(axis=1)
m.name = 'Medium'
result.update(m)
columns = interpolation.matching_data_sources(data_sources=data_sources,
name=tamconfig['source_after_2014'], groups_only=False)
if columns and len(columns) > 1:
# see comment above about Mean and this lambda function
m = forecast.loc[2015:, columns].mask(lambda f: f == 0.0, np.nan).mean(axis=1)
m.name = 'Medium'
result.update(m)
elif columns and len(columns) == 1:
m = forecast.loc[2015:, columns].mean(axis=1)
m.name = 'Medium'
result.update(m)
low_sd_mult = tamconfig['low_sd_mult']
high_sd_mult = tamconfig['high_sd_mult']
result.loc[:, 'Low'] = result.loc[:, 'Medium'] - (min_max_sd.loc[:, 'S.D'] * low_sd_mult)
result.loc[:, 'High'] = result.loc[:, 'Medium'] + (min_max_sd.loc[:, 'S.D'] * high_sd_mult)
return result
def _low_med_high(self, adoption_data, min_max_sd, adconfig, source,
data_sources):
"""Return the selected data sources as Medium, and N stddev away as Low and High."""
result = pd.DataFrame(index=adoption_data.index.copy(),
columns=['Low', 'Medium', 'High'])
columns = interpolation.matching_data_sources(
data_sources=data_sources, name=source, groups_only=False)
if columns is None:
result.loc[:, 'Medium'] = np.nan
result.loc[:, 'Low'] = np.nan
result.loc[:, 'High'] = np.nan
else:
# In Excel, the Mean computation is:
# SUM($C46:$Q46)/COUNTIF($C46:$Q46,">0")
#
# The intent is to skip sources which are empty, but also means that
# a source where the real data is 0.0 will not impact the Medium result.
#
# See this document for more information:
# https://docs.google.com/document/d/19sq88J_PXY-y_EnqbSJDl0v9CdJArOdFLatNNUFhjEA/edit#heading=h.yvwwsbvutw2j
#
# We're matching the Excel behavior in the initial product. This decision can
# be revisited later, when matching results from Excel is no longer required.
# To revert, use: medium = adoption_data.loc[:, columns].mean(axis=1)
medium = adoption_data.loc[:,
columns].mask(lambda f: f == 0.0,
np.nan).mean(axis=1)
result.loc[:, 'Medium'] = medium
result.loc[:, 'Low'] = medium - (min_max_sd.loc[:, 'S.D'] *
adconfig.loc['low_sd_mult'])
result.loc[:, 'High'] = medium + (min_max_sd.loc[:, 'S.D'] *
adconfig.loc['high_sd_mult'])
return result
def _min_max_sd(self, adoption_data, source, data_sources, region):
"""Return the min, max, and standard deviation for adoption data."""
result = pd.DataFrame(index=adoption_data.index.copy(), columns=['Min', 'Max', 'S.D'])
result.loc[:, 'Min'] = adoption_data.min(axis=1)
result.loc[:, 'Max'] = adoption_data.max(axis=1)
region_key = None if region is None else f'Region: {region}'
columns = interpolation.matching_data_sources(data_sources=data_sources, name=source,
groups_only=False, region_key=region_key)
if columns is None:
result.loc[:, 'S.D'] = np.nan
elif len(columns) > 1:
# Excel STDDEV.P is a whole population stddev, ddof=0
result.loc[:, 'S.D'] = adoption_data.loc[:, columns].std(axis=1, ddof=0)
else:
result.loc[:, 'S.D'] = adoption_data.std(axis=1, ddof=0)
return result