def _set_params(self):
"""
Set input parameters based on the request.
Parameters implemented for the Prophet() function are: growth, cap, floor, changepoint_prior_scale, interval_width
Parameters implemented for the make_future_dataframe() function are: freq, periods
Parameters implemented for seasonality are: add_seasonality, seasonality_period, seasonality_fourier, seasonality_prior_scale
Parameters implemented for holidays are: holidays_prior_scale, lower_window, upper_window
Additional parameters for seasonlity requests are: weekly_start, yearly_start
Additional parameters used are: return, take_log, seasonality, debug
"""
# Calculate the forecast periods based on the number of placeholders in the data
self.periods = utils.count_placeholders(self.request_df.loc[:,'y'])
# Set the row count in the original request
self.request_row_count = len(self.request_df) + len(self.NaT_df)
# Set default values which will be used if an argument is not passed
self.result_type = 'yhat'
self.take_log = False
self.seasonality = 'yearly'
self.debug = False
self.freq = 'D'
self.cap = None
self.floor = None
self.growth = None
self.changepoint_prior_scale = None
self.interval_width = None
self.name = None
self.period = None
self.fourier_order = None
self.seasonality_prior_scale = None
self.holidays_prior_scale = None
self.is_seasonality_request = False
self.weekly_start = 6 # Defaulting to a Monday start for the week as used in Qlik
self.yearly_start = 0
self.lower_window = None
self.upper_window = None
# Set optional parameters
# Check if there is a fourth column in the request
try:
# If there is a fourth column, it is assumed to contain the key word arguments
args = self.request[0].rows[0].duals[3].strData
# The third column should then provide the holiday name or null for each row
self.has_holidays = True
except IndexError:
# If there is no fourth column, the request does not include holidays
self.has_holidays = False
# If the fourth column did not exist, we try again with the third column
if not self.has_holidays:
try:
args = self.request[0].rows[0].duals[2].strData
except IndexError:
args = None
# If the key word arguments were included in the request, get the parameters and values
if args is not None:
# The parameter and values are transformed into key value pairs
args = args.translate(str.maketrans('', '', string.whitespace)).split(",")
self.kwargs = dict([arg.split("=") for arg in args])
# Make sure the key words are in lower case
self.kwargs = {k.lower(): v for k, v in self.kwargs.items()}
# Set the return type
# Valid values are: yhat, trend, seasonal, seasonalities.
# Add _lower or _upper to the series name to get lower or upper limits.
if 'return' in self.kwargs:
self.result_type = self.kwargs['return'].lower()
# Set the option to take a logarithm of y values before forecast calculations
# Valid values are: true, false
if 'take_log' in self.kwargs:
self.take_log = 'true' == self.kwargs['take_log'].lower()
# Set the type of seasonlity requested. Used only for seasonality requests
# Valid values are: yearly, weekly, monthly, holidays
if 'seasonality' in self.kwargs:
self.seasonality = self.kwargs['seasonality'].lower()
# Set the debug option for generating execution logs
# Valid values are: true, false
if 'debug' in self.kwargs:
self.debug = 'true' == self.kwargs['debug'].lower()
# Set the frequency of the timeseries
# Any valid frequency for pd.date_range, such as 'D' or 'M'
# For options see: http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases
if 'freq' in self.kwargs:
self.freq = self.kwargs['freq']
# Set the cap which adds an upper limit at which the forecast will saturate
# This changes the default linear growth model to a logistic growth model
if 'cap' in self.kwargs:
self.cap = float(self.kwargs['cap'])
self.growth = 'logistic'
# Set the floor which adds a lower limit at which the forecast will saturate
# To use a logistic growth trend with a floor, a cap must also be specified
if 'floor' in self.kwargs:
self.floor = float(self.kwargs['floor'])
# Set the changepoint_prior_scale to adjust the trend flexibility
# If the trend changes are being overfit (too much flexibility) or underfit (not enough flexibility),
# you can adjust the strength of the sparse prior.
# Default value is 0.05. Increasing it will make the trend more flexible.
if 'changepoint_prior_scale' in self.kwargs:
self.changepoint_prior_scale = float(self.kwargs['changepoint_prior_scale'])
# Set the width for the uncertainty intervals
# Default value is 0.8 (i.e. 80%)
if 'interval_width' in self.kwargs:
self.interval_width = float(self.kwargs['interval_width'])
# Set additional seasonality to be added to the model
# Default seasonalities are yearly and weekly, as well as daily for sub daily data
if 'add_seasonality' in self.kwargs:
self.name = self.kwargs['add_seasonality'].lower()
# Set the seasonality period
# e.g. 30.5 for 'monthly' seasonality
if 'seasonality_period' in self.kwargs:
self.period = float(self.kwargs['seasonality_period'])
# Set the seasonality fourier terms
# Increasing the number of Fourier terms allows the seasonality to fit faster changing cycles,
# but can also lead to overfitting
if 'seasonality_fourier' in self.kwargs:
self.fourier_order = int(self.kwargs['seasonality_fourier'])
# Set the seasonality prior scale to smooth seasonality effects.
# Reducing this parameter dampens seasonal effects
if 'seasonality_prior_scale' in self.kwargs:
self.seasonality_prior_scale = float(self.kwargs['seasonality_prior_scale'])
# Set the holiday prior scale to smooth holiday effects.
# Reducing this parameter dampens holiday effects. Default is 10, which provides very little regularization.
if 'holidays_prior_scale' in self.kwargs:
self.holidays_prior_scale = float(self.kwargs['holidays_prior_scale'])
# Set the weekly start for 'weekly' seasonality requests
# Default week start is 0 which represents Sunday. Add offset as required.
if 'weekly_start' in self.kwargs:
self.weekly_start = int(self.kwargs['weekly_start'])
# Set the weekly start for 'yearly' seasonality requests
# Default week start is 0 which represents 1st of Jan. Add offset as required.
if 'yearly_start' in self.kwargs:
self.yearly_start = int(self.kwargs['yearly_start'])
# Set a period to extend the holidays by lower_window number of days before the date.
# This can be used to extend the holiday effect
if 'lower_window' in self.kwargs:
self.lower_window = int(self.kwargs['lower_window'])
# Set a period to extend the holidays by upper_window number of days after the date.
# This can be used to extend the holiday effect
if 'upper_window' in self.kwargs:
self.upper_window = int(self.kwargs['upper_window'])
# Create dictionary of arguments for the Prophet(), make_future_dataframe() and add_seasonality() functions
self.prophet_kwargs = {}
self.make_kwargs = {}
self.add_seasonality_kwargs = {}
# Populate the parameters in the corresponding dictionary:
# Set up a list of possible key word arguments for the Prophet() function
prophet_params = ['growth', 'changepoint_prior_scale', 'interval_width', 'seasonality_prior_scale',\
'holidays_prior_scale']
# Create dictionary of key word arguments for the Prophet() function
self.prophet_kwargs = self._populate_dict(prophet_params)
# Set up a list of possible key word arguments for the make_future_dataframe() function
make_params = ['periods', 'freq']
# Create dictionary of key word arguments for the make_future_dataframe() function
self.make_kwargs = self._populate_dict(make_params)
# Set up a list of possible key word arguments for the add_seasonality() function
seasonality_params = ['name', 'period', 'fourier_order']
# Create dictionary of key word arguments for the add_seasonality() function
self.add_seasonality_kwargs = self._populate_dict(seasonality_params)
def _set_params(self):
"""
Set input parameters based on the request.
Parameters implemented for the Prophet() function are: growth, cap, floor, changepoint_prior_scale, interval_width
Parameters implemented for the make_future_dataframe() function are: freq, periods
Parameters implemented for seasonality are: add_seasonality, seasonality_period, seasonality_fourier, seasonality_prior_scale
Parameters implemented for holidays are: holidays_prior_scale, lower_window, upper_window
Additional parameters for seasonlity requests are: weekly_start, yearly_start
Additional parameters used are: return, take_log, seasonality, debug
"""
# Calculate the forecast periods based on the number of placeholders in the data
self.periods = utils.count_placeholders(self.request_df.loc[:, 'y'])
# Set the row count in the original request
self.request_row_count = len(self.request_df) + len(self.NaT_df)
# Set default values which will be used if an argument is not passed
self.load_script = False
self.result_type = 'yhat'
self.take_log = False
self.seasonality = 'yearly'
self.seasonality_mode = None
self.debug = False
self.freq = 'D'
self.cap = None
self.floor = None
self.growth = None
self.changepoint_prior_scale = None
self.interval_width = None
self.name = None
self.period = None
self.fourier_order = None
self.mode = None
self.seasonality_prior_scale = None
self.holidays_prior_scale = None
self.mcmc_samples = None
self.seed = None
self.n_changepoints = None
self.changepoint_range = None
self.uncertainty_samples = None
self.is_seasonality_request = False
self.weekly_start = 1 # Defaulting to a Monday start for the week as used in Qlik
self.yearly_start = 0
self.lower_window = None
self.upper_window = None
# Set optional parameters
# Check the number of columns in the request to determine whether we have holidays and/or added regressors
cols = len(self.request[0].rows[0].duals)
self.has_holidays = False
self.has_regressors = False
# If we receive five columns, we expect both holidays and additional regressors
if cols == 6:
self.has_regressors = True
# For a request with four columns, we only expect holidays
if cols >= 4:
self.has_holidays = True
# If there are three or more columns, the last column should contain the key word arguments
if cols < 3:
args = None
else:
args = self.request[0].rows[0].duals[cols - 1].strData
# If the key word arguments were included in the request, get the parameters and values
if args is not None:
# The parameter and values are transformed into key value pairs
args = args.translate(str.maketrans('', '',
string.whitespace)).split(",")
self.kwargs = dict([arg.split("=") for arg in args])
# Make sure the key words are in lower case
self.kwargs = {k.lower(): v for k, v in self.kwargs.items()}
# Set the load_script parameter to determine the output format
# Set to 'true' if calling the functions from the load script in the Qlik app
if 'load_script' in self.kwargs:
self.load_script = 'true' == self.kwargs['load_script'].lower()
# Set the return type
# Valid values are: yhat, trend, seasonal, seasonalities, all, y_then_yhat, residual.
# Add _lower or _upper to the series name to get lower or upper limits.
# The special case of 'all' returns all output columns from Prophet. This can only be used with 'load_script=true'.
# 'y_then_yhat' returns actual values for historical periods and forecast values for future periods
# 'residual' returns y - yhat for historical periods
if 'return' in self.kwargs:
self.result_type = self.kwargs['return'].lower()
# Set a flag to return the seasonality plot instead
# Only usable through the load script as the result will have a different cardinality to the request
if 'is_seasonality_request' in self.kwargs:
self.is_seasonality_request = 'true' == self.kwargs[
'is_seasonality_request'].lower()
self.load_script = True
# Set the option to take a logarithm of y values before forecast calculations
# Valid values are: true, false
if 'take_log' in self.kwargs:
self.take_log = 'true' == self.kwargs['take_log'].lower()
# Set the type of seasonlity requested. Used only for seasonality requests
# Valid values are: yearly, weekly, monthly, holidays
if 'seasonality' in self.kwargs:
self.seasonality = self.kwargs['seasonality'].lower()
# Set the seasonlity mode. Useful if the seasonality is not a constant additive factor as assumed by Prophet
# Valid values are: additive, multiplicative
if 'seasonality_mode' in self.kwargs:
self.seasonality_mode = self.kwargs['seasonality_mode'].lower()
# Set the debug option for generating execution logs
# Valid values are: true, false
if 'debug' in self.kwargs:
self.debug = 'true' == self.kwargs['debug'].lower()
# Set the frequency of the timeseries
# Any valid frequency for pd.date_range, such as 'D' or 'M'
# For options see: http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases
if 'freq' in self.kwargs:
self.freq = self.kwargs['freq']
# Set the cap which adds an upper limit at which the forecast will saturate
# This changes the default linear growth model to a logistic growth model
if 'cap' in self.kwargs:
self.cap = utils.atof(self.kwargs['cap'])
self.growth = 'logistic'
# Set the floor which adds a lower limit at which the forecast will saturate
# To use a logistic growth trend with a floor, a cap must also be specified
if 'floor' in self.kwargs:
self.floor = utils.atof(self.kwargs['floor'])
# Set the changepoint_prior_scale to adjust the trend flexibility
# If the trend changes are being overfit (too much flexibility) or underfit (not enough flexibility),
# you can adjust the strength of the sparse prior.
# Default value is 0.05. Increasing it will make the trend more flexible.
if 'changepoint_prior_scale' in self.kwargs:
self.changepoint_prior_scale = utils.atof(
self.kwargs['changepoint_prior_scale'])
# Set the width for the uncertainty intervals
# Default value is 0.8 (i.e. 80%)
if 'interval_width' in self.kwargs:
self.interval_width = utils.atof(self.kwargs['interval_width'])
# Set additional seasonality to be added to the model
# Default seasonalities are yearly and weekly, as well as daily for sub daily data
if 'add_seasonality' in self.kwargs:
self.name = self.kwargs['add_seasonality'].lower()
# Set 'additive' or 'multiplicative' mode for the additional seasonality
# Default value follows the seasonality_mode parameter
if 'add_seasonality_mode' in self.kwargs:
self.mode = self.kwargs['add_seasonality_mode'].lower()
# Set the seasonality period
# e.g. 30.5 for 'monthly' seasonality
if 'seasonality_period' in self.kwargs:
self.period = utils.atof(self.kwargs['seasonality_period'])
# Set the seasonality fourier terms
# Increasing the number of Fourier terms allows the seasonality to fit faster changing cycles,
# but can also lead to overfitting
if 'seasonality_fourier' in self.kwargs:
self.fourier_order = int(self.kwargs['seasonality_fourier'])
# Set the seasonality prior scale to smooth seasonality effects.
# Reducing this parameter dampens seasonal effects
if 'seasonality_prior_scale' in self.kwargs:
self.seasonality_prior_scale = utils.atof(
self.kwargs['seasonality_prior_scale'])
# Set the holiday prior scale to smooth holiday effects.
# Reducing this parameter dampens holiday effects. Default is 10, which provides very little regularization.
if 'holidays_prior_scale' in self.kwargs:
self.holidays_prior_scale = utils.atof(
self.kwargs['holidays_prior_scale'])
# Set the number of MCMC samples.
# If greater than 0, Prophet will do full Bayesian inference with the specified number of MCMC samples.
# If 0, Prophet will do MAP estimation. Default is 0.
if 'mcmc_samples' in self.kwargs:
self.mcmc_samples = utils.atoi(self.kwargs['mcmc_samples'])
# Random seed that can be used to control stochasticity.
# Used for setting the numpy random seed used in predict and also for pystan when using mcmc_samples>0.
if 'random_seed' in self.kwargs:
self.seed = utils.atoi(self.kwargs['random_seed'])
# Set the random seed for numpy
np.random.seed(self.seed)
# Number of potential changepoints to include. Default value is 25.
# Potential changepoints are selected uniformly from the first `changepoint_range` proportion of the history.
if 'n_changepoints' in self.kwargs:
self.n_changepoints = utils.atoi(self.kwargs['n_changepoints'])
# Proportion of history in which trend changepoints will be estimated.
# Defaults to 0.8 for the first 80%.
if 'changepoint_range' in self.kwargs:
self.changepoint_range = utils.atof(
self.kwargs['changepoint_range'])
# Number of simulated draws used to estimate uncertainty intervals.
if 'uncertainty_samples' in self.kwargs:
self.uncertainty_samples = utils.atoi(
self.kwargs['uncertainty_samples'])
# Set the weekly start for 'weekly' seasonality requests
# Default week start is 0 which represents Sunday. Add offset as required.
if 'weekly_start' in self.kwargs:
self.weekly_start = utils.atoi(self.kwargs['weekly_start'])
# Set the weekly start for 'yearly' seasonality requests
# Default week start is 0 which represents 1st of Jan. Add offset as required.
if 'yearly_start' in self.kwargs:
self.yearly_start = utils.atoi(self.kwargs['yearly_start'])
# Set a period to extend the holidays by lower_window number of days before the date.
# This can be used to extend the holiday effect
if 'lower_window' in self.kwargs:
self.lower_window = utils.atoi(self.kwargs['lower_window'])
# Set a period to extend the holidays by upper_window number of days after the date.
# This can be used to extend the holiday effect
if 'upper_window' in self.kwargs:
self.upper_window = utils.atoi(self.kwargs['upper_window'])
# Create dictionary of arguments for the Prophet(), make_future_dataframe(), add_seasonality() and fit() functions
self.prophet_kwargs = {}
self.make_kwargs = {}
self.add_seasonality_kwargs = {}
self.fit_kwargs = {}
# Populate the parameters in the corresponding dictionary:
# Set up a list of possible key word arguments for the Prophet() function
prophet_params = ['seasonality_mode', 'growth', 'changepoint_prior_scale', 'interval_width',\
'seasonality_prior_scale', 'holidays_prior_scale', 'mcmc_samples', 'n_changepoints',\
'changepoint_range', 'uncertainty_samples']
# Create dictionary of key word arguments for the Prophet() function
self.prophet_kwargs = self._populate_dict(prophet_params)
# Set up a list of possible key word arguments for the make_future_dataframe() function
make_params = ['periods', 'freq']
# Create dictionary of key word arguments for the make_future_dataframe() function
self.make_kwargs = self._populate_dict(make_params)
# Set up a list of possible key word arguments for the add_seasonality() function
seasonality_params = ['name', 'period', 'fourier_order', 'mode']
# Create dictionary of key word arguments for the add_seasonality() function
self.add_seasonality_kwargs = self._populate_dict(seasonality_params)
# Pass the random seed to the fit method if MCMC is being used
if self.mcmc_samples is not None and self.mcmc_samples > 0:
# Set up a list of possible key word arguments for the fit() function
fit_params = ['seed']
# Create dictionary of key word arguments for the fit() function
self.fit_kwargs = self._populate_dict(fit_params)