def _set_params(self, kwargs):
"""
Set input parameters based on the request.
:
:Parameters implemented for the HDBSCAN() function are: algorithm, metric, min_cluster_size, min_samples,
:p, alpha, cluster_selection_method, allow_single_cluster, match_reference_implementation.
:More information here: https://hdbscan.readthedocs.io/en/latest/api.html#hdbscan
:
:Scaler types implemented for preprocessing data are: StandardScaler, MinMaxScaler, MaxAbsScaler,
:RobustScaler and QuantileTransformer.
:More information here: http://scikit-learn.org/stable/modules/preprocessing.html
:
:Additional parameters used are: load_script, return, missing, scaler, debug
"""
# Set the row count in the original request
self.request_row_count = len(self.request_df) + len(self.NaN_df)
# Set default values which will be used if arguments are not passed
# SSE parameters:
self.load_script = False
self.result_type = 'labels_'
self.missing = 'zeros'
self.scaler = 'robust'
self.debug = False
# HDBSCAN parameters:
self.algorithm = None
self.metric = None
self.min_cluster_size = None
self.min_samples = None
self.p = None
self.alpha = None
self.cluster_selection_method = None
self.allow_single_cluster = None
self.match_reference_implementation = None
# Standard scaler parameters:
self.with_mean = None
self.with_std = None
# MinMaxScaler scaler parameters:
self.feature_range = None
# Robust scaler parameters:
self.with_centering = None
self.with_scaling = None
self.quantile_range = None
# Quantile Transformer parameters:
self.n_quantiles = None
self.output_distribution = None
self.ignore_implicit_zeros = None
self.subsample = None
self.random_state = None
# Adjust default options if variant is two_dims
if self.variant == "two_dims":
self.load_script = True
# Adjust default options if variant is lat_long
elif self.variant == "lat_long":
self.scaler = "none"
self.metric = "haversine"
# Set optional parameters
# If the key word arguments were included in the request, get the parameters and values
if len(kwargs) > 0:
# The parameter and values are transformed into key value pairs
args = kwargs.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: labels, probabilities, cluster_persistence, outlier_scores
if 'return' in self.kwargs:
self.result_type = self.kwargs['return'].lower() + '_'
# Set the strategy for missing data
# Valid values are: zeros, mean, median, mode
if 'missing' in self.kwargs:
self.missing = self.kwargs['missing'].lower()
# Set the standardization strategy for the data
# Valid values are: standard, minmax, maxabs, robust, quantile, none
if 'scaler' in self.kwargs:
self.scaler = self.kwargs['scaler'].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 optional parameters for the HDBSCAN algorithmn
# For documentation see here: https://hdbscan.readthedocs.io/en/latest/api.html#id20
# Options are: best, generic, prims_kdtree, prims_balltree, boruvka_kdtree, boruvka_balltree
# Default is 'best'.
if 'algorithm' in self.kwargs:
self.algorithm = self.kwargs['algorithm'].lower()
# The metric to use when calculating distance between instances in a feature array.
# More information here: https://hdbscan.readthedocs.io/en/latest/basic_hdbscan.html#what-about-different-metrics
# And here: http://scikit-learn.org/stable/modules/generated/sklearn.neighbors.DistanceMetric.html
# Default is 'euclidean' for 'standard' and 'two_dims' variants, and 'haversine' for the lat_long variant.
if 'metric' in self.kwargs:
self.metric = self.kwargs['metric'].lower()
# The minimum size of clusters.
# The default value is 5.
if 'min_cluster_size' in self.kwargs:
self.min_cluster_size = utils.atoi(
self.kwargs['min_cluster_size'])
# The number of samples in a neighbourhood for a point to be considered a core point.
if 'min_samples' in self.kwargs:
self.min_samples = utils.atoi(self.kwargs['min_samples'])
# p value to use if using the minkowski metric.
if 'p' in self.kwargs:
self.p = utils.atoi(self.kwargs['p'])
# A distance scaling parameter as used in robust single linkage.
if 'alpha' in self.kwargs:
self.alpha = utils.atof(self.kwargs['alpha'])
# The method used to select clusters from the condensed tree.
# Options are: eom, leaf.
if 'cluster_selection_method' in self.kwargs:
self.cluster_selection_method = self.kwargs[
'cluster_selection_method'].lower()
# By default HDBSCAN* will not produce a single cluster.
# Setting this to True will override this and allow single cluster results.
if 'allow_single_cluster' in self.kwargs:
self.allow_single_cluster = 'true' == self.kwargs[
'allow_single_cluster'].lower()
# There exist some interpretational differences between this HDBSCAN implementation
# and the original authors reference implementation in Java.
# Note that there is a performance cost for setting this to True.
if 'match_reference_implementation' in self.kwargs:
self.match_reference_implementation = 'true' == self.kwargs[
'match_reference_implementation']
# Set optional parameters for the scaler functions
# Parameters for the Standard scaler
# http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html
if self.scaler == 'standard':
if 'with_mean' in self.kwargs:
self.with_mean = 'true' == self.kwargs['with_mean'].lower()
if 'with_std' in self.kwargs:
self.with_std = 'true' == self.kwargs['with_std'].lower()
# Parameters for the MinMax scaler
# http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.MinMaxScaler.html
if self.scaler == 'minmax':
if 'feature_range' in self.kwargs:
self.feature_range = ''.join(
c for c in self.kwargs['feature_range']
if c not in '()').split(';')
self.feature_range = (utils.atoi(self.feature_range[0]),
utils.atoi(self.feature_range[1]))
# Parameters for the Robust scaler
# http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.RobustScaler.html
if self.scaler == 'robust':
if 'with_centering' in self.kwargs:
self.with_centering = 'true' == self.kwargs[
'with_centering'].lower()
if 'with_scaling' in self.kwargs:
self.with_scaling = 'true' == self.kwargs[
'with_scaling'].lower()
if 'quantile_range' in self.kwargs:
self.quantile_range = ''.join(
c for c in self.kwargs['quantile_range']
if c not in '()').split(';')
self.quantile_range = (utils.atof(self.quantile_range[0]),
utils.atof(self.quantile_range[1]))
# Parameters for the Quantile Transformer
# http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.QuantileTransformer.html
if self.scaler == 'quantile':
if 'n_quantiles' in self.kwargs:
self.n_quantiles = utils.atoi(self.kwargs['n_quantiles'])
if 'output_distribution' in self.kwargs:
self.output_distribution = self.kwargs[
'output_distribution'].lower()
if 'ignore_implicit_zeros' in self.kwargs:
self.ignore_implicit_zeros = 'true' == self.kwargs[
'ignore_implicit_zeros'].lower()
if 'subsample' in self.kwargs:
self.subsample = utils.atoi(self.kwargs['subsample'])
if 'random_state' in self.kwargs:
self.random_state = utils.atoi(self.kwargs['random_state'])
# Set up a list of possible key word arguments for the HDBSCAN() function
hdbscan_params = ['algorithm', 'metric', 'min_cluster_size', 'min_samples', 'p', 'alpha',\
'cluster_selection_method', 'allow_single_cluster', 'match_reference_implementation']
# Create dictionary of key word arguments for the HDBSCAN() function
self.hdbscan_kwargs = self._populate_dict(hdbscan_params)
# Set up a list of possible key word arguments for the sklearn preprocessing functions
scaler_params = ['with_mean', 'with_std', 'feature_range', 'with_centering', 'with_scaling',\
'quantile_range', 'n_quantiles', 'output_distribution', 'ignore_implicit_zeros',\
'subsample', 'random_state']
# Create dictionary of key word arguments for the scaler functions
self.scaler_kwargs = self._populate_dict(scaler_params)
def _set_params(self, kwargs):
"""
Set input parameters based on the request.
:
:For details refer to the GitHub project: https://github.com/nabeel-oz/qlik-py-tools
"""
# Set default values which will be used if execution arguments are not passed
# Default parameters:
self.debug = False
self.model = 'en_core_web_sm'
self.custom = False
self.base_model = 'en_core_web_sm'
self.blank = False
self.epochs = 100
self.batch_size = compounding(4.0, 32.0, 1.001)
self.drop = 0.25
self.test = 0
# Extract the model path if required
try:
# Get the model name from the first row in the request_df
self.model = self.request_df.loc[0, 'model_name']
# Remove the model_name column from the request_df
self.request_df = self.request_df.drop(['model_name'], axis=1)
except KeyError:
pass
# If key word arguments were included in the request, get the parameters and values
if len(kwargs) > 0:
# Transform the string of arguments into a dictionary
self.kwargs = utils.get_kwargs(kwargs)
# 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()
# Additional information is printed to the terminal and logs if the paramater debug = true
if self.debug:
# Increment log counter for the class. Each instance of the class generates a new log.
self.__class__.log_no += 1
# Create a log file for the instance
# Logs will be stored in ..\logs\SpaCy Log <n>.txt
self.logfile = os.path.join(
os.getcwd(), 'logs',
'SpaCy Log {}.txt'.format(self.log_no))
self._print_log(1)
# Set whether the model (if getting named entites) or base model (if retraining) is a custom model
# i.e. not one of the pre-trained models provided by spaCy
if 'custom' in self.kwargs:
self.custom = 'true' == self.kwargs['custom'].lower()
# Set the base model, i.e an existing spaCy model to be retrained.
if 'base_model' in self.kwargs:
self.base_model = self.kwargs['base_model'].lower()
# Set the retraining to be done on a blank Language class
if 'blank' in self.kwargs:
self.blank = 'true' == self.kwargs['blank'].lower()
# Set the epochs for training the model.
# This is the the number times that the learning algorithm will work through the entire training dataset.
# Valid values are an integer e.g. 200
if 'epochs' in self.kwargs:
self.epochs = utils.atoi(self.kwargs['epochs'])
# Set the batch size to be used during model training.
# The model's internal parameters will be updated at the end of each batch.
# Valid values are a single integer or compounding or decaying parameters.
if 'batch_size' in self.kwargs:
# The batch size may be a single integer
try:
self.batch_size = utils.atoi(self.kwargs['batch_size'])
# Or a list of floats
except ValueError:
sizes = utils.get_kwargs_by_type(self.kwargs['batch_size'])
# If the start < end, batch sizes will be compounded
if sizes[0] < sizes[1]:
self.batch_size = compounding(sizes[0], sizes[1],
sizes[2])
# else bath sizes will decay during training
else:
self.batch_size = decaying(sizes[0], sizes[1],
sizes[2])
# Set the dropout rate for retraining the model
# This determines the likelihood that a feature or internal representation in the model will be dropped,
# making it harder for the model to memorize the training data.
# Valid values are a float lesser than 1.0 e.g. 0.35
if 'drop' in self.kwargs:
self.drop = utils.atof(self.kwargs['drop'])
# Set the ratio of data to be used for testing.
# This data will be held out from training and just used to provide evaluation metrics.
# Valid values are a float >= zero and < 1.0 e.g. 0.3
if 'test' in self.kwargs:
self.test = utils.atof(self.kwargs['test'])
# Debug information is printed to the terminal and logs if the paramater debug = true
if self.debug:
self._print_log(2)
# Remove the kwargs column from the request_df
self.request_df = self.request_df.drop(['kwargs'], axis=1)
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 = 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 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.
# 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 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)
def _set_params(self, kwargs):
"""
Set input parameters based on the request.
:
:For details refer to the GitHub project: https://github.com/nabeel-oz/qlik-py-tools
"""
# If key word arguments were included in the request, get the parameters and values,
# by transforming the string of arguments into a dictionary
self.kwargs = {} if len(kwargs) == 0 else utils.get_kwargs(kwargs)
# Set the debug option for generating execution logs
# Valid values are: true, false
self.debug = False if 'debug' not in self.kwargs else (
'true' == self.kwargs.pop('debug').lower())
# Additional information is printed to the terminal and logs if the paramater debug = true
if self.debug:
# Increment log counter for the class. Each instance of the class generates a new log.
self.__class__.log_no += 1
# Create a log file for the instance
# Logs will be stored in ..\logs\Common Functions Log <n>.txt
self.logfile = os.path.join(
os.getcwd(), 'logs',
'Common Functions Log {}.txt'.format(self.log_no))
self._print_log(1)
# Set the name of the function to be called on the model
# By default this is the 'predict' function, but could be other functions such as 'predict_proba' if supported by the model
self.prediction_func = 'predict' if 'return' not in self.kwargs else self.kwargs.pop(
'return')
# Certain models may need sorted data for predictions
# A feature can be specified for use in sorting using the identifier argument.
self.identifier = None if 'identifier' not in self.kwargs else self.kwargs.pop(
'identifier')
# The identifier can be excluded from the inputs to the model using the exclude_identifier argument.
self.exclude_identifier = False if 'exclude_identifier' not in self.kwargs else (
self.kwargs.pop('exclude_identifier').lower() == 'true')
# Number of seconds to wait if a Keras model is being loaded by another thread
self.wait = 2 if 'keras_wait' not in self.kwargs else utils.atoi(
self.kwargs.pop('keras_wait'))
# Number of retries if a Keras model is being loaded by another thread
self.retries = 5 if 'keras_retries' not in self.kwargs else utils.atoi(
self.kwargs.pop('keras_retries'))
# Get the rest of the parameters, converting values to the correct data type
self.pass_on_kwargs = {} if len(
self.kwargs) == 0 else utils.get_kwargs_by_type(self.kwargs)
# The predictions may need to be decoded in case of classification labels
# The labels can be passed as a dictionary using the 'labels' argument.
self.labels = None if 'labels' not in self.pass_on_kwargs else self.pass_on_kwargs.pop(
'labels')
# Debug information is printed to the terminal and logs if the paramater debug = true
if self.debug:
self._print_log(2)
# Remove the kwargs column from the request_df
self.request_df = self.request_df.drop(['kwargs'], axis=1)
