TD_​PACF

the TD_PACF, Partial Auto Correlation function, can be passed either a discrete series - time or spatial series (INPUT_TYPE(DATA_SERIES)) - as an input; or, alternatively, can be passed a series containing previously computed Auto Correlation coefficients - lag and magnitude (INPUT_TYPE(ACF)). The passed in logical-runtime series is permitted to have elements which are either univariate or multivariate reals. Each input series produces a result series, which is indexed on 'LAG', and containing univariate or multivariate real number magnitudes as it result series elements. This function provides the ability to generate 'on-demand' plots. The generated plots can be either univariate, multivariate, or composite in nature. The chosen implementation’s output and style specification closely match Matplotlib ( https://matplotlib.org/ ), an extremely popular Python plotting library. The primary purpose for this decision is to jump start existing Matplotlib users into TD_PLOT usage. However, the Teradata implementation is a completely independent and separate one based on C/C++.

Options

ALGORITHM
Specifies algorithm that data scientist wishes to use to generate the PACF coefficientsLEVINSON_DURBIN - Uses the set of recursive formulas devised by Levinson-Durbin to solve for PACF coefficientsOLS - Solves incremental series of regression equations to determine the PACF coefficients
ALPHA
Positive Float value. If a non-zero positive number is given, the confidence intervals for the given level are returned. For instance if alpha=.05, 95% confidence intervals are returned where the standard deviation is computed according to Bartlett’s formula. Passing in a positive number results in a CONFINT result column being returned.
INPUT_TYPE
Optional parameter. Specifies whether to source 1D array contains a data series or contains previously generated ACF results. Default is DATA_SERIES, meaning a data series is being passed in.DATA_SERIES - 1D input array contains time or spatial seriesACF - 1D input array is indexed by LAG and contains previously generated ACF magnitudes
MAXLAGS
Positive Integer value. Maximum number of lags at which to calculate the partial autocorrelation. Default is 10*log10(N) where N is the number of observations. Is automatically limited to one less than the number of observations in the series. If the numLags value specified by the user exceeds this limit, the user input value is ignored and replaced with the system defined max value.
Output Schema
Output Schema, if Volatile is true then use user login as the schema.
Output Table
Output Table
VAL Location
VAL Location
Volatile
Specifies whether the table should be a VOLATILE table. If true, then the table is automatically deleted, otherwise it is users responsibility to remove or clean it up for space.
UNBIASED
Only valid when INPUT_TYPE(DATA_SERIES). This effects the manner in which the auto-correlation intermediate values are calculated.Positive Integer value. If 0, then denominator for autocorrelation calculation is n-k (Jenkins & Watts formula), otherwise if 1, denominator for autocorrelation calculation is n (Box & Jenkins formula). Default is 0.

Input Ports

Icon
Connection to a Teradata Database Instance
Icon
discrete series - time or spatial series (INPUT_TYPE(DATA_SERIES)) - as an input; or, alternatively, can be passed a series containing previously computed Auto Correlation coefficients - lag and magnitude (INPUT_TYPE(ACF))

Output Ports

Icon
output of TD_PACF

Nodes

Extensions

Links

Download

To use this component in KNIME, download it from the below URL and open it in KNIME:

Download Component
On NodePit since: 2023-12-01
Last update: 2024-11-21
Created with KNIME version: v4.7.0

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!