TD_RegressionEvaluator Syntax Elements - Teradata Vantage

Teradata® VantageCloud Lake
Deployment
VantageCloud
Edition
Lake
Product
Teradata Vantage
Published
January 2023
Language
English (United States)
Last Update
2024-04-03
dita:mapPath
phg1621910019905.ditamap
dita:ditavalPath
pny1626732985837.ditaval
dita:id
phg1621910019905
ObservationColumn
[Required] Specify the column name that has observation values.
PredictionColumn
[Required] Specify the column name that has prediction values.
NumOfIndependentVariables
[Optional] Specify the number of independent variables in the model. Required with Adjusted R Squared metric, otherwise ignored.
DegreesOfFreedom
[Optional] Specify the numerator degrees of freedom (df1) and denominator degrees of freedom (df2). Required with fstat metric, else ignored.
Metrics
[Optional] Specify the list of evaluation metrics. The function returns the following metrics if the list is not provided:
  • MAE: Mean absolute error (MAE) is the arithmetic average of the absolute errors between observed values and predicted values.
  • MSE: Mean squared error (MSE) is the average of the squares of the errors between observed values and predicted values.
  • MSLE: Mean Square Log Error (MSLE) is the relative difference between the log-transformed observed values and predicted values.
  • MAPE: Mean Absolute Percentage Error (MAPE) is the mean or average of the absolute percentage errors of forecasts.
  • MPE: Mean percentage error (MPE) is the computed average of percentage errors by which predicted values differ from observed values.
  • RMSE: Root means squared error (MSE) is the square root of the average of the squares of the errors between observed values and predicted values.
  • RMSLE: Root means Square Log Error (MSLE) is the square root of the relative difference between the log-transformed observed values and predicted values.
  • R2: R Squared (R2) is the proportion of the variation in the dependent variable that is predictable from the independent variable(s).
  • AR2: Adjusted R-squared (AR2) is a modified version of R-squared that has been adjusted for the independent variable(s) in the model.
  • EV: Explained variation (EV) measures the proportion to which a mathematical model accounts for the variation (dispersion) of a given data set.
  • ME: Max-Error (ME) is the worst-case error between observed values and predicted values.
  • MPD: Mean Poisson Deviance (MPD) is equivalent to Tweedie Deviances when the power parameter value is 1.
  • MGD: Mean Gamma Deviance (MGD) is equivalent to Tweedie Deviances when the power parameter value is 2.
  • FSTAT: F-statistics (FSTAT) conducts an F-test. An F-test is any statistical test in which the test statistic has an F-distribution under the null hypothesis.
    • F_score = F_score value from the F-test.
    • F_Critcialvalue = F critical value from the F-test. (alpha, df1, df2, UPPER_TAILED) , alpha = 95%
    • p_value = Probability value associated with the F_score value (F_score, df1, df2, UPPER_TAILED)
    • F_conclusion = F-test result, either 'reject null hypothesis' or 'fail to reject null hypothesis'. If F_score > F_Critcialvalue, then 'reject null hypothesis' Else 'fail to reject null hypothesis'