NonLinear_Logistic: R6 Class for NonLinear_Logistic modeling of crop responses...
In paulhegedus/OFPE: On-Farm Precision Experiments (OFPE) Data Management and Analysis Tools
NonLinear_Logistic R Documentation
R6 Class for NonLinear_Logistic modeling of crop responses (deprecated)
Description
R6 class using non-linear logistic regression (NonLinear_Logistic) to
model a crop response model with the experimental variable and remotely sensed covariate
data. This class is initialized with a named list of traning (named 'trn')
and validation (named 'val') datasets, the response variable, the experimental
variable, and the means of the centered data.
The initialization creates a data frame ('parm_df') containing the parameter names,
function component and id, the mean and standard deviation, and whether it meets
the criteria to be omitted from the model, making it a 'bad_parm'. The criteria for
this is over 30% of data for a given year missing for a parameter or a standard
deviation of zero, indicating singularity.
The process then creates a formula for a final model with all parameters that
are not considered 'bad'. This is used to fit the final model that is returned
to the user for use in the simulation to predict the response under varying
rates of the experimental variable. This process is iterative and fits each
model component at a time, using default coefficient estimates and updating
as each component is fit and new coefficients are generated.
The 'saveDiagnostics' method include residuals vs. fitted, normal QQ-
plots, etc. The fitting process also prepares data for validation plots in the
'ModClass' R6 class. This includes predicting observations in the validation
dataset, making a unique id using the year and fieldname, uncentering data, and
identifying a field name to use for plotting that reflects all fields in the
dataset.
Public fields
datNamed list of traning (named 'trn') and validation (named 'val')
datasets with the response, experimental, and remotely sensed variables.
respvarCharacter, the response variable of interest.
expvarCharacter, the experimental variable of interest.
covarsCharacter vector of covariates to use for training the model.
mFitted non-linear logistic model.
m0Fitted non-linear logistic model with the minimum rates and locking beta,
delta, and gamma.
formFinal non-linear logistic formula.
parm_dfData frame of parameter names, the function component and ID, and a column
named 'bad_parms' to indicate whether to include in the model formula. Also includes
columns for the mean and standard deviation of each parameter.
fieldnameUnique name for the field(s) analyzed. If multiple fields are used
they are separated by an ampersand, otherwise the singular field name is used. This
is used for plottting.
mod_typeName of the model of this class, used for plotting.
Methods
Public methods
-
-
-
-
-
Method new()
The initialization creates a data frame ('parm_df') containing the parameter names,
the function component and id, the mean and standard deviation, and whether it meets
the criteria to be omitted from the model, making it a 'bad_parm'. The criteria for
this is over 30% of data for a given year missing for a parameter or a standard
deviation of zero, indicating singularity.
Usage
NonLinear_Logistic$new(dat, respvar, expvar, covars)
Arguments
datNamed list of traning (named 'trn') and validation (named 'val')
datasets with the response, experimental, and remotely sensed variables.
respvarCharacter, the response variable of interest.
expvarCharacter, the experimental variable of interest.
covarsCharacter vector of covariates to use for training the model.
Returns
A instantiated 'NonLinear_Logistic' object.
Method fitMod()
Method for fitting the non-linear logistic regression model to response variables
using experimental and covariate data.
The process first identifies parameters that will cause errors in the model fitting
method, then creates some initial coefficient estimates to use for fitting an initial
model. The estimates are based off of the mean to reduce the weight of large parameter
values on the estimates. Then the alpha and beta components are estimated with these
initial values and the means of each parameter. If alpha and beta fall outside of half a
standard deviation from the 1st and 3rd quantiles of the data the intercept for each
component of alpha and beta (a0 and b0) are set to the 1st and 3rd quantiles, respectively.
This sets up the initial model to follow a logistic curve from the 1st to the 3rd quantile
levels of the response variable, mimicking the expected response of crop yield and protein
to look.
Then, an initial model only using data from the lowest experimental rates is used to fit
the coefficients for the alpha component. Beta components are held constant in this process.
Once the alpha coefficients are fitted, these are locked in and another model fitting step
uses the estimated alpha component in a model to fit the beta, delta, and gamma components.
If this fails, delta is set at the mean of the experimental value and the fit is tried again.
This usually works, if not there are deeper issues in the data. This final model is returned
to the user for use in the simulation to predict the response under varying
rates of the experimental variable.
The fitting process also prepares data for validation plots in the
'ModClass' R6 class. This includes predicting observations in the validation
dataset, making a unique id using the year and fieldname, uncentering data, and
identifying a field name to use for plotting that reflects all fields in the
dataset.
Usage
NonLinear_Logistic$fitMod()
Arguments
NonePut parameters here
Returns
A fitted logistic model.
Method predResps()
Method for predicting response variables using data and a model.
Usage
NonLinear_Logistic$predResps(dat, m)
Arguments
datData for predicting response variables for.
mThe fitted model to use for predicting the response
variable for each observation in 'dat'.
Returns
Vector of predicted values for each location in 'dat'.
Method saveDiagnostics()
Method for saving diagnostic plots of the fitted model. These include residual
vs. fitted values, normal QQ plots, etc.
Usage
NonLinear_Logistic$saveDiagnostics(out_path, SAVE)
Arguments
out_pathThe path to the folder in which to store and
save outputs from the model fitting process
SAVEWhether to save diagnostic plots.
Returns
Diagnostic plots.
Method clone()
The objects of this class are cloneable with this method.
Usage
NonLinear_Logistic$clone(deep = FALSE)
Arguments
deepWhether to make a deep clone.
See Also
ModClass for the class that calls the ModClass interface,
GAM, RF, and BayesLinear
for alternative model classes.
paulhegedus/OFPE documentation built on Nov. 23, 2022, 5:09 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
| NonLinear_Logistic | R Documentation |
R6 Class for NonLinear_Logistic modeling of crop responses (deprecated)
Description
R6 class using non-linear logistic regression (NonLinear_Logistic) to model a crop response model with the experimental variable and remotely sensed covariate data. This class is initialized with a named list of traning (named 'trn') and validation (named 'val') datasets, the response variable, the experimental variable, and the means of the centered data.
The initialization creates a data frame ('parm_df') containing the parameter names, function component and id, the mean and standard deviation, and whether it meets the criteria to be omitted from the model, making it a 'bad_parm'. The criteria for this is over 30% of data for a given year missing for a parameter or a standard deviation of zero, indicating singularity.
The process then creates a formula for a final model with all parameters that are not considered 'bad'. This is used to fit the final model that is returned to the user for use in the simulation to predict the response under varying rates of the experimental variable. This process is iterative and fits each model component at a time, using default coefficient estimates and updating as each component is fit and new coefficients are generated.
The 'saveDiagnostics' method include residuals vs. fitted, normal QQ- plots, etc. The fitting process also prepares data for validation plots in the 'ModClass' R6 class. This includes predicting observations in the validation dataset, making a unique id using the year and fieldname, uncentering data, and identifying a field name to use for plotting that reflects all fields in the dataset.
Public fields
datNamed list of traning (named 'trn') and validation (named 'val') datasets with the response, experimental, and remotely sensed variables.
respvarCharacter, the response variable of interest.
expvarCharacter, the experimental variable of interest.
covarsCharacter vector of covariates to use for training the model.
mFitted non-linear logistic model.
m0Fitted non-linear logistic model with the minimum rates and locking beta, delta, and gamma.
formFinal non-linear logistic formula.
parm_dfData frame of parameter names, the function component and ID, and a column named 'bad_parms' to indicate whether to include in the model formula. Also includes columns for the mean and standard deviation of each parameter.
fieldnameUnique name for the field(s) analyzed. If multiple fields are used they are separated by an ampersand, otherwise the singular field name is used. This is used for plottting.
mod_typeName of the model of this class, used for plotting.
Methods
Public methods
Method new()
The initialization creates a data frame ('parm_df') containing the parameter names, the function component and id, the mean and standard deviation, and whether it meets the criteria to be omitted from the model, making it a 'bad_parm'. The criteria for this is over 30% of data for a given year missing for a parameter or a standard deviation of zero, indicating singularity.
Usage
NonLinear_Logistic$new(dat, respvar, expvar, covars)
Arguments
datNamed list of traning (named 'trn') and validation (named 'val') datasets with the response, experimental, and remotely sensed variables.
respvarCharacter, the response variable of interest.
expvarCharacter, the experimental variable of interest.
covarsCharacter vector of covariates to use for training the model.
Returns
A instantiated 'NonLinear_Logistic' object.
Method fitMod()
Method for fitting the non-linear logistic regression model to response variables using experimental and covariate data.
The process first identifies parameters that will cause errors in the model fitting method, then creates some initial coefficient estimates to use for fitting an initial model. The estimates are based off of the mean to reduce the weight of large parameter values on the estimates. Then the alpha and beta components are estimated with these initial values and the means of each parameter. If alpha and beta fall outside of half a standard deviation from the 1st and 3rd quantiles of the data the intercept for each component of alpha and beta (a0 and b0) are set to the 1st and 3rd quantiles, respectively. This sets up the initial model to follow a logistic curve from the 1st to the 3rd quantile levels of the response variable, mimicking the expected response of crop yield and protein to look.
Then, an initial model only using data from the lowest experimental rates is used to fit the coefficients for the alpha component. Beta components are held constant in this process. Once the alpha coefficients are fitted, these are locked in and another model fitting step uses the estimated alpha component in a model to fit the beta, delta, and gamma components. If this fails, delta is set at the mean of the experimental value and the fit is tried again. This usually works, if not there are deeper issues in the data. This final model is returned to the user for use in the simulation to predict the response under varying rates of the experimental variable.
The fitting process also prepares data for validation plots in the 'ModClass' R6 class. This includes predicting observations in the validation dataset, making a unique id using the year and fieldname, uncentering data, and identifying a field name to use for plotting that reflects all fields in the dataset.
Usage
NonLinear_Logistic$fitMod()
Arguments
NonePut parameters here
Returns
A fitted logistic model.
Method predResps()
Method for predicting response variables using data and a model.
Usage
NonLinear_Logistic$predResps(dat, m)
Arguments
datData for predicting response variables for.
mThe fitted model to use for predicting the response variable for each observation in 'dat'.
Returns
Vector of predicted values for each location in 'dat'.
Method saveDiagnostics()
Method for saving diagnostic plots of the fitted model. These include residual vs. fitted values, normal QQ plots, etc.
Usage
NonLinear_Logistic$saveDiagnostics(out_path, SAVE)
Arguments
out_pathThe path to the folder in which to store and save outputs from the model fitting process
SAVEWhether to save diagnostic plots.
Returns
Diagnostic plots.
Method clone()
The objects of this class are cloneable with this method.
Usage
NonLinear_Logistic$clone(deep = FALSE)
Arguments
deepWhether to make a deep clone.
See Also
ModClass for the class that calls the ModClass interface,
GAM, RF, and BayesLinear
for alternative model classes.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.