aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--R/mkinfit.R17
-rw-r--r--docs/pkgdown.yml2
-rw-r--r--docs/reference/mkinfit.html44
-rw-r--r--man/mkinfit.Rd19
4 files changed, 39 insertions, 43 deletions
diff --git a/R/mkinfit.R b/R/mkinfit.R
index 0f478910..8231cd00 100644
--- a/R/mkinfit.R
+++ b/R/mkinfit.R
@@ -68,12 +68,11 @@ if(getRversion() >= '2.15.1') utils::globalVariables(c("name", "time", "value"))
#' coefficient matrix in cases that this is possible. If set to "deSolve", a
#' numerical ode solver from package \code{\link{deSolve}} is used. If set to
#' "analytical", an analytical solution of the model is used. This is only
-#' implemented for simple degradation experiments with only one state
-#' variable, i.e. with no metabolites. The default is "auto", which uses
-#' "analytical" if possible, otherwise "deSolve" if a compiler is present,
-#' and "eigen" if no compiler is present and the model can be expressed using
-#' eigenvalues and eigenvectors. This argument is passed on to the helper
-#' function \code{\link{mkinpredict}}.
+#' implemented for relatively simple degradation models. The default is
+#' "auto", which uses "analytical" if possible, otherwise "deSolve" if a
+#' compiler is present, and "eigen" if no compiler is present and the model
+#' can be expressed using eigenvalues and eigenvectors. This argument is
+#' passed on to the helper function \code{\link{mkinpredict}}.
#' @param method.ode The solution method passed via \code{\link{mkinpredict}}
#' to \code{\link{ode}} in case the solution type is "deSolve". The default
#' "lsoda" is performant, but sometimes fails to converge.
@@ -118,9 +117,9 @@ if(getRversion() >= '2.15.1') utils::globalVariables(c("name", "time", "value"))
#' least squares fitting ("OLS") is selected. If the error model is "obs", or
#' "tc", the "d_3" algorithm is selected.
#'
-#' The algorithm "d_3" will directly minimize the negative log-likelihood and
-#' - independently - also use the three step algorithm described below. The
-#' fit with the higher likelihood is returned.
+#' The algorithm "d_3" will directly minimize the negative log-likelihood
+#' and independently also use the three step algorithm described below.
+#' The fit with the higher likelihood is returned.
#'
#' The algorithm "direct" will directly minimize the negative log-likelihood.
#'
diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml
index 5147a265..cd82d482 100644
--- a/docs/pkgdown.yml
+++ b/docs/pkgdown.yml
@@ -10,7 +10,7 @@ articles:
NAFTA_examples: web_only/NAFTA_examples.html
benchmarks: web_only/benchmarks.html
compiled_models: web_only/compiled_models.html
-last_built: 2020-05-12T15:51Z
+last_built: 2020-05-12T17:10Z
urls:
reference: https://pkgdown.jrwb.de/mkin/reference
article: https://pkgdown.jrwb.de/mkin/articles
diff --git a/docs/reference/mkinfit.html b/docs/reference/mkinfit.html
index 54ca377f..3438b8b1 100644
--- a/docs/reference/mkinfit.html
+++ b/docs/reference/mkinfit.html
@@ -115,6 +115,9 @@ likelihood function." />
<li>
<a href="../articles/web_only/NAFTA_examples.html">Example evaluation of NAFTA SOP Attachment examples</a>
</li>
+ <li>
+ <a href="../articles/web_only/benchmarks.html">Some benchmark timings</a>
+ </li>
</ul>
</li>
<li>
@@ -265,12 +268,11 @@ differential equations is based on the spectral decomposition of the
coefficient matrix in cases that this is possible. If set to "deSolve", a
numerical ode solver from package <code>deSolve</code> is used. If set to
"analytical", an analytical solution of the model is used. This is only
-implemented for simple degradation experiments with only one state
-variable, i.e. with no metabolites. The default is "auto", which uses
-"analytical" if possible, otherwise "deSolve" if a compiler is present,
-and "eigen" if no compiler is present and the model can be expressed using
-eigenvalues and eigenvectors. This argument is passed on to the helper
-function <code><a href='mkinpredict.html'>mkinpredict</a></code>.</p></td>
+implemented for relatively simple degradation models. The default is
+"auto", which uses "analytical" if possible, otherwise "deSolve" if a
+compiler is present, and "eigen" if no compiler is present and the model
+can be expressed using eigenvalues and eigenvectors. This argument is
+passed on to the helper function <code><a href='mkinpredict.html'>mkinpredict</a></code>.</p></td>
</tr>
<tr>
<th>method.ode</th>
@@ -342,11 +344,9 @@ normal distribution as assumed by this method.</p></td>
the error model. If the error model is "const", unweighted nonlinear
least squares fitting ("OLS") is selected. If the error model is "obs", or
"tc", the "d_3" algorithm is selected.</p>
-<p>The algorithm "d_3" will directly minimize the negative log-likelihood and</p><ul>
-<li><p>independently - also use the three step algorithm described below. The
-fit with the higher likelihood is returned.</p></li>
-</ul>
-
+<p>The algorithm "d_3" will directly minimize the negative log-likelihood
+and independently also use the three step algorithm described below.
+The fit with the higher likelihood is returned.</p>
<p>The algorithm "direct" will directly minimize the negative log-likelihood.</p>
<p>The algorithm "twostep" will minimize the negative log-likelihood after an
initial unweighted least squares optimisation step.</p>
@@ -422,15 +422,15 @@ Degradation Data. <em>Environments</em> 6(12) 124
<span class='no'>fit</span> <span class='kw'>&lt;-</span> <span class='fu'>mkinfit</span>(<span class='st'>"FOMC"</span>, <span class='no'>FOCUS_2006_C</span>, <span class='kw'>quiet</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>)
<span class='fu'><a href='https://rdrr.io/r/base/summary.html'>summary</a></span>(<span class='no'>fit</span>)</div><div class='output co'>#&gt; mkin version used for fitting: 0.9.50.2
#&gt; R version used for fitting: 4.0.0
-#&gt; Date of fit: Tue May 12 15:29:48 2020
-#&gt; Date of summary: Tue May 12 15:29:48 2020
+#&gt; Date of fit: Tue May 12 19:10:13 2020
+#&gt; Date of summary: Tue May 12 19:10:13 2020
#&gt;
#&gt; Equations:
#&gt; d_parent/dt = - (alpha/beta) * 1/((time/beta) + 1) * parent
#&gt;
#&gt; Model predictions using solution type analytical
#&gt;
-#&gt; Fitted using 222 model solutions performed in 0.043 s
+#&gt; Fitted using 222 model solutions performed in 0.047 s
#&gt;
#&gt; Error model: Constant variance
#&gt;
@@ -597,7 +597,7 @@ Degradation Data. <em>Environments</em> 6(12) 124
#&gt; Sum of squared residuals at call 166: 371.2134
#&gt; Sum of squared residuals at call 168: 371.2134
#&gt; Negative log-likelihood at call 178: 97.22429</div><div class='output co'>#&gt; <span class='message'>Optimisation successfully terminated.</span></div><div class='output co'>#&gt; User System verstrichen
-#&gt; 0.363 0.001 0.364 </div><div class='input'><span class='fu'><a href='parms.html'>parms</a></span>(<span class='no'>fit.deSolve</span>)</div><div class='output co'>#&gt; parent_0 k_parent k_m1 f_parent_to_m1 sigma
+#&gt; 0.351 0.000 0.352 </div><div class='input'><span class='fu'><a href='parms.html'>parms</a></span>(<span class='no'>fit.deSolve</span>)</div><div class='output co'>#&gt; parent_0 k_parent k_m1 f_parent_to_m1 sigma
#&gt; 99.598480759 0.098697739 0.005260651 0.514475958 3.125503874 </div><div class='input'><span class='fu'><a href='endpoints.html'>endpoints</a></span>(<span class='no'>fit.deSolve</span>)</div><div class='output co'>#&gt; $ff
#&gt; parent_m1 parent_sink
#&gt; 0.514476 0.485524
@@ -631,8 +631,8 @@ Degradation Data. <em>Environments</em> 6(12) 124
<span class='no'>SFO_SFO.ff</span> <span class='kw'>&lt;-</span> <span class='fu'><a href='mkinmod.html'>mkinmod</a></span>(<span class='kw'>parent</span> <span class='kw'>=</span> <span class='fu'><a href='mkinsub.html'>mkinsub</a></span>(<span class='st'>"SFO"</span>, <span class='st'>"m1"</span>),
<span class='kw'>m1</span> <span class='kw'>=</span> <span class='fu'><a href='mkinsub.html'>mkinsub</a></span>(<span class='st'>"SFO"</span>), <span class='kw'>use_of_ff</span> <span class='kw'>=</span> <span class='st'>"max"</span>)</div><div class='output co'>#&gt; <span class='message'>Successfully compiled differential equation model from auto-generated C code.</span></div><div class='input'><span class='no'>f.noweight</span> <span class='kw'>&lt;-</span> <span class='fu'>mkinfit</span>(<span class='no'>SFO_SFO.ff</span>, <span class='no'>FOCUS_2006_D</span>, <span class='kw'>quiet</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>)</div><div class='output co'>#&gt; <span class='warning'>Warning: Observations with value of zero were removed from the data</span></div><div class='input'><span class='fu'><a href='https://rdrr.io/r/base/summary.html'>summary</a></span>(<span class='no'>f.noweight</span>)</div><div class='output co'>#&gt; mkin version used for fitting: 0.9.50.2
#&gt; R version used for fitting: 4.0.0
-#&gt; Date of fit: Tue May 12 15:29:53 2020
-#&gt; Date of summary: Tue May 12 15:29:53 2020
+#&gt; Date of fit: Tue May 12 19:10:18 2020
+#&gt; Date of summary: Tue May 12 19:10:18 2020
#&gt;
#&gt; Equations:
#&gt; d_parent/dt = - k_parent * parent
@@ -640,7 +640,7 @@ Degradation Data. <em>Environments</em> 6(12) 124
#&gt;
#&gt; Model predictions using solution type analytical
#&gt;
-#&gt; Fitted using 421 model solutions performed in 0.13 s
+#&gt; Fitted using 421 model solutions performed in 0.146 s
#&gt;
#&gt; Error model: Constant variance
#&gt;
@@ -753,8 +753,8 @@ Degradation Data. <em>Environments</em> 6(12) 124
#&gt; 120 m1 25.15 28.78984 -3.640e+00
#&gt; 120 m1 33.31 28.78984 4.520e+00</div><div class='input'><span class='no'>f.obs</span> <span class='kw'>&lt;-</span> <span class='fu'>mkinfit</span>(<span class='no'>SFO_SFO.ff</span>, <span class='no'>FOCUS_2006_D</span>, <span class='kw'>error_model</span> <span class='kw'>=</span> <span class='st'>"obs"</span>, <span class='kw'>quiet</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>)</div><div class='output co'>#&gt; <span class='warning'>Warning: Observations with value of zero were removed from the data</span></div><div class='input'><span class='fu'><a href='https://rdrr.io/r/base/summary.html'>summary</a></span>(<span class='no'>f.obs</span>)</div><div class='output co'>#&gt; mkin version used for fitting: 0.9.50.2
#&gt; R version used for fitting: 4.0.0
-#&gt; Date of fit: Tue May 12 15:29:53 2020
-#&gt; Date of summary: Tue May 12 15:29:53 2020
+#&gt; Date of fit: Tue May 12 19:10:19 2020
+#&gt; Date of summary: Tue May 12 19:10:19 2020
#&gt;
#&gt; Equations:
#&gt; d_parent/dt = - k_parent * parent
@@ -890,8 +890,8 @@ Degradation Data. <em>Environments</em> 6(12) 124
#&gt; 120 m1 25.15 28.80429 -3.654e+00
#&gt; 120 m1 33.31 28.80429 4.506e+00</div><div class='input'><span class='no'>f.tc</span> <span class='kw'>&lt;-</span> <span class='fu'>mkinfit</span>(<span class='no'>SFO_SFO.ff</span>, <span class='no'>FOCUS_2006_D</span>, <span class='kw'>error_model</span> <span class='kw'>=</span> <span class='st'>"tc"</span>, <span class='kw'>quiet</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>)</div><div class='output co'>#&gt; <span class='warning'>Warning: Observations with value of zero were removed from the data</span></div><div class='input'><span class='fu'><a href='https://rdrr.io/r/base/summary.html'>summary</a></span>(<span class='no'>f.tc</span>)</div><div class='output co'>#&gt; mkin version used for fitting: 0.9.50.2
#&gt; R version used for fitting: 4.0.0
-#&gt; Date of fit: Tue May 12 15:29:54 2020
-#&gt; Date of summary: Tue May 12 15:29:54 2020
+#&gt; Date of fit: Tue May 12 19:10:19 2020
+#&gt; Date of summary: Tue May 12 19:10:19 2020
#&gt;
#&gt; Equations:
#&gt; d_parent/dt = - k_parent * parent
diff --git a/man/mkinfit.Rd b/man/mkinfit.Rd
index 5a2b3e53..b8d44fba 100644
--- a/man/mkinfit.Rd
+++ b/man/mkinfit.Rd
@@ -94,12 +94,11 @@ differential equations is based on the spectral decomposition of the
coefficient matrix in cases that this is possible. If set to "deSolve", a
numerical ode solver from package \code{\link{deSolve}} is used. If set to
"analytical", an analytical solution of the model is used. This is only
-implemented for simple degradation experiments with only one state
-variable, i.e. with no metabolites. The default is "auto", which uses
-"analytical" if possible, otherwise "deSolve" if a compiler is present,
-and "eigen" if no compiler is present and the model can be expressed using
-eigenvalues and eigenvectors. This argument is passed on to the helper
-function \code{\link{mkinpredict}}.}
+implemented for relatively simple degradation models. The default is
+"auto", which uses "analytical" if possible, otherwise "deSolve" if a
+compiler is present, and "eigen" if no compiler is present and the model
+can be expressed using eigenvalues and eigenvectors. This argument is
+passed on to the helper function \code{\link{mkinpredict}}.}
\item{method.ode}{The solution method passed via \code{\link{mkinpredict}}
to \code{\link{ode}} in case the solution type is "deSolve". The default
@@ -154,11 +153,9 @@ the error model. If the error model is "const", unweighted nonlinear
least squares fitting ("OLS") is selected. If the error model is "obs", or
"tc", the "d_3" algorithm is selected.
-The algorithm "d_3" will directly minimize the negative log-likelihood and
-\itemize{
-\item independently - also use the three step algorithm described below. The
-fit with the higher likelihood is returned.
-}
+The algorithm "d_3" will directly minimize the negative log-likelihood
+and independently also use the three step algorithm described below.
+The fit with the higher likelihood is returned.
The algorithm "direct" will directly minimize the negative log-likelihood.

Contact - Imprint