[GRASS-user] v.class.mlR Error

Moritz Lennert mlennert at club.worldonline.be
Tue Jun 19 02:58:35 PDT 2018


P.S. I'm not sure that for the landscape you are working on (mainly 
forest areas) OBIA is the best approach. You might want to also try a 
pixel-based approach with i.smap:

#create raster training areas
v.to.rast Training_Ben5 out=training use=attr attrcol=Ecosystem
#create a subgroup with all four bands
i.group WV_Benatimofo subg=sub 
in=WV_Benatimofo.1 at haarlooj_Ben_Test,WV_Benatimofo.2 at haarlooj_Ben_Test,WV_Benatimofo.3 at haarlooj_Ben_Test,WV_Benatimofo.4 at haarlooj_Ben_Test
#create signature file
i.gensigset training group=WV_Benatimofo sub=sub
#classify
i.smap group=WV_Benatimofo sub=sub sig=sig out=smap_classified 
goodness=smap_goodness

Moritz

On 19/06/18 11:33, Moritz Lennert wrote:
> Hi Jamille,
> 
> Testing with the data you sent me offlist (which BTW was a mapset, not a
> location. A location contains at least one mapset named PERMANENT which
> contains the projection info - I just assumed that you are working in
> UTM Zone 21N, created my own location and copied your mapset into that
> location.) and with the following command:
> 
> v.class.mlR -i --overwrite
> segments_map=Segments_vector_Stats_Ben_test at haarlooj_Ben_Test
> training_map=Training_Ben5 at haarlooj_Ben_Test
> raster_segments_map=best5_myregion1_at_haarlooj_Ben_Test_rank1 at haarlooj_Ben_Test
> train_class_column=Ecosystem output_class_column=vote
> output_prob_column=prob classifiers=svmRadial,rf,C5.0 folds=5
> partitions=10 tunelength=10 weighting_metric=accuracy
> r_script_file=R-script processes=3
> 
> the module runs perfectly fine for me here on GNU/Linux. Note the fact
> that the train_class_column=Ecosystem, not ecosystem. Case matters here.
> 
> Could you try with the training class column in the right case ?
> 
> Moritz
> 
> On 18/06/18 21:51, Jamille Haarloo wrote:
>> Hello Moritz,
>>
>> It looks like I got some results, but I suspect there are still some
>> issues due to the warning messages.
>>
>> I either kept getting that a file couldn't be found or that it had
>> trouble running the R-script.
>> My actions:
>>
>>   1. I found that it was looking in "C:\Program Files\QGIS
>>      2.16.0\apps\Python27\Lib" for certain scripts but I also had another
>>      location of the Python27 library "C:\Program Files\GRASS GIS
>>      7.4.0\Python27\Lib". So I tried adding the second location via the
>>      black terminal because I figured it needed the GRASS
>>      versions/formats (with my lack of experience I am not sure if I
>>      succeeded).
>>   2. It was still failing, and I suspected this had to do with the qbwwv
>>      voting method (see output). So I unchecked that option and got
>>      results. I'am also sending a screenshot of the attribute table with
>>      results.
>>
>> Do you have any suggestions for improvement?
>> Soon I will test with a much bigger area for a land-use planning project.
>>
>>
>> /The last 2 command outputs:/
>>
>> Running R now. Following output is R output.
>> During startup - Warning messages:
>> 1: Setting LC_CTYPE=en_US.cp1252 failed
>> 2: Setting LC_COLLATE=en_US.cp1252 failed
>> 3: Setting LC_TIME=en_US.cp1252 failed
>> 4: Setting LC_MONETARY=en_US.cp1252 failed
>> Loading required package: caret
>> Loading required package: lattice
>> Loading required package: ggplot2
>> Loading required package: foreach
>> Loading required package: iterators
>> Loading required package: parallel
>> During startup - Warning messages:
>> 1: Setting LC_CTYPE=en_US.cp1252 failed
>> 2: Setting LC_COLLATE=en_US.cp1252 failed
>> 3: Setting LC_TIME=en_US.cp1252 failed
>> 4: Setting LC_MONETARY=en_US.cp1252 failed
>> During startup - Warning messages:
>> 1: Setting LC_CTYPE=en_US.cp1252 failed
>> 2: Setting LC_COLLATE=en_US.cp1252 failed
>> 3: Setting LC_TIME=en_US.cp1252 failed
>> 4: Setting LC_MONETARY=en_US.cp1252 failed
>> Warning message:
>> In nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo,  :
>>     There were missing values in resampled performance measures.
>> Error in `$<-.data.frame`(`*tmp*`, vote_qbwwv, value = numeric(0)) :
>>     replacement has 0 rows, data has 1965
>> Calls: $<- -> $<-.data.frame
>> Execution halted
>> ERROR: There was an error in the execution of the R script.
>> Please check the R output.
>> (Mon Jun 18 15:36:47 2018) Command finished (1 min 24 sec)
>> (Mon Jun 18 15:50:30 2018)
>> v.class.mlR -i --overwrite
>> segments_map=Segments_vector_Stats_Ben_test at haarlooj_Ben_Test
>> training_map=Training_Ben_Grass at haarlooj_Ben_Test
>> raster_segments_map=best5_myregion1_at_haarlooj_Ben_Test_rank1 at haarlooj_Ben_Test
>> train_class_column=ecosystem output_class_column=vote
>> output_prob_column=prob classifiers=svmRadial,rf,C5.0 folds=5
>> partitions=10 tunelength=10 weighting_metric=accuracy
>> r_script_file=C:\Users\haarlooj\Documents\CELOS\v.class.mIRR_optional_output\Ben_test_mlR-script3
>> processes=2
>> Running R now. Following output is R output.
>> During startup - Warning messages:
>> 1: Setting LC_CTYPE=en_US.cp1252 failed
>> 2: Setting LC_COLLATE=en_US.cp1252 failed
>> 3: Setting LC_TIME=en_US.cp1252 failed
>> 4: Setting LC_MONETARY=en_US.cp1252 failed
>> Loading required package: caret
>> Loading required package: lattice
>> Loading required package: ggplot2
>> Loading required package: foreach
>> Loading required package: iterators
>> Loading required package: parallel
>> During startup - Warning messages:
>> 1: Setting LC_CTYPE=en_US.cp1252 failed
>> 2: Setting LC_COLLATE=en_US.cp1252 failed
>> 3: Setting LC_TIME=en_US.cp1252 failed
>> 4: Setting LC_MONETARY=en_US.cp1252 failed
>> During startup - Warning messages:
>> 1: Setting LC_CTYPE=en_US.cp1252 failed
>> 2: Setting LC_COLLATE=en_US.cp1252 failed
>> 3: Setting LC_TIME=en_US.cp1252 failed
>> 4: Setting LC_MONETARY=en_US.cp1252 failed
>> Warning message:
>> In nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo,  :
>>     There were missing values in resampled performance measures.
>> Finished running R.
>> Loading results into attribute table
>> (Mon Jun 18 15:51:58 2018) Command finished (1 min 27 sec)
>>
>>
>> Best,
>> Jamille Haarloo
>> Department of Natural Resources and Environmental Assessment (NARENA)
>> Centre for Agricultural Research in Suriname (CELOS)
>> <http://www.celos.sr.org/>
>>
>> Prof. Dr. Ir. Jan Ruinardlaan
>> AdeKUS University campus
>> Phone: 439982
>>
>>
>> On Thu, Jun 14, 2018 at 11:02 AM, Jamille Haarloo <j.r.haarloo at gmail.com
>> <mailto:j.r.haarloo at gmail.com>> wrote:
>>
>>      Hello Moritz,
>>
>>      Sorry about that. I am sending the zip of the location. The output
>>      at the other machine (system cannot find the file specified) was due
>>      to location/ directory issues and has been resolved, but also stops
>>      executing the R-script saying there were more than 50 errors. Been
>>      looking for similar cases online but haven't found many.
>>
>>>>      haarlooj_Ben_Test.zip
>>      <https://drive.google.com/file/d/1wQqmreMbbd3oRfoVXWIIGJOG9L63miV6/view?usp=drive_web>
>>>>
>>      On Thu, Jun 14, 2018 at 5:19 AM, Moritz Lennert
>>      <mlennert at club.worldonline.be <mailto:mlennert at club.worldonline.be>>
>>      wrote:
>>
>>          P.S. Your vector data also does not contain any attribute
>>          information as this is contained in a separate sqlite file. Just
>>          another reason never to touch the contents of a GRASS database
>>          directly, but only using dedicated tools. :-)
>>
>>
>>          On 14/06/18 10:11, Moritz Lennert wrote:
>>
>>              Hi Jamille,
>>
>>              Sorry, but I've been hopping from meeting to meeting these
>>              days and
>>              haven't had the opportunity to look at your data.
>>
>>              Actually, the form you transmit them in is very
>>              inconvenient. If you
>>              want to transmit GRASS data to someone, you should either
>>              zip an entire
>>              location directory and send that, or export the data with
>>              r.pack/v.pack.
>>
>>              In this form it is difficult to know which projection is
>>              used and I have
>>              to handcraft the data by copying the files into different
>>              directories.
>>
>>              So, please resend your data in a format that I can easily use.
>>
>>              Best wishes,
>>              Moritz
>>
>>              On 11/06/18 20:55, Jamille Haarloo wrote:
>>
>>                  Hello Moritz,
>>
>>                  I managed to edit my copy of v.class.mlR with the lines
>>                  you sent. But I
>>                  am still getting errors on two different machines.
>>                  I am sending you the data (hope I didn't miss anything)
>>                  and the command
>>                  outputs. I think there is sth wrong with my computer,
>>                  but also with one
>>                  of the files because of the error on the other machine.
>>
>>                  _Computer I normally use:_
>>
>>                  v.class.mlR -i --overwrite
>>                  segments_map=Segments_vector_Stats_Ben_test at haarlooj_Ben_Test
>>                  training_map=Training_Ben5 at haarlooj_Ben_Test
>>                  raster_segments_map=best5_myregion1_at_haarlooj_Ben_Test_rank1 at haarlooj_Ben_Test
>>                  train_class_column=Ecosystem output_class_column=vote
>>                  output_prob_column=prob classifiers=svmRadial,rf,C5.0
>>                  folds=5
>>                  partitions=10 tunelength=10 weighting_modes=smv,qbwwv
>>                  weighting_metric=accuracy
>>                  Running R now. Following output is R output.
>>                  During startup - Warning messages:
>>                  1: Setting LC_CTYPE=en_US.cp1252 failed
>>                  2: Setting LC_COLLATE=en_US.cp1252 failed
>>                  3: Setting LC_TIME=en_US.cp1252 failed
>>                  4: Setting LC_MONETARY=en_US.cp1252 failed
>>                  Loading required package: caret
>>                  Loading required package: lattice
>>                  Loading required package: ggplot2
>>                  There were 50 or more warnings (use warnings() to see
>>                  the first 50)
>>                  There were 50 or more warnings (use warnings() to see
>>                  the first 50)
>>                  Error in `$<-.data.frame`(`*tmp*`, vote_qbwwv, value =
>>                  numeric(0)) :
>>                       replacement has 0 rows, data has 1965
>>                  Calls: $<- -> $<-.data.frame
>>                  Execution halted
>>                  ERROR: There was an error in the execution of the R script.
>>                  Please check the R output.
>>
>>
>>                  _The output from the other machine:_
>>                  (Mon Jun 11 13:27:39 2018)
>>                  v.class.mlR -i --overwrite
>>                  segments_map=Segments_vector_Stats_Ben_test at haarlooj_Ben_Test
>>                  training_map=Training_Ben5 at haarlooj_Ben_Test
>>                  raster_segments_map=best5_myregion1_at_haarlooj_Ben_Test_rank1 at haarlooj_Ben_Test
>>                  train_class_column=Ecosystem output_class_column=vote
>>                  output_prob_column=prob classifiers=svmRadial,rf,C5.0
>>                  folds=5
>>                  partitions=10 tunelength=10 weighting_metric=accuracy
>>                  Running R now. Following output is R output.
>>                  Traceback (most recent call last):
>>                       File
>>                  "C:\Users\HaarlooJ\AppData\Roaming\GRASS7\addons/scri
>>                  pts/v.class.mlR.py <http://v.class.mlR.py>
>>                  <http://v.class.mlR.py>", line 639, in <module>
>>                       File
>>                  "C:\Users\HaarlooJ\AppData\Roaming\GRASS7\addons/scri
>>                  pts/v.class.mlR.py <http://v.class.mlR.py>
>>                  <http://v.class.mlR.py>", line 576, in main
>>                         shutil.copy(r_commands, r_script_file)
>>                       File "C:\Program Files\GRASS GIS
>>                  7.4.0\Python27\lib\subprocess.py", line 537, in check_call
>>                         retcode = call(*popenargs, **kwargs)
>>                       File "C:\Program Files\GRASS GIS
>>                  7.4.0\Python27\lib\subprocess.py", line 524, in call
>>                         return Popen(*popenargs, **kwargs).wait()
>>                       File "C:\Program Files\GRASS GIS
>>                  7.4.0\Python27\lib\subprocess.py", line 711, in __init__
>>                         errread, errwrite)
>>                       File "C:\Program Files\GRASS GIS
>>                  7.4.0\Python27\lib\subprocess.py", line 948, in
>>                  _execute_child
>>                         startupinfo)
>>                  WindowsError: [Error 2] The system cannot find the file
>>                  specified
>>                  (Mon Jun 11 13:27:42 2018) Command finished (3 sec)
>>
>>
>>                  On Mon, Jun 11, 2018 at 5:47 AM, Moritz Lennert
>>                  <mlennert at club.worldonline.be
>>                  <mailto:mlennert at club.worldonline.be>
>>                  <mailto:mlennert at club.worldonline.be
>>                  <mailto:mlennert at club.worldonline.be>>> wrote:
>>
>>                        Hi Jamille,
>>
>>                        Le Fri, 8 Jun 2018 16:14:45 -0300,
>>                        Jamille Haarloo <j.r.haarloo at gmail.com
>>                  <mailto:j.r.haarloo at gmail.com>
>>                        <mailto:j.r.haarloo at gmail.com
>>                  <mailto:j.r.haarloo at gmail.com>>> a écrit :
>>
>>                        > Hello Moritz,
>>                        >
>>                        > This time I asked a vector to be created with
>>                  the stats and used this
>>                        > to extract training polygons in QGIS and
>>                  imported the training map in
>>                        > GRASS. I had to do some interventions regarding
>>                  the column names to
>>                        > make sure they are the same except for the class.
>>                        > I still get an error, and the only thing I could
>>                  trace is the fact
>>                        > that values are missing in some rows  for both
>>                  vectors. I am not sure
>>                        > if I should correct this/ retry it all.
>>
>>                        I haven't seen this before, so yes, please try to
>>                  eliminate the rows
>>                        with missing values. How did you get the feature
>>                  variables and how come
>>                        there are missing values ?
>>
>>                        I don't have the time to test this right now, so I
>>                  prefer not to commit
>>                        as is, but you could try to edit your copy of
>>                  v.class.mlR to add the
>>                        four lines marked with a plus:
>>
>>                              r_file.write('features <- read.csv("%s",
>>                  sep="%s", header=TRUE,
>>                              row.names=1)' % (feature_vars, separator))
>>                  r_file.write("\n")
>>                        +    r_file.write("features <- na.omit(features)")
>>                        +    r_file.write("\n")
>>                              r_file.write('training <- read.csv("%s",
>>                  sep="%s", header=TRUE,
>>                              row.names=1)' % (training_vars, separator))
>>                  r_file.write("\n")
>>                        +    r_file.write("training <- na.omit(training)")
>>                        +    r_file.write("\n")
>>
>>                        This would eliminate all lines that have at least
>>                  one missing value.
>>
>>                        Another option would be for you to send me the
>>                  data (segments
>>                        and training) privately, so that I can test.
>>
>>                        Moritz
>>
>>
>>                         >
>>                         > This is the command output:
>>                         >
>>                         > (Fri Jun 08 15:48:28 2018)
>>                         >
>>                         > v.class.mlR -i --overwrite
>>                         >
>>                  segments_map=Segments_vector_Stats_Ben_test at haarlooj_Ben_Test
>>                         > training_map=Training_Ben5 at haarlooj_Ben_Test
>>                         >
>>                      
>>                    raster_segments_map=best5_myregion1_at_haarlooj_Ben_Test_rank1 at haarlooj_Ben_Test
>>                         > train_class_column=Ecosystem
>>                  output_class_column=vote
>>                         > output_prob_column=prob
>>                  classifiers=svmRadial,rf,C5.0 folds=5
>>                         > partitions=10 tunelength=10
>>                  weighting_modes=smv,qbwwv
>>                         > weighting_metric=accuracy
>>                         >
>>                      
>>                    classification_results=C:\Users\haarlooj\Documents\CELOS\v.class.mIRR_optional_output\Ben_test_Classifier-results
>>                         >
>>                      
>>                    accuracy_file=C:\Users\haarlooj\Documents\CELOS\v.class.mIRR_optional_output\Ben_test_Classifier-accuracy
>>                         >
>>                      
>>                    model_details=C:\Users\haarlooj\Documents\CELOS\v.class.mIRR_optional_output\Ben_test_Classifier-module-runs
>>                         >
>>                      
>>                    bw_plot_file=C:\Users\haarlooj\Documents\CELOS\v.class.mIRR_optional_output\Ben_test_Classifier-performance
>>                         >
>>                      
>>                    r_script_file=C:\Users\haarlooj\Documents\CELOS\v.class.mIRR_optional_output\Ben_test_R_script
>>                         > processes=3 Running R now. Following output is
>>                  R output.
>>                         > During startup - Warning messages:
>>                         > 1: Setting LC_CTYPE=en_US.cp1252 failed
>>                         > 2: Setting LC_COLLATE=en_US.cp1252 failed
>>                         > 3: Setting LC_TIME=en_US.cp1252 failed
>>                         > 4: Setting LC_MONETARY=en_US.cp1252 failed
>>                         > Loading required package: caret
>>                         > Loading required package: lattice
>>                         > Loading required package: ggplot2
>>                         > Loading required package: foreach
>>                         > Loading required package: iterators
>>                         > Loading required package: parallel
>>                         > During startup - Warning messages:
>>                         > 1: Setting LC_CTYPE=en_US.cp1252 failed
>>                         > 2: Setting LC_COLLATE=en_US.cp1252 failed
>>                         > 3: Setting LC_TIME=en_US.cp1252 failed
>>                         > 4: Setting LC_MONETARY=en_US.cp1252 failed
>>                         > During startup - Warning messages:
>>                         > 1: Setting LC_CTYPE=en_US.cp1252 failed
>>                         > 2: Setting LC_COLLATE=en_US.cp1252 failed
>>                         > 3: Setting LC_TIME=en_US.cp1252 failed
>>                         > 4: Setting LC_MONETARY=en_US.cp1252 failed
>>                         > During startup - Warning messages:
>>                         > 1: Setting LC_CTYPE=en_US.cp1252 failed
>>                         > 2: Setting LC_COLLATE=en_US.cp1252 failed
>>                         > 3: Setting LC_TIME=en_US.cp1252 failed
>>                         > 4: Setting LC_MONETARY=en_US.cp1252 failed
>>                         > Warning message:
>>                         > In nominalTrainWorkflow(x = x, y = y, wts =
>>                  weights, info =
>>                         > trainInfo,  : There were missing values in
>>                  resampled performance
>>                         > measures. Error in `$<-.data.frame`(`*tmp*`,
>>                  vote_qbwwv, value =
>>                         > numeric(0)) : replacement has 0 rows, data has 1965
>>                         > Calls: $<- -> $<-.data.frame
>>                         > Execution halted
>>                         > ERROR: There was an error in the execution of
>>                  the R script.
>>                         > Please check the R output.
>>                         > (Fri Jun 08 15:49:32 2018) Command finished (1
>>                  min 4 sec)
>>                         >
>>                         >
>>                         >
>>                         > Best,
>>                         > Jamille
>>                         >
>>                         >
>>                         >
>>                         >
>>                         > On Thu, Jun 7, 2018 at 11:09 AM, Jamille Haarloo
>>                         > <j.r.haarloo at gmail.com
>>                  <mailto:j.r.haarloo at gmail.com>
>>                  <mailto:j.r.haarloo at gmail.com
>>                  <mailto:j.r.haarloo at gmail.com>>> wrote:
>>                         >
>>                         > > Hello Moritz,
>>                         > >
>>                         > > No worries. Thankful these modules are made
>>                  available for newbies
>>                         > > in RS like me and also happy these
>>                  interactions are possible for
>>                         > > learning. Hope to get back soon after some
>>                  adjustments.
>>                         > >
>>                         > > Best,
>>                         > > Jamille
>>                         > >
>>                         > > On Thu, Jun 7, 2018 at 10:44 AM, Moritz Lennert <
>>                         > > mlennert at club.worldonline.be
>>                  <mailto:mlennert at club.worldonline.be>
>>                        <mailto:mlennert at club.worldonline.be
>>                  <mailto:mlennert at club.worldonline.be>>> wrote:
>>                         > >
>>                         > >> Thanks
>>                         > >>
>>                         > >> On 07/06/18 15:17, Jamille Haarloo wrote:
>>                         > >>
>>                         > >>> The first 20+ lines of Stats_Training_Ben_test:
>>                         > >>>
>>                         > >>>
>>                  cat,area,perimeter,compact_circle,compact_square,fd,WV_Benat
>>                         > >>>
>>                  imofo_1_min,WV_Benatimofo_1_max,WV_Benatimofo_1_range,WV_Ben
>>                         > >>>
>>                  atimofo_1_mean,WV_Benatimofo_1_stddev,WV_Benatimofo_1_varia
>>                         > >>>
>>                  nce,WV_Benatimofo_1_coeff_var,WV_Benatimofo_1_sum,WV_
>>                         > >>>
>>                  Benatimofo_1_first_quart,WV_Benatimofo_1_median,WV_Benatim
>>                         > >>>
>>                  ofo_1_third_quart,WV_Benatimofo_2_min,WV_Benatimofo_2_max,
>>                         > >>>
>>                  WV_Benatimofo_2_range,WV_Benatimofo_2_mean,WV_Benatimofo_2_
>>                         > >>>
>>                  stddev,WV_Benatimofo_2_variance,WV_Benatimofo_2_coeff_var,
>>                         > >>>
>>                  WV_Benatimofo_2_sum,WV_Benatimofo_2_first_quart,WV_
>>                         > >>>
>>                  Benatimofo_2_median,WV_Benatimofo_2_third_quart,WV_Benatimof
>>                         > >>>
>>                  o_3_min,WV_Benatimofo_3_max,WV_Benatimofo_3_range,WV_Benat
>>                         > >>>
>>                  imofo_3_mean,WV_Benatimofo_3_stddev,WV_Benatimofo_3_varianc
>>                         > >>>
>>                  e,WV_Benatimofo_3_coeff_var,WV_Benatimofo_3_sum,WV_
>>                         > >>>
>>                  Benatimofo_3_first_quart,WV_Benatimofo_3_median,WV_Benatim
>>                         > >>>
>>                  ofo_3_third_quart,WV_Benatimofo_4_min,WV_Benatimofo_4_max,
>>                         > >>>
>>                  WV_Benatimofo_4_range,WV_Benatimofo_4_mean,WV_Benatimofo_4_
>>                         > >>>
>>                  stddev,WV_Benatimofo_4_variance,WV_Benatimofo_4_coeff_var,
>>                         > >>>
>>                  WV_Benatimofo_4_sum,WV_Benatimofo_4_first_quart,WV_
>>                         > >>> Benatimofo_4_median,WV_Benatimofo_4_third_quart
>>                         > >>>
>>                  1144,3832.000000,1256.000000,5.723635,0.197144,1.729624,13,7
>>                         > >>>
>>                  6,63,46.4097077244259,9.98454911351384,99.69122100017,21.513
>>                         > >>>
>>                  9237092391,177842,40,47,53,40,138,98,90.2687891440501,15.250
>>                         > >>>
>>                  0825418009,232.565017531741,16.8940812061464,345910,81,92,
>>                         > >>>
>>                  100,15,61,46,40.8582985386221,7.82663897784868,61.2562776895
>>                         > >>>
>>                  802,19.1555675536767,156569,36,42,47,28,124,96,68.42536534
>>                         > >>>
>>                      
>>                    44676,13.5774536655369,184.347248039801,19.8427200164517,262206,59,68,77
>>                         > >>>
>>                  1145,12092.000000,2282.000000,5.854120,0.192750,1.645226,13,
>>                         > >>>
>>                  94,81,51.386288455177,10.5294376761475,110.869057775874,20.4
>>                         > >>>
>>                  907534532914,621363,45,52,59,21,220,199,114.230731061859,23.
>>                         > >>>
>>                  3590328249442,545.644414516822,20.4489917973953,1381278,101,
>>                         > >>>
>>                  114,128,7,76,69,46.4219318557724,8.42747122371732,71.
>>                         > >>>
>>                  0222712265835,18.1540726264915,561334,42,48,52,17,198,181,
>>                         > >>>
>>                  97.2732385047966,22.492313569247,505.904169697333,23.
>>                         > >>> 1228176577445,1176228,84,97,110
>>                         > >>>
>>                         > >>> [...]
>>                         > >>
>>                         > >> ---------------------
>>                         > >>> All the lines of the output of v.db.select
>>                         > >>> Training_Ben2 at haarlooj_Ben_Tes t:
>>                         > >>>
>>                         > >>> cat|id|Type|code
>>                         > >>> 1|4|B29|18
>>                         > >>> 2|5|B31|19
>>                         > >>> 3|3|B28|17
>>                         > >>>
>>                         > >>
>>                         > >>
>>                         > >> Again a lack of clear documentation on my
>>                  side: both the training
>>                         > >> and the segment info should contain the same
>>                  attributes, with only
>>                         > >> additional one column ('code' in your case)
>>                  present in the
>>                         > >> training data.
>>                         > >>
>>                         > >> It should be possible to do this
>>                  differently, i.e. provide the
>>                         > >> module with the features of all segments,
>>                  and only the id/cat of
>>                         > >> each training segment with the relevant
>>                  class and have the module
>>                         > >> merge the two, but this is not implemented, yet.
>>                         > >>
>>                         > >> I also just notice that you have the word
>>                  'Training' in both
>>                        names.
>>                         > >>
>>                         > >> The segment_file/segment_map contains the
>>                  info (cat + all feature
>>                         > >> variables) of all segments you wish to
>>                  classify, either in the
>>                         > >> form of a csv file or in the form of a
>>                  vector map with the info in
>>                         > >> the attribute table.
>>                         > >>
>>                         > >> The training_file/training_map contains the
>>                  info (cat + all
>>                        feature
>>                         > >> variables + class) of the training data.
>>                  Often this is an extract
>>                         > >> of the former, but not necessarily.
>>                         > >>
>>                         > >> All columns in the training file have to be
>>                  present in the segment
>>                         > >> file, except for the class column (your 'code').
>>                         > >>
>>                         > >> Sorry for the lack of docs. This module has
>>                  mostly been used
>>                         > >> internally here and so we are not always
>>                  aware of the unclear and
>>                         > >> missing parts. Having your feedback has been
>>                  very useful !
>>                         > >>
>>                         > >> Moritz
>>                         > >>
>>                         > >>
>>                         > >
>>
>>
>>
>>
>>
>>
>>
>>
> 
> 
> _______________________________________________
> grass-user mailing list
> grass-user at lists.osgeo.org
> https://lists.osgeo.org/mailman/listinfo/grass-user
> 




More information about the grass-user mailing list