search

e-sensing / sits

Satellite image time series in R
https://e-sensing.github.io/sitsbook/
GNU General Public License v2.0
479 stars 78 forks source link

sits_train Samples #169

Closed StellaCarneiro closed 4 years ago

StellaCarneiro commented 4 years ago

Where can I find more samples to train my model for the Legal Amazon? I see the Mato Grosso sample, isn't it too small? Thanks

gilbertocamara commented 4 years ago

Hi Stella

Please take a look at the “inSitu” package (https://github.com/e-sensing/inSitu https://github.com/e-sensing/inSitu). There are more samples there.

Best Gilberto

On 29 Jul 2020, at 14:21, Stella Mendes Carneiro notifications@github.com wrote:

Where can I find more samples to train my model for the Legal Amazon? I see the Mato Grosso sample, isn't it too small? Thanks

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/e-sensing/sits/issues/169, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABOHEDNJI5XBS6AUW27H5A3R6AH6JANCNFSM4PLRIKXA.

StellaCarneiro commented 4 years ago

Hi Gilberto,

Thanks for the quick reply. This package has been amazingly useful to me.

Unfortunately, the dataset amazonia_33K_12classes_4bands is not working. It shows me the following error:

<error/vctrs_error_scalar_type>x must be a vector, not a tbl_df/tbl/data.frame/sits_tibble object.

Backtrace:

  1. sits::sits_select_bands(...)
  2. sits:::.sits_tibble_rename(data)
  3. dplyr::rename(., cube = coverage)
  4. tidyselect::eval_rename(expr(c(...)), .data)
  5. tidyselect:::rename_impl(...)
  6. tidyselect:::eval_select_impl(...)
  7. vctrs::vec_assert(x)
  8. vctrs:::stop_scalar_type(x, arg)
  9. vctrs:::stop_vctrs(msg, "vctrs_error_scalar_type", actual = x)

Run rlang::last_trace() to see the full context.

I've attached my code and system info in case you want to see it. All the other datasets I have managed to use are fine.

Should I report the error at “inSitu” package​ then?

Thank you,

Stella

From: Gilberto Camara notifications@github.com Sent: 29 July 2020 13:54 To: e-sensing/sits sits@noreply.github.com Cc: MENDES CARNEIRO, STELLA (PGT) Stella.Mendes-Carneiro@warwick.ac.uk; Author author@noreply.github.com Subject: Re: [e-sensing/sits] sits_train Samples (#169)

Hi Stella

Please take a look at the “inSitu” package (https://github.com/e-sensing/inSitu https://github.com/e-sensing/inSitu). There are more samples there.

Best Gilberto

On 29 Jul 2020, at 14:21, Stella Mendes Carneiro notifications@github.com wrote:

Where can I find more samples to train my model for the Legal Amazon? I see the Mato Grosso sample, isn't it too small? Thanks

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/e-sensing/sits/issues/169, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABOHEDNJI5XBS6AUW27H5A3R6AH6JANCNFSM4PLRIKXA.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHubhttps://github.com/e-sensing/sits/issues/169#issuecomment-665678440, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AG5JRC2VKUG7K2O3IN3VBJ3R6ASYJANCNFSM4PLRIKXA.

<error/vctrs_error_scalar_type> x must be a vector, not a tbl_df/tbl/data.frame/sits_tibble object. Backtrace:

  1. sits::sits_select_bands(...)
  2. sits:::.sits_tibble_rename(data)
    1. dplyr::rename(., cube = coverage)
    2. tidyselect::eval_rename(expr(c(...)), .data)
    3. tidyselect:::rename_impl(...)
    4. tidyselect:::eval_select_impl(...)
    5. vctrs::vec_assert(x)
    6. vctrs:::stop_scalar_type(x, arg)
    7. vctrs:::stop_vctrs(msg, "vctrs_error_scalar_type", actual = x) Run rlang::last_trace() to see the full context.

      A tibble: 16 x 3

      label count prop

      1 Araguaia 3038 0.0245 2 Campo_Cerrado 17235 0.139 3 Cerradao 18576 0.150 4 Cerrado 49583 0.399 5 Cerrado_Rupestre 7143 0.0575 6 Ciliary_Forest 1989 0.0160 7 Dunas 550 0.00443 8 Fallow_Cotton 703 0.00566 9 Millet_Cotton 386 0.00311 10 Pasture 11740 0.0946 11 Perennial_Crop 132 0.00106 12 Semi_Perennial_Crop 825 0.00664 13 Soy_Corn 5737 0.0462 14 Soy_Cotton 4409 0.0355 15 Soy_Fallow 1873 0.0151 16 Soy_Millet 246 0.00198 [1] "mir" "blue" "nir" "red" "evi" "ndvi" # A tibble: 124,165 x 7 longitude latitude start_date end_date label cube time_series 1 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 2 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 3 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 4 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 5 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 6 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 7 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 8 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 9 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 10 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 # … with 124,155 more rows R version 4.0.2 (2020-06-22) Platform: x86_64-apple-darwin17.0 (64-bit) Running under: macOS Mojave 10.14.6

Matrix products: default BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib LAPACK: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRlapack.dylib

Random number generation: RNG: L'Ecuyer-CMRG Normal: Inversion Sample: Rejection

locale: [1] pt_BR.UTF-8/pt_BR.UTF-8/pt_BR.UTF-8/C/pt_BR.UTF-8/pt_BR.UTF-8

attached base packages: [1] stats4 grid stats graphics grDevices utils datasets methods
[9] base

other attached packages: [1] inSitu_1.1.1 sits_0.9.5.1 wtss_2.2.0 keras_2.3.0.0.9000 [5] dplyr_1.0.0 sf_0.9-5 tmap_3.1 vctrs_0.3.2
[9] tidyselect_1.1.0 xgboost_1.1.1.1 signal_0.7-6 RSQLite_2.2.0
[13] RCurl_1.98-1.2 ranger_0.12.1 ptw_1.9-15 proto_1.0.0
[17] nnet_7.3-14 mgcv_1.8-31 nlme_3.1-148 MASS_7.3-51.6
[21] lwgeom_0.2-5 kohonen_3.0.10 imputeTS_3.0 imager_0.42.3
[25] magrittr_1.5 flexclust_1.4-0 modeltools_0.2-23 lattice_0.20-41
[29] e1071_1.7-3 dtwSat_0.2.6 ggplot2_3.3.2 snow_0.4-3
[33] raster_3.3-13 sp_1.4-2 zoo_1.8-8 dtwclust_5.5.6
[37] dtw_1.21-3 proxy_0.4-24 dendextend_1.13.4 DBI_1.1.0
[41] testthat_2.3.2 knitr_1.29 Rcpp_1.0.5 rmarkdown_2.3
[45] devtools_2.3.1 usethis_1.6.1

loaded via a namespace (and not attached): [1] utf8_1.1.4 reticulate_1.16-9000 htmlwidgets_1.5.1 pROC_1.16.2
[5] munsell_0.5.0 codetools_0.2-16 units_0.6-7 withr_2.2.0
[9] colorspace_1.4-1 config_0.3 tensorflow_2.2.0 TTR_0.23-6
[13] gbRd_0.4-11 Rdpack_1.0.0 bit64_0.9-7.1 rprojroot_1.3-2
[17] generics_0.0.2 ipred_0.9-9 xfun_0.16 R6_2.4.1
[21] clue_0.3-57 bitops_1.0-6 assertthat_0.2.1 promises_1.1.1
[25] scales_1.1.1 forecast_8.12 gtable_0.3.0 log4r_0.3.2
[29] bmp_0.3 processx_3.4.3 timeDate_3043.102 rlang_0.4.7
[33] zeallot_0.1.0 splines_4.0.2 rgdal_1.5-12 ModelMetrics_1.2.2.2 [37] dichromat_2.0-0 yaml_2.2.1 reshape2_1.4.4 abind_1.4-5
[41] crosstalk_1.1.0.1 backports_1.1.8 httpuv_1.5.4 quantmod_0.4.17
[45] caret_6.0-86 tools_4.0.2 lava_1.6.7 stinepack_1.4
[49] ellipsis_0.3.1 RColorBrewer_1.1-2 sessioninfo_1.1.1 plyr_1.8.6
[53] base64enc_0.1-3 classInt_0.4-3 purrr_0.3.4 ps_1.3.3
[57] prettyunits_1.1.1 rpart_4.1-15 viridis_0.5.1 fracdiff_1.5-1
[61] tmaptools_3.1 ggrepel_0.8.2 cluster_2.1.0 fs_1.4.2
[65] leafem_0.1.3 data.table_1.13.0 RSpectra_0.16-0 readbitmap_0.1.5
[69] lmtest_0.9-37 whisker_0.4 pkgload_1.1.0 shinyjs_1.1
[73] mime_0.9 evaluate_0.14 xtable_1.8-4 XML_3.99-0.5
[77] leaflet_2.0.3 jpeg_0.1-8.1 tfruns_1.4 gridExtra_2.3
[81] compiler_4.0.2 tibble_3.0.3 KernSmooth_2.23-17 crayon_1.3.4
[85] htmltools_0.5.0 later_1.1.0.1 tiff_0.1-5 RcppParallel_5.0.2
[89] lubridate_1.7.9 Matrix_1.2-18 cli_2.0.2 quadprog_1.5-8
[93] parallel_4.0.2 gower_0.2.2 igraph_1.2.5 pkgconfig_2.0.3
[97] bigmemory.sri_0.1.3 geosphere_1.5-10 recipes_0.1.13 foreach_1.5.0
[101] prodlim_2019.11.13 bibtex_0.4.2.2 stringr_1.4.0 callr_3.4.3
[105] digest_0.6.25 leafsync_0.1.0 curl_4.3 shiny_1.5.0
[109] urca_1.3-0 nloptr_1.2.2.2 jsonlite_1.7.0 lifecycle_0.2.0
[113] tseries_0.10-47 bigmemory_4.5.36 desc_1.2.0 viridisLite_0.3.0
[117] fansi_0.4.1 pillar_1.4.6 fastmap_1.0.1 pkgbuild_1.1.0
[121] survival_3.2-3 glue_1.4.1 xts_0.12-0 remotes_2.2.0
[125] png_0.1-7 iterators_1.0.12 bit_1.1-15.2 class_7.3-17
[129] stringi_1.4.6 blob_1.2.1 stars_0.4-3 memoise_1.1.0

gilbertocamara commented 4 years ago

Hi Stella, the problems in the inSitu data have been solved. Please download the inSitu package again.

StellaCarneiro commented 4 years ago

Hi Gilberto,

I get the error of not found for all datasets of insitu now. This does not happen with the data from sits, like samples_mt_4bands, that runs normally.

I've download and reinstalled all packages both in Mac OS and Windows and the error occurs in both. I saw that yesterday, some changes were made in sits package so I'm guessing this has sth to do with it, because when I made a quick test after your reply it was working smoothly.

Erro: objeto 'amazonia_33K_12classes_4bands' não encontrado

Thanks and sorry for the hassle,

Stella

On 31 Jul 2020, at 14:39, Gilberto Camara notifications@github.com wrote:



Hi Stella, the problems in the inSitu data have been solved. Please download the inSitu package again.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHubhttps://github.com/e-sensing/sits/issues/169#issuecomment-667247169, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AG5JRC3FZEIUZCLEMUCGOLLR6L6VHANCNFSM4PLRIKXA.

albhasan commented 4 years ago

Hi Stella,

From your post, it seems like the package dplyr isn't loaded. Try library(dplyr) or library(tidyverse) before loading the samples. Like this:

library(tidyverse) library(devtools) devtools::install_github("e-sensing/inSitu") library(inSitu) data("amazonia_33K_12classes_4bands") amazonia_33K_12classes_4bands.rda

I just tested this code on R version 4.0.2 (2020-06-22) on Ubuntu 16.04.

Cheers!

gilbertocamara commented 4 years ago

Hi Stella

Could you please install the inSitu package again? There were errors in the data set that have now been corrected. Please let me know if it works.

Best Gilberto

On 29 Jul 2020, at 23:01, Stella Mendes Carneiro notifications@github.com wrote:

Hi Gilberto,

Thanks for the quick reply. This package has been amazingly useful to me.

Unfortunately, the dataset amazonia_33K_12classes_4bands is not working. It shows me the following error:

<error/vctrs_error_scalar_type>x must be a vector, not a tbl_df/tbl/data.frame/sits_tibble object.

Backtrace:

  1. sits::sits_select_bands(...)
  2. sits:::.sits_tibble_rename(data)
  3. dplyr::rename(., cube = coverage)
  4. tidyselect::eval_rename(expr(c(...)), .data)
  5. tidyselect:::rename_impl(...)
  6. tidyselect:::eval_select_impl(...)
  7. vctrs::vec_assert(x)
  8. vctrs:::stop_scalar_type(x, arg)
  9. vctrs:::stop_vctrs(msg, "vctrs_error_scalar_type", actual = x)

Run rlang::last_trace() to see the full context.

I've attached my code and system info in case you want to see it. All the other datasets I have managed to use are fine.

Should I report the error at “inSitu” package​ then?

Thank you,

Stella

From: Gilberto Camara notifications@github.com Sent: 29 July 2020 13:54 To: e-sensing/sits sits@noreply.github.com Cc: MENDES CARNEIRO, STELLA (PGT) Stella.Mendes-Carneiro@warwick.ac.uk; Author author@noreply.github.com Subject: Re: [e-sensing/sits] sits_train Samples (#169)

Hi Stella

Please take a look at the “inSitu” package (https://github.com/e-sensing/inSitu https://github.com/e-sensing/inSitu). There are more samples there.

Best Gilberto

On 29 Jul 2020, at 14:21, Stella Mendes Carneiro notifications@github.com wrote:

Where can I find more samples to train my model for the Legal Amazon? I see the Mato Grosso sample, isn't it too small? Thanks

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/e-sensing/sits/issues/169, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABOHEDNJI5XBS6AUW27H5A3R6AH6JANCNFSM4PLRIKXA.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHubhttps://github.com/e-sensing/sits/issues/169#issuecomment-665678440, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AG5JRC2VKUG7K2O3IN3VBJ3R6ASYJANCNFSM4PLRIKXA.

<error/vctrs_error_scalar_type> x must be a vector, not a tbl_df/tbl/data.frame/sits_tibble object. Backtrace:

  1. sits::sits_select_bands(...)
  2. sits:::.sits_tibble_rename(data)
  3. dplyr::rename(., cube = coverage)
  4. tidyselect::eval_rename(expr(c(...)), .data)
  5. tidyselect:::rename_impl(...)
  6. tidyselect:::eval_select_impl(...)
  7. vctrs::vec_assert(x)
  8. vctrs:::stop_scalar_type(x, arg)
  9. vctrs:::stop_vctrs(msg, "vctrs_error_scalar_type", actual = x) Run rlang::last_trace() to see the full context.

    A tibble: 16 x 3

    label count prop

    1 Araguaia 3038 0.0245 2 Campo_Cerrado 17235 0.139 3 Cerradao 18576 0.150 4 Cerrado 49583 0.399 5 Cerrado_Rupestre 7143 0.0575 6 Ciliary_Forest 1989 0.0160 7 Dunas 550 0.00443 8 Fallow_Cotton 703 0.00566 9 Millet_Cotton 386 0.00311 10 Pasture 11740 0.0946 11 Perennial_Crop 132 0.00106 12 Semi_Perennial_Crop 825 0.00664 13 Soy_Corn 5737 0.0462 14 Soy_Cotton 4409 0.0355 15 Soy_Fallow 1873 0.0151 16 Soy_Millet 246 0.00198 [1] "mir" "blue" "nir" "red" "evi" "ndvi" # A tibble: 124,165 x 7 longitude latitude start_date end_date label cube time_series 1 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 2 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 3 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 4 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 5 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 6 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 7 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 8 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 9 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 10 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 # … with 124,155 more rows R version 4.0.2 (2020-06-22) Platform: x86_64-apple-darwin17.0 (64-bit) Running under: macOS Mojave 10.14.6

Matrix products: default BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib LAPACK: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRlapack.dylib

Random number generation: RNG: L'Ecuyer-CMRG Normal: Inversion Sample: Rejection

locale: [1] pt_BR.UTF-8/pt_BR.UTF-8/pt_BR.UTF-8/C/pt_BR.UTF-8/pt_BR.UTF-8

attached base packages: [1] stats4 grid stats graphics grDevices utils datasets methods [9] base

other attached packages: [1] inSitu_1.1.1 sits_0.9.5.1 wtss_2.2.0 keras_2.3.0.0.9000 [5] dplyr_1.0.0 sf_0.9-5 tmap_3.1 vctrs_0.3.2 [9] tidyselect_1.1.0 xgboost_1.1.1.1 signal_0.7-6 RSQLite_2.2.0 [13] RCurl_1.98-1.2 ranger_0.12.1 ptw_1.9-15 proto_1.0.0 [17] nnet_7.3-14 mgcv_1.8-31 nlme_3.1-148 MASS_7.3-51.6 [21] lwgeom_0.2-5 kohonen_3.0.10 imputeTS_3.0 imager_0.42.3 [25] magrittr_1.5 flexclust_1.4-0 modeltools_0.2-23 lattice_0.20-41 [29] e1071_1.7-3 dtwSat_0.2.6 ggplot2_3.3.2 snow_0.4-3 [33] raster_3.3-13 sp_1.4-2 zoo_1.8-8 dtwclust_5.5.6 [37] dtw_1.21-3 proxy_0.4-24 dendextend_1.13.4 DBI_1.1.0 [41] testthat_2.3.2 knitr_1.29 Rcpp_1.0.5 rmarkdown_2.3 [45] devtools_2.3.1 usethis_1.6.1

loaded via a namespace (and not attached): [1] utf8_1.1.4 reticulate_1.16-9000 htmlwidgets_1.5.1 pROC_1.16.2 [5] munsell_0.5.0 codetools_0.2-16 units_0.6-7 withr_2.2.0 [9] colorspace_1.4-1 config_0.3 tensorflow_2.2.0 TTR_0.23-6 [13] gbRd_0.4-11 Rdpack_1.0.0 bit64_0.9-7.1 rprojroot_1.3-2 [17] generics_0.0.2 ipred_0.9-9 xfun_0.16 R6_2.4.1 [21] clue_0.3-57 bitops_1.0-6 assertthat_0.2.1 promises_1.1.1 [25] scales_1.1.1 forecast_8.12 gtable_0.3.0 log4r_0.3.2 [29] bmp_0.3 processx_3.4.3 timeDate_3043.102 rlang_0.4.7 [33] zeallot_0.1.0 splines_4.0.2 rgdal_1.5-12 ModelMetrics_1.2.2.2 [37] dichromat_2.0-0 yaml_2.2.1 reshape2_1.4.4 abind_1.4-5 [41] crosstalk_1.1.0.1 backports_1.1.8 httpuv_1.5.4 quantmod_0.4.17 [45] caret_6.0-86 tools_4.0.2 lava_1.6.7 stinepack_1.4 [49] ellipsis_0.3.1 RColorBrewer_1.1-2 sessioninfo_1.1.1 plyr_1.8.6 [53] base64enc_0.1-3 classInt_0.4-3 purrr_0.3.4 ps_1.3.3 [57] prettyunits_1.1.1 rpart_4.1-15 viridis_0.5.1 fracdiff_1.5-1 [61] tmaptools_3.1 ggrepel_0.8.2 cluster_2.1.0 fs_1.4.2 [65] leafem_0.1.3 data.table_1.13.0 RSpectra_0.16-0 readbitmap_0.1.5 [69] lmtest_0.9-37 whisker_0.4 pkgload_1.1.0 shinyjs_1.1 [73] mime_0.9 evaluate_0.14 xtable_1.8-4 XML_3.99-0.5 [77] leaflet_2.0.3 jpeg_0.1-8.1 tfruns_1.4 gridExtra_2.3 [81] compiler_4.0.2 tibble_3.0.3 KernSmooth_2.23-17 crayon_1.3.4 [85] htmltools_0.5.0 later_1.1.0.1 tiff_0.1-5 RcppParallel_5.0.2 [89] lubridate_1.7.9 Matrix_1.2-18 cli_2.0.2 quadprog_1.5-8 [93] parallel_4.0.2 gower_0.2.2 igraph_1.2.5 pkgconfig_2.0.3 [97] bigmemory.sri_0.1.3 geosphere_1.5-10 recipes_0.1.13 foreach_1.5.0 [101] prodlim_2019.11.13 bibtex_0.4.2.2 stringr_1.4.0 callr_3.4.3 [105] digest_0.6.25 leafsync_0.1.0 curl_4.3 shiny_1.5.0 [109] urca_1.3-0 nloptr_1.2.2.2 jsonlite_1.7.0 lifecycle_0.2.0 [113] tseries_0.10-47 bigmemory_4.5.36 desc_1.2.0 viridisLite_0.3.0 [117] fansi_0.4.1 pillar_1.4.6 fastmap_1.0.1 pkgbuild_1.1.0 [121] survival_3.2-3 glue_1.4.1 xts_0.12-0 remotes_2.2.0 [125] png_0.1-7 iterators_1.0.12 bit_1.1-15.2 class_7.3-17 [129] stringi_1.4.6 blob_1.2.1 stars_0.4-3 memoise_1.1.0 — You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/e-sensing/sits/issues/169#issuecomment-665925369, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABOHEDP7IPI7443JJNSUQCDR6CE4DANCNFSM4PLRIKXA.

StellaCarneiro commented 4 years ago

Hi Gilberto,

It did work! Sorry for the delay. At least for Amazon it’s done. This week, as I get back from holidays, I’ll run it for cerrado.

Thanks a lot for the help! I would also like it to share it with you my working paper in a few weeks - the one I’ve been using e-sensing for.

Best,

Stella

On 11 Aug 2020, at 08:45, Gilberto Camara notifications@github.com wrote:



Hi Stella

Could you please install the inSitu package again? There were errors in the data set that have now been corrected. Please let me know if it works.

Best Gilberto

On 29 Jul 2020, at 23:01, Stella Mendes Carneiro notifications@github.com wrote:

Hi Gilberto,

Thanks for the quick reply. This package has been amazingly useful to me.

Unfortunately, the dataset amazonia_33K_12classes_4bands is not working. It shows me the following error:

<error/vctrs_error_scalar_type>x must be a vector, not a tbl_df/tbl/data.frame/sits_tibble object.

Backtrace:

  1. sits::sits_select_bands(...)
  2. sits:::.sits_tibble_rename(data)
  3. dplyr::rename(., cube = coverage)
  4. tidyselect::eval_rename(expr(c(...)), .data)
  5. tidyselect:::rename_impl(...)
  6. tidyselect:::eval_select_impl(...)
  7. vctrs::vec_assert(x)
  8. vctrs:::stop_scalar_type(x, arg)
  9. vctrs:::stop_vctrs(msg, "vctrs_error_scalar_type", actual = x)

Run rlang::last_trace() to see the full context.

I've attached my code and system info in case you want to see it. All the other datasets I have managed to use are fine.

Should I report the error at “inSitu” package​ then?

Thank you,

Stella

From: Gilberto Camara notifications@github.com Sent: 29 July 2020 13:54 To: e-sensing/sits sits@noreply.github.com Cc: MENDES CARNEIRO, STELLA (PGT) Stella.Mendes-Carneiro@warwick.ac.uk; Author author@noreply.github.com Subject: Re: [e-sensing/sits] sits_train Samples (#169)

Hi Stella

Please take a look at the “inSitu” package (https://github.com/e-sensing/inSitu https://github.com/e-sensing/inSitu). There are more samples there.

Best Gilberto

On 29 Jul 2020, at 14:21, Stella Mendes Carneiro notifications@github.com wrote:

Where can I find more samples to train my model for the Legal Amazon? I see the Mato Grosso sample, isn't it too small? Thanks

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/e-sensing/sits/issues/169, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABOHEDNJI5XBS6AUW27H5A3R6AH6JANCNFSM4PLRIKXA.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHubhttps://github.com/e-sensing/sits/issues/169#issuecomment-665678440, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AG5JRC2VKUG7K2O3IN3VBJ3R6ASYJANCNFSM4PLRIKXA.

<error/vctrs_error_scalar_type> x must be a vector, not a tbl_df/tbl/data.frame/sits_tibble object. Backtrace:

  1. sits::sits_select_bands(...)
  2. sits:::.sits_tibble_rename(data)
  3. dplyr::rename(., cube = coverage)
  4. tidyselect::eval_rename(expr(c(...)), .data)
  5. tidyselect:::rename_impl(...)
  6. tidyselect:::eval_select_impl(...)
  7. vctrs::vec_assert(x)
  8. vctrs:::stop_scalar_type(x, arg)
  9. vctrs:::stop_vctrs(msg, "vctrs_error_scalar_type", actual = x) Run rlang::last_trace() to see the full context.

    A tibble: 16 x 3

    label count prop

    1 Araguaia 3038 0.0245 2 Campo_Cerrado 17235 0.139 3 Cerradao 18576 0.150 4 Cerrado 49583 0.399 5 Cerrado_Rupestre 7143 0.0575 6 Ciliary_Forest 1989 0.0160 7 Dunas 550 0.00443 8 Fallow_Cotton 703 0.00566 9 Millet_Cotton 386 0.00311 10 Pasture 11740 0.0946 11 Perennial_Crop 132 0.00106 12 Semi_Perennial_Crop 825 0.00664 13 Soy_Corn 5737 0.0462 14 Soy_Cotton 4409 0.0355 15 Soy_Fallow 1873 0.0151 16 Soy_Millet 246 0.00198 [1] "mir" "blue" "nir" "red" "evi" "ndvi" # A tibble: 124,165 x 7 longitude latitude start_date end_date label cube time_series 1 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 2 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 3 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 4 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 5 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 6 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 7 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 8 -44.7 -12.7 2015-09-01 2016-08-31 Perennial_Crop MOD13Q1 9 -44.7 -12.7 2014-09-01 2015-08-31 Perennial_Crop MOD13Q1 10 -44.7 -12.7 2016-09-01 2017-08-31 Perennial_Crop MOD13Q1 # … with 124,155 more rows R version 4.0.2 (2020-06-22) Platform: x86_64-apple-darwin17.0 (64-bit) Running under: macOS Mojave 10.14.6

Matrix products: default BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib LAPACK: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRlapack.dylib

Random number generation: RNG: L'Ecuyer-CMRG Normal: Inversion Sample: Rejection

locale: [1] pt_BR.UTF-8/pt_BR.UTF-8/pt_BR.UTF-8/C/pt_BR.UTF-8/pt_BR.UTF-8

attached base packages: [1] stats4 grid stats graphics grDevices utils datasets methods [9] base

other attached packages: [1] inSitu_1.1.1 sits_0.9.5.1 wtss_2.2.0 keras_2.3.0.0.9000 [5] dplyr_1.0.0 sf_0.9-5 tmap_3.1 vctrs_0.3.2 [9] tidyselect_1.1.0 xgboost_1.1.1.1 signal_0.7-6 RSQLite_2.2.0 [13] RCurl_1.98-1.2 ranger_0.12.1 ptw_1.9-15 proto_1.0.0 [17] nnet_7.3-14 mgcv_1.8-31 nlme_3.1-148 MASS_7.3-51.6 [21] lwgeom_0.2-5 kohonen_3.0.10 imputeTS_3.0 imager_0.42.3 [25] magrittr_1.5 flexclust_1.4-0 modeltools_0.2-23 lattice_0.20-41 [29] e1071_1.7-3 dtwSat_0.2.6 ggplot2_3.3.2 snow_0.4-3 [33] raster_3.3-13 sp_1.4-2 zoo_1.8-8 dtwclust_5.5.6 [37] dtw_1.21-3 proxy_0.4-24 dendextend_1.13.4 DBI_1.1.0 [41] testthat_2.3.2 knitr_1.29 Rcpp_1.0.5 rmarkdown_2.3 [45] devtools_2.3.1 usethis_1.6.1

loaded via a namespace (and not attached): [1] utf8_1.1.4 reticulate_1.16-9000 htmlwidgets_1.5.1 pROC_1.16.2 [5] munsell_0.5.0 codetools_0.2-16 units_0.6-7 withr_2.2.0 [9] colorspace_1.4-1 config_0.3 tensorflow_2.2.0 TTR_0.23-6 [13] gbRd_0.4-11 Rdpack_1.0.0 bit64_0.9-7.1 rprojroot_1.3-2 [17] generics_0.0.2 ipred_0.9-9 xfun_0.16 R6_2.4.1 [21] clue_0.3-57 bitops_1.0-6 assertthat_0.2.1 promises_1.1.1 [25] scales_1.1.1 forecast_8.12 gtable_0.3.0 log4r_0.3.2 [29] bmp_0.3 processx_3.4.3 timeDate_3043.102 rlang_0.4.7 [33] zeallot_0.1.0 splines_4.0.2 rgdal_1.5-12 ModelMetrics_1.2.2.2 [37] dichromat_2.0-0 yaml_2.2.1 reshape2_1.4.4 abind_1.4-5 [41] crosstalk_1.1.0.1 backports_1.1.8 httpuv_1.5.4 quantmod_0.4.17 [45] caret_6.0-86 tools_4.0.2 lava_1.6.7 stinepack_1.4 [49] ellipsis_0.3.1 RColorBrewer_1.1-2 sessioninfo_1.1.1 plyr_1.8.6 [53] base64enc_0.1-3 classInt_0.4-3 purrr_0.3.4 ps_1.3.3 [57] prettyunits_1.1.1 rpart_4.1-15 viridis_0.5.1 fracdiff_1.5-1 [61] tmaptools_3.1 ggrepel_0.8.2 cluster_2.1.0 fs_1.4.2 [65] leafem_0.1.3 data.table_1.13.0 RSpectra_0.16-0 readbitmap_0.1.5 [69] lmtest_0.9-37 whisker_0.4 pkgload_1.1.0 shinyjs_1.1 [73] mime_0.9 evaluate_0.14 xtable_1.8-4 XML_3.99-0.5 [77] leaflet_2.0.3 jpeg_0.1-8.1 tfruns_1.4 gridExtra_2.3 [81] compiler_4.0.2 tibble_3.0.3 KernSmooth_2.23-17 crayon_1.3.4 [85] htmltools_0.5.0 later_1.1.0.1 tiff_0.1-5 RcppParallel_5.0.2 [89] lubridate_1.7.9 Matrix_1.2-18 cli_2.0.2 quadprog_1.5-8 [93] parallel_4.0.2 gower_0.2.2 igraph_1.2.5 pkgconfig_2.0.3 [97] bigmemory.sri_0.1.3 geosphere_1.5-10 recipes_0.1.13 foreach_1.5.0 [101] prodlim_2019.11.13 bibtex_0.4.2.2 stringr_1.4.0 callr_3.4.3 [105] digest_0.6.25 leafsync_0.1.0 curl_4.3 shiny_1.5.0 [109] urca_1.3-0 nloptr_1.2.2.2 jsonlite_1.7.0 lifecycle_0.2.0 [113] tseries_0.10-47 bigmemory_4.5.36 desc_1.2.0 viridisLite_0.3.0 [117] fansi_0.4.1 pillar_1.4.6 fastmap_1.0.1 pkgbuild_1.1.0 [121] survival_3.2-3 glue_1.4.1 xts_0.12-0 remotes_2.2.0 [125] png_0.1-7 iterators_1.0.12 bit_1.1-15.2 class_7.3-17 [129] stringi_1.4.6 blob_1.2.1 stars_0.4-3 memoise_1.1.0 — You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/e-sensing/sits/issues/169#issuecomment-665925369, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABOHEDP7IPI7443JJNSUQCDR6CE4DANCNFSM4PLRIKXA.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHubhttps://github.com/e-sensing/sits/issues/169#issuecomment-671786392, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AG5JRCZAFIIUER4AVMITWBLSADZKLANCNFSM4PLRIKXA.

gilbertocamara commented 4 years ago

Problem solved.