Skip to content

dealing with infinite or missing values #21

@qmwnebrv

Description

@qmwnebrv

Hi Philipp, Just wondering if you could help me identify how to debug the following error:
Error in svd(x, nu = 0, nv = k) : infinite or missing values in 'x'
This is coming from the following:

spectra <- read_opus_univ(vial_paths)

test_table <- spectra %>%
  gather_spc() %>%
  resample_spc(x_unit = 'wavenumber',
               wn_interval=2) %>%
  average_spc() %>%
  preprocess_spc(select = 'sg_1_w21')

#### Read N ANalysis data ####

Nitrogen_Raw <- readxl::read_xlsx('Nitrogen_analysis.xlsx', skip = 5)[1:108,] %>%
  mutate(sample_id = paste('Harvest',H,'Row',Row,'Range',Range, sep = ' ')) %>% # Create a sampleID
  select(sample_id, H, Row, Range, `%C`, `%N`) %>% # Move sampleID to the front
  mutate(sample_id = as.factor(sample_id)) %>%
  rename(N = `%N`,
         C = `%C`)

#### Join N analysis dataset with Spectral data ####
spec_chem <- join_spc_chem(spc_tbl = test_table, chem_tbl = Nitrogen_Raw, by = "sample_id")

pls_mod <- fit_pls(
  spec_chem = spec_chem[!is.na(spec_chem$N),],
  response =
    N, 
  center = T,
  scale = T,
  print = T
)

I assume this is because there is missing data somewhere, but I don't know how exactly to clean it up. Any ideas would be appreciated!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions