I have a code written in R that extracts data from an NC file to compute a time series for a specific location using latitude and longitude. However, the file only outputs three values instead of the entire date timeline. Why is this happening?
Additionally, I received an error message.
`x` must not contain list or matrix columns:✖ invalid columns at index(s): 1 Run `rlang::last_trace()` to see where the error occurred. How can I fix this?
install.packages("ncdf4") install.packages("tidyverse") install.packages("lubridate") library(ncdf4) library(tidyverse) library(lubridate) # Step 1: Define the folder containing NetCDF files and output path folder_path <- "C:/Users/WINDOWS 10/Downloads/MSWEP/Daily" output_csv <- "C:/Users/WINDOWS 10/Downloads/Full_Precipitation_Timeseries2.csv" # Define the target latitude and longitude target_lat <- 14.8903 target_lon <- -19.2321 # Initialize an empty data frame to store the results all_time_series <- data.frame(Date = as.Date(character()), Precipitation = numeric()) # Step 2: Process each NetCDF file in the folder nc_files <- list.files(folder_path, pattern = "\\.nc$", full.names = TRUE) for (file in nc_files) { cat("\nProcessing file:", file, "\n") # Open the NetCDF file nc <- nc_open(file) # Extract latitude, longitude, and time variables latitudes <- ncvar_get(nc, "lat") # Adjust "lat" if variable name differs longitudes <- ncvar_get(nc, "lon") # Adjust "lon" if variable name differs time <- ncvar_get(nc, "time") # Adjust "time" if variable name differs # Convert time to dates time_units <- ncatt_get(nc, "time", "units")$value cat("Time units:", time_units, "\n") time_origin <- strsplit(time_units, "since ")[[1]][2] if (!is.null(time_origin)) { dates <- as.Date(time, origin = time_origin) cat("Sample dates:", head(dates), "\n") } else { cat("Warning: Time origin not found in file:", file, "\n") nc_close(nc) next } # Enforce `dates` as a Date vector dates <- as.Date(dates) # Find the nearest grid point indices for target lat/lon lat_idx <- which.min(abs(latitudes - target_lat)) lon_idx <- which.min(abs(longitudes - target_lon)) cat("Latitude index:", lat_idx, "Longitude index:", lon_idx, "\n") # Extract precipitation data for all available time points precip_subset <- ncvar_get(nc, "precipitation", start = c(lon_idx, lat_idx, 1), count = c(1, 1, -1)) # Adjust count if needed # Ensure `precip_subset` is a numeric vector precip_subset <- as.vector(precip_subset) # Debugging: Check dimensions and content of precipitation data cat("Length of precip_subset:", length(precip_subset), "\n") if (length(precip_subset) > 0) { cat("Sample precipitation data:", head(precip_subset), "\n") } else { cat("Warning: Empty precipitation data for file:", file, "\n") nc_close(nc) next } # Combine dates and precipitation into a data frame file_time_series <- data.frame(Date = dates, Precipitation = precip_subset) # Ensure Date is consistently a Date type file_time_series$Date <- as.Date(file_time_series$Date) # Append to the overall time series all_time_series <- bind_rows(all_time_series, file_time_series) # Close the NetCDF file nc_close(nc) } # Debugging: Check the final combined time series cat("\nFinal time series preview:\n") print(head(all_time_series)) # Step 3: Save the combined time series to a CSV file if (nrow(all_time_series) > 0) { write_csv(all_time_series, output_csv) cat("Precipitation time series saved to:", output_csv, "\n") } else { cat("No valid data extracted. CSV file was not created.\n") } 
