Mercurial > repos > greg > extract_ipm_date_interval

comparison extract_ipm_date_interval.R @ 0:4dccc60b3525 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Tue, 31 Jul 2018 14:36:56 -0400
parents
children 3126def1a8e9
comparison
equal deleted inserted replaced
-1:000000000000 0:4dccc60b3525
1 #!/usr/bin/env Rscript
2
3 suppressPackageStartupMessages(library("data.table"))
4 suppressPackageStartupMessages(library("optparse"))
5
6 option_list <- list(
7 make_option(c("--input_dir"), action="store", dest="input_dir", help="Directory containing .csv outputs from insect_phenology_model"),
8 make_option(c("--start_date"), action="store", dest="start_date", default=NULL, help="Start date for custom date interval"),
9 make_option(c("--script_dir"), action="store", dest="script_dir", help="R script source directory")
10 )
11
12 parser <- OptionParser(usage="%prog [options] file", option_list=option_list);
13 args <- parse_args(parser, positional_arguments=TRUE);
14 opt <- args$options;
15
16 get_new_temperature_data_frame = function(input_file) {
17 temperature_data_frame = read.csv(file=input_file, header=T, strip.white=TRUE, stringsAsFactors=FALSE, sep=",");
18 colnames(temperature_data_frame) = c("LATITUDE", "LONGITUDE", "DATE", "DOY", "TMIN", "TMAX");
19 return(temperature_data_frame);
20 }
21
22 # Import the shared utility functions.
23 utils_path <- paste(opt$script_dir, "utils.R", sep="/");
24 source(utils_path);
25
26 # FIXME: currently custom date fields are free text, but
27 # Galaxy should soon include support for a date selector
28 # at which point this tool should be enhanced to use it.
29 # Validate start_date.
30
31 # Calaculate the number of days in the date interval.
32 start_date = validate_date(opt$start_date);
33 # Validate end_date.
34 end_date = validate_date(opt$end_date);
35 if (start_date >= end_date) {
36 stop_err("The start date must be between 1 and 50 days before the end date when setting date intervals for plots.");
37 }
38 # Calculate the number of days in the date interval.
39 num_days = difftime(end_date, start_date, units=c("days"));
40 # Add 1 to the number of days to make the dates inclusive. For
41 # example, if the user enters a date range of 2018-01-01 to
42 # 2018-01-31, they likely expect the end date to be included.
43 num_days = num_days + 1;
44 if (num_days > 50) {
45 # We need to restrict date intervals since
46 # plots render tick marks for each day.
47 stop_err("Date intervals for plotting cannot exceed 50 days.");
48 }
49 # Display the total number of days in the Galaxy history item blurb.
50 cat("Number of days in date interval: ", num_days, "\n");
51
52 # Get the year from the start_date.
53 year = get_year_from_date(start_date);
54 # Get the DOY for start_date and end_date.
55 start_date_doy = as.integer(strftime(start_date, format="%j"));
56 end_date_doy = as.integer(strftime(end_date, format="%j"));
57 # Get the ticks date labels for plots.
58 ticks_and_labels = get_x_axis_ticks_and_labels(temperature_data_frame, prepend_end_doy_norm, append_start_doy_norm, date_interval=TRUE);
59 ticks = c(unlist(ticks_and_labels[1]));
60 date_labels = c(unlist(ticks_and_labels[2]));
61 # All latitude values are the same, so get the value
62 # for plots from the first row.
63 latitude = temperature_data_frame$LATITUDE[1];
64
65 input_files = list.files(path=input_dir, full.names=TRUE);
66 for(input_file in input_files) {
67 temperature_data_frame = get_new_temperature_data_frame(input_file);
68 start_date_row = which(temperature_data_frame$DATE==start_date);
69 end_date_row = which(temperature_data_frame$DATE==end_date);
70 # Extract the date interval.
71 temperature_data_frame = temperature_data_frame[start_date_row:end_date_row,];
72 # Save the date interval data into an output file
73 # named the same as the input.
74 file_path = paste("output_data_dir", input_file, sep="/");
75 write.csv(temperature_data_frame, file=file_path, row.names=F);
76 # TODO: Save the dat interval plots...
77 }