possibility to truncate timeseries with --start/stop cli arguments

Cargo.lock

@@ -293,7 +293,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 
 [[package]]
 name = "wham"
-version = "0.9.2"
+version = "0.9.4"
 dependencies = [
  "GSL 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "clap 2.32.0 (registry+https://github.com/rust-lang/crates.io-index)",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "wham"
-version = "0.9.3"
+version = "0.9.4"
 authors = ["D. Bauer <bauer@bio.tu-darmstadt.de>"]
 description = "An implementation of the weighted histogram analysis method"
 license = "GPL-3.0"

src/cli.yml

@@ -86,3 +86,13 @@ args:
         help: Number of bayesian bootstrapping runs for error analysis by assigning random weights (defaults to 0).
         takes_value: true
         required: false
+    - start:
+        long: start
+        help: Skip rows in timeseries with an index smaller than this value (defaults to 0)
+        takes_value: true
+        required: false
+    - end:
+        long: end
+        help: Skip rows in timeseries with an index larger than this value (defaults to 1e+20)
+        takes_value: true
+        required: false

src/io.rs

@@ -101,7 +101,7 @@ fn flat_index(indeces: &Vec<usize>, lengths: &Vec<usize>) -> usize {
 }
 
 // returns true if the values are inside the histogram boundaries defined by cfg
-fn is_in_hist_boundaries(values: &Vec<f64>, cfg: &Config) -> bool {
+fn is_in_hist_boundaries(values: &[f64], cfg: &Config) -> bool {
     for dimen in 0..cfg.dimens {
         if values[dimen] < cfg.hist_min[dimen] || values[dimen] > cfg.hist_max[dimen] {
             return false
@@ -110,6 +110,14 @@ fn is_in_hist_boundaries(values: &Vec<f64>, cfg: &Config) -> bool {
     true
 }
 
+// returns true given time in inside the time boundaries defined by cfg
+fn is_in_time_boundaries(time: f64, cfg: &Config) -> bool {
+    if cfg.start <= time && time <= cfg.end {
+        return true
+    }
+    false
+}
+
 // parse a timeseries file into a histogram
 fn read_window_file(window_file: &str, cfg: &Config) -> Result<Histogram> {
 	let f = File::open(window_file)
@@ -143,15 +151,15 @@ fn read_window_file(window_file: &str, cfg: &Config) -> Result<Histogram> {
                 bail!(format!("Wrong number of columns in line {} of window file {}. Empty Line?.", linecount, window_file));
             }
 
-            let mut values: Vec<f64> = vec![f64::NAN; cfg.dimens];
+            let mut values: Vec<f64> = vec![f64::NAN; cfg.dimens+1];
             for i in 0..values.len() {
-                values[i] = split[i+1].parse::<f64>()
+                values[i] = split[i].parse::<f64>()
                     .chain_err(|| format!("Failed to parse line {} of window file {}.", linecount, window_file))?;
             }
 
-            if is_in_hist_boundaries(&values, cfg) {
+            if is_in_hist_boundaries(&values[1..], cfg) && is_in_time_boundaries(values[0], cfg) {
                 let bin_indeces = (0..cfg.dimens).map(|dimen: usize| {
-                    let val = values[dimen];
+                    let val = values[dimen+1];
                     ((val - cfg.hist_min[dimen]) / bin_width[dimen]) as usize
                 }).collect();
                 let index = flat_index(&bin_indeces, &cfg.num_bins);
@@ -203,6 +211,8 @@ mod tests {
             cyclic: false,
             output: "qwert".to_string(),
             bootstrap: 0,
+            start: 0.0,
+            end: 1e+20
         }
     }
 

src/lib.rs

@@ -38,6 +38,8 @@ pub struct Config {
 	pub cyclic: bool,
 	pub output: String,
 	pub bootstrap: usize,
+    pub start: f64,
+    pub end: f64,
 }
 
 impl fmt::Display for Config {

src/main.rs

@@ -30,7 +30,11 @@ fn cli() -> Result<Config> {
         .split(',').map(|x| { x.parse().unwrap() }).collect();
 	let bootstrap: usize = matches.value_of("bootstrap").unwrap_or("0").parse()
 		.chain_err(|| "Cannot parse bootstrap iteration.")?;
-
+    let start: f64 = matches.value_of("start").unwrap_or("0").parse()
+        .chain_err(|| "Cannot parse start time.")?;
+    let end: f64 = matches.value_of("end").unwrap_or("1e+20").parse()
+        .chain_err(|| "Cannot parse end time.")?;
+     
     if num_bins.len() != hist_max.len() || num_bins.len() != hist_max.len() {
         eprintln!("Input dimensions do not match (min: {}, max: {}, bins: {})",
                   hist_min.len(), hist_max.len(), num_bins.len());
@@ -41,7 +45,7 @@ fn cli() -> Result<Config> {
 
 	Ok(wham::Config{metadata_file, hist_min, hist_max, num_bins, dimens,
 		verbose, tolerance, max_iterations, temperature, cyclic, output,
-		bootstrap})
+		bootstrap, start, end})
 }
 
 fn main() {

tests/integration.rs

@@ -16,21 +16,6 @@ mod integration {
         assert!(out.contains(expected_error));
     }
 
-    #[test]
-    fn data_out_of_bonds() {
-        let output = Command::new("./target/debug/wham")
-            .args(&["--bins", "100", "--min", "2.0", "--max", "3.0", "-T", "300"])
-            .args(&["-f", "example/1d/metadata.dat"])
-            .args(&["-o", "/dev/null"])
-            .output()
-            .expect("failed to execute process");
-        let output = String::from_utf8_lossy(&output.stderr);
-        println!("{}", output);
-        assert!(output.to_string().contains(
-            "No data points in histogram boundaries"
-        ));
-    }
-
     #[test]
     fn unparseable_bias_pos() {
         let output = Command::new("./target/debug/wham")
@@ -107,6 +92,25 @@ mod integration {
         ));
     }
 
+    #[test]
+    fn skip_rows() {
+        let output = Command::new("./target/debug/wham")
+            .args(&["--bins", "100", "--max", "3.14", "--min", "-3.14", "-T", "300", "--cyclic"])
+            .args(&["-f", "example/1d/metadata.dat"])
+            .args(&["-o", "/tmp/wham_test_1d.out"])
+            .args(&["--start", "50", "--end", "60"])
+            .args(&["-v"])
+            .output()
+            .expect("failed to execute process");
+
+        let output = String::from_utf8_lossy(&output.stdout);
+        println!("{}", output);
+        assert!(output.to_string().contains(
+            "25 windows, 12489 datapoints"
+        ));
+    }
+
+
     #[test]
     fn wham_1d() {;
         Command::new("./target/debug/wham")