pipe input

This commit is contained in:
randogoth 2024-02-10 20:12:00 +02:00
parent 7ad1f49dc8
commit aac9ba5aff
3 changed files with 69 additions and 38 deletions

43
Cargo.lock generated
View file

@ -2,6 +2,17 @@
# It is not intended for manual editing.
version = 3
[[package]]
name = "atty"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
dependencies = [
"hermit-abi",
"libc",
"winapi",
]
[[package]]
name = "cfg-if"
version = "1.0.0"
@ -19,6 +30,15 @@ dependencies = [
"wasi",
]
[[package]]
name = "hermit-abi"
version = "0.1.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
dependencies = [
"libc",
]
[[package]]
name = "itoa"
version = "1.0.10"
@ -137,6 +157,7 @@ dependencies = [
name = "traktor"
version = "0.1.0"
dependencies = [
"atty",
"rand",
"serde",
"serde_json",
@ -153,3 +174,25 @@ name = "wasi"
version = "0.11.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"

View file

@ -6,6 +6,7 @@ edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
atty = "0.2.14"
rand = "0.8.5"
serde = { version = "1.0.196", features = ["derive"] }
serde_json = "1.0.113"

View file

@ -1,5 +1,5 @@
use std::fs::File;
use std::io::{self, BufRead, BufReader};
use std::io::{self, BufRead, BufReader, stdin, Read};
use std::env;
use std::process;
use serde::Serialize;
@ -102,51 +102,38 @@ fn create_cluster_info(cluster: &[Point]) -> ClusterGapInfo {
}
}
// Adjust the main function and subsequent calculations to work with the new structure and calculate Z-scores accordingly
fn calculate_cluster_density(cluster: &[u32]) -> f32 {
if cluster.len() < 2 { return 0.0; } // Adjust based on how you define density for single-element clusters
let &max_value = cluster.iter().max().unwrap();
let &min_value = cluster.iter().min().unwrap();
let span = (max_value - min_value) as f32;
if span == 0.0 {
return cluster.len() as f32; // Handle clusters where all points have the same value
}
cluster.len() as f32 / span
}
// Assume distance function is defined as before
fn distance(p1: &Point, p2: &Point) -> u32 {
if p1.value > p2.value { p1.value - p2.value } else { p2.value - p1.value }
}
fn calculate_mean_and_std_dev(densities: &[f32]) -> (f32, f32) {
let mean = densities.iter().sum::<f32>() / densities.len() as f32;
let variance = densities.iter().map(|&v| (v - mean).powi(2)).sum::<f32>() / densities.len() as f32;
(mean, variance.sqrt())
}
fn calculate_z_scores(densities: &[f32], mean: f32, std_dev: f32) -> Vec<f32> {
densities.iter().map(|&density| (density - mean) / std_dev).collect()
}
fn main() -> io::Result<()> {
let args: Vec<String> = env::args().collect();
if args.len() < 4 {
eprintln!("Usage: {} <filename> <factor> <min_cluster_size>", args[0]);
process::exit(1);
let mut dataset: Vec<Point> = Vec::new();
// Check if data is being piped into the program
if atty::is(atty::Stream::Stdin) {
// Not receiving piped input, expect filename as argument
if args.len() < 4 {
eprintln!("Usage: {} <filename> <factor> <min_cluster_size>", args[0]);
eprintln!("Or pipe in a list of integers and provide <factor> <min_cluster_size>");
process::exit(1);
}
let filename = &args[1];
dataset = load_dataset(filename)?;
} else {
// Receiving piped input, read from stdin
let stdin = io::stdin();
let reader = stdin.lock();
for line in reader.lines() {
let value: u32 = line?.trim().parse().unwrap();
dataset.push(Point::new(value));
}
dataset.sort_by_key(|p| p.value);
}
let filename = &args[1];
let factor: f32 = args[2].parse().expect("Factor must be a float");
let min_cluster_size: usize = args[3].parse().expect("Min cluster size must be an integer");
let dataset = load_dataset(filename)?;
let factor: f32 = args[args.len() - 2].parse().expect("Factor must be a float");
let min_cluster_size: usize = args[args.len() - 1].parse().expect("Min cluster size must be an integer");
let mut cluster_gap_infos = calculate_densities_and_gaps(&dataset, factor, min_cluster_size);