Rust implementation of the CVM algorithm for counting distinct elements in a stream
Don't use positional arguments
author
Stephan Hügel
date
(May 23, 2024, 11:33 AM +0100)
commit
3b4da2f2
3b4da2f2ceddffdb02c0e27718a573e8d27c3cdd
parent
5e12c908
5e12c908ffb1e05e737886fbdc4dc373b2ab26b7
+6
-6
+6
-6
src/main.rs
+6
-6
src/main.rs
···
1
1
use clap::{arg, crate_version, value_parser, Command};
2
-
use std::io::BufRead;
3
-
use std::path::PathBuf;
4
2
use std::fs::File;
3
+
use std::io::BufRead;
5
4
use std::io::BufReader;
6
5
use std::path::Path;
6
+
use std::path::PathBuf;
7
7
8
8
use cvmcount::CVM;
9
9
···
21
21
.version(crate_version!())
22
22
.author("Stephan Hügel <urschrei@gmail.com>")
23
23
.about("Use the CVM algorithm to estimate the number of unique tokens in a stream")
24
-
.arg(arg!(-t --tokens <FILE> "A text file containing words").index(1).required(true).value_parser(value_parser!(PathBuf)))
25
-
.arg(arg!(-e --epsilon <EPSILON> "How close you want your estimate to be to the true number of distinct tokens. A smaller ε means you require a more precise estimate. For example, ε = 0.05 means you want your estimate to be within 5 % of the actual value. An epsilon of 0.8 is a good starting point for most applications").index(2).required(true).value_parser(value_parser!(f64)))
26
-
.arg(arg!(-d --delta <DELTA> "The level of certainty that the algorithm's estimate will fall within the desired accuracy range. A higher confidence (e.g., 99.9 %) means you're very sure the estimate will be accurate, while a lower confidence (e.g., 90 %) means there's a higher chance the estimate might be outside the desired range. A delta of 0.1 is a good starting point for most applications").index(3).required(true).value_parser(value_parser!(f64)))
27
-
.arg(arg!(-s --streamsize <STREAM_SIZE> "This is used to determine buffer size and can be a loose approximation. The closer it is to the stream size, the more accurate the results").index(4).required(true).value_parser(value_parser!(usize)))
24
+
.arg(arg!(-t --tokens <FILE> "A text file containing words").required(true).value_parser(value_parser!(PathBuf)))
25
+
.arg(arg!(-e --epsilon <EPSILON> "How close you want your estimate to be to the true number of distinct tokens. A smaller ε means you require a more precise estimate. For example, ε = 0.05 means you want your estimate to be within 5 % of the actual value. An epsilon of 0.8 is a good starting point for most applications").required(true).value_parser(value_parser!(f64)))
26
+
.arg(arg!(-d --delta <DELTA> "The level of certainty that the algorithm's estimate will fall within the desired accuracy range. A higher confidence (e.g., 99.9 %) means you're very sure the estimate will be accurate, while a lower confidence (e.g., 90 %) means there's a higher chance the estimate might be outside the desired range. A delta of 0.1 is a good starting point for most applications").required(true).value_parser(value_parser!(f64)))
27
+
.arg(arg!(-s --streamsize <STREAM_SIZE> "This is used to determine buffer size and can be a loose approximation. The closer it is to the stream size, the more accurate the results").required(true).value_parser(value_parser!(usize)))
28
28
.get_matches();
29
29
let input_file = params.get_one::<PathBuf>("tokens").unwrap();
30
30
let epsilon = params.get_one::<f64>("epsilon").unwrap();