Rust implementation of the CVM algorithm for counting distinct elements in a stream
Better arg layout
author
Stephan Hügel
date
(May 23, 2024, 1:20 PM +0100)
commit
d9be0ba3
d9be0ba3a759a554d08ec43ba40bcabbca232197
parent
79ecb61a
79ecb61a6fa3eee3cfc3f1d9107637228394e520
+13
-4
+13
-4
src/main.rs
+13
-4
src/main.rs
···
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").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)))
24
+
.arg(arg!(-t --tokens <FILE> "A text file containing words")
25
+
.required(true)
26
+
.value_parser(value_parser!(PathBuf)))
27
+
.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")
28
+
.required(true)
29
+
.value_parser(clap::value_parser!(f64))
30
+
)
31
+
.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")
32
+
.required(true)
33
+
.value_parser(value_parser!(f64)))
34
+
.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")
35
+
.required(true)
36
+
.value_parser(value_parser!(usize)))
28
37
.get_matches();
29
38
let input_file = params.get_one::<PathBuf>("tokens").unwrap();
30
39
let epsilon = params.get_one::<f64>("epsilon").unwrap();