Function recoreco::indicators
source · pub fn indicators<T>(
interactions: T,
data_dict: &DataDictionary,
num_indicators_per_item: usize,
f_max: u32,
k_max: u32
) -> SparseBinaryMatrixwhere
T: Iterator<Item = (String, String)>,
Expand description
Compute item indicators from a stream of interactions.
interactions
- the observed interactionsdata_dict
- a data dictionary which maps string to integer identifiersnum_indicators_per_item
- the number of highly associated items to compute per item (use 10 as default)f_max
- the maximum number of interactions to account for per user (use 500 as default)k_max
- The maximum number of interactions to account for per item (use 500 as default)
Examples
Basic usage:
extern crate recoreco;
use recoreco::stats::{DataDictionary, Renaming};
use recoreco::indicators;
/* Our input data comprises of observed interactions between users and items.
The identifiers used can be strings of arbitrary length and structure. */
let interactions = vec![
(String::from("alice"), String::from("apple")),
(String::from("alice"), String::from("dog")),
(String::from("alice"), String::from("pony")),
(String::from("bob"), String::from("apple")),
(String::from("bob"), String::from("pony")),
(String::from("charles"), String::from("pony")),
(String::from("charles"), String::from("bike"))
];
/* Internally, recoreco uses consecutive integer ids and requires some knowledge about
the statistics of the data for efficient allocation. Therefore, we read the
interaction data once to compute a data dictionary that helps us map from string to
integer identifiers and has basic statistics of the data */
let data_dict = DataDictionary::from(interactions.iter());
println!(
"Found {} interactions between {} users and {} items.",
data_dict.num_interactions(),
data_dict.num_users(),
data_dict.num_items(),
);
/* Now we read the interactions a second time and compute the indicator matrix from item
cooccurrences. The result is the so-called indicator matrix, where each entry
indicates highly associated pairs of items. */
let indicated_items = indicators(
interactions.into_iter(),
&data_dict,
10,
500,
500
);
/* The renaming data structure helps us map the integer ids back to the original
string ids. */
let renaming = Renaming::from(data_dict);
/* We print the resulting highly associated pairs of items. */
for (item_index, indicated_items_for_item) in indicated_items.iter().enumerate() {
let item_name = renaming.item_name(item_index as u32);
println!("Items highly associated with {}:", item_name);
for indicated_item_index in indicated_items_for_item.iter() {
let indicated_item_name = renaming.item_name(*indicated_item_index as u32);
println!("\t{}", indicated_item_name);
}
}