work/smartcore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fmt fix

Browse Source
This commit is contained in:
gaxler
2021-01-25 23:55:43 -08:00
parent 991631876e
commit dbca6d43ce
3 changed files with 79 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lib.rs
+2 -2
View File
@@ -91,9 +91,9 @@ pub mod naive_bayes;
/// Supervised neighbors-based learning methods
pub mod neighbors;
pub(crate) mod optimization;
/// Preprocessing utilities
pub mod preprocessing;
/// Support Vector Machines
pub mod svm;
/// Supervised tree-based learning methods
pub mod tree;
/// Preprocessing utilities
pub mod preprocessing;
src/preprocessing/mod.rs
+1 -1
View File
@@ -1 +1 @@
pub mod target_encoders;
pub mod target_encoders;
src/preprocessing/target_encoders.rs
+76 -72
View File
@@ -1,22 +1,18 @@
#![allow(clippy::ptr_arg)]
//! # Encode categorical features as a one-hot or multi-class numeric array.
//!
//!
use std::hash::Hash;
use std::collections::HashMap;
use crate::math::num::RealNumber;
use crate::error::Failed;
use crate::math::num::RealNumber;
use std::collections::HashMap;
use std::hash::Hash;
/// Turn a collection of label types into a one-hot vectors.
/// This struct encodes single class per exmample
pub struct OneHotEncoder<T> {
label_to_idx: HashMap<T, usize>,
labels: Vec<T>,
num_classes: usize
num_classes: usize,
}
enum LabelDefinition<T> {
@@ -27,13 +23,18 @@ enum LabelDefinition<T> {
/// Crearte a vector of size num_labels with zeros everywhere and 1 at label_idx (one-hot vector)
pub fn make_one_hot<T: RealNumber>(label_idx: usize, num_labels: usize) -> Vec<T> {
let (pos, neg) = (T::from_f64(1f64).unwrap(), T::from_f64(0f64).unwrap());
(0..num_labels).map(|idx| if idx == label_idx {pos.clone()} else {neg.clone()}).collect()
(0..num_labels)
.map(|idx| {
if idx == label_idx {
pos.clone()
} else {
neg.clone()
}
})
.collect()
}
impl<'a, T: Hash + Eq + Clone> OneHotEncoder<T>
{
impl<'a, T: Hash + Eq + Clone> OneHotEncoder<T> {
/// Fit an encoder to a lable list
///
/// Label numbers will be assigned in the order they are encountered
@@ -45,23 +46,24 @@ impl<'a, T: Hash + Eq + Clone> OneHotEncoder<T>
/// assert_eq!(oh_vec, vec![1f64,0f64,0f64,0f64,0f64]);
/// ```
pub fn fit(labels: &[T]) -> Self {
let mut label_map: HashMap<T, usize> = HashMap::new();
let mut class_num = 0usize;
let mut unique_lables: Vec<T> = Vec::new();
for l in labels
{
for l in labels {
if !label_map.contains_key(&l) {
label_map.insert(l.clone(), class_num);
unique_lables.push(l.clone());
class_num += 1;
}
}
Self {label_to_idx: label_map, num_classes: class_num, labels:unique_lables}
Self {
label_to_idx: label_map,
num_classes: class_num,
labels: unique_lables,
}
}
/// Build an encoder from a predefined (label -> class number) map
///
/// Definition example:
@@ -84,21 +86,18 @@ impl<'a, T: Hash + Eq + Clone> OneHotEncoder<T>
pub fn from_positional_label_vec(labels: Vec<T>) -> Self {
Self::from_label_def(LabelDefinition::PositionalLabel(labels))
}
/// Transform a slice of label types into one-hot vectors
/// None is returned if unknown label is encountered
/// None is returned if unknown label is encountered
pub fn transform(&self, labels: &[T]) -> Vec<Option<Vec<f64>>> {
labels
.into_iter()
.map(|l| self.transform_one(l))
.collect()
labels.into_iter().map(|l| self.transform_one(l)).collect()
}
/// Transform a single label type into a one-hot vector
pub fn transform_one(&self, label: &T) -> Option<Vec<f64>> {
match self.label_to_idx.get(label) {
None => None,
Some(&idx) => Some(make_one_hot(idx, self.num_classes))
Some(&idx) => Some(make_one_hot(idx, self.num_classes)),
}
}
@@ -111,99 +110,104 @@ impl<'a, T: Hash + Eq + Clone> OneHotEncoder<T>
let pos = U::from_f64(1f64).unwrap();
let s: Vec<usize> = one_hot
.into_iter()
.enumerate()
.filter_map(|(idx, v)| if v == pos {Some(idx)} else {None})
.collect();
.into_iter()
.enumerate()
.filter_map(|(idx, v)| if v == pos { Some(idx) } else { None })
.collect();
if s.len() == 1 {
let idx = s[0];
return Ok(self.labels[idx].clone())
return Ok(self.labels[idx].clone());
}
let pos_entries = format!("Expected a single positive entry, {} entires found", s.len());
let pos_entries = format!(
"Expected a single positive entry, {} entires found",
s.len()
);
Err(Failed::transform(&pos_entries[..]))
}
fn from_label_def(labels: LabelDefinition<T>) -> Self {
let (label_map, class_num, unique_lables) = match labels {
LabelDefinition::LabelToClsNumMap(h) => {
let mut _unique_lab: Vec<(T, usize)> = h.iter().map(|(k,v)| (k.clone(), v.clone())).collect();
_unique_lab.sort_by(|a,b| a.1.cmp(&b.1));
let mut _unique_lab: Vec<(T, usize)> =
h.iter().map(|(k, v)| (k.clone(), v.clone())).collect();
_unique_lab.sort_by(|a, b| a.1.cmp(&b.1));
let unique_lab: Vec<T> = _unique_lab.into_iter().map(|a| a.0).collect();
(h, unique_lab.len(), unique_lab)
},
}
LabelDefinition::PositionalLabel(unique_lab) => {
let h: HashMap<T, usize> = unique_lab.iter().enumerate().map(|(v, k)| (k.clone(),v)).collect();
let h: HashMap<T, usize> = unique_lab
.iter()
.enumerate()
.map(|(v, k)| (k.clone(), v))
.collect();
(h, unique_lab.len(), unique_lab)
}
};
Self {label_to_idx: label_map, num_classes: class_num, labels:unique_lables}
Self {
label_to_idx: label_map,
num_classes: class_num,
labels: unique_lables,
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn from_labels() {
let fake_labels: Vec<usize> = vec![1,2,3,4,5,3,5,3,1,2,4];
let fake_labels: Vec<usize> = vec![1, 2, 3, 4, 5, 3, 5, 3, 1, 2, 4];
let enc = OneHotEncoder::<usize>::fit(&fake_labels[0..]);
let oh_vec = match enc.transform_one(&1) {
None => panic!("Wrong labels"),
Some(v) => v
Some(v) => v,
};
let res: Vec<f64> = vec![1f64,0f64,0f64,0f64,0f64];
let res: Vec<f64> = vec![1f64, 0f64, 0f64, 0f64, 0f64];
assert_eq!(oh_vec, res);
}
fn build_fake_str_enc<'a>() -> OneHotEncoder<&'a str>{
let fake_label_pos = vec!["background","dog", "cat"];
fn build_fake_str_enc<'a>() -> OneHotEncoder<&'a str> {
let fake_label_pos = vec!["background", "dog", "cat"];
let enc = OneHotEncoder::<&str>::from_positional_label_vec(fake_label_pos);
enc
}
#[test]
fn label_map_and_vec() {
let fake_label_map: HashMap<&str, usize> = vec![("background",0), ("dog", 1), ("cat", 2)].into_iter().collect();
let enc = OneHotEncoder::<&str>::from_label_map(fake_label_map);
let oh_vec = match enc.transform_one(&"dog") {
None => panic!("Wrong labels"),
Some(v) => v
};
let res: Vec<f64> = vec![0f64, 1f64,0f64];
assert_eq!(oh_vec, res);
}
let fake_label_map: HashMap<&str, usize> = vec![("background", 0), ("dog", 1), ("cat", 2)]
.into_iter()
.collect();
let enc = OneHotEncoder::<&str>::from_label_map(fake_label_map);
let oh_vec = match enc.transform_one(&"dog") {
None => panic!("Wrong labels"),
Some(v) => v,
};
let res: Vec<f64> = vec![0f64, 1f64, 0f64];
assert_eq!(oh_vec, res);
}
#[test]
fn positional_labels_vec() {
let enc = build_fake_str_enc();
let oh_vec = match enc.transform_one(&"dog") {
None => panic!("Wrong labels"),
Some(v) => v
};
let res: Vec<f64> = vec![0f64, 1f64,0f64];
assert_eq!(oh_vec, res);
let enc = build_fake_str_enc();
let oh_vec = match enc.transform_one(&"dog") {
None => panic!("Wrong labels"),
Some(v) => v,
};
let res: Vec<f64> = vec![0.0, 1.0, 0.0];
assert_eq!(oh_vec, res);
}
#[test]
fn invert_label_test() {
let enc = build_fake_str_enc();
let res: Vec<f64> = vec![0f64, 1f64,0f64];
let res: Vec<f64> = vec![0.0, 1.0, 0.0];
let lab = enc.invert_one(res).unwrap();
assert_eq!(lab, "dog");
if let Err(e) = enc.invert_one(vec![0.0, 0.0,0.0]) {
if let Err(e) = enc.invert_one(vec![0.0, 0.0, 0.0]) {
let pos_entries = format!("Expected a single positive entry, 0 entires found");
assert_eq!(e, Failed::transform(&pos_entries[..]));
};
}
}
}