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

fix needless-range and clippy::ptr_arg warnings. (#36)

Browse Source 
* Fix needless for loop range

* Do not ignore clippy::ptr_arg
This commit is contained in:
morenol
2020-12-11 16:52:39 -04:00
committed by GitHub
parent 2650416235
commit 53351b2ece
27 changed files with 208 additions and 219 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/tree/decision_tree_classifier.rs
+27 -30
View File
@@ -187,42 +187,42 @@ impl<T: RealNumber> Node<T> {
struct NodeVisitor<'a, T: RealNumber, M: Matrix<T>> {
x: &'a M,
y: &'a Vec<usize>,
y: &'a [usize],
node: usize,
samples: Vec<usize>,
order: &'a Vec<Vec<usize>>,
order: &'a [Vec<usize>],
true_child_output: usize,
false_child_output: usize,
level: u16,
phantom: PhantomData<&'a T>,
}
fn impurity<T: RealNumber>(criterion: &SplitCriterion, count: &Vec<usize>, n: usize) -> T {
fn impurity<T: RealNumber>(criterion: &SplitCriterion, count: &[usize], n: usize) -> T {
let mut impurity = T::zero();
match criterion {
SplitCriterion::Gini => {
impurity = T::one();
for i in 0..count.len() {
if count[i] > 0 {
let p = T::from(count[i]).unwrap() / T::from(n).unwrap();
for count_i in count.iter() {
if *count_i > 0 {
let p = T::from(*count_i).unwrap() / T::from(n).unwrap();
impurity -= p * p;
}
}
}
SplitCriterion::Entropy => {
for i in 0..count.len() {
if count[i] > 0 {
let p = T::from(count[i]).unwrap() / T::from(n).unwrap();
for count_i in count.iter() {
if *count_i > 0 {
let p = T::from(*count_i).unwrap() / T::from(n).unwrap();
impurity -= p * p.log2();
}
}
}
SplitCriterion::ClassificationError => {
for i in 0..count.len() {
if count[i] > 0 {
impurity = impurity.max(T::from(count[i]).unwrap() / T::from(n).unwrap());
for count_i in count.iter() {
if *count_i > 0 {
impurity = impurity.max(T::from(*count_i).unwrap() / T::from(n).unwrap());
}
}
impurity = (T::one() - impurity).abs();
@@ -236,9 +236,9 @@ impl<'a, T: RealNumber, M: Matrix<T>> NodeVisitor<'a, T, M> {
fn new(
node_id: usize,
samples: Vec<usize>,
order: &'a Vec<Vec<usize>>,
order: &'a [Vec<usize>],
x: &'a M,
y: &'a Vec<usize>,
y: &'a [usize],
level: u16,
) -> Self {
NodeVisitor {
@@ -255,13 +255,13 @@ impl<'a, T: RealNumber, M: Matrix<T>> NodeVisitor<'a, T, M> {
}
}
pub(in crate) fn which_max(x: &Vec<usize>) -> usize {
pub(in crate) fn which_max(x: &[usize]) -> usize {
let mut m = x[0];
let mut which = 0;
for i in 1..x.len() {
if x[i] > m {
m = x[i];
for (i, x_i) in x.iter().enumerate().skip(1) {
if *x_i > m {
m = *x_i;
which = i;
}
}
@@ -304,9 +304,9 @@ impl<T: RealNumber> DecisionTreeClassifier<T> {
let mut yi: Vec<usize> = vec![0; y_ncols];
for i in 0..y_ncols {
for (i, yi_i) in yi.iter_mut().enumerate().take(y_ncols) {
let yc = y_m.get(0, i);
yi[i] = classes.iter().position(|c| yc == *c).unwrap();
*yi_i = classes.iter().position(|c| yc == *c).unwrap();
}
let mut nodes: Vec<Node<T>> = Vec::new();
@@ -431,23 +431,20 @@ impl<T: RealNumber> DecisionTreeClassifier<T> {
let parent_impurity = impurity(&self.parameters.criterion, &count, n);
let mut variables = vec![0; n_attr];
for i in 0..n_attr {
variables[i] = i;
}
let mut variables = (0..n_attr).collect::<Vec<_>>();
if mtry < n_attr {
variables.shuffle(&mut rand::thread_rng());
}
for j in 0..mtry {
for variable in variables.iter().take(mtry) {
self.find_best_split(
visitor,
n,
&count,
&mut false_count,
parent_impurity,
variables[j],
*variable,
);
}
@@ -458,7 +455,7 @@ impl<T: RealNumber> DecisionTreeClassifier<T> {
&mut self,
visitor: &mut NodeVisitor<'_, T, M>,
n: usize,
count: &Vec<usize>,
count: &[usize],
false_count: &mut Vec<usize>,
parent_impurity: T,
j: usize,
@@ -527,13 +524,13 @@ impl<T: RealNumber> DecisionTreeClassifier<T> {
let mut fc = 0;
let mut true_samples: Vec<usize> = vec![0; n];
for i in 0..n {
for (i, true_sample) in true_samples.iter_mut().enumerate().take(n) {
if visitor.samples[i] > 0 {
if visitor.x.get(i, self.nodes[visitor.node].split_feature)
<= self.nodes[visitor.node].split_value.unwrap_or_else(T::nan)
{
true_samples[i] = visitor.samples[i];
tc += true_samples[i];
*true_sample = visitor.samples[i];
tc += *true_sample;
visitor.samples[i] = 0;
} else {
fc += visitor.samples[i];
src/tree/decision_tree_regressor.rs
+11 -14
View File
@@ -161,7 +161,7 @@ struct NodeVisitor<'a, T: RealNumber, M: Matrix<T>> {
y: &'a M,
node: usize,
samples: Vec<usize>,
order: &'a Vec<Vec<usize>>,
order: &'a [Vec<usize>],
true_child_output: T,
false_child_output: T,
level: u16,
@@ -171,7 +171,7 @@ impl<'a, T: RealNumber, M: Matrix<T>> NodeVisitor<'a, T, M> {
fn new(
node_id: usize,
samples: Vec<usize>,
order: &'a Vec<Vec<usize>>,
order: &'a [Vec<usize>],
x: &'a M,
y: &'a M,
level: u16,
@@ -219,9 +219,9 @@ impl<T: RealNumber> DecisionTreeRegressor<T> {
let mut n = 0;
let mut sum = T::zero();
for i in 0..y_ncols {
n += samples[i];
sum += T::from(samples[i]).unwrap() * y_m.get(0, i);
for (i, sample_i) in samples.iter().enumerate().take(y_ncols) {
n += *sample_i;
sum += T::from(*sample_i).unwrap() * y_m.get(0, i);
}
let root = Node::new(0, sum / T::from(n).unwrap());
@@ -312,10 +312,7 @@ impl<T: RealNumber> DecisionTreeRegressor<T> {
let sum = self.nodes[visitor.node].output * T::from(n).unwrap();
let mut variables = vec![0; n_attr];
for i in 0..n_attr {
variables[i] = i;
}
let mut variables = (0..n_attr).collect::<Vec<_>>();
if mtry < n_attr {
variables.shuffle(&mut rand::thread_rng());
@@ -324,8 +321,8 @@ impl<T: RealNumber> DecisionTreeRegressor<T> {
let parent_gain =
T::from(n).unwrap() * self.nodes[visitor.node].output * self.nodes[visitor.node].output;
for j in 0..mtry {
self.find_best_split(visitor, n, sum, parent_gain, variables[j]);
for variable in variables.iter().take(mtry) {
self.find_best_split(visitor, n, sum, parent_gain, *variable);
}
self.nodes[visitor.node].split_score != Option::None
@@ -399,13 +396,13 @@ impl<T: RealNumber> DecisionTreeRegressor<T> {
let mut fc = 0;
let mut true_samples: Vec<usize> = vec![0; n];
for i in 0..n {
for (i, true_sample) in true_samples.iter_mut().enumerate().take(n) {
if visitor.samples[i] > 0 {
if visitor.x.get(i, self.nodes[visitor.node].split_feature)
<= self.nodes[visitor.node].split_value.unwrap_or_else(T::nan)
{
true_samples[i] = visitor.samples[i];
tc += true_samples[i];
*true_sample = visitor.samples[i];
tc += *true_sample;
visitor.samples[i] = 0;
} else {
fc += visitor.samples[i];