Skip to content

Optimization: borrow texts #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vody-am wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Optimization: borrow texts #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 17 additions & 15 deletions rust/rssparse.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,21 @@ pub struct SparseMatrixBuilder {
num_cols: usize,
}

impl SparseMatrixBuilder {
fn _fit(&mut self, texts: &Vec<HashMap<String, usize>>) {
let mut col_index: usize = 0;
for doc in texts {
for token in doc.keys() {
if !self.vocab.contains_key(token) {
self.vocab.insert(token.clone(), col_index);
col_index += 1;
}
}
}
self.num_cols = col_index;
}
}

#[pymethods]
impl SparseMatrixBuilder {
#[new]
Expand Down Expand Up @@ -59,7 +74,7 @@ impl SparseMatrixBuilder {
self.normalize,
);

self._fit(texts.clone());
self._fit(&texts);

// Scipy csr_matrix are faster to build from numpy arrays.
let (vec1, vec2, vec3) = self._transform(texts);
Expand All @@ -80,20 +95,7 @@ impl SparseMatrixBuilder {
self.normalize,
);

self._fit(texts);
}

fn _fit(&mut self, texts: Vec<HashMap<String, usize>>) {
let mut col_index: usize = 0;
for doc in &texts {
for token in doc.keys() {
if !self.vocab.contains_key(token) {
self.vocab.insert(token.clone(), col_index);
col_index += 1;
}
}
}
self.num_cols = col_index;
self._fit(&texts);
}

pub fn transform(
Expand Down