rich7420 commented on code in PR #1407:
URL: https://github.com/apache/mahout/pull/1407#discussion_r3448690172
##########
qdp/qdp-core/src/pipeline_runner.rs:
##########
@@ -389,28 +428,67 @@ fn path_extension_lower(path: &Path) -> Option<String> {
.map(|s| s.to_lowercase())
}
-/// Dispatches by path extension to the appropriate io reader. Returns (data,
num_samples, sample_size).
-/// Unsupported or missing extension returns Err with message listing
supported formats.
+/// f64→f32 narrowing cast: values outside f32 range silently become ±Inf.
+fn cast_f64_to_batch_data(
+ data: Vec<f64>,
+ n: usize,
+ s: usize,
+ dtype: Precision,
+ fmt: &str,
+) -> (BatchData, usize, usize) {
+ if matches!(dtype, Precision::Float32) {
+ log::warn!(
+ "{fmt} file loaded as f64, casting to f32: values outside f32
range become ±Inf."
+ );
+ (
+ BatchData::F32(data.iter().map(|&x| x as f32).collect()),
+ n,
+ s,
+ )
+ } else {
+ (BatchData::F64(data), n, s)
+ }
+}
+
fn read_file_by_extension(
path: &Path,
null_handling: NullHandling,
-) -> Result<(Vec<f64>, usize, usize)> {
+ dtype: Precision,
+) -> Result<(BatchData, usize, usize)> {
+ use crate::reader::DataReader;
let ext_lower = path_extension_lower(path);
let ext = ext_lower.as_deref();
match ext {
Some("parquet") => {
- use crate::reader::DataReader;
- let mut reader = crate::readers::ParquetReader::new(path, None,
null_handling)?;
- reader.read_batch()
+ if matches!(dtype, Precision::Float32) {
Review Comment:
+1
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
