kosiew commented on code in PR #1041:
URL:
https://github.com/apache/datafusion-python/pull/1041#discussion_r1982348422
##########
src/dataframe.rs:
##########
@@ -90,59 +90,108 @@ impl PyDataFrame {
}
fn __repr__(&self, py: Python) -> PyDataFusionResult<String> {
- let df = self.df.as_ref().clone().limit(0, Some(10))?;
+ // Get 11 rows to check if there are more than 10
+ let df = self.df.as_ref().clone().limit(0, Some(11))?;
let batches = wait_for_future(py, df.collect())?;
- let batches_as_string = pretty::pretty_format_batches(&batches);
+ let num_rows = batches.iter().map(|batch|
batch.num_rows()).sum::<usize>();
+
+ // Flatten batches into a single batch for the first 10 rows
+ let mut all_rows = Vec::new();
+ let mut total_rows = 0;
+
+ for batch in &batches {
+ let num_rows_to_take = if total_rows + batch.num_rows() > 10 {
+ 10 - total_rows
+ } else {
+ batch.num_rows()
+ };
+
+ if num_rows_to_take > 0 {
+ let sliced_batch = batch.slice(0, num_rows_to_take);
+ all_rows.push(sliced_batch);
+ total_rows += num_rows_to_take;
+ }
+
+ if total_rows >= 10 {
+ break;
+ }
+ }
+
+ let batches_as_string = pretty::pretty_format_batches(&all_rows);
+
Review Comment:
hi @Spaarsh
Sorry, in my previous test, I overlooked to `maturin develop` for the Rust
changes.
In my retests, two collects does take about 53% longer.
<img width="669" alt="image"
src="https://github.com/user-attachments/assets/032ced3f-3d7d-40cf-9027-42df95799530";
/>
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
