kosiew commented on code in PR #1041:
URL:
https://github.com/apache/datafusion-python/pull/1041#discussion_r1978736375
##########
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);
+
match batches_as_string {
- Ok(batch) => Ok(format!("DataFrame()\n{batch}")),
+ Ok(batch) => {
+ if num_rows > 10 {
Review Comment:
using `has_more_rows` from above
```rust
+ if has_more_rows {
```
##########
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:
You can simplify `batches_as_string` to:
```rust
// First get just the first 10 rows
let preview_df = self.df.as_ref().clone().limit(0, Some(10))?;
let preview_batches = wait_for_future(py, preview_df.collect())?;
// Check if there are more rows by trying to get the 11th row
let has_more_rows = {
let check_df = self.df.as_ref().clone().limit(10, Some(1))?;
let check_batch = wait_for_future(py, check_df.collect())?;
!check_batch.is_empty()
};
let batches_as_string =
pretty::pretty_format_batches(&preview_batches);
```
This directly retrieves just the first 10 rows, eliminating the need for
manual row tracking and slicing.
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
