Rename min_rows_display to min_rows in formatter configuration and update related tests

Author: kosiew

docs/source/user-guide/dataframe/rendering.rst

@@ -57,7 +57,7 @@ You can customize how DataFrames are rendered by configuring the formatter:
         max_width=1000,            # Maximum width in pixels
         max_height=300,            # Maximum height in pixels
         max_memory_bytes=2097152,  # Maximum memory for rendering (2MB)
-        min_rows_display=20,       # Minimum number of rows to display
+        min_rows=10,               # Minimum number of rows to display
         max_rows=10,               # Maximum rows to display in __repr__
         enable_cell_expansion=True,# Allow expanding truncated cells
         custom_css=None,           # Additional custom CSS
@@ -190,8 +190,8 @@ You can control how much data is displayed and how much memory is used for rende
 
     configure_formatter(
         max_memory_bytes=4 * 1024 * 1024,  # 4MB maximum memory for display
-        min_rows_display=50,               # Always show at least 50 rows
-        max_rows=20                        # Show 20 rows in __repr__ output
+        min_rows=20,                       # Always show at least 20 rows
+        max_rows=50                        # Show up to 50 rows in output
     )
 
 These parameters help balance comprehensive data display against performance considerations.

python/datafusion/dataframe_formatter.py

@@ -67,7 +67,7 @@ def _validate_formatter_parameters(
     max_width: int,
     max_height: int,
     max_memory_bytes: int,
-    min_rows_display: int,
+    min_rows: int,
     max_rows: int | None,
     repr_rows: int | None,
     enable_cell_expansion: bool,
@@ -83,7 +83,7 @@ def _validate_formatter_parameters(
         max_width: Maximum width value to validate
         max_height: Maximum height value to validate
         max_memory_bytes: Maximum memory bytes value to validate
-        min_rows_display: Minimum rows to display value to validate
+        min_rows: Minimum rows to display value to validate
         max_rows: Maximum rows value to validate (None means use default)
         repr_rows: Deprecated repr_rows value to validate
         enable_cell_expansion: Boolean expansion flag to validate
@@ -105,7 +105,7 @@ def _validate_formatter_parameters(
     _validate_positive_int(max_width, "max_width")
     _validate_positive_int(max_height, "max_height")
     _validate_positive_int(max_memory_bytes, "max_memory_bytes")
-    _validate_positive_int(min_rows_display, "min_rows_display")
+    _validate_positive_int(min_rows, "min_rows")
 
     # Handle deprecated repr_rows parameter
     if repr_rows is not None:
@@ -126,9 +126,9 @@ def _validate_formatter_parameters(
 
     _validate_positive_int(max_rows, "max_rows")
 
-    # Validate constraint: min_rows_display <= max_rows
-    if min_rows_display > max_rows:
-        msg = "min_rows_display must be less than or equal to max_rows"
+    # Validate constraint: min_rows <= max_rows
+    if min_rows > max_rows:
+        msg = "min_rows must be less than or equal to max_rows"
         raise ValueError(msg)
 
     # Validate boolean parameters
@@ -214,7 +214,7 @@ class DataFrameHtmlFormatter:
         max_width: Maximum width of the HTML table in pixels
         max_height: Maximum height of the HTML table in pixels
         max_memory_bytes: Maximum memory in bytes for rendered data (default: 2MB)
-        min_rows_display: Minimum number of rows to display (must be <= max_rows)
+        min_rows: Minimum number of rows to display (must be <= max_rows)
         max_rows: Maximum number of rows to display in repr output
         repr_rows: Deprecated alias for max_rows
         enable_cell_expansion: Whether to add expand/collapse buttons for long cell
@@ -232,7 +232,7 @@ def __init__(
         max_width: int = 1000,
         max_height: int = 300,
         max_memory_bytes: int = 2 * 1024 * 1024,  # 2 MB
-        min_rows_display: int = 10,
+        min_rows: int = 10,
         max_rows: int | None = None,
         repr_rows: int | None = None,
         enable_cell_expansion: bool = True,
@@ -253,7 +253,7 @@ def __init__(
             Maximum height of the displayed table in pixels.
         max_memory_bytes : int, default 2097152 (2MB)
             Maximum memory in bytes for rendered data.
-        min_rows_display : int, default 10
+        min_rows : int, default 10
             Minimum number of rows to display. Must be less than or equal to
             ``max_rows``.
         max_rows : int, default 10
@@ -276,7 +276,7 @@ def __init__(
         ------
         ValueError
             If max_cell_length, max_width, max_height, max_memory_bytes,
-            min_rows_display or max_rows is not a positive integer.
+            min_rows or max_rows is not a positive integer.
         TypeError
             If enable_cell_expansion, show_truncation_message, or use_shared_styles is
             not a boolean,
@@ -290,7 +290,7 @@ def __init__(
             max_width,
             max_height,
             max_memory_bytes,
-            min_rows_display,
+            min_rows,
             max_rows,
             repr_rows,
             enable_cell_expansion,
@@ -304,7 +304,7 @@ def __init__(
         self.max_width = max_width
         self.max_height = max_height
         self.max_memory_bytes = max_memory_bytes
-        self.min_rows_display = min_rows_display
+        self.min_rows = min_rows
         self._max_rows = resolved_max_rows
         self.enable_cell_expansion = enable_cell_expansion
         self.custom_css = custom_css
@@ -794,7 +794,7 @@ def configure_formatter(**kwargs: Any) -> None:
         "max_width",
         "max_height",
         "max_memory_bytes",
-        "min_rows_display",
+        "min_rows",
         "max_rows",
         "repr_rows",
         "enable_cell_expansion",

python/tests/test_dataframe.py

@@ -1438,7 +1438,7 @@ def get_header_style(self) -> str:
 
 def test_html_formatter_memory(df, clean_formatter_state):
     """Test the memory and row control parameters in DataFrameHtmlFormatter."""
-    configure_formatter(max_memory_bytes=10, min_rows_display=1)
+    configure_formatter(max_memory_bytes=10, min_rows=1)
     html_output = df._repr_html_()
 
     # Count the number of table rows in the output
@@ -1448,7 +1448,7 @@ def test_html_formatter_memory(df, clean_formatter_state):
     assert tr_count == 2  # 1 for header row, 1 for data row
     assert "data truncated" in html_output.lower()
 
-    configure_formatter(max_memory_bytes=10 * MB, min_rows_display=1)
+    configure_formatter(max_memory_bytes=10 * MB, min_rows=1)
     html_output = df._repr_html_()
     # With larger memory limit and min_rows=2, should display all rows
     tr_count = count_table_rows(html_output)
@@ -1468,55 +1468,55 @@ def test_html_formatter_memory_boundary_conditions(df, clean_formatter_state):
 
     # Get the raw size of the data to test boundary conditions
     # First, capture output with no limits
-    configure_formatter(max_memory_bytes=10 * MB, min_rows_display=1, max_rows=100)
+    configure_formatter(max_memory_bytes=10 * MB, min_rows=1, max_rows=100)
     unrestricted_output = df._repr_html_()
     unrestricted_rows = count_table_rows(unrestricted_output)
 
     # Test 1: Very small memory limit should still respect min_rows
-    configure_formatter(max_memory_bytes=10, min_rows_display=1)
+    configure_formatter(max_memory_bytes=10, min_rows=1)
     html_output = df._repr_html_()
     tr_count = count_table_rows(html_output)
     assert tr_count >= 2  # At least header + 1 data row (minimum)
     # Should show truncation since we limited memory so aggressively
     assert "data truncated" in html_output.lower()
 
     # Test 2: Memory limit at default size should work well
-    configure_formatter(max_memory_bytes=2 * MB, min_rows_display=1)
+    configure_formatter(max_memory_bytes=2 * MB, min_rows=1)
     html_output = df._repr_html_()
     tr_count = count_table_rows(html_output)
     assert tr_count >= 2  # At least header + min_rows
 
     # Test 3: Very large memory limit should show all data
-    configure_formatter(max_memory_bytes=100 * MB, min_rows_display=1)
+    configure_formatter(max_memory_bytes=100 * MB, min_rows=1)
     html_output = df._repr_html_()
     tr_count = count_table_rows(html_output)
     assert tr_count == unrestricted_rows  # Should show all rows
 
     # Test 4: Min rows should override memory limit
     # With tiny memory and larger min_rows, min_rows should win
-    configure_formatter(max_memory_bytes=10, min_rows_display=2)
+    configure_formatter(max_memory_bytes=10, min_rows=2)
     html_output = df._repr_html_()
     tr_count = count_table_rows(html_output)
     assert tr_count >= 3  # At least header + 2 data rows (min_rows)
     # Should show truncation message despite min_rows being satisfied
     assert "data truncated" in html_output.lower()
 
     # Test 5: Default memory limit with different min_rows
-    configure_formatter(max_memory_bytes=2 * MB, min_rows_display=2, max_rows=2)
+    configure_formatter(max_memory_bytes=2 * MB, min_rows=2, max_rows=2)
     html_output = df._repr_html_()
     tr_count = count_table_rows(html_output)
     assert tr_count == 3  # header + 2 data rows
 
 
 def test_html_formatter_max_rows(df, clean_formatter_state):
-    configure_formatter(min_rows_display=2, max_rows=2)
+    configure_formatter(min_rows=2, max_rows=2)
     html_output = df._repr_html_()
 
     tr_count = count_table_rows(html_output)
     # Table should have header row (1) + 2 data rows = 3 rows
     assert tr_count == 3
 
-    configure_formatter(min_rows_display=2, max_rows=3)
+    configure_formatter(min_rows=2, max_rows=3)
     html_output = df._repr_html_()
 
     tr_count = count_table_rows(html_output)
@@ -1542,11 +1542,11 @@ def test_html_formatter_validation():
     with pytest.raises(ValueError, match="max_memory_bytes must be a positive integer"):
         DataFrameHtmlFormatter(max_memory_bytes=-100)
 
-    with pytest.raises(ValueError, match="min_rows_display must be a positive integer"):
-        DataFrameHtmlFormatter(min_rows_display=0)
+    with pytest.raises(ValueError, match="min_rows must be a positive integer"):
+        DataFrameHtmlFormatter(min_rows=0)
 
-    with pytest.raises(ValueError, match="min_rows_display must be a positive integer"):
-        DataFrameHtmlFormatter(min_rows_display=-5)
+    with pytest.raises(ValueError, match="min_rows must be a positive integer"):
+        DataFrameHtmlFormatter(min_rows=-5)
 
     with pytest.raises(ValueError, match="max_rows must be a positive integer"):
         DataFrameHtmlFormatter(max_rows=0)
@@ -1555,16 +1555,16 @@ def test_html_formatter_validation():
         DataFrameHtmlFormatter(max_rows=-10)
 
     with pytest.raises(
-        ValueError, match="min_rows_display must be less than or equal to max_rows"
+        ValueError, match="min_rows must be less than or equal to max_rows"
     ):
-        DataFrameHtmlFormatter(min_rows_display=5, max_rows=4)
+        DataFrameHtmlFormatter(min_rows=5, max_rows=4)
 
 
 def test_repr_rows_backward_compatibility(clean_formatter_state):
     """Test that repr_rows parameter still works as deprecated alias."""
     # Should work when not conflicting with max_rows
     with pytest.warns(DeprecationWarning, match="repr_rows parameter is deprecated"):
-        formatter = DataFrameHtmlFormatter(repr_rows=15, min_rows_display=10)
+        formatter = DataFrameHtmlFormatter(repr_rows=15, min_rows=10)
     assert formatter.max_rows == 15
     assert formatter.repr_rows == 15
 
@@ -1589,7 +1589,7 @@ def test_configure_formatter(df, clean_formatter_state):
     max_width = 500
     max_height = 30
     max_memory_bytes = 3 * MB
-    min_rows_display = 2
+    min_rows = 2
     max_rows = 2
     enable_cell_expansion = False
     show_truncation_message = False
@@ -1602,7 +1602,7 @@ def test_configure_formatter(df, clean_formatter_state):
     assert formatter_default.max_width != max_width
     assert formatter_default.max_height != max_height
     assert formatter_default.max_memory_bytes != max_memory_bytes
-    assert formatter_default.min_rows_display != min_rows_display
+    assert formatter_default.min_rows != min_rows
     assert formatter_default.max_rows != max_rows
     assert formatter_default.enable_cell_expansion != enable_cell_expansion
     assert formatter_default.show_truncation_message != show_truncation_message
@@ -1614,7 +1614,7 @@ def test_configure_formatter(df, clean_formatter_state):
         max_width=max_width,
         max_height=max_height,
         max_memory_bytes=max_memory_bytes,
-        min_rows_display=min_rows_display,
+        min_rows=min_rows,
         max_rows=max_rows,
         enable_cell_expansion=enable_cell_expansion,
         show_truncation_message=show_truncation_message,
@@ -1625,7 +1625,7 @@ def test_configure_formatter(df, clean_formatter_state):
     assert formatter_custom.max_width == max_width
     assert formatter_custom.max_height == max_height
     assert formatter_custom.max_memory_bytes == max_memory_bytes
-    assert formatter_custom.min_rows_display == min_rows_display
+    assert formatter_custom.min_rows == min_rows
     assert formatter_custom.max_rows == max_rows
     assert formatter_custom.enable_cell_expansion == enable_cell_expansion
     assert formatter_custom.show_truncation_message == show_truncation_message

src/dataframe.rs

@@ -152,7 +152,7 @@ where
 fn build_formatter_config_from_python(formatter: &Bound<'_, PyAny>) -> PyResult<FormatterConfig> {
     let default_config = FormatterConfig::default();
     let max_bytes = get_attr(formatter, "max_memory_bytes", default_config.max_bytes);
-    let min_rows = get_attr(formatter, "min_rows_display", default_config.min_rows);
+    let min_rows = get_attr(formatter, "min_rows", default_config.min_rows);
     let max_rows = get_attr(formatter, "max_rows", default_config.max_rows);
 
     let config = FormatterConfig {