refactor: update HistogramResult attributes for consistency and improve test cases

Author: ElouenGinat

src/khisto/array/histogram/api.py

@@ -119,8 +119,8 @@ def histogram(
     histogram_result = _select_histogram(histogram_results, max_bins=max_bins)
 
     if density:
-        return histogram_result.density.copy(), histogram_result.bin_edges.copy()
+        return histogram_result.densities.copy(), histogram_result.bin_edges.copy()
     else:
-        return histogram_result.frequency.astype(
+        return histogram_result.frequencies.astype(
             np.float64
         ), histogram_result.bin_edges.copy()

src/khisto/core/backend.py

@@ -88,15 +88,15 @@ class HistogramResult:
 
     Attributes
     ----------
-    lower_bound : NDArray[np.float64]
+    lower_bounds : NDArray[np.float64]
         Lower bounds of each bin.
-    upper_bound : NDArray[np.float64]
+    upper_bounds : NDArray[np.float64]
         Upper bounds of each bin.
-    frequency : NDArray[np.int64]
+    frequencies : NDArray[np.int64]
         Count of values in each bin.
-    probability : NDArray[np.float64]
+    probabilities : NDArray[np.float64]
         Probability of each bin (frequency / total).
-    density : NDArray[np.float64]
+    densities : NDArray[np.float64]
         Density of each bin (probability / bin_width).
     is_best : bool
         Whether this histogram is the optimal one.
@@ -114,11 +114,11 @@ class HistogramResult:
         Number of empty intervals in this histogram.
     """
 
-    lower_bound: NDArray[np.float64]
-    upper_bound: NDArray[np.float64]
-    frequency: NDArray[np.int64]
-    probability: NDArray[np.float64]
-    density: NDArray[np.float64]
+    lower_bounds: NDArray[np.float64]
+    upper_bounds: NDArray[np.float64]
+    frequencies: NDArray[np.int64]
+    probabilities: NDArray[np.float64]
+    densities: NDArray[np.float64]
     is_best: bool = False
     granularity: int = 0
     level: float = 0.0
@@ -130,31 +130,31 @@ class HistogramResult:
     @property
     def bin_edges(self) -> NDArray[np.float64]:
         """Return bin edges array (n_bins + 1 values)."""
-        return np.concatenate([self.lower_bound, [self.upper_bound[-1]]])
+        return np.concatenate([self.lower_bounds, [self.upper_bounds[-1]]])
 
     @property
     def bin_widths(self) -> NDArray[np.float64]:
         """Return width of each bin."""
-        return self.upper_bound - self.lower_bound
+        return self.upper_bounds - self.lower_bounds
 
     @property
     def bin_centers(self) -> NDArray[np.float64]:
         """Return center of each bin."""
-        return (self.lower_bound + self.upper_bound) / 2
+        return (self.lower_bounds + self.upper_bounds) / 2
 
     def __len__(self) -> int:
         """Return number of bins."""
-        return len(self.lower_bound)
+        return len(self.lower_bounds)
 
 
 def _to_result(h: _HistogramPayload, **kwargs: Any) -> HistogramResult:
     """Convert a JSON histogram payload to a HistogramResult."""
     return HistogramResult(
-        lower_bound=np.asarray(h.lowerBounds, dtype=np.float64),
-        upper_bound=np.asarray(h.upperBounds, dtype=np.float64),
-        frequency=np.asarray(h.frequencies, dtype=np.int64),
-        probability=np.asarray(h.probabilities, dtype=np.float64),
-        density=np.asarray(h.densities, dtype=np.float64),
+        lower_bounds=np.asarray(h.lowerBounds, dtype=np.float64),
+        upper_bounds=np.asarray(h.upperBounds, dtype=np.float64),
+        frequencies=np.asarray(h.frequencies, dtype=np.int64),
+        probabilities=np.asarray(h.probabilities, dtype=np.float64),
+        densities=np.asarray(h.densities, dtype=np.float64),
         **kwargs,
     )
 
@@ -170,11 +170,13 @@ def _format_runtime_error(
 
 
 def _process_histogram_file(
-    temp_output_file: tempfile._TemporaryFileWrapper[str],
+    temp_output_file_path: str,
 ) -> list[HistogramResult]:
     """Process exploratory JSON generated by khisto CLI."""
-    temp_output_file.seek(0)
-    khisto_output: _KhistoOutput = _KhistoOutput.from_dict(json.load(temp_output_file))
+    with open(temp_output_file_path, "r") as temp_output_file:
+        khisto_output: _KhistoOutput = _KhistoOutput.from_dict(
+            json.load(temp_output_file)
+        )
 
     histogram_series = khisto_output.histogramSeries
     best_idx = histogram_series.interpretableHistogramNumber - 1
@@ -255,7 +257,7 @@ def compute_histograms(x: np.ndarray) -> list[HistogramResult]:
                 raise RuntimeError(message) from e
 
             try:
-                return _process_histogram_file(temp_output_file)
+                return _process_histogram_file(temp_output_file.name)
             except json.JSONDecodeError as e:
                 message = _format_runtime_error(
                     "khisto produced invalid JSON output",

tests/core/test_backend.py

@@ -45,11 +45,11 @@ class TestHistogramResult:
     def test_histogram_result_properties(self):
         """Test HistogramResult properties."""
         result = HistogramResult(
-            lower_bound=np.array([0.0, 1.0, 2.0]),
-            upper_bound=np.array([1.0, 2.0, 3.0]),
-            frequency=np.array([10, 20, 15]),
-            probability=np.array([0.222, 0.444, 0.333]),
-            density=np.array([0.222, 0.444, 0.333]),
+            lower_bounds=np.array([0.0, 1.0, 2.0]),
+            upper_bounds=np.array([1.0, 2.0, 3.0]),
+            frequencies=np.array([10, 20, 15]),
+            probabilities=np.array([0.222, 0.444, 0.333]),
+            densities=np.array([0.222, 0.444, 0.333]),
             is_best=True,
             granularity=2,
         )
@@ -114,7 +114,7 @@ def test_compute_histograms_nan_handling(self):
         results = compute_histograms(data)
 
         finest_result = results[-1]
-        assert np.sum(finest_result.frequency) == 4
+        assert np.sum(finest_result.frequencies) == 4
 
     def test_compute_histograms_reports_cli_failure(self, monkeypatch):
         """Test that CLI failures raise a descriptive runtime error."""
@@ -173,11 +173,11 @@ def test_compute_histograms_writes_binary_input(self, monkeypatch):
 
         expected_result = [
             HistogramResult(
-                lower_bound=np.array([0.0]),
-                upper_bound=np.array([1.0]),
-                frequency=np.array([2]),
-                probability=np.array([1.0]),
-                density=np.array([1.0]),
+                lower_bounds=np.array([0.0]),
+                upper_bounds=np.array([1.0]),
+                frequencies=np.array([2]),
+                probabilities=np.array([1.0]),
+                densities=np.array([1.0]),
                 is_best=True,
                 granularity=0,
             )