Merge pull request #278 from uriahf/273-small-changes-for-better-calibration-plots

273 small changes for better calibration plots

Author: uriahf

pyproject.toml

@@ -6,16 +6,16 @@ license = {text = "MIT"}
 requires-python = ">=3.9"
 dependencies = [
     "plotly<6.0.0,>=5.13.1",
-    "polars>=1.28.0",
     "pandas>=2.2.3",
     "typing>=3.7.4.3",
     "polarstate==0.1.8",
     "marimo>=0.17.0",
     "pyarrow>=21.0.0",
     "statsmodels>=0.14.0",
+    "polars>=1.31.0",
 ]
 name = "rtichoke"
-version = "0.1.26"
+version = "0.1.27"
 description = "interactive visualizations for performance of predictive models"
 readme = "README.md"
 

src/rtichoke/calibration/calibration.py

@@ -329,8 +329,6 @@ def _create_plotly_curve_from_calibration_curve_list(
                 pl.col("reference_group") == reference_group
             )
 
-            print(dec_sub)
-
             calibration_curve.add_trace(
                 go.Scatter(
                     x=dec_sub.get_column("x").to_list(),
@@ -438,8 +436,6 @@ def _create_plotly_curve_from_calibration_curve_list(
                 col=1,
             )
 
-    print(calibration_curve_list["axes_ranges"]["xaxis"])
-
     calibration_curve.update_xaxes(
         zeroline=True,
         range=calibration_curve_list["axes_ranges"]["xaxis"],
@@ -458,10 +454,6 @@ def _create_plotly_curve_from_calibration_curve_list(
     )
     calibration_curve.update_yaxes(title="Observed", row=1, col=1)
 
-    print("size")
-    print(calibration_curve_list["size"])
-    print(calibration_curve_list["size"][0])
-
     calibration_curve.update_layout(
         width=calibration_curve_list["size"][0][0],
         height=calibration_curve_list["size"][0][0],
@@ -534,18 +526,18 @@ def _make_deciles_dat_binary(
 
         df = pl.concat(frames, how="vertical")
 
-    labels = [str(i) for i in range(1, n_bins + 1)]
-
     df = df.with_columns(
         [
             pl.col("prob").cast(pl.Float64),
             pl.col("real").cast(pl.Float64),
-            pl.col("prob")
-            .qcut(n_bins, labels=labels, allow_duplicates=True)
-            .over(["reference_group", "model"])
-            .alias("decile"),
+            (
+                (pl.col("prob").rank("ordinal").over(["reference_group", "model"]) - 1)
+                * n_bins
+                // pl.count().over(["reference_group", "model"])
+                + 1
+            ).alias("decile"),
         ]
-    ).with_columns(pl.col("decile").cast(pl.Int32))
+    )
 
     deciles_data = (
         df.group_by(["reference_group", "model", "decile"])
@@ -616,12 +608,8 @@ def _create_calibration_curve_list(
         reference_groups, color_values, performance_type
     )
 
-    print("histogram for calibration")
-
     histogram_for_calibration = _create_histogram_for_calibration(probs)
 
-    print(histogram_for_calibration)
-
     limits = _define_limits_for_calibration_plot(deciles_data)
     axes_ranges = {"xaxis": limits, "yaxis": limits}