Fix/Don't remove rows with mean R = 1 (#70)

* Don't remove rows with mean R = 1 * More rigorous outlier filter * Update pyproject.toml --------- Co-authored-by: Jarrett Ye <[email protected]>
open-spaced-repetition · Dec 26, 2023 · 84f3d15 · 84f3d15
1 parent 267e66d
commit 84f3d15
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 4 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "FSRS-Optimizer"
-version = "4.20.3"
+version = "4.20.4"
 readme = "README.md"
 dependencies = [
     "matplotlib>=3.7.0",

diff --git a/src/fsrs_optimizer/fsrs_optimizer.py b/src/fsrs_optimizer/fsrs_optimizer.py
@@ -646,14 +646,13 @@ def remove_outliers(group: pd.DataFrame) -> pd.DataFrame:
             has_been_removed = 0
             for i in sort_index:
                 count = grouped_group.loc[i, ("y", "count")]
-                if has_been_removed + count >= total * 0.05:
+                if has_been_removed + count >= max(total * 0.05, 20):
                     break
                 has_been_removed += count
             group = group[
                 group["delta_t"].isin(
                     grouped_group[
-                        (grouped_group[("y", "count")] >= count)
-                        & (grouped_group[("y", "mean")] < 1)
+                        (grouped_group[("y", "count")] >= max(count, 6))
                     ]["delta_t"]
                 )
             ]