add find_outliers percentage of total (#81)

WayScience · Sep 3, 2024 · 6122320 · 6122320
1 parent 2d66b5a
commit 6122320
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 199 deletions.
diff --git a/docs/src/examples/cosmicqc_in_a_nutshell.ipynb b/docs/src/examples/cosmicqc_in_a_nutshell.ipynb
diff --git a/docs/src/examples/cosmicqc_in_a_nutshell.py b/docs/src/examples/cosmicqc_in_a_nutshell.py
@@ -25,7 +25,8 @@
 # set a path for the parquet-based dataset
 # (in this case, CellProfiler SQLite data processed by CytoTable)
 data_path = (
-    "../../tests/data/cytotable/NF1_cellpainting_data/Plate_2_with_image_data.parquet"
+    "../../../tests/data/cytotable/NF1_cellpainting_data/"
+    "Plate_2_with_image_data.parquet"
 )
 
 # set a context directory for images associated with the dataset
@@ -76,7 +77,6 @@
 # show histogram reports on the outliers and inliers
 # for each threshold set in the new columns
 labeled_scdf.show_report()
-
 # show cropped images through CytoDataFrame from the dataset to help analyze outliers
 labeled_scdf.sort_values(by="cqc.large_nuclei.is_outlier", ascending=False)[
     [

diff --git a/src/cosmicqc/analyze.py b/src/cosmicqc/analyze.py
@@ -196,7 +196,11 @@ def find_outliers(
     ]
 
     # Print outliers count and range for each feature
-    print("Number of outliers:", outliers_df.shape[0])
+    print(
+        "Number of outliers:",
+        outliers_df.shape[0],
+        f"({'{:.2f}'.format((outliers_df.shape[0] / df.shape[0])*100)}%)",
+    )
     print("Outliers Range:")
     for feature in feature_thresholds:
         print(f"{feature} Min:", outliers_df[feature].min())

diff --git a/tests/test_cli.py b/tests/test_cli.py
@@ -84,7 +84,7 @@ def test_cli_find_outliers(tmp_path: pathlib.Path, basic_outlier_csv: str):
     assert returncode == 0
     assert (
         stdout.strip()
-        == """Number of outliers: 2
+        == """Number of outliers: 2 (20.00%)
 Outliers Range:
 example_feature Min: 9
 example_feature Max: 10