refactor: move max_prob_diff to comparisons registry

ing-bank · Dec 13, 2021 · 47336bc · 47336bc
1 parent c6a1ca7
commit 47336bc
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 7 deletions.
diff --git a/popmon/analysis/comparison/hist_comparer.py b/popmon/analysis/comparison/hist_comparer.py
@@ -40,7 +40,7 @@
 )
 from ...base import Pipeline
 from ...hist.hist_utils import COMMON_HIST_TYPES, is_numeric
-from ...stats.numpy import googl_test, ks_prob, ks_test, uu_chi2
+from ...stats.numpy import ks_prob, ks_test, uu_chi2
 
 
 def hist_compare(row, hist_name1="", hist_name2="", max_res_bound=7.0):
@@ -70,7 +70,6 @@ def hist_compare(row, hist_name1="", hist_name2="", max_res_bound=7.0):
         "chi2_pvalue": np.nan,
         "chi2_max_residual": np.nan,
         "chi2_spike_count": np.nan,
-        "max_prob_diff": np.nan,
         "unknown_labels": np.nan,
     }
 
@@ -137,7 +136,6 @@ def hist_compare(row, hist_name1="", hist_name2="", max_res_bound=7.0):
     x["chi2_pvalue"] = pvalue
     x["chi2_max_residual"] = max(list(map(abs, res)))
     x["chi2_spike_count"] = sum(abs(r) > max_res_bound for r in res)
-    x["max_prob_diff"] = googl_test(*entries_list)
     for key, func in Comparisons.get_comparisons().items():
         x[key] = func(*entries_list)
     return pd.Series(x)

diff --git a/popmon/config.py b/popmon/config.py
@@ -52,8 +52,6 @@
     + "(one histogram in a time slot and one in {ref})",
     "chi2_spike_count": "The number of normalized residuals of all bin pairs (one histogram in a time"
     + " slot and one in {ref}) with absolute value bigger than a given threshold (default: 7).",
-    "max_prob_diff": "The largest absolute difference between all bin pairs of two normalized "
-    + "histograms (one histogram in a time slot and one in {ref})",
     "unknown_labels": "Are categories observed in a given time slot that are not present in {ref}?",
 }
 comparisons.update(Comparisons.get_descriptions())
@@ -100,7 +98,6 @@
         "*unknown_labels*",
         "*chi2_norm*",
         "*ks*",
-        "*max_prob_diff*",
         "*zscore*",
         "n_*",
         "worst",

diff --git a/popmon/pipeline/metrics_pipelines.py b/popmon/pipeline/metrics_pipelines.py
@@ -141,7 +141,7 @@ def __init__(
                 suffix_mean="_mean",
                 suffix_std="_std",
                 suffix_pull="_pull",
-                metrics=["ref_max_prob_diff"] + [f"ref_{key}" for key in Comparisons.get_comparisons().keys()],
+                metrics=[f"ref_{key}" for key in Comparisons.get_comparisons().keys()],
             ),
             # 4. profiling of histograms, then pull calculation compared with reference mean and std,
             #        to obtain normalized residuals of profiles

diff --git a/popmon/stats/numpy.py b/popmon/stats/numpy.py
@@ -346,6 +346,10 @@ def ks_prob(testscore):
     return pvalue
 
 
+@Comparisons.register(
+    key="max_prob_diff",
+    description="The largest absolute difference between all bin pairs of two normalized histograms (one histogram in a time slot and one in {ref})",
+)
 def googl_test(bins_1, bins_2):
     """Google-paper test