gitlabds 2.2.0__tar.gz → 2.2.1__tar.gz

{gitlabds-2.2.0 → gitlabds-2.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gitlabds
-Version: 2.2.0
+Version: 2.2.1
 Summary: GitLab Data Science Tools
 Author-email: Kevin Dietz <kdietz@gitlab.com>
 License-Expression: MIT
@@ -836,13 +836,13 @@ Status label for a value vs. its peer median (+/- tolerance), not percentile ran
 - _**labels**_ : tuple of (below average, average, above average, no activity) labels
 
 #### Returns
-- Series of status labels, one per input value
+- Series of level labels, one per input value
 
 #### Examples:
 ```python
 import gitlabds
 
-status = gitlabds.value_vs_peer_status(
+level = gitlabds.value_vs_peer_status(
     value=df["monthly_spend"],
     peer_median=df["peer_median_spend"],
     peer_percentile=df["peer_percentile_spend"],
@@ -909,7 +909,7 @@ shap_df = gitlabds.per_record_shap(
 - _**n_bins**_ : quantile bins for numeric `peer_group` columns
 
 #### Returns
-- Long DataFrame, one row per (record, lever): `current_value`, `intervention_value`, `intervention_quantile`, `p_before`, `p_after`, `delta_p`, `impact_bucket`, `band_before`, `band_after`, `crosses_band`
+- Long DataFrame, one row per (record, lever): `current_value`, `intervention_value`, `intervention_quantile`, `p_before`, `p_after`, `delta_p`, `impact_bucket`, `level_before`, `level_after`, `crosses_band`
 
 #### Requirements
 For XGBoost models without `predict_proba`, requires the `xgboost` package (included in core dependencies).

{gitlabds-2.2.0 → gitlabds-2.2.1}/README.md

@@ -804,13 +804,13 @@ Status label for a value vs. its peer median (+/- tolerance), not percentile ran
 - _**labels**_ : tuple of (below average, average, above average, no activity) labels
 
 #### Returns
-- Series of status labels, one per input value
+- Series of level labels, one per input value
 
 #### Examples:
 ```python
 import gitlabds
 
-status = gitlabds.value_vs_peer_status(
+level = gitlabds.value_vs_peer_status(
     value=df["monthly_spend"],
     peer_median=df["peer_median_spend"],
     peer_percentile=df["peer_percentile_spend"],
@@ -877,7 +877,7 @@ shap_df = gitlabds.per_record_shap(
 - _**n_bins**_ : quantile bins for numeric `peer_group` columns
 
 #### Returns
-- Long DataFrame, one row per (record, lever): `current_value`, `intervention_value`, `intervention_quantile`, `p_before`, `p_after`, `delta_p`, `impact_bucket`, `band_before`, `band_after`, `crosses_band`
+- Long DataFrame, one row per (record, lever): `current_value`, `intervention_value`, `intervention_quantile`, `p_before`, `p_after`, `delta_p`, `impact_bucket`, `level_before`, `level_after`, `crosses_band`
 
 #### Requirements
 For XGBoost models without `predict_proba`, requires the `xgboost` package (included in core dependencies).

{gitlabds-2.2.0 → gitlabds-2.2.1}/gitlabds/record_benchmarking.py

@@ -5,7 +5,7 @@ These functions benchmark, explain, and prescribe changes for any indexed set of
 scored records (accounts, users, deals, transactions, etc.) -- `unique_id` is just
 whichever column identifies a row in your data. Includes:
 
-- value_vs_peer_status : status label for a value vs. its peer median (+/- band)
+- value_vs_peer_status : level label for a value vs. its peer median (+/- band)
 - per_record_shap : per-record SHAP attribution (log-odds/margin space) for a tree model
 - per_record_counterfactuals : per-record "change X -> +Y" counterfactual search
 - per_record_peer_percentiles : per-record percentile standing within a peer group
@@ -43,7 +43,7 @@ def value_vs_peer_status(value, peer_median, good_direction=None, tolerance=0.15
     labels : (below average, average, above average, no activity) labels to use
         in place of the defaults.
 
-    Returns a Series of status labels, one per input value.
+    Returns a Series of level labels, one per input value.
     """
     value = pd.Series(value)
     # index=value.index (not .reindex()) so a bare scalar broadcasts correctly.
@@ -56,9 +56,9 @@ def value_vs_peer_status(value, peer_median, good_direction=None, tolerance=0.15
     with np.errstate(divide="ignore", invalid="ignore"):
         rel_diff = (eff_value - eff_median) / denom
     rel_diff = rel_diff.where(denom > 0, np.sign(eff_value - eff_median))
-    status = pd.Series(np.select([rel_diff > tolerance, rel_diff < -tolerance],
-                                  [labels[2], labels[0]], default=labels[1]),
-                        index=value.index)
+    level = pd.Series(np.select([rel_diff > tolerance, rel_diff < -tolerance],
+                                 [labels[2], labels[0]], default=labels[1]),
+                       index=value.index)
     # "near ceiling": already above the peer median AND in the top ceiling_pct of the peer
     # group toward good_direction. Gating on labels[2] (above average) means a compressed
     # peer group whose top decile is still ~median is left "average", not falsely capped.
@@ -66,12 +66,12 @@ def value_vs_peer_status(value, peer_median, good_direction=None, tolerance=0.15
     if peer_percentile is not None:
         pct = pd.Series(peer_percentile, index=value.index).astype(float)
         eff_pct = pct.where(~decreasing, 1 - pct)   # percentile toward the good direction
-        status = status.mask((eff_pct >= ceiling_pct) & (status == labels[2]), ceiling_label)
-    status = status.mask(value.isna(), labels[3])
+        level = level.mask((eff_pct >= ceiling_pct) & (level == labels[2]), ceiling_label)
+    level = level.mask(value.isna(), labels[3])
     if no_activity_value is not None:
         no_activity_value = pd.Series(no_activity_value, index=value.index)
-        status = status.where(value != no_activity_value, labels[3])
-    return status
+        level = level.where(value != no_activity_value, labels[3])
+    return level
 
 
 def per_record_shap(
@@ -205,7 +205,7 @@ def per_record_counterfactuals(
 
     Returns a long DataFrame: one row per (record, lever) with the best move found
     (current_value, intervention_value, intervention_quantile, p_before/p_after/delta_p,
-    impact_bucket, band_before, band_after, crosses_band).
+    impact_bucket, level_before, level_after, crosses_band).
     """
     if impact_medium >= impact_high:
         raise ValueError(f"impact_medium ({impact_medium}) must be less than impact_high ({impact_high})")
@@ -289,9 +289,9 @@ def per_record_counterfactuals(
     _labels = [label for label, _ in _sorted_bands]
     def _band(p):
         return pd.cut(p, bins=_edges, labels=_labels).astype(str)
-    out["band_before"] = _band(out["p_before"])
-    out["band_after"] = _band(out["p_after"])
-    out["crosses_band"] = out["band_before"] != out["band_after"]
+    out["level_before"] = _band(out["p_before"])
+    out["level_after"] = _band(out["p_after"])
+    out["crosses_level"] = out["level_before"] != out["level_after"]
     out.loc[out["crosses_band"] & (out["impact_bucket"] == "Low"), "impact_bucket"] = "Medium"
     return out.sort_values([unique_id, "delta_p"], ascending=[True, False]).reset_index(drop=True)
 

{gitlabds-2.2.0 → gitlabds-2.2.1}/gitlabds.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gitlabds
-Version: 2.2.0
+Version: 2.2.1
 Summary: GitLab Data Science Tools
 Author-email: Kevin Dietz <kdietz@gitlab.com>
 License-Expression: MIT
@@ -836,13 +836,13 @@ Status label for a value vs. its peer median (+/- tolerance), not percentile ran
 - _**labels**_ : tuple of (below average, average, above average, no activity) labels
 
 #### Returns
-- Series of status labels, one per input value
+- Series of level labels, one per input value
 
 #### Examples:
 ```python
 import gitlabds
 
-status = gitlabds.value_vs_peer_status(
+level = gitlabds.value_vs_peer_status(
     value=df["monthly_spend"],
     peer_median=df["peer_median_spend"],
     peer_percentile=df["peer_percentile_spend"],
@@ -909,7 +909,7 @@ shap_df = gitlabds.per_record_shap(
 - _**n_bins**_ : quantile bins for numeric `peer_group` columns
 
 #### Returns
-- Long DataFrame, one row per (record, lever): `current_value`, `intervention_value`, `intervention_quantile`, `p_before`, `p_after`, `delta_p`, `impact_bucket`, `band_before`, `band_after`, `crosses_band`
+- Long DataFrame, one row per (record, lever): `current_value`, `intervention_value`, `intervention_quantile`, `p_before`, `p_after`, `delta_p`, `impact_bucket`, `level_before`, `level_after`, `crosses_band`
 
 #### Requirements
 For XGBoost models without `predict_proba`, requires the `xgboost` package (included in core dependencies).