From cd7fbe6ee16d2ba04378f3709197a42ee01dc67f Mon Sep 17 00:00:00 2001
From: maurever <veronika@maurerova.cz>
Date: Fri, 11 Feb 2022 15:06:58 +0100
Subject: [PATCH] PUDBEV-8485 fix python examples, fix type

---
 h2o-py/h2o/model/metrics_base.py | 59 +++++++++++++++-----------------
 h2o-py/h2o/model/model_base.py   | 23 ++++++++++++-
 2 files changed, 50 insertions(+), 32 deletions(-)

diff --git a/h2o-py/h2o/model/metrics_base.py b/h2o-py/h2o/model/metrics_base.py
index 92660ab9746e..37cd7c374cdf 100644
--- a/h2o-py/h2o/model/metrics_base.py
+++ b/h2o-py/h2o/model/metrics_base.py
@@ -1808,9 +1808,8 @@ def auuc(self, metric=None):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
@@ -1842,9 +1841,8 @@ def qini(self):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
@@ -1873,13 +1871,13 @@ def aecu(self, metric="qini"):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.aecu()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.aecu()
         """
         assert metric in ['qini', 'lift', 'gain'], \
             "AECU metric "+metric+" should be 'qini','lift' or 'gain'."
@@ -1906,13 +1904,13 @@ def uplift(self, metric="AUTO"):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.uplift()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.uplift()
         """
         assert metric in ['AUTO', 'qini', 'lift', 'gain']
        
@@ -1941,13 +1939,13 @@ def uplift_random(self, metric="AUTO"):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.uplift()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.uplift()
         """
         assert metric in ['AUTO', 'qini', 'lift', 'gain']
 
@@ -1974,13 +1972,13 @@ def n(self):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.n()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.n()
         """  
         return self._metric_json["thresholds_and_metric_scores"]["n"]
     
@@ -2003,13 +2001,13 @@ def thresholds(self):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.thresholds()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.thresholds()
         """
         return self._metric_json["thresholds_and_metric_scores"]["thresholds"]
 
@@ -2032,13 +2030,13 @@ def thresholds_and_metric_scores(self):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.thresholds_and_metric_scores()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.thresholds_and_metric_scores()
         """
         return self._metric_json["thresholds_and_metric_scores"]
 
@@ -2061,17 +2059,17 @@ def auuc_table(self):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.auuc_table()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.auuc_table()
         """
         return self._metric_json["auuc_table"]
 
-    def eacu_table(self):
+    def aecu_table(self):
         """
         Retrieve all types of AECU values in a table.
          
@@ -2090,13 +2088,13 @@ def eacu_table(self):
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
-        >>> uplift_model.aecu_table()
+        >>> perf = uplift_model.model_performance()
+        >>> perf.aecu_table()
         """
         return self._metric_json["aecu_table"]
 
@@ -2123,9 +2121,8 @@ def plot_uplift(self, server=False, save_to_file=None, plot=True, metric="AUTO")
         >>> uplift_model = H2OUpliftRandomForestEstimator(ntrees=10, 
         ...                                               max_depth=5,
         ...                                               treatment_column=treatment_column,
-        ...                                               uplift_metric="qini",
+        ...                                               uplift_metric="kl",
         ...                                               distribution="bernoulli",
-        ...                                               gainslift_bins=10,
         ...                                               min_rows=10,
         ...                                               auuc_type="gain")
         >>> uplift_model.train(y=response_column, x=predictors, training_frame=train)
diff --git a/h2o-py/h2o/model/model_base.py b/h2o-py/h2o/model/model_base.py
index d2795e2d0c75..09f7414812f4 100644
--- a/h2o-py/h2o/model/model_base.py
+++ b/h2o-py/h2o/model/model_base.py
@@ -956,7 +956,28 @@ def auuc_table(self, train=False, valid=False):
                 raise H2OValueError("auuc_table() is only available for Uplift Binomial classifiers.")
             m[k] = None if v is None else v.auuc_table()
         return list(m.values())[0] if len(m) == 1 else m
-    
+
+    def qini(self, train=False, valid=False):
+        """
+        Get the Qini value (Area Under Uplift Curve - Area Under Random Curve for Qini uplift).
+
+        If all are False (default), then return the training metric value.
+        If more than one options is set to True, then return a dictionary of metrics where the keys are "train",
+        "valid".
+
+        :param bool train: If train is True, then return the Qini value for the training data.
+        :param bool valid: If valid is True, then return the Qini value for the validation data.
+
+        :returns: The Qini value.
+        """
+        tm = ModelBase._get_metrics(self, train, valid, False)
+        m = {}
+        for k, v in viewitems(tm):
+            if not(v is None) and not(is_type(v, h2o.model.metrics_base.H2OBinomialUpliftModelMetrics)):
+                raise H2OValueError("auuc() is only available for Uplift Binomial classifiers.")
+            m[k] = None if v is None else v.qini()
+        return list(m.values())[0] if len(m) == 1 else m
+
     def aic(self, train=False, valid=False, xval=False):
         """
         Get the AIC (Akaike Information Criterium).