review-suggestioons

h2o-bindings/bin/custom/python/gen_rulefit.py

@@ -43,16 +43,19 @@ def predict_rules(self, frame, rule_ids):
         >>> import h2o
         >>> h2o.init()
         >>> from h2o.estimators import H2ORuleFitEstimator
-        >>> f = "https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/titanic.csv"
-        >>> df = h2o.import_file(path=f, col_types={'pclass': "enum", 'survived': "enum"})
-        >>> x = ["age", "sibsp", "parch", "fare", "sex", "pclass"]
-        >>> y = "survived"
-        >>> rfit = H2ORuleFitEstimator(max_rule_length=10,
-        ...                            max_num_rules=100,
-        ...                            seed=1)
-        >>> rfit.train(training_frame=df, x=x, y=y)
-        >>> predictions = rfit.predict(test)
-        >>> print("Predictions:\n", predictions)
+        >>> f = "https://s3.amazonaws.com/h2o-public-test-data/smalldata/iris/iris_train.csv"
+        >>> df = h2o.import_file(path=f, col_types={'species': "enum"})
+        >>> x = df.columns
+        >>> y = "species"
+        >>> x.remove(y)
+        >>> train, test = df.split_frame(ratios=[.8], seed=1234)
+        >>> rfit = H2ORuleFitEstimator(min_rule_length=4,
+        ...                            max_rule_length=5,
+        ...                            max_num_rules=3,
+        ...                            seed=1234,
+        ...                            model_type="rules")
+        >>> rfit.train(training_frame=train, x=x, y=y, validation_frame=test)
+        >>> print(rfit.predict_rules(train, ['M0T38N5_Iris-virginica']))
         """
         from h2o.frame import H2OFrame
         from h2o.utils.typechecks import assert_is_type