Fix junit tests

h2oai · Jan 10, 2025 · d19bd44 · d19bd44
1 parent 465c049
commit d19bd44
Show file tree

Hide file tree

Showing 4 changed files with 58 additions and 6 deletions.
diff --git a/h2o-algos/src/main/java/hex/knn/KNNModel.java b/h2o-algos/src/main/java/hex/knn/KNNModel.java
@@ -21,7 +21,6 @@ public String javaName() {
         }
 
         public int _k = 3;
-        //public KNNDistance _distance;
         public DistanceType _distance;
         public boolean _compute_metrics;
 

diff --git a/h2o-algos/src/test/java/hex/knn/KNNTest.java b/h2o-algos/src/test/java/hex/knn/KNNTest.java
@@ -35,7 +35,7 @@ public void testIris() {
             KNNModel.KNNParameters parms = new KNNModel.KNNParameters();
             parms._train = fr._key;
             parms._k = 3;
-            parms._distance = new EuclideanDistance();
+            parms._distance = DistanceType.EUCLIDEAN;
             parms._response_column = response;
             parms._id_column = idColumn;
             parms._auc_type = MultinomialAucType.MACRO_OVR;
@@ -90,7 +90,7 @@ public void testSimpleFrameEuclidean() {
             KNNModel.KNNParameters parms = new KNNModel.KNNParameters();
             parms._train = fr._key;
             parms._k = 2;
-            parms._distance = new EuclideanDistance();
+            parms._distance = DistanceType.EUCLIDEAN;
             parms._response_column = response;
             parms._id_column = idColumn;
             parms._auc_type = MultinomialAucType.MACRO_OVR;
@@ -165,7 +165,7 @@ public void testSimpleFrameManhattan() {
             KNNModel.KNNParameters parms = new KNNModel.KNNParameters();
             parms._train = fr._key;
             parms._k = 2;
-            parms._distance = new ManhattanDistance();
+            parms._distance = DistanceType.MANHATTAN;
             parms._response_column = response;
             parms._id_column = idColumn;
             parms._auc_type = MultinomialAucType.MACRO_OVR;
@@ -240,7 +240,7 @@ public void testSimpleFrameCosine() {
             KNNModel.KNNParameters parms = new KNNModel.KNNParameters();
             parms._train = fr._key;
             parms._k = 2;
-            parms._distance = new CosineDistance();
+            parms._distance = DistanceType.COSINE;
             parms._response_column = response;
             parms._id_column = idColumn;
             parms._auc_type = MultinomialAucType.MACRO_OVR;
@@ -332,7 +332,7 @@ public void testIdColumnIsNotDefined() {
             KNNModel.KNNParameters parms = new KNNModel.KNNParameters();
             parms._train = fr._key;
             parms._k = 2;
-            parms._distance = new EuclideanDistance();
+            parms._distance = DistanceType.EUCLIDEAN;
             parms._response_column = "class";
             parms._id_column = null;
 

diff --git a/h2o-py/tests/testdir_algos/knn/pyunit_knn_api_test.py b/h2o-py/tests/testdir_algos/knn/pyunit_knn_api_test.py
@@ -17,6 +17,7 @@ def knn_api_smoke():
     train_h2o[response_column] = train_h2o[response_column].asfactor()
     train_h2o[id_column] = h2o.H2OFrame(np.arange(0, train_h2o.shape[0]))
 
+
     model = H2OKnnEstimator(
         k=3,
         id_column=id_column,

diff --git a/h2o-py/tests/testdir_algos/knn/pyunit_knn_compare_sklearn.py b/h2o-py/tests/testdir_algos/knn/pyunit_knn_compare_sklearn.py
@@ -0,0 +1,52 @@
+import sys, os
+
+sys.path.insert(1, os.path.join("..", "..", ".."))
+import h2o
+from tests import pyunit_utils, assert_equals
+from h2o.estimators.knn import H2OKnnEstimator
+import numpy as np
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.neighbors import kneighbors_graph
+import pandas as pd
+
+
+def knn_sklearn_compare():
+    seed = 12345
+    id_column = "id"
+    response_column = "class"
+    x_names = ["sepal_len", "sepal_wid", "petal_len", "petal_wid"]
+
+    train = pd.read_csv(pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
+
+    knn = KNeighborsClassifier(n_neighbors=3)
+    knn.fit(train[x_names], train[response_column])
+    print(knn)
+    knn_score = knn.score(train[x_names], train[response_column])
+    print(knn_score)
+
+    knn_graph = kneighbors_graph(train[x_names], 3, mode='connectivity', include_self=False, metric="euclidean")
+    print(knn_graph)
+
+    train_h2o = h2o.H2OFrame(train)
+    train_h2o[response_column] = train_h2o[response_column].asfactor()
+    train_h2o[id_column] = h2o.H2OFrame(np.arange(0, train_h2o.shape[0]))
+
+    h2o_knn = H2OKnnEstimator(
+        k=3,
+        id_column=id_column,
+        distance="euclidean",
+        seed=seed,
+        auc_type="macroovr"
+    )
+
+    h2o_knn.train(y=response_column, x=x_names, training_frame=train_h2o)
+    distances_key = h2o_knn._model_json["output"]["distances"]
+    print(distances_key)
+    distances_frame = h2o.get_frame(distances_key)
+    print(distances_frame)
+
+
+if __name__ == "__main__":
+    pyunit_utils.standalone_test(knn_sklearn_compare)
+else:
+    knn_sklearn_compare()