def test_model(self): print "Initialize KMeansModel object" k = ta.KMeansModel() print "Initialize LogisticRegressionModel object" l = ta.LogisticRegressionModel() print "Initialize NaiveBayesModel object" n = ta.NaiveBayesModel()
def test_model(self): print "Initialize KMeansModel object with name" k1 = ta.KMeansModel(name='smoke_kmeans_model') name = k1.name print "Initialize KMeansModel object" k2 = ta.KMeansModel() print "Initialize LogisticRegressionModel object with name" l1 = ta.LogisticRegressionModel(name='myLogisticRegressionModel1') print "Initialize LogisticRegressionModel object" l2 = ta.LogisticRegressionModel() print "Initialize NaiveBayesModel object" n = ta.NaiveBayesModel()
def test_naive_bayes(self): print "define csv file" schema = [("Class", ta.int32), ("Dim_1", ta.int32), ("Dim_2", ta.int32), ("Dim_3", ta.int32)] train_file = ta.CsvFile("/datasets/naivebayes_spark_data.csv", schema=schema) print "creating the frame" train_frame = ta.Frame(train_file) print "initializing the naivebayes model" n = ta.NaiveBayesModel() print "training the model on the frame" n.train(train_frame, 'Class', ['Dim_1', 'Dim_2', 'Dim_3']) print "predicting the class using the model and the frame" output = n.predict(train_frame) self.assertEqual( output.column_names, ['Class', 'Dim_1', 'Dim_2', 'Dim_3', 'predicted_class'])