Fixes for dataframe tool

src/python/tests_extended/data_frame_tool.py

@@ -190,7 +190,7 @@ def execute(self, df, output_names=None, output_types=None, run_options=None):
                 continue
 
             r = np.split(r, r.shape[-1], axis=-1) \
-                if r.shape[-1] > 1 else [r]
+                if (r.shape[-1] > 1 and r.shape[0] > 1) else [r]
 
             for suffix, col in enumerate(r):
                 col = col.flatten()

src/python/tests_extended/test_export_to_onnx.py

@@ -45,7 +45,6 @@
                                  SsaForecaster)
 from data_frame_tool import DataFrameTool as DFT
 
-
 SHOW_ONNX_JSON = False
 SHOW_TRANSFORMED_RESULTS = True
 SHOW_FULL_PANDAS_OUTPUT = False
@@ -580,7 +579,6 @@ def test_export_to_onnx(estimator, class_name):
         try:
             onnxrunner = OnnxRunner(model_file=onnx_path)
             result_onnx = onnxrunner.fit_transform(dataset)
-
             df_tool = DFT(onnx_path)
             result_ort = df_tool.execute(dataset, [])
 
@@ -615,7 +613,7 @@ def test_export_to_onnx(estimator, class_name):
 for entry_point in entry_points:
     class_name = entry_point['NewName']
 
-#    if not class_name in ['Handler']:
+#    if not class_name in ['FastLinearClassifier']:
 #        continue
 
     print('\n===========> %s' % class_name)

src/python/tests_extended/vinod.py

@@ -1,12 +1,15 @@
 import os
+import time
 import tempfile
 import nimbusml.linear_model as nml_linear
 from nimbusml.feature_extraction.categorical import OneHotVectorizer
 from nimbusml.preprocessing.missing_values import Handler
 from nimbusml import FileDataStream
 from nimbusml.preprocessing import DatasetTransformer
+from nimbusml.preprocessing.schema import ColumnSelector
 from nimbusml import Pipeline
 from nimbusml.preprocessing import OnnxRunner
+from data_frame_tool import DataFrameTool as DFT
 
 def get_tmp_file(suffix=None):
     fd, file_name = tempfile.mkstemp(suffix=suffix)
@@ -38,26 +41,35 @@ def get_tmp_file(suffix=None):
     print('export done')
 
     # Perform the transform using the standard ML.Net backend
-    result_standard = pipe_training.transform(X_test_dprep)
+    start = time.time()
+    result_standard = pipe_training.predict(X_test_dprep)
+    end = time.time()
     print(result_standard)
-    print('done transform using standard backend')
-    #          c1        c2
-    # 0  0.025025  0.000998
-    # 1  0.305305  0.000998
+    print('%ss done transform using standard backend' % round(end - start, 3))
 
     # Perform the transform using the ONNX backend.
     # Note, the extra columns and column name differences
     # is a known issue with the ML.Net backend.
-    onnxrunner = OnnxRunner(model_file=onnx_path)
-    result_onnx = onnxrunner.fit_transform(X_test_dprep)
-    print('done transform using onnx backend')
-    print(result_onnx)
-    #      c1   c2     c12.0     c22.0
-    # 0   2.5  1.0  0.025025  0.000998
-    # 1  30.5  1.0  0.305305  0.000998
+    onnxrunner = Pipeline([OnnxRunner(model_file=onnx_path), 
+                           ColumnSelector(columns=['Score'])])
+    # Performance issue, commenting out for now
+    #start = time.time()
+    #result_onnx = onnxrunner.fit_transform(X_test_dprep, as_binary_data_stream=True)
+    #end = time.time()
+    #print(result_onnx.head(5))
+    #print('%ss done transform using onnx backend' % round(end - start, 3))
+
+    df_tool = DFT(onnx_path)
+    dataset = X_test_dprep.to_df()
+    start = time.time()
+    result_ort = df_tool.execute(dataset, [])
+    end = time.time()
+    print(result_ort)
+    print('%ss done transform using ORT backend (excludes df load time)' % round(end - start, 3))
+
 
 except Exception as e:
-    print('tragedy')
+    print('=============== ERROR =================')
     print(e)
 
 print ("done")

src/python/tools/manifest.json

@@ -1903,9 +1903,9 @@
           }
         },
         {
-          "Name": "SupressScoresAndLabels",
+          "Name": "SuppressScoresAndLabels",
           "Type": "Bool",
-          "Desc": "Supress labels and scores in per-instance outputs?",
+          "Desc": "Suppress labels and scores in per-instance outputs?",
           "Aliases": [
             "noScores"
           ],
@@ -23945,7 +23945,7 @@
         {
           "Name": "SupressTypeErrors",
           "Type": "Bool",
-          "Desc": "Supress the errors that would occur if a column and impute mode are imcompatible. If true, will skip the column. If false, will stop and throw an error.",
+          "Desc": "Suppress the errors that would occur if a column and impute mode are incompatible. If true, will skip the column. If false, will stop and throw an error.",
           "Aliases": [
             "error"
           ],