updates

Author: martham93

label_maker/package.py

@@ -99,16 +99,14 @@ def package_directory(dest_folder, classes, imagery, ml_type, seed=False, split_
 
     # Convert lists to numpy arrays
     x_vals = np.array(x_vals, dtype=np.uint8)
-    print(x_vals.shape)
     y_vals = np.array(y_vals, dtype=np.uint8)
-    print(y_vals).shape
 
     # Get number of data samples per split from the float proportions
     split_n_samps = np.rint([len(x_vals) * val for val in split_vals])
-    print(split_n_samps)
+    #print(split_n_samps)
 
     if np.any(split_n_samps == 0):
-        raise ValueError
+        raise ValueError('split must not generate zero samples per partition, change ratio of values in config file.')
 
     # Convert into a cumulative sum to get indices
     split_inds = np.cumsum(split_n_samps).astype(np.integer)

test/fixtures/integration/config_3way.integration.json

@@ -19,5 +19,5 @@
   "ml_type": "classification",
   "seed": 19,
   "split_names": ["train", "test", "val"],
-  "split_vals": [0.7, 0.2, 0.1]
+  "split_vals": [0.6, 0.2, 0.2]
 }

test/integration/test_classification_package.py

@@ -7,11 +7,12 @@
 
 import numpy as np
 
+
 class TestClassificationPackage(unittest.TestCase):
     """Tests for classification package creation"""
+
     @classmethod
     def setUpClass(cls):
-
         makedirs('integration-cl')
         copyfile('test/fixtures/integration/labels-cl.npz', 'integration-cl/labels.npz')
         copytree('test/fixtures/integration/tiles', 'integration-cl/tiles')
@@ -58,7 +59,8 @@ def test_cli(self):
     def test_cli_3way_split(self):
         """Verify data.npz produced by CLI when split into train/test/val"""
 
-        cmd = 'label-maker package --dest integration-cl-split --config test/fixtures/integration/config_3way.integration.json'
+        cmd = 'label-maker package --dest integration-cl-split --config ' \
+              'test/fixtures/integration/config_3way.integration.json '
         cmd = cmd.split(' ')
         subprocess.run(cmd, universal_newlines=True)
 
@@ -72,4 +74,4 @@ def test_cli_3way_split(self):
         # validate label data with shapes
         self.assertEqual(data['y_train'].shape, (5, 7))
         self.assertEqual(data['y_test'].shape, (2, 7))
-        self.assertEqual(data['y_val'].shape, (1, 7))
+        self.assertEqual(data['y_val'].shape, (1, 7))