Merge branch 'master' of github.com:developmentseed/label-maker

Author: drewbo

.circleci/config.yml

@@ -28,13 +28,19 @@ jobs:
             mkdir integration
             cp test/fixtures/integration/portugal-z17.mbtiles integration/portugal-z17.mbtiles
             cp -r test/fixtures/integration/tiles integration/tiles
+
+            # Test `label-maker labels --sparse`; must be run before `label-maker labels` so `verify-package.py` passes
+            label-maker labels --dest integration --config test/fixtures/integration/config.integration_sparse.json --sparse > stdout_sparse
+            python test/verify-sparse-labels.py
+            # Test `label-maker labels`
             label-maker labels --dest integration --config test/fixtures/integration/config.integration.json > stdout
             python test/verify-labels.py
+            # Test `label-maker package`
             label-maker package --dest integration --config test/fixtures/integration/config.integration.json
             python test/verify-package.py
 
             # Retest that `label-maker labels` works, but from outside the module directory
             cd ~
             label-maker labels --dest label-maker/integration --config label-maker/test/fixtures/integration/config.integration.json > stdout
             cd ~/label-maker            
-            python test/verify-labels.py
+            python test/verify-labels.py

.config/pylintrc

@@ -50,7 +50,7 @@ confidence=
 # --enable=similarities". If you want to run only the classes checker, but have
 # no Warning level messages displayed, use"--disable=all --enable=classes
 # --disable=W"
-disable=print-statement,parameter-unpacking,unpacking-in-except,old-raise-syntax,backtick,long-suffix,old-ne-operator,old-octal-literal,import-star-module-level,raw-checker-failed,bad-inline-option,locally-disabled,locally-enabled,file-ignored,suppressed-message,useless-suppression,deprecated-pragma,apply-builtin,basestring-builtin,buffer-builtin,cmp-builtin,coerce-builtin,execfile-builtin,file-builtin,long-builtin,raw_input-builtin,reduce-builtin,standarderror-builtin,unicode-builtin,xrange-builtin,coerce-method,delslice-method,getslice-method,setslice-method,no-absolute-import,old-division,dict-iter-method,dict-view-method,next-method-called,metaclass-assignment,indexing-exception,raising-string,reload-builtin,oct-method,hex-method,nonzero-method,cmp-method,input-builtin,round-builtin,intern-builtin,unichr-builtin,map-builtin-not-iterating,zip-builtin-not-iterating,range-builtin-not-iterating,filter-builtin-not-iterating,using-cmp-argument,eq-without-hash,div-method,idiv-method,rdiv-method,exception-message-attribute,invalid-str-codec,sys-max-int,bad-python3-import,deprecated-string-function,deprecated-str-translate-call,invalid-name,line-too-long,global-statement,too-many-locals,too-many-arguments,too-many-branches
+disable=print-statement,parameter-unpacking,unpacking-in-except,old-raise-syntax,backtick,long-suffix,old-ne-operator,old-octal-literal,import-star-module-level,raw-checker-failed,bad-inline-option,locally-disabled,locally-enabled,file-ignored,suppressed-message,useless-suppression,deprecated-pragma,apply-builtin,basestring-builtin,buffer-builtin,cmp-builtin,coerce-builtin,execfile-builtin,file-builtin,long-builtin,raw_input-builtin,reduce-builtin,standarderror-builtin,unicode-builtin,xrange-builtin,coerce-method,delslice-method,getslice-method,setslice-method,no-absolute-import,old-division,dict-iter-method,dict-view-method,next-method-called,metaclass-assignment,indexing-exception,raising-string,reload-builtin,oct-method,hex-method,nonzero-method,cmp-method,input-builtin,round-builtin,intern-builtin,unichr-builtin,map-builtin-not-iterating,zip-builtin-not-iterating,range-builtin-not-iterating,filter-builtin-not-iterating,using-cmp-argument,eq-without-hash,div-method,idiv-method,rdiv-method,exception-message-attribute,invalid-str-codec,sys-max-int,bad-python3-import,deprecated-string-function,deprecated-str-translate-call,invalid-name,line-too-long,global-statement,too-many-locals,too-many-arguments,too-many-branches,too-many-statements
 
 # Enable the message, report, category or checker with the given id(s). You can
 # either give multiple identifier separated by comma (,) or put this option

label_maker/label.py

@@ -17,12 +17,13 @@
 from tilepie import tilereduce
 
 import label_maker
+from label_maker.utils import class_match
 from label_maker.filter import create_filter
 
 # declare a global accumulator so the workers will have access
 tile_results = dict()
 
-def make_labels(dest_folder, zoom, country, classes, ml_type, bounding_box, **kwargs):
+def make_labels(dest_folder, zoom, country, classes, ml_type, bounding_box, sparse, **kwargs):
     """Create label data from OSM QA tiles for specified classes
 
     Perform the following operations:
@@ -73,30 +74,49 @@ def make_labels(dest_folder, zoom, country, classes, ml_type, bounding_box, **kw
     # Call tilereduce
     print('Determining labels for each tile')
     mbtiles_to_reduce = mbtiles_file_zoomed
-    tilereduce(dict(zoom=zoom, source=mbtiles_to_reduce, bbox=bounding_box, args=dict(ml_type=ml_type, classes=classes)),
+    tilereduce(dict(zoom=zoom, source=mbtiles_to_reduce, bbox=bounding_box,
+                    args=dict(ml_type=ml_type, classes=classes)),
                _mapper, _callback, _done)
 
     # Add empty labels to any tiles which didn't have data
     empty_label = _create_empty_label(ml_type, classes)
     for tile in tiles(*bounding_box, [zoom]):
         index = '-'.join([str(i) for i in tile])
+        global tile_results
         if tile_results.get(index) is None:
             tile_results[index] = empty_label
 
     # Print a summary of the labels
     _tile_results_summary(ml_type, classes)
 
+    # If the --sparse flag is provided, limit the total background tiles to write
+    if sparse:
+        pos_examples, neg_examples = [], []
+        for k in tile_results.keys():
+            if class_match(ml_type, tile_results[k], 0):
+                neg_examples.append(k)
+            else:
+                pos_examples.append(k)
+
+        # Choose random subset of negative examples
+        n_neg_ex = int(kwargs['background_ratio'] * len(pos_examples))
+        neg_examples = np.random.choice(neg_examples, n_neg_ex, replace=False).tolist()
+
+        tile_results = {k: tile_results.get(k) for k in pos_examples + neg_examples}
+        print('Using sparse mode; subselected {} background tiles'.format(n_neg_ex))
+
     # write out labels as numpy arrays
     labels_file = op.join(dest_folder, 'labels.npz')
-    print('Write out labels to {}'.format(labels_file))
+    print('Writing out labels to {}'.format(labels_file))
     np.savez(labels_file, **tile_results)
 
     # write out labels as GeoJSON or PNG
     if ml_type == 'classification':
         features = []
         for tile, label in tile_results.items():
             feat = feature(Tile(*[int(t) for t in tile.split('-')]))
-            features.append(Feature(geometry=feat['geometry'], properties=dict(label=label.tolist())))
+            features.append(Feature(geometry=feat['geometry'],
+                                    properties=dict(label=label.tolist())))
         json.dump(fc(features), open(op.join(dest_folder, 'classification.geojson'), 'w'))
     elif ml_type == 'object-detection':
         label_folder = op.join(dest_folder, 'labels')

label_maker/main.py

@@ -39,11 +39,14 @@ def parse_args(args):
     subparsers = parser.add_subparsers(dest='command')
 
     subparsers.add_parser('download', parents=[pparser], help='', formatter_class=dhf)
-    subparsers.add_parser('labels', parents=[pparser], help='', formatter_class=dhf)
+    l = subparsers.add_parser('labels', parents=[pparser], help='', formatter_class=dhf)
     p = subparsers.add_parser('preview', parents=[pparser], help='', formatter_class=dhf)
     subparsers.add_parser('images', parents=[pparser], help='', formatter_class=dhf)
     subparsers.add_parser('package', parents=[pparser], help='', formatter_class=dhf)
 
+    # labels has an optional parameter
+    l.add_argument('-s', '--sparse', action='store_true')
+
     # preview has an optional parameter
     p.add_argument('-n', '--number', default=5, type=int,
                    help='number of examples images to create per class')
@@ -77,7 +80,8 @@ def cli():
     if cmd == 'download':
         download_mbtiles(dest_folder=dest_folder, **config)
     elif cmd == 'labels':
-        make_labels(dest_folder=dest_folder, **config)
+        sparse = args.get('sparse', False)
+        make_labels(dest_folder=dest_folder, sparse=sparse, **config)
     elif cmd == 'preview':
         number = args.get('number')
         preview(dest_folder=dest_folder, number=number, **config)

label_maker/version.py

@@ -1,2 +1,2 @@
 """Library verison"""
-__version__ = '0.1.2'
+__version__ = '0.1.3'

test/fixtures/integration/config.integration_sparse.json

@@ -0,0 +1,22 @@
+{
+  "country": "portugal",
+  "bounding_box": [
+    -9.4575,
+    38.8467,
+    -9.4510,
+    38.8513
+  ],
+  "zoom": 17,
+  "classes": [
+    { "name": "Water Tower", "filter": ["==", "man_made", "water_tower"] },
+    { "name": "Building", "filter": ["has", "building"] },
+    { "name": "Farmland", "filter": ["==", "landuse", "farmland"] },
+    { "name": "Ruins", "filter": ["==", "historic", "ruins"] },
+    { "name": "Parking", "filter": ["==", "amenity", "parking"] },
+    { "name": "Roads", "filter": ["has", "highway"] }
+  ],
+  "imagery": "https://api.mapbox.com/v4/mapbox.satellite/{z}/{x}/{y}.jpg?access_token=ACCESS_TOKEN",
+  "background_ratio": 0,
+  "ml_type": "classification",
+  "seed": 19
+}

test/verify-labels.py

@@ -16,8 +16,9 @@
 }
 
 labels = np.load('integration/labels.npz')
+assert len(labels.files) == len(expected_labels.keys())  # First check number of tiles
 for tile in labels.files:
-    assert np.array_equal(expected_labels[tile], labels[tile])
+    assert np.array_equal(expected_labels[tile], labels[tile])  # Now, content
 
 # our GeoJSON looks like the fixture
 expected_geojson = json.load(open('test/fixtures/integration/classification.geojson'))
@@ -36,7 +37,7 @@
 Parking: 1 tiles
 Roads: 8 tiles
 Total tiles: 9
-Write out labels to integration/labels.npz
+Writing out labels to integration/labels.npz
 """
 
 with open('stdout', 'r') as output:

test/verify-sparse-labels.py

@@ -0,0 +1,44 @@
+"""Validate that the output produced by integration testing on 'label-maker labels' matches our expectations"""
+import json
+import numpy as np
+
+# our labels should look like this
+expected_labels = {
+    '62092-50163-17': np.array([0, 0, 0, 0, 0, 0, 1]),
+    '62092-50164-17': np.array([0, 0, 0, 0, 0, 0, 1]),
+    '62093-50162-17': np.array([0, 0, 0, 0, 0, 0, 1]),
+    '62093-50164-17': np.array([0, 0, 0, 0, 0, 0, 1]),
+    '62094-50162-17': np.array([0, 0, 0, 0, 0, 0, 1]),
+    '62094-50164-17': np.array([0, 0, 0, 0, 0, 0, 1]),
+    '62094-50163-17': np.array([0, 1, 1, 0, 0, 0, 1]),
+    '62093-50163-17': np.array([0, 0, 0, 0, 1, 1, 1])
+}
+
+labels = np.load('integration/labels.npz')
+assert len(labels.files) == len(expected_labels.keys())  # First check number of tiles
+for tile in labels.files:
+    assert np.array_equal(expected_labels[tile], labels[tile])  # Now, content
+
+# our GeoJSON looks like the fixture
+expected_geojson = json.load(open('test/fixtures/integration/classification.geojson'))
+geojson = json.load(open('integration/classification.geojson'))
+
+for feature in geojson['features']:
+    assert feature in expected_geojson['features']
+
+# our command line output should look like this
+expected_output = """Determining labels for each tile
+---
+Water Tower: 1 tiles
+Building: 1 tiles
+Farmland: 0 tiles
+Ruins: 1 tiles
+Parking: 1 tiles
+Roads: 8 tiles
+Total tiles: 9
+Using sparse mode; subselected 0 background tiles
+Writing out labels to integration/labels.npz
+"""
+
+with open('stdout_sparse', 'r') as output:
+    assert expected_output == output.read()