Merge pull request #18 from IndicoDataSolutions/texttagging-batch

Batch image preprocessing and text tagging tweak

CHANGES.txt

@@ -13,6 +13,7 @@ v0.4.4, Thu Sep 25 -- Added dependencies installation to setup.py
 v0.4.5, Thu Sep 25 -- Added interface to local indico server
 v0.4.6, Fri Oct 27 -- Updated to point to new indico api servers, cleaner REST API
 v0.4.8, Fri Nov 7 -- Updated API interface to include new text tags API
-v0.4.11, Wed Dec 18 -- Updated tests for text tags
-v0.4.12, Thu Dec 19 -- Added batch support interface
-v0.4.13, Thu Dec 19 -- Added optional arguments to text tags API
+v0.4.11, Thu Dec 18 -- Updated tests for text tags
+v0.4.12, Fri Dec 19 -- Added batch support interface
+v0.4.13, Fri Dec 19 -- Added optional arguments to text tags API
+v0.4.14, Sat Dec 20 -- Fix for batch image features preprocessing, increased test coverage

indicoio/__init__.py

@@ -3,7 +3,7 @@ import indicoio.config as config
 
 JSON_HEADERS = {'Content-type': 'application/json', 'Accept': 'text/plain'}
 
-Version, version, __version__, VERSION = ('0.4.13',) * 4
+Version, version, __version__, VERSION = ('0.4.14',) * 4
 
 from indicoio.text.sentiment import political, posneg
 from indicoio.text.sentiment import posneg as sentiment

indicoio/images/features.py

@@ -59,5 +59,5 @@ def image_features(api_root, image, batch=False, auth=None, **kwargs):
     :type image: numpy.ndarray
     :rtype: List containing features
     """
-    image = image_preprocess(image)
+    image = image_preprocess(image, batch=batch)
     return api_handler(image, api_root + "imagefeatures", batch=batch, auth=auth, **kwargs)

indicoio/text/tagging.py

@@ -22,4 +22,4 @@ def text_tags(api_root, text, batch=False, auth=None, **kwargs):
     :rtype: Dictionary of class probability pairs
     """
     
-    return api_handler(text, api_root + "texttags", batch=batch, auth=None, **kwargs)
+    return api_handler(text, api_root + "texttags", batch=batch, auth=auth, **kwargs)

indicoio/utils/__init__.py

@@ -26,8 +26,9 @@ def api_handler(arg, url, batch=False, auth=None, **kwargs):
     json_data = json.dumps(data)
     if batch:
         url += "/batch"
-        if not auth:
-            auth = auth_query()
+        # if not auth:
+        #     auth = auth_query()
+    print auth
     response = requests.post(url, data=json_data, headers=JSON_HEADERS, auth=auth).json()
     results = response.get('results', False)
     if results is False:
@@ -119,11 +120,13 @@ def normalize(array, distribution=1, norm_range=(0, 1), **kwargs):
         return dict(zip(keys, norm_array))
     return norm_array
 
-def image_preprocess(image):
+def image_preprocess(image, batch=False):
     """
     Takes an image and prepares it for sending to the api including 
     resizing and image data/structure standardizing.
     """
+    if batch:
+        return [image_preprocess(img, batch=False) for img in image]
     if isinstance(image,list):
         image = np.asarray(image)
     if type(image).__module__ != np.__name__:

setup.py

@@ -8,7 +8,7 @@ except ImportError:
 
 setup(
     name="IndicoIo",
-    version='0.4.13',
+    version='0.4.14',
     packages=[
         "indicoio",
         "indicoio.text",

tests/remote/test_remote.py

@@ -3,11 +3,73 @@ import os
 
 import numpy as np
 import skimage.io
+from nose.plugins.skip import Skip, SkipTest
 
 from indicoio import political, sentiment, fer, facial_features, language, image_features, text_tags
+from indicoio import batch_political, batch_sentiment, batch_fer, batch_facial_features
+from indicoio import batch_language, batch_image_features, batch_text_tags
 
 DIR = os.path.dirname(os.path.realpath(__file__))
 
+class BatchAPIRun(unittest.TestCase):
+
+    def setUp(self):
+        self.username = os.getenv("INDICO_USERNAME")
+        self.password = os.getenv("INDICO_PASSWORD")
+        self.auth = (self.username, self.password)
+
+        if not self.username or not self.password:
+            raise SkipTest
+
+    def test_batch_texttags(self):
+        test_data = ["On Monday, president Barack Obama will be..."]
+        response = batch_text_tags(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+
+    def test_batch_posneg(self):
+        test_data = ['Worst song ever', 'Best song ever']
+        response = batch_sentiment(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+        self.assertTrue(response[0] < 0.5)
+
+    def test_batch_political(self):
+        test_data = ["Guns don't kill people, people kill people."]
+        response = batch_political(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+
+    def test_batch_fer(self):
+        test_data = [np.random.rand(48, 48).tolist()]
+        response = batch_fer(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+        self.assertTrue(isinstance(response[0], dict))
+
+    def test_batch_facial_features(self):
+        test_data = [np.random.rand(48, 48).tolist()]
+        response = batch_facial_features(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+        self.assertTrue(isinstance(response[0], list))
+        self.assertEqual(len(response[0]), 48)
+    
+    def test_batch_image_features_greyscale(self):
+        test_data = [np.random.rand(64, 64).tolist()]
+        response = batch_image_features(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+        self.assertTrue(isinstance(response[0], list))
+        self.assertEqual(len(response[0]), 2048)
+
+    def test_batch_image_features_rgb(self):
+        test_data = [np.random.rand(64, 64, 3).tolist()]
+        response = batch_image_features(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+        self.assertTrue(isinstance(response[0], list))
+        self.assertEqual(len(response[0]), 2048)
+        
+    def test_batch_language(self):
+        test_data = ['clearly an english sentence']
+        response = batch_language(test_data, auth=self.auth)
+        self.assertTrue(isinstance(response, list))
+        self.assertTrue(response[0]['English'] > 0.25)
+
 
 class FullAPIRun(unittest.TestCase):