Merge pull request #85 from IndicoDataSolutions/keywords

ADD: keywords api support

indicoio/__init__.py

@@ -13,6 +13,7 @@ from indicoio.text.sentiment import political, posneg, sentiment_hq
 from indicoio.text.sentiment import posneg as sentiment
 from indicoio.text.lang import language
 from indicoio.text.tagging import text_tags
+from indicoio.text.keywords import keywords
 from indicoio.images.fer import fer
 from indicoio.images.features import facial_features
 from indicoio.images.features import image_features
@@ -20,6 +21,7 @@ from indicoio.utils.multi import predict_image, predict_text
 
 from indicoio.config import API_NAMES
 
+
 apis = dict((api, globals().get(api)) for api in API_NAMES)
 
 for api in apis:

indicoio/config.py

@@ -50,7 +50,8 @@ TEXT_APIS = [
     'political',
     'sentiment',
     'language',
-    'sentiment_hq'
+    'sentiment_hq',
+    'keywords'
 ]
 
 IMAGE_APIS = [

indicoio/images/features.py

@@ -26,7 +26,8 @@ def facial_features(image, cloud=None, batch=False, api_key=None, **kwargs):
     :rtype: List containing feature responses
     """
     image = image_preprocess(image, batch=batch)
-    return api_handler(image, cloud=cloud, api="facialfeatures", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    url_params = {"batch": batch, "api_key": api_key}
+    return api_handler(image, cloud=cloud, api="facialfeatures", url_params=url_params, **kwargs)
 
 def image_features(image, cloud=None, batch=False, api_key=None, **kwargs):
     """
@@ -59,4 +60,5 @@ def image_features(image, cloud=None, batch=False, api_key=None, **kwargs):
     :rtype: List containing features
     """
     image = image_preprocess(image, batch=batch, size=(64,64))
-    return api_handler(image, cloud=cloud, api="imagefeatures", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    url_params = {"batch": batch, "api_key": api_key}
+    return api_handler(image, cloud=cloud, api="imagefeatures", url_params=url_params, **kwargs)

indicoio/images/fer.py

@@ -28,4 +28,5 @@ def fer(image, cloud=None, batch=False, api_key=None, **kwargs):
     :rtype: Dictionary containing emotion probability pairs
     """
     image = image_preprocess(image, batch=batch)
-    return api_handler(image, cloud=cloud, api="fer", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    url_params = {"batch": batch, "api_key": api_key}
+    return api_handler(image, cloud=cloud, api="fer", url_params=url_params, **kwargs)

indicoio/text/keywords.py

@@ -0,0 +1,24 @@
+from indicoio.utils.api import api_handler
+import indicoio.config as config
+
+def keywords(text, cloud=None, batch=False, api_key=None, **kwargs):
+    """
+    Given input text, returns series of keywords and associated scores
+
+    Example usage:
+
+    .. code-block:: python
+
+       >>> import indicoio
+       >>> import numpy as np
+       >>> text = 'Monday: Delightful with mostly sunny skies. Highs in the low 70s.'
+       >>> keywords = indicoio.keywords(text, top_n=3)
+       >>> print "The keywords are: "+str(keywords.keys())
+       u'The keywords are ['delightful', 'highs', 'skies']
+
+    :param text: The text to be analyzed.
+    :type text: str or unicode
+    :rtype: Dictionary of feature score pairs
+    """
+    url_params = {'batch': batch, 'api_key': api_key}
+    return api_handler(text, cloud=cloud, api="keywords", url_params=url_params, **kwargs)

indicoio/text/lang.py

@@ -23,5 +23,5 @@ def language(text, cloud=None, batch=False, api_key=None, **kwargs):
     :type text: str or unicode
     :rtype: Dictionary of language probability pairs
     """
-
+    url_params = {"batch": batch, "api_key": api_key}
-    return api_handler(text, cloud=cloud, api="language", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    return api_handler(text, cloud=cloud, api="language", url_params=url_params, **kwargs)

indicoio/text/sentiment.py

@@ -25,8 +25,8 @@ def political(text, cloud=None, batch=False, api_key=None, **kwargs):
     :type text: str or unicode
     :rtype: Dictionary of party probability pairs
     """
-
+    url_params = {"batch": batch, "api_key": api_key}
-    return api_handler(text, cloud=cloud, api="political", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    return api_handler(text, cloud=cloud, api="political", url_params=url_params, **kwargs)
 
 def posneg(text, cloud=None, batch=False, api_key=None, **kwargs):
     """
@@ -48,8 +48,8 @@ def posneg(text, cloud=None, batch=False, api_key=None, **kwargs):
     :type text: str or unicode
     :rtype: Float
     """
-
+    url_params = {"batch": batch, "api_key": api_key}
-    return api_handler(text, cloud=cloud, api="sentiment", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    return api_handler(text, cloud=cloud, api="sentiment", url_params=url_params, **kwargs)
 
 def sentiment_hq(text, cloud=None, batch=False, api_key=None, **kwargs):
     """
@@ -71,5 +71,5 @@ def sentiment_hq(text, cloud=None, batch=False, api_key=None, **kwargs):
     :type text: str or unicode
     :rtype: Float
     """
-
+    url_params = {"batch": batch, "api_key": api_key}
-    return api_handler(text, cloud=cloud, api="sentimenthq", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    return api_handler(text, cloud=cloud, api="sentimenthq", url_params=url_params, **kwargs)

indicoio/text/tagging.py

@@ -22,5 +22,5 @@ def text_tags(text, cloud=None, batch=False, api_key=None, **kwargs):
     :type text: str or unicode
     :rtype: Dictionary of class probability pairs
     """
-
+    url_params = {"batch": batch, "api_key": api_key}
-    return api_handler(text, cloud=cloud, api="texttags", url_params={"batch":batch, "api_key":api_key}, **kwargs)
+    return api_handler(text, cloud=cloud, api="texttags", url_params=url_params, **kwargs)

indicoio/utils/api.py

@@ -29,6 +29,8 @@ def api_handler(arg, cloud, api, url_params = {"batch":False, "api_key":None}, *
     if apis:
         url += "&apis=%s" % ",".join(apis)
 
+    print url
+
     response = requests.post(url, data=json_data, headers=JSON_HEADERS)
     if response.status_code == 503 and cloud != None:
         raise IndicoError("Private cloud '%s' does not include api '%s'" % (cloud, api))

tests/test_remote.py

@@ -9,6 +9,7 @@ from indicoio import config
 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
+from indicoio import keywords, batch_keywords
 from indicoio import sentiment_hq, batch_sentiment_hq
 from indicoio import predict_image, predict_text, batch_predict_image, batch_predict_text
 from indicoio.utils.errors import IndicoError
@@ -32,18 +33,22 @@ class BatchAPIRun(unittest.TestCase):
         response = batch_text_tags(test_data, api_key=self.api_key)
         self.assertTrue(isinstance(response, list))
 
+    def test_batch_keywords(self):
+        test_data = ["A working api is key to the success of our young company"]
+        response = batch_keywords(test_data, api_key=self.api_key)
+        self.assertTrue(isinstance(response, list))
+
     def test_batch_posneg(self):
         test_data = ['Worst song ever', 'Best song ever']
         response = batch_sentiment(test_data, api_key=self.api_key)
         self.assertTrue(isinstance(response, list))
         self.assertTrue(response[0] < 0.5)
 
-    # TODO: uncomment once the high quality sentiment API is publicly released
+    def test_batch_sentiment_hq(self):
-    # def test_batch_sentiment_hq(self):
+        test_data = ['Worst song ever', 'Best song ever']
-    #     test_data = ['Worst song ever', 'Best song ever']
+        response = batch_sentiment_hq(test_data, api_key=self.api_key)
-    #     response = batch_sentiment_hq(test_data, api_key=self.api_key)
+        self.assertTrue(isinstance(response, list))
-    #     self.assertTrue(isinstance(response, list))
+        self.assertTrue(response[0] < 0.5)
-    #     self.assertTrue(response[0] < 0.5)
 
     def test_batch_political(self):
         test_data = ["Guns don't kill people, people kill people."]
@@ -202,6 +207,20 @@ class FullAPIRun(unittest.TestCase):
         for v in results.values():
             assert v >= 0.1
 
+    def test_keywords(self):
+        text = "A working api is key to the success of our young company"
+
+        results = keywords(text)
+        assert 'api' in results.keys()
+
+        results = keywords(text, top_n=3)
+        assert len(results) is 3
+
+        results = keywords(text, threshold=.1)
+        for v in results.values():
+            assert v >= .1
+
+
     def test_political(self):
         political_set = set(['Libertarian', 'Liberal', 'Conservative', 'Green'])
         test_string = "Guns don't kill people, people kill people."
@@ -228,18 +247,17 @@ class FullAPIRun(unittest.TestCase):
         self.assertTrue(isinstance(response, float))
         self.assertTrue(response > 0.5)
 
-    # TODO: uncomment when the high quality sentiment API is publicly released
+    def test_sentiment_hq(self):
-    # def test_sentiment_hq(self):
+        test_string = "Worst song ever."
-    #     test_string = "Worst song ever."
+        response = sentiment_hq(test_string)
-    #     response = sentiment_hq(test_string)
 
-    #     self.assertTrue(isinstance(response, float))
+        self.assertTrue(isinstance(response, float))
-    #     self.assertTrue(response < 0.5)
+        self.assertTrue(response < 0.5)
 
-    #     test_string = "Best song ever."
+        test_string = "Best song ever."
-    #     response = sentiment_hq(test_string)
+        response = sentiment_hq(test_string)
-    #     self.assertTrue(isinstance(response, float))
+        self.assertTrue(isinstance(response, float))
-    #     self.assertTrue(response > 0.5)
+        self.assertTrue(response > 0.5)
 
     def test_good_fer(self):
         fer_set = set(['Angry', 'Sad', 'Neutral', 'Surprise', 'Fear', 'Happy'])