add compute_prediction

pplonski · pplonski · commit c631a59c8f00 · 2017-04-06T19:23:09.000+02:00
diff --git a/mljar/mljar.py b/mljar/mljar.py
@@ -24,7 +24,8 @@ class Mljar(object):
     This is a wrapper over MLJAR API - it does all the stuff.
     '''
 
-    def __init__(self, project, experiment,
+    def __init__(self, project,
+                        experiment,
                         metric = '',
                         algorithms = [],
                         validation_kfolds = MLJAR_DEFAULT_FOLDS,
@@ -316,3 +317,40 @@ def predict(self, X):
             logger.error('Sorry, there was some problem with computing prediction for your dataset. \
                             Please login to mljar.com to your account and check details.')
             return None
+
+
+    @staticmethod
+    def compute_prediction(X, model_id, project_id):
+
+
+        # chack if dataset exists in mljar if not upload dataset for prediction
+        dataset = DatasetClient(project_id).add_dataset_if_not_exists(X, y = None)
+
+        # check if prediction is available
+        total_checks = 100
+        for i in xrange(total_checks):
+            prediction = PredictionClient(project_id).\
+                            get_prediction(dataset.hid, model_id)
+
+            # prediction is not available, first check so submit job
+            if i == 0 and prediction is None:
+                # create prediction job
+                submitted = PredictJobClient().submit(project_id, dataset.hid,
+                                                        model_id)
+                if not submitted:
+                    logger.error('Problem with prediction for your dataset')
+                    return None
+
+            if prediction is not None:
+                pred = PredictionDownloadClient().download(prediction.hid)
+                #sys.stdout.write('\r\n')
+                return pred
+
+            #sys.stdout.write('\rFetch predictions: {0}%'.format(round(i/(total_checks*0.01))))
+            #sys.stdout.flush()
+            time.sleep(5)
+
+        #sys.stdout.write('\r\n')
+        logger.error('Sorry, there was some problem with computing prediction for your dataset. \
+                        Please login to mljar.com to your account and check details.')
+        return None
diff --git a/setup.py b/setup.py
@@ -10,7 +10,7 @@
 
 setup(
     name='mljar',
-    version='0.0.6',
+    version='0.0.7',
     description='Python wrapper over MLJAR API',
     long_description=long_description,
     url='https://github.com/mljar/mljar-api-python',
diff --git a/tests/mljar_test.py b/tests/mljar_test.py
@@ -26,16 +26,38 @@ def setUp(self):
         self.X = df[cols]
         self.y = df[target]
 
-    def tearDown(self):
-        # clean
-        ProjectBasedTest.clean_projects()
+    #def tearDown(self):
+    #    # clean
+    #    ProjectBasedTest.clean_projects()
 
     def mse(self, predictions, targets):
         predictions = np.array(predictions)
         targets = np.array(targets)
         targets = targets.reshape((targets.shape[0],1))
         return ((predictions - targets) ** 2).mean()
 
+
+    def test_compute_prediction(self):
+        '''
+        Test the most common usage.
+        '''
+        model = Mljar(project = self.proj_title, experiment = self.expt_title,
+                        algorithms = ['rfc'], metric='logloss',
+                        validation_kfolds=3, tuning_mode='Normal')
+        self.assertTrue(model is not None)
+        # fit models and wait till all models are trained
+        model.fit(X = self.X, y = self.y)
+
+        # get project id
+        project_id = model.project.hid
+        # get model id
+        model_id = model.selected_algorithm.hid
+        # compute predictions
+        pred = Mljar.compute_prediction(self.X, model_id, project_id)
+        # compute score
+        score = self.mse(pred, self.y)
+        self.assertTrue(score < 0.1)
+
     def test_basic_usage(self):
         '''
         Test the most common usage.
