removed full_feature_names usage from quickstart and README to have m…

…ore simple examples. Resolved failing tests. Signed-off-by: Mwad22 <51929507+Mwad22@users.noreply.github.com>
feast-dev · feast-ci-bot · Jul 8, 2021 · Jun 12, 2021 · Jun 16, 2021 · Jun 16, 2021
commit 4b7dd1897d5e8b7891233959cba40d01dfa523f4
diff --git a/README.md b/README.md
@@ -67,7 +67,6 @@ training_df = store.get_historical_features(
         'driver_hourly_stats:acc_rate',
         'driver_hourly_stats:avg_daily_trips'
     ],
-    full_feature_names=True
 ).to_df()
 
 print(training_df.head())
@@ -76,11 +75,11 @@ print(training_df.head())
 # model = ml.fit(training_df)
 ```
 ```commandline
-      event_timestamp  driver_id  driver_hourly_stats__conv_rate  driver_hourly_stats__acc_rate
-  2021-04-12 08:12:10       1002                        0.497279                       0.357702
-  2021-04-12 10:59:42       1001                        0.979747                       0.008166
-  2021-04-12 15:01:12       1004                        0.151432                       0.551748
-  2021-04-12 16:40:26       1003                        0.951506                       0.753572
+            event_timestamp  driver_id  conv_rate  acc_rate  avg_daily_trips
+0 2021-04-12 08:12:10+00:00       1002   0.713465  0.597095              531
+1 2021-04-12 10:59:42+00:00       1001   0.072752  0.044344               11
+2 2021-04-12 15:01:12+00:00       1004   0.658182  0.079150              220
+3 2021-04-12 16:40:26+00:00       1003   0.162092  0.309035              959
 
 ```
 

@@ -234,8 +234,7 @@ feature_vector = store.get_online_features(
         'driver_hourly_stats:acc_rate',
         'driver_hourly_stats:avg_daily_trips'
     ],
-    entity_rows=[{"driver_id": 1001}],
-    full_feature_names=True
+    entity_rows=[{"driver_id": 1001}]
 ).to_dict()
 
 pprint(feature_vector)
@@ -245,9 +244,9 @@ pprint(feature_vector)
 ```text
 {
     'driver_id': [1001],
-    'driver_hourly_stats__conv_rate': [0.49274],
-    'driver_hourly_stats__acc_rate': [0.92743],
-    'driver_hourly_stats__avg_daily_trips': [72],
+    'conv_rate': [0.49274],
+    'acc_rate': [0.92743],
+    'avg_daily_trips': [72],
 }
 ```
 

@@ -634,7 +634,6 @@ def _group_refs(
             raise FeatureViewNotFoundException(view_name)
         views_features[view_name].append(feat_name)
 
-    print(full_feature_names)
     if not full_feature_names and len(feature_collision_set) > 0:
         err = ", ".join(x for x in feature_collision_set)
         raise FeatureNameCollisionError(err)

@@ -651,8 +651,7 @@ def test_feature_name_collision_on_historical_retrieval_from_bigquery_sources():
     bigquery_dataset = (
         f"test_hist_retrieval_{int(time.time_ns())}_{random.randint(1000, 9999)}"
     )
-
-    gcp_project = bigquery.Client().project
+    gcp_project = "project_name"
 
     # Driver Feature View
     driver_table_id = f"{gcp_project}.{bigquery_dataset}.driver_hourly"

@@ -276,7 +276,7 @@ def test_online_to_df():
         for (d, c) in zip(driver_ids, customer_ids):
             """
             driver table:
-            driver driver_locations__lon  driver_locations__lat
+                                    lon                    lat
                 1                   1.0                    0.1
                 2                   2.0                    0.2
                 3                   3.0                    0.3
@@ -303,10 +303,10 @@ def test_online_to_df():
 
             """
             customer table
-            customer  customer_profile__avg_orders_day customer_profile__name  customer_profile__age
-                4                               4.0                  foo4                     40
-                5                               5.0                  foo5                     50
-                6                               6.0                  foo6                     60
+            customer     avg_orders_day          name        age
+                4           4.0                  foo4         40
+                5           5.0                  foo5         50
+                6           6.0                  foo6         60
             """
             customer_key = EntityKeyProto(
                 join_keys=["customer"], entity_values=[ValueProto(int64_val=c)]
@@ -332,10 +332,10 @@ def test_online_to_df():
             )
             """
             customer_driver_combined table
-            customer  driver  customer_driver_combined__trips
-                4       1                                4
-                5       2                               10
-                6       3                               18
+            customer  driver    trips
+                4       1       4
+                5       2       10
+                6       3       18
             """
             combo_keys = EntityKeyProto(
                 join_keys=["customer", "driver"],
@@ -373,35 +373,31 @@ def test_online_to_df():
         ).to_df()
         """
         Construct the expected dataframe with reversed row order like so:
-        driver  customer driver_locations__lon  driver_locations__lat  customer_profile__avg_orders_day customer_profile__name  customer_profile__age  customer_driver_combined__trips
-            3       6         3.0                   0.3                    6.0                               foo6                   60                     18
-            2       5         2.0                   0.2                    5.0                               foo5                   50                     10
-            1       4         1.0                   0.1                    4.0                               foo4                   40                     4
+        driver  customer     lon    lat     avg_orders_day      name        age     trips
+            3       6        3.0    0.3         6.0             foo6        60       18
+            2       5        2.0    0.2         5.0             foo5        50       10
+            1       4        1.0    0.1         4.0             foo4        40       4
         """
         df_dict = {
             "driver": driver_ids,
             "customer": customer_ids,
-            "driver_locations__lon": [str(d * lon_multiply) for d in driver_ids],
-            "driver_locations__lat": [d * lat_multiply for d in driver_ids],
-            "customer_profile__avg_orders_day": [
-                c * avg_order_day_multiply for c in customer_ids
-            ],
-            "customer_profile__name": [name + str(c) for c in customer_ids],
-            "customer_profile__age": [c * age_multiply for c in customer_ids],
-            "customer_driver_combined__trips": [
-                d * c for (d, c) in zip(driver_ids, customer_ids)
-            ],
+            "lon": [str(d * lon_multiply) for d in driver_ids],
+            "lat": [d * lat_multiply for d in driver_ids],
+            "avg_orders_day": [c * avg_order_day_multiply for c in customer_ids],
+            "name": [name + str(c) for c in customer_ids],
+            "age": [c * age_multiply for c in customer_ids],
+            "trips": [d * c for (d, c) in zip(driver_ids, customer_ids)],
         }
         # Requested column order
         ordered_column = [
             "driver",
             "customer",
-            "driver_locations__lon",
-            "driver_locations__lat",
-            "customer_profile__avg_orders_day",
-            "customer_profile__name",
-            "customer_profile__age",
-            "customer_driver_combined__trips",
+            "lon",
+            "lat",
+            "avg_orders_day",
+            "name",
+            "age",
+            "trips",
         ]
         expected_df = pd.DataFrame({k: reversed(v) for (k, v) in df_dict.items()})
         assert_frame_equal(result_df[ordered_column], expected_df)