fiddler-client 3.0.0.dev12__tar.gz → 3.0.0.dev13__tar.gz

{fiddler-client-3.0.0.dev12/fiddler_client.egg-info → fiddler-client-3.0.0.dev13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fiddler-client
-Version: 3.0.0.dev12
+Version: 3.0.0.dev13
 Summary: Python client for Fiddler Platform
 Home-page: https://fiddler.ai
 Author: Fiddler Labs

fiddler-client-3.0.0.dev13/fiddler/VERSION

@@ -0,0 +1 @@
+3.0.0.dev13

{fiddler-client-3.0.0.dev12 → fiddler-client-3.0.0.dev13}/fiddler/entities/events.py

@@ -1,11 +1,13 @@
 from __future__ import annotations
 
+import tempfile
 from pathlib import Path
-from typing import Any, Iterator
+from typing import Any
 from uuid import UUID
 
 import pandas as pd
 from requests import Response
+from tqdm import tqdm
 
 from fiddler.configs import STREAM_EVENT_LIMIT
 from fiddler.connection import ConnectionMixin
@@ -28,21 +30,6 @@ class EventPublisher(ConnectionMixin):
         """
         self.model_id = model_id
 
-    def _get_stream_chunks(
-        self, source: pd.DataFrame | list[dict[str, Any]]
-    ) -> Iterator[list[dict[str, Any]]]:
-        """Chunk the source based on stream limit"""
-
-        for i in range(0, len(source), self.STREAM_LIMIT):
-            chunk = source[i : i + self.STREAM_LIMIT]
-
-            if isinstance(chunk, pd.DataFrame):
-                events = chunk.to_dict('records')
-            else:
-                events = chunk
-
-            yield events
-
     @handle_api_error
     def publish(
         self,
@@ -56,13 +43,13 @@ class EventPublisher(ConnectionMixin):
 
         :param source: one of:
             Path or str path: path for data file.
-            list[dict]: list of event dicts (max 1000) EnvType.PRE_PRODUCTION is not supported
-            dataframe: events dataframe. EnvType.PRE_PRODUCTION not supported.
+            dataframe: events dataframe.
+            list[dict]: list of event dicts EnvType.PRE_PRODUCTION is not supported
         :param environment: Either EnvType.PRE_PRODUCTION or EnvType.PRODUCTION
         :param dataset_name: Name of the dataset. Not supported for EnvType.PRODUCTION
         :param update: flag indicating if the events are updates to previously published rows
 
-        :return: list[UUID] for list of dicts or dataframe source and Job object for file path source.
+        :return: list[UUID] for list of dicts source and Job object for file path or dataframe source.
         """
         if isinstance(source, (str, Path)):
             return self._publish_file(
@@ -72,20 +59,30 @@ class EventPublisher(ConnectionMixin):
                 update=update,
             )
 
-        if isinstance(source, (list, pd.DataFrame)):
+        if isinstance(source, pd.DataFrame):
+            with tempfile.NamedTemporaryFile(suffix='.csv') as temp_file:
+                source.to_csv(temp_file.name, index=False)
+                return self._publish_file(
+                    source=temp_file.name,
+                    environment=environment,
+                    dataset_name=dataset_name,
+                    update=update,
+                )
+
+        elif isinstance(source, list):
             return self._publish_stream(source=source, update=update)
 
         raise ValueError(f'Unsupported source - {type(source)}')
 
     def _publish_stream(
         self,
-        source: list[dict[str, Any]] | pd.DataFrame,
+        source: list[dict[str, Any]],
         update: bool = False,
     ) -> list[UUID]:
         event_ids = []
-        for events in self._get_stream_chunks(source=source):
+        for i in tqdm(range(0, len(source), self.STREAM_LIMIT)):
             response = self._publish_call(
-                source=EventsSource(events=events),
+                source=EventsSource(events=source[i : i + self.STREAM_LIMIT]),
                 environment=EnvType.PRODUCTION,
                 dataset_name=None,
                 update=update,

{fiddler-client-3.0.0.dev12 → fiddler-client-3.0.0.dev13}/fiddler/tests/apis/test_events.py

@@ -100,52 +100,74 @@ def test_publish_file() -> None:
 
 
 @responses.activate
-def test_publish_stream() -> None:
+def test_publish_df() -> None:
     responses.get(
         url=f'{URL}/v3/models/{MODEL_ID}',
         json=MODEL_API_RESPONSE_200,
     )
     model = Model.get(id_=MODEL_ID)
 
+    responses.post(
+        url=f'{URL}/v3/files/upload',
+        json=SINGLE_UPLOAD_200_RESPONSE,
+    )
+    responses.get(
+        url=f'{URL}/v3/jobs/{JOB_ID}',
+        json=PUBLISH_JOB_RESPONSE,
+    )
+
     responses.post(
         url=f'{URL}/v3/events',
-        json=STREAM_PUBLISH_202_API_RESPONSE,
+        json=FILE_PUBLISH_202_API_RESPONSE,
     )
     publish_response = model.publish(
-        source=df,
-        environment=EnvType.PRODUCTION,
+        source=df, environment=EnvType.PRE_PRODUCTION, dataset_name='dataset_1'
     )
 
-    assert isinstance(publish_response, list)
-    assert len(publish_response) == df.shape[0]
+    assert isinstance(publish_response, Job)
+
+    FILE_PUBLISH_202_API_RESPONSE['data']['job']['name'] = 'Publish events'
 
     publish_response = model.publish(
-        source=df.to_dict('records'),
+        source=df,
         environment=EnvType.PRODUCTION,
     )
 
-    assert isinstance(publish_response, list)
-    assert len(publish_response) == df.shape[0]
+    assert isinstance(publish_response, Job)
+
+    FILE_PUBLISH_202_API_RESPONSE['data']['job']['name'] = 'Publish events'
 
 
 @responses.activate
-def test_publish_update() -> None:
+def test_publish_stream() -> None:
     responses.get(
         url=f'{URL}/v3/models/{MODEL_ID}',
         json=MODEL_API_RESPONSE_200,
     )
     model = Model.get(id_=MODEL_ID)
 
-    responses.patch(
+    responses.post(
         url=f'{URL}/v3/events',
         json=STREAM_PUBLISH_202_API_RESPONSE,
     )
+
     publish_response = model.publish(
-        source=df, environment=EnvType.PRODUCTION, update=True
+        source=df.to_dict('records'),
+        environment=EnvType.PRODUCTION,
     )
+
     assert isinstance(publish_response, list)
     assert len(publish_response) == df.shape[0]
 
+
+@responses.activate
+def test_publish_update() -> None:
+    responses.get(
+        url=f'{URL}/v3/models/{MODEL_ID}',
+        json=MODEL_API_RESPONSE_200,
+    )
+    model = Model.get(id_=MODEL_ID)
+
     responses.post(
         url=f'{URL}/v3/files/upload',
         json=SINGLE_UPLOAD_200_RESPONSE,
@@ -167,3 +189,8 @@ def test_publish_update() -> None:
     )
 
     assert isinstance(publish_response, Job)
+
+    publish_response = model.publish(
+        source=df, environment=EnvType.PRODUCTION, update=True
+    )
+    assert isinstance(publish_response, Job)

{fiddler-client-3.0.0.dev12 → fiddler-client-3.0.0.dev13/fiddler_client.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fiddler-client
-Version: 3.0.0.dev12
+Version: 3.0.0.dev13
 Summary: Python client for Fiddler Platform
 Home-page: https://fiddler.ai
 Author: Fiddler Labs

fiddler-client-3.0.0.dev12/fiddler/VERSION

@@ -1 +0,0 @@
-3.0.0.dev12