From 4e14c375a6b3072be719729c32af52f9e44f23b8 Mon Sep 17 00:00:00 2001
From: Andrew Crozier <wacrozier@gmail.com>
Date: Wed, 22 Jan 2020 13:03:46 +0000
Subject: [PATCH 1/3] Add module to make datasets IO easier with pandas

---
 faculty/datasets/pandas.py | 77 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 faculty/datasets/pandas.py

diff --git a/faculty/datasets/pandas.py b/faculty/datasets/pandas.py
new file mode 100644
index 00000000..4dcd527a
--- /dev/null
+++ b/faculty/datasets/pandas.py
@@ -0,0 +1,77 @@
+# Copyright 2018-2019 Faculty Science Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import pandas
+
+from faculty.session import get_session
+from faculty.context import get_context
+from faculty.clients.object import ObjectClient
+from faculty.datasets import transfer
+
+
+def read_csv(project_path, project_id=None, *args, **kwargs):
+    """Read a CSV file from a project's datasets as a pandas DataFrame.
+
+    Requires pandas to be installed.
+
+    Parameters
+    ----------
+    project_path : str
+        The path of the CSV file in the project's datasets to read.
+    project_id : str, optional
+        The project to get the CSV file from. You need to have access to this
+        project for it to work. Defaults to the project set by
+        FACULTY_PROJECT_ID in your environment.
+    *args
+        Additional positional arguments to pass to ``pandas.read_csv``.
+    **kwargs
+        Additional keyword arguments to pass to ``pandas.read_csv``.
+    """
+
+    project_id = project_id or get_context().project_id
+    object_client = ObjectClient(get_session())
+    presigned_url = object_client.presign_download(project_id, project_path)
+
+    return pandas.read_csv(presigned_url, *args, **kwargs)
+
+
+def to_csv(dataframe, project_path, project_id=None, *args, **kwargs):
+    """Write a pandas DataFrame to a CSV file in a project's datasets.
+
+    Requires pandas to be installed.
+
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        The DataFrame to write.
+    project_path : str
+        The path in the project's datasets to write to.
+    project_id : str, optional
+        The project to write the CSV file to. You need to have access to this
+        project for it to work. Defaults to the project set by
+        FACULTY_PROJECT_ID in your environment.
+    *args
+        Additional positional arguments to pass to ``pandas.DataFrame.to_csv``.
+    **kwargs
+        Additional keyword arguments to pass to ``pandas.DataFrame.to_csv``.
+    """
+
+    project_id = project_id or get_context().project_id
+    object_client = ObjectClient(get_session())
+
+    content = dataframe.to_csv(path_or_buf=None, *args, **kwargs)
+
+    transfer.upload(
+        object_client, project_id, project_path, content.encode("utf-8")
+    )

From 0691b3f8429f76d452cfa55731df5eca11416252 Mon Sep 17 00:00:00 2001
From: Andrew Crozier <acroz@acroz-laptop.local>
Date: Wed, 23 Jun 2021 10:32:17 +0100
Subject: [PATCH 2/3] Update copyright notice

---
 faculty/datasets/pandas.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/faculty/datasets/pandas.py b/faculty/datasets/pandas.py
index 4dcd527a..2c88c48a 100644
--- a/faculty/datasets/pandas.py
+++ b/faculty/datasets/pandas.py
@@ -1,4 +1,4 @@
-# Copyright 2018-2019 Faculty Science Limited
+# Copyright 2018-2021 Faculty Science Limited
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

From 0ef85aaafa9ff80a1a416e46494356d090c1e453 Mon Sep 17 00:00:00 2001
From: Andrew Crozier <acroz@acroz-laptop.local>
Date: Wed, 23 Jun 2021 12:39:19 +0100
Subject: [PATCH 3/3] Update to latest client APIs

---
 faculty/datasets/pandas.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/faculty/datasets/pandas.py b/faculty/datasets/pandas.py
index 2c88c48a..07a4f6eb 100644
--- a/faculty/datasets/pandas.py
+++ b/faculty/datasets/pandas.py
@@ -40,7 +40,11 @@ def read_csv(project_path, project_id=None, *args, **kwargs):
     """
 
     project_id = project_id or get_context().project_id
-    object_client = ObjectClient(get_session())
+
+    session = get_session()
+    url = session.service_url(ObjectClient.SERVICE_NAME)
+    object_client = ObjectClient(url, session)
+
     presigned_url = object_client.presign_download(project_id, project_path)
 
     return pandas.read_csv(presigned_url, *args, **kwargs)
@@ -68,7 +72,10 @@ def to_csv(dataframe, project_path, project_id=None, *args, **kwargs):
     """
 
     project_id = project_id or get_context().project_id
-    object_client = ObjectClient(get_session())
+
+    session = get_session()
+    url = session.service_url(ObjectClient.SERVICE_NAME)
+    object_client = ObjectClient(url, session)
 
     content = dataframe.to_csv(path_or_buf=None, *args, **kwargs)