Merge branch 'main' into xgboost-cyclic

.devcontainer/Dockerfile

@@ -24,8 +24,8 @@ RUN SNIPPET="export PROMPT_COMMAND='history -a' && export HISTFILE=/commandhisto
     && echo $SNIPPET >> "/home/$USERNAME/.bashrc"
 
 # Install system dependencies
-RUN apt update 
-RUN apt install -y curl wget gnupg python3 python-is-python3 python3-pip git \
+RUN apt-get update
+RUN apt-get install -y curl wget gnupg python3 python-is-python3 python3-pip git \
     build-essential tmux vim
 
 RUN python -m pip install \

.devcontainer/devcontainer.json

@@ -1,11 +1,15 @@
 {
   "dockerFile": "Dockerfile",
-  "postCreateCommand": "poetry install --extras \"simulation\"",
-  "extensions": ["ms-python.python"],
-  "settings": {
-    "files.watcherExclude": {},
-    "search.exclude": {},
-    "terminal.integrated.defaultProfile.linux": "bash"
+  "postCreateCommand": "sudo poetry install --extras \"simulation\"",
+  "customizations": {
+    "vscode": {
+      "settings": {
+        "files.watcherExclude": { },
+        "search.exclude": { },
+        "terminal.integrated.defaultProfile.linux": "bash"
+      },
+      "extensions": [ "ms-python.python" ]
+    }
   },
   "remoteUser": "flwr-vscode",
   "containerEnv": {

.github/workflows/android-release.yml

@@ -16,7 +16,7 @@ jobs:
             working-directory: src/kotlin
     name: Release build and publish
     if: github.repository == 'adap/flower'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Check out code
         uses: actions/checkout@v4

.github/workflows/cpp.yml

@@ -11,7 +11,7 @@ on:
 jobs:
   build_and_test:
     name: Build and test
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
 
     steps:
     - uses: actions/checkout@v4

.github/workflows/framework-release.yml

@@ -9,7 +9,7 @@ jobs:
   publish:
     if: ${{ github.repository == 'adap/flower' }}
     name: Publish draft
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -53,7 +53,7 @@ jobs:
           cat body.md
           
       - name: Release
-        uses: softprops/action-gh-release@de2c0eb
+        uses: softprops/action-gh-release@v1
         with:
           body_path: ./body.md
           draft: true

.github/workflows/update-pr.yml

@@ -6,7 +6,7 @@ on:
       - 'main'
 jobs:
   autoupdate:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Automatically update mergeable PRs
         uses: adRise/[email protected]

baselines/doc/source/conf.py

@@ -36,7 +36,7 @@
 author = "The Flower Authors"
 
 # The full version, including alpha/beta/rc tags
-release = "1.6.0"
+release = "1.7.0"
 
 
 # -- General configuration ---------------------------------------------------

datasets/doc/source/how-to-use-with-numpy.rst

@@ -3,14 +3,30 @@ Use with NumPy
 
 Let's integrate ``flwr-datasets`` with NumPy.
 
-Prepare the desired partitioning::
+Create a ``FederatedDataset``::
 
   from flwr_datasets import FederatedDataset
 
   fds = FederatedDataset(dataset="cifar10", partitioners={"train": 10})
   partition = fds.load_partition(0, "train")
   centralized_dataset = fds.load_full("test")
 
+Inspect the names of the features::
+
+  partition.features
+
+In case of CIFAR10, you should see the following output.
+
+.. code-block:: none
+
+  {'img': Image(decode=True, id=None),
+  'label': ClassLabel(names=['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog',
+  'frog', 'horse', 'ship', 'truck'], id=None)}
+
+We will use the keys in the partition features in order to apply transformations to the data or pass it to a ML model.  Let's move to the transformations.
+
+NumPy
+-----
 Transform to NumPy::
 
   partition_np = partition.with_format("numpy")

datasets/doc/source/how-to-use-with-tensorflow.rst

@@ -1,10 +1,32 @@
 Use with TensorFlow
 ===================
 
-Let's integrate ``flwr-datasets`` with TensorFlow. We show you three ways how to convert the data into the formats
+Let's integrate ``flwr-datasets`` with ``TensorFlow``. We show you three ways how to convert the data into the formats
 that ``TensorFlow``'s models expect.  Please note that, especially for the smaller datasets, the performance of the
 following methods is very close. We recommend you choose the method you are the most comfortable with.
 
+Create a ``FederatedDataset``::
+
+  from flwr_datasets import FederatedDataset
+
+  fds = FederatedDataset(dataset="cifar10", partitioners={"train": 10})
+  partition = fds.load_partition(0, "train")
+  centralized_dataset = fds.load_full("test")
+
+Inspect the names of the features::
+
+  partition.features
+
+In case of CIFAR10, you should see the following output.
+
+.. code-block:: none
+
+  {'img': Image(decode=True, id=None),
+  'label': ClassLabel(names=['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog',
+  'frog', 'horse', 'ship', 'truck'], id=None)}
+
+We will use the keys in the partition features in order to construct a `tf.data.Dataset <https://www.tensorflow.org/api_docs/python/tf/data/Dataset>`_. Let's move to the transformations.
+
 NumPy
 -----
 The first way is to transform the data into the NumPy arrays. It's an easier option that is commonly used. Feel free to
@@ -14,17 +36,7 @@ follow the :doc:`how-to-use-with-numpy` tutorial, especially if you are a beginn
 
 TensorFlow Dataset
 ------------------
-Work with ``TensorFlow Dataset`` abstraction.
-
-Standard setup::
-
-  from flwr_datasets import FederatedDataset
-
-  fds = FederatedDataset(dataset="cifar10", partitioners={"train": 10})
-  partition = fds.load_partition(0, "train")
-  centralized_dataset = fds.load_full("test")
-
-Transformation to the TensorFlow Dataset::
+Transform the data to ``TensorFlow Dataset``::
 
   tf_dataset = partition.to_tf_dataset(columns="img", label_cols="label", batch_size=64,
                                      shuffle=True)
@@ -33,17 +45,7 @@ Transformation to the TensorFlow Dataset::
 
 TensorFlow Tensors
 ------------------
-Change the data type to TensorFlow Tensors (it's not the TensorFlow dataset).
-
-Standard setup::
-
-  from flwr_datasets import FederatedDataset
-
-  fds = FederatedDataset(dataset="cifar10", partitioners={"train": 10})
-  partition = fds.load_partition(0, "train")
-  centralized_dataset = fds.load_full("test")
-
-Transformation to the TensorFlow Tensors ::
+Transform the data to the TensorFlow `tf.Tensor <https://www.tensorflow.org/api_docs/python/tf/Tensor>`_ (it's not the TensorFlow dataset)::
 
   data_tf = partition.with_format("tf")
   # Assuming you have defined your model and compiled it

datasets/doc/source/tutorial-quickstart.rst

@@ -5,11 +5,11 @@ Run Flower Datasets as fast as possible by learning only the essentials.
 
 Install Federated Datasets
 --------------------------
-Run on the command line
+On the command line, run
 
 .. code-block:: bash
 
-  python -m pip install flwr-datasets[vision]
+  python -m pip install "flwr-datasets[vision]"
 
 Install the ML framework
 ------------------------
@@ -28,12 +28,11 @@ PyTorch
 Choose the dataset
 ------------------
 Choose the dataset by going to Hugging Face `Datasets Hub <https://huggingface.co/datasets>`_ and searching for your
-dataset by name. Note that the name is case sensitive, so make sure to pass the correct name as the `dataset` parameter
-to `FederatedDataset`.
+dataset by name that you will pass to the `dataset` parameter of `FederatedDataset`. Note that the name is case sensitive.
 
 Partition the dataset
 ---------------------
-::
+To iid partition your dataset, choose the split you want to partition and the number of partitions::
 
   from flwr_datasets import FederatedDataset
 
@@ -42,12 +41,32 @@ Partition the dataset
   centralized_dataset = fds.load_full("test")
 
 Now you're ready to go. You have ten partitions created from the train split of the MNIST dataset and the test split
-for the centralized evaluation. We will convert the type of the dataset from Hugging Face's Dataset type to the one
+for the centralized evaluation. We will convert the type of the dataset from Hugging Face's `Dataset` type to the one
 supported by your framework.
 
+Display the features
+--------------------
+Determine the names of the features of your dataset (you can alternatively do that directly on the Hugging Face
+website). The names can vary along different datasets e.g. "img" or "image", "label" or "labels". You will also see
+the names of label categories. Type::
+
+  partition.features
+
+In case of CIFAR10, you should see the following output.
+
+.. code-block:: none
+
+  {'img': Image(decode=True, id=None),
+  'label': ClassLabel(names=['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog',
+  'frog', 'horse', 'ship', 'truck'], id=None)}
+
+Note that the image is denoted by "img" which is crucial for the next steps (conversion you the ML
+framework of your choice).
+
 Conversion
 ----------
-For more detailed instructions, go to :doc:`how-to-use-with-pytorch`.
+For more detailed instructions, go to :doc:`how-to-use-with-pytorch`, :doc:`how-to-use-with-numpy`, or
+:doc:`how-to-use-with-tensorflow`.
 
 PyTorch DataLoader
 ^^^^^^^^^^^^^^^^^^

dev/get-latest-changelog.sh

@@ -9,9 +9,9 @@ tags=$(git tag --sort=-v:refname)
 new_version=$(echo "$tags" | sed -n '1p')
 old_version=$(echo "$tags" | sed -n '2p')
 
-awk -v start="$new_version" -v end="$old_version" '
+awk '{sub(/<!--.*-->/, ""); print}' doc/source/ref-changelog.md | awk -v start="$new_version" -v end="$old_version" '
     $0 ~ start {flag=1; next}
     $0 ~ end {flag=0}
     flag && !printed && /^$/ {next}  # skip the first blank line
     flag && !printed {printed=1}
-    flag' doc/source/ref-changelog.md
+    flag'

dev/add-shortlog.sh → dev/prepare-release-changelog.sh

@@ -2,20 +2,23 @@
 set -e
 cd "$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"/../
 
+# Get the current date in the format YYYY-MM-DD
+current_date=$(date +"%Y-%m-%d")
+
 tags=$(git tag --sort=-v:refname)
-new_version=$(echo "$tags" | sed -n '1p')
-old_version=$(echo "$tags" | sed -n '2p')
+new_version=$1
+old_version=$(echo "$tags" | sed -n '1p')
 
-shortlog=$(git shortlog "$old_version".."$new_version" -s | grep -vEi '(\(|\[)bot(\)|\])' | awk '{name = substr($0, index($0, $2)); printf "%s`%s`", sep, name; sep=", "} END {print ""}')
+shortlog=$(git shortlog "$old_version"..main -s | grep -vEi '(\(|\[)bot(\)|\])' | awk '{name = substr($0, index($0, $2)); printf "%s`%s`", sep, name; sep=", "} END {print ""}')
 
 token="<!---TOKEN_$new_version-->"
 thanks="\n### Thanks to our contributors\n\nWe would like to give our special thanks to all the contributors who made the new version of Flower possible (in \`git shortlog\` order):\n\n$shortlog $token"
 
 # Check if the token exists in the markdown file
 if ! grep -q "$token" doc/source/ref-changelog.md; then
     # If the token does not exist in the markdown file, append the new content after the version
-    awk -v version="$new_version" -v text="$thanks" \
-        '{print} $0 ~ "## " version {print text}' doc/source/ref-changelog.md > temp.md && mv temp.md doc/source/ref-changelog.md
+    awk -v version="$new_version" -v date="$current_date" -v text="$thanks" \
+        '{ if ($0 ~ "## Unreleased") print "## " version " (" date ")\n" text; else print $0 }' doc/source/ref-changelog.md > temp.md && mv temp.md doc/source/ref-changelog.md
 else
     # If the token exists, replace the line containing the token with the new shortlog
     awk -v token="$token" -v newlog="$shortlog $token" '{ if ($0 ~ token) print newlog; else print $0 }' doc/source/ref-changelog.md > temp.md && mv temp.md doc/source/ref-changelog.md

dev/update-examples.sh

@@ -22,9 +22,14 @@ cd examples/
 for d in $(printf '%s\n' */ | sort -V); do
   example=${d%/}
   # For each example, copy the README into the source of the Example docs
-  [[ $example = doc ]] || cp $example/README.md $ROOT/examples/doc/source/$example.md 2>&1 >/dev/null
+  [[ $example != doc ]] && cp $example/README.md $ROOT/examples/doc/source/$example.md 2>&1 >/dev/null
+  # For each example, copy all images of the _static folder into the examples
+  # docs static folder
+  [[ $example != doc ]] && [ -d "$example/_static" ] && {
+    cp $example/_static/**.{jpg,png,jpeg} $ROOT/examples/doc/source/_static/ 2>/dev/null || true
+  }
   # For each example, insert the name of the example into the index file
-  [[ $example = doc ]] || (echo $INSERT_LINE; echo a; echo $example; echo .; echo wq) | ed $INDEX 2>&1 >/dev/null
+  [[ $example != doc ]] && (echo $INSERT_LINE; echo a; echo $example; echo .; echo wq) | ed $INDEX 2>&1 >/dev/null
 done
 
 echo "\`\`\`" >> $INDEX