Drop support for Python 3.8

.github/actions/setup/action.yml

@@ -3,7 +3,7 @@ name: Setup
 inputs:
   python-version:
     required: false
-    default: '3.8'
+    default: '3.9'
   torch-version:
     required: false
     default: '2.2.0'
@@ -16,7 +16,7 @@ runs:
 
   steps:
     - name: Set up Python ${{ inputs.python-version }}
-      uses: actions/setup-python@v4.3.0
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ inputs.python-version }}
         check-latest: true

.github/workflows/linting.yml

@@ -15,7 +15,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.9
       - name: Install dependencies
         run: |
           pip install -e '.[full,test]' -f https://download.pytorch.org/whl/cpu

.pre-commit-config.yaml

@@ -38,7 +38,7 @@ repos:
     hooks:
       - id: pyupgrade
         name: Upgrade Python syntax
-        args: [--py38-plus]
+        args: [--py39-plus]
 
   - repo: https://github.com/PyCQA/autoflake
     rev: v2.3.1

CHANGELOG.md

@@ -19,6 +19,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Removed
 
+- Dropped support for Python 3.8 ([#462](https://github.com/pyg-team/pytorch-frame/pull/462))
+
 ### Fixed
 
 - Fixed size mismatch `RuntimeError` in `transforms.CatToNumTransform` ([#446](https://github.com/pyg-team/pytorch-frame/pull/446))

README.md

@@ -245,7 +245,7 @@ The benchmark script for Hugging Face text encoders is in this [file](https://gi
 
 ## Installation
 
-PyTorch Frame is available for Python 3.8 to Python 3.11.
+PyTorch Frame is available for Python 3.9 to Python 3.11.
 
 ```
 pip install pytorch_frame

benchmark/data_frame_benchmark.py

@@ -3,7 +3,7 @@
 import os
 import os.path as osp
 import time
-from typing import Any, Dict, Optional, Tuple
+from typing import Any, Optional
 
 import numpy as np
 import optuna
@@ -303,10 +303,10 @@ def test(
 
 
 def train_and_eval_with_cfg(
-    model_cfg: Dict[str, Any],
-    train_cfg: Dict[str, Any],
+    model_cfg: dict[str, Any],
+    train_cfg: dict[str, Any],
     trial: Optional[optuna.trial.Trial] = None,
-) -> Tuple[float, float]:
+) -> tuple[float, float]:
     # Use model_cfg to set up training procedure
     if args.model_type == 'FTTransformerBucket':
         # Use LinearBucketEncoder instead

benchmark/encoder/encoder_benchmark.py

@@ -1,7 +1,6 @@
 import time
 from argparse import ArgumentParser
 from contextlib import nullcontext
-from typing import Dict
 
 import torch
 from line_profiler import profile
@@ -115,7 +114,7 @@
 }
 
 
-def make_stype_encoder_dict() -> Dict[stype, StypeEncoder]:
+def make_stype_encoder_dict() -> dict[stype, StypeEncoder]:
     stype_encoder_dict = {}
     for stype_str, encoder_str in args.stype_kv:
         encoder_kwargs = encoder_str2encoder_cls_kwargs[encoder_str]

docs/requirements.txt

@@ -1,2 +1,2 @@
-https://download.pytorch.org/whl/cpu/torch-2.0.0%2Bcpu-cp38-cp38-linux_x86_64.whl
+https://download.pytorch.org/whl/cpu/torch-2.4.1%2Bcpu-cp39-cp39-linux_x86_64.whl
 git+https://github.com/pyg-team/pyg_sphinx_theme.git

docs/source/get_started/installation.rst

@@ -1,7 +1,7 @@
 Installation
 ============
 
-:pyf:`PyTorch Frame` is available for `Python 3.8` to `Python 3.11` on Linux, Windows and macOS.
+:pyf:`PyTorch Frame` is available for `Python 3.9` to `Python 3.11` on Linux, Windows and macOS.
 
 Installation via PyPI
 ---------------------

examples/llm_embedding.py

@@ -1,7 +1,6 @@
 import argparse
 import os
 import os.path as osp
-from typing import List
 
 import torch
 import torch.nn.functional as F
@@ -64,10 +63,10 @@ def __init__(self, model: str = "text-embedding-ada-002"):
         self.client = OpenAI(api_key=api_key)
         self.model = model
 
-    def __call__(self, sentences: List[str]) -> Tensor:
+    def __call__(self, sentences: list[str]) -> Tensor:
         from openai import Embedding
 
-        items: List[Embedding] = self.client.embeddings.create(
+        items: list[Embedding] = self.client.embeddings.create(
             input=sentences, model=self.model).data
         assert len(items) == len(sentences)
         embeddings = [
@@ -87,7 +86,7 @@ def __init__(self, model: str = "embed-english-v3.0"):
         self.model = model
         self.co = cohere.Client(api_key)
 
-    def __call__(self, sentences: List[str]) -> Tensor:
+    def __call__(self, sentences: list[str]) -> Tensor:
         from cohere import EmbedResponse
 
         response: EmbedResponse = self.co.embed(model=self.model,
@@ -106,13 +105,13 @@ def __init__(self, model: str = "voyage-01"):
         # Please run `pip install voyageai` to install the package
         self.model = model
 
-    def __call__(self, sentences: List[str]) -> Tensor:
+    def __call__(self, sentences: list[str]) -> Tensor:
         import voyageai  # noqa
 
         voyageai.api_key = api_key
         from voyageai import get_embeddings
 
-        items: List[List[float]] = get_embeddings(sentences, model=self.model)
+        items: list[list[float]] = get_embeddings(sentences, model=self.model)
         assert len(items) == len(sentences)
         embeddings = [torch.FloatTensor(item).view(1, -1) for item in items]
         return torch.cat(embeddings, dim=0)

examples/tutorial.py

@@ -5,7 +5,7 @@
 import argparse
 import math
 import os.path as osp
-from typing import Any, Dict, List
+from typing import Any
 
 import torch
 import torch.nn.functional as F
@@ -157,8 +157,8 @@ def __init__(
         out_channels: int,
         num_layers: int,
         # kwargs for feature encoder
-        col_stats: Dict[str, Dict[StatType, Any]],
-        col_names_dict: Dict[torch_frame.stype, List[str]],
+        col_stats: dict[str, dict[StatType, Any]],
+        col_names_dict: dict[torch_frame.stype, list[str]],
     ):
         super().__init__()
         # Specify what feature encoder to use for each stype.

pyproject.toml

@@ -10,7 +10,7 @@ authors=[
 ]
 description="Tabular Deep Learning Library for PyTorch"
 readme="README.md"
-requires-python=">=3.8"
+requires-python=">=3.9"
 keywords=[
     "deep-learning",
     "pytorch",
@@ -21,7 +21,6 @@ classifiers=[
     "Development Status :: 4 - Beta",
     "License :: OSI Approved :: MIT License",
     "Programming Language :: Python",
-    "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
@@ -83,7 +82,7 @@ ignore = [
 src = ["torch_frame"]
 line-length = 80
 indent-width = 4
-target-version = "py38"
+target-version = "py39"
 
 # [tool.ruff.per-files-ignores]
 

readthedocs.yml

@@ -3,7 +3,7 @@ version: 2
 build:
    os: ubuntu-22.04
    tools:
-      python: "3.8"
+      python: "3.9"
 
 python:
    install:

test/data/test_multi_embedding_tensor.py

@@ -1,5 +1,5 @@
 import random
-from typing import List, Optional, Tuple, Union
+from typing import Optional, Union
 
 import pytest
 import torch
@@ -9,7 +9,7 @@
 
 
 def assert_equal(
-    tensor_list: List[torch.Tensor],
+    tensor_list: list[torch.Tensor],
     met: MultiEmbeddingTensor,
 ) -> None:
     assert len(tensor_list) == met.num_cols
@@ -22,9 +22,9 @@ def assert_equal(
 
 
 def row_select(
-    tensor_list: List[torch.Tensor],
-    index: Union[List[int], slice],
-) -> List[torch.Tensor]:
+    tensor_list: list[torch.Tensor],
+    index: Union[list[int], slice],
+) -> list[torch.Tensor]:
     """Selects rows from a list of column tensors.
 
     Args:
@@ -45,7 +45,7 @@ def get_fake_multi_embedding_tensor(
     num_cols: int,
     embedding_dim: Optional[int] = None,
     device: Optional[torch.device] = None,
-) -> Tuple[MultiEmbeddingTensor, List[torch.Tensor]]:
+) -> tuple[MultiEmbeddingTensor, list[torch.Tensor]]:
     tensor_list = []
     for _ in range(num_cols):
         embedding_dim = embedding_dim or random.randint(1, 5)

test/data/test_multi_nested_tensor.py

@@ -1,5 +1,5 @@
 import random
-from typing import List, Union
+from typing import Union
 
 import pytest
 import torch
@@ -9,7 +9,7 @@
 from torch_frame.testing import withCUDA
 
 
-def assert_equal(tensor_mat: List[List[Tensor]],
+def assert_equal(tensor_mat: list[list[Tensor]],
                  multi_nested_tensor: MultiNestedTensor):
     assert len(tensor_mat) == multi_nested_tensor.shape[0]
     assert len(tensor_mat[0]) == multi_nested_tensor.shape[1]
@@ -20,9 +20,9 @@ def assert_equal(tensor_mat: List[List[Tensor]],
 
 
 def column_select(
-    tensor_mat: List[List[Tensor]],
-    index: Union[List[int], slice],
-) -> List[List[Tensor]]:
+    tensor_mat: list[list[Tensor]],
+    index: Union[list[int], slice],
+) -> list[list[Tensor]]:
     new_tensor_mat = []
     for tensor_vec in tensor_mat:
         if isinstance(index, slice):

test/nn/test_simple_basecls.py

@@ -1,5 +1,3 @@
-from typing import List, Tuple
-
 import torch
 from torch import Tensor
 
@@ -15,7 +13,7 @@ def __init__(
             self,
             out_channels: int,
             num_numerical: int,
-            num_categories: List[int],
+            num_categories: list[int],
         ):
             super().__init__()
 
@@ -31,7 +29,7 @@ def __init__(
                 for num_category in num_categories
             ])
 
-        def forward(self, tf: TensorFrame) -> Tuple[Tensor, List[str]]:
+        def forward(self, tf: TensorFrame) -> tuple[Tensor, list[str]]:
             xs = []
             for i, lin in enumerate(self.lins):
                 xs.append(lin(tf.feat_dict[torch_frame.numerical][:, i:i + 1]))

torch_frame/data/mapper.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
-from typing import Any, Callable, Iterable, Mapping
+from collections.abc import Iterable, Mapping
+from typing import Any, Callable
 
 import numpy as np
 import pandas as pd

torch_frame/data/multi_embedding_tensor.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Sequence
+from collections.abc import Sequence
 
 import torch
 from torch import Tensor

torch_frame/data/multi_nested_tensor.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
-from typing import Sequence, cast
+from collections.abc import Sequence
+from typing import cast
 
 import torch
 from torch import Tensor

torch_frame/data/multi_tensor.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
 import copy
-from typing import Any, Callable, Sequence, TypeVar
+from collections.abc import Sequence
+from typing import Any, Callable, TypeVar
 
 import torch
 from torch import Tensor

torch_frame/nn/encoder/encoder.py

@@ -1,5 +1,4 @@
 from abc import ABC, abstractmethod
-from typing import List, Tuple
 
 from torch import Tensor
 from torch.nn import Module
@@ -16,7 +15,7 @@ class FeatureEncoder(Module, ABC):
     value handling.
     """
     @abstractmethod
-    def forward(self, tf: TensorFrame) -> Tuple[Tensor, List[str]]:
+    def forward(self, tf: TensorFrame) -> tuple[Tensor, list[str]]:
         r"""Encode :class:`TensorFrame` object into a tuple
         :obj:`(x, col_names)`.
 

torch_frame/typing.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
+from collections.abc import Mapping
 from enum import Enum
-from typing import Dict, List, Mapping, Union
+from typing import Union
 
 import pandas as pd
 import torch
@@ -109,14 +110,14 @@ def is_timestamp_strategy(self) -> bool:
 Series = pd.Series
 DataFrame = pd.DataFrame
 
-IndexSelectType = Union[int, List[int], range, slice, Tensor]
-ColumnSelectType = Union[str, List[str]]
+IndexSelectType = Union[int, list[int], range, slice, Tensor]
+ColumnSelectType = Union[str, list[str]]
 TextTokenizationMapping = Mapping[str, Tensor]
-TextTokenizationOutputs = Union[List[TextTokenizationMapping],
+TextTokenizationOutputs = Union[list[TextTokenizationMapping],
                                 TextTokenizationMapping]
 TensorData = Union[
     Tensor,
     MultiNestedTensor,
     MultiEmbeddingTensor,
-    Dict[str, MultiNestedTensor],
+    dict[str, MultiNestedTensor],
 ]