From fe06e6f2a4ba567941fde688360e26583736c78d Mon Sep 17 00:00:00 2001
From: kljk345 <lewis.mervin1@astrazeneca.com>
Date: Wed, 17 Jul 2024 09:37:49 +0100
Subject: [PATCH] Depreciate typing-extensions. Inference fix for side info
 smiles and predict.py

---
 optunaz/config/buildconfig.py               |  3 +--
 optunaz/config/optconfig.py                 |  3 +--
 optunaz/descriptors.py                      |  3 +--
 optunaz/predict.py                          | 30 ++++++++++-----------
 optunaz/utils/preprocessing/deduplicator.py |  3 +--
 optunaz/utils/preprocessing/splitter.py     |  3 +--
 pyproject.toml                              |  1 -
 7 files changed, 20 insertions(+), 26 deletions(-)

diff --git a/optunaz/config/buildconfig.py b/optunaz/config/buildconfig.py
index 411578b..25a1a19 100644
--- a/optunaz/config/buildconfig.py
+++ b/optunaz/config/buildconfig.py
@@ -1,6 +1,6 @@
 import abc
 from dataclasses import dataclass, field
-from typing import Optional, Union
+from typing import Optional, Union, Literal
 
 import sklearn
 import sklearn.cross_decomposition
@@ -11,7 +11,6 @@
 import xgboost
 from apischema import schema
 from sklearn.base import BaseEstimator
-from typing_extensions import Literal
 
 import optunaz
 from optunaz import algorithms
diff --git a/optunaz/config/optconfig.py b/optunaz/config/optconfig.py
index 2ebd157..f8b70fd 100644
--- a/optunaz/config/optconfig.py
+++ b/optunaz/config/optconfig.py
@@ -1,11 +1,10 @@
 import logging
 from dataclasses import dataclass, field
 from enum import Enum
-from typing import Union, Optional, List, Iterable, Type, Any
+from typing import Union, Optional, List, Iterable, Type, Any, Literal, Annotated
 
 from apischema import schema, type_name, serialize
 from apischema.metadata import none_as_undefined, required
-from typing_extensions import Literal, Annotated
 
 from optunaz.config import (
     ModelMode,
diff --git a/optunaz/descriptors.py b/optunaz/descriptors.py
index e82d3b6..57cbdb0 100644
--- a/optunaz/descriptors.py
+++ b/optunaz/descriptors.py
@@ -4,7 +4,7 @@
 import os
 import pathlib
 from dataclasses import dataclass, field
-from typing import List, Union, Type, Optional, Any, Tuple, Dict
+from typing import List, Union, Type, Optional, Any, Tuple, Dict, Literal, Annotated
 from functools import partial
 
 import apischema
@@ -34,7 +34,6 @@
 from jazzy.api import molecular_vector_from_smiles
 from jazzy.exception import JazzyError
 from sklearn import preprocessing
-from typing_extensions import Literal, Annotated
 from joblib import Parallel, delayed, effective_n_jobs
 from optunaz.config import NameParameterDataclass
 from optunaz.utils import load_df_from_file
diff --git a/optunaz/predict.py b/optunaz/predict.py
index 8d05a49..6236016 100644
--- a/optunaz/predict.py
+++ b/optunaz/predict.py
@@ -45,6 +45,21 @@ def validate_uncertainty(args, model):
             raise UncertaintyError("Uncertainty not availble for this model")
 
 
+def check_precomp_args(args):
+    try:
+        assert (
+            args.input_precomputed_file is not None
+        ), "Must supply precomputed descriptor parameters"
+        assert (
+            args.input_precomputed_input_column
+        ), "Must supply input column for precomputed descriptor"
+        assert (
+            args.input_precomputed_response_column
+        ), "Must supply response column for precomputed descriptor"
+    except AssertionError as e:
+        raise PrecomputedError(e)
+
+
 def set_inference_params(args, desc):
     if hasattr(desc.parameters, "descriptor") and hasattr(
         desc.parameters.descriptor, "inference_parameters"
@@ -62,21 +77,6 @@ def set_inference_params(args, desc):
     return False
 
 
-def check_precomp_args(args):
-    try:
-        assert (
-            args.input_precomputed_file is not None
-        ), "Must supply precomputed descriptor parameters"
-        assert (
-            args.input_precomputed_input_column
-        ), "Must supply input column for precomputed descriptor"
-        assert (
-            args.input_precomputed_response_column
-        ), "Must supply response column for precomputed descriptor"
-    except AssertionError as e:
-        raise PrecomputedError(e)
-
-
 def validate_set_precomputed(args, model):
     descriptor_str = model.descriptor.name
     if set_inference_params(args, model.descriptor):
diff --git a/optunaz/utils/preprocessing/deduplicator.py b/optunaz/utils/preprocessing/deduplicator.py
index 724ea68..a745e74 100644
--- a/optunaz/utils/preprocessing/deduplicator.py
+++ b/optunaz/utils/preprocessing/deduplicator.py
@@ -1,12 +1,11 @@
 import abc
 from dataclasses import dataclass, field
-from typing import Optional, Union, Any
+from typing import Optional, Union, Any, Literal
 
 import pandas as pd
 from apischema import deserializer, serializer, schema, identity
 from apischema.conversions import Conversion
 from apischema.metadata import none_as_undefined
-from typing_extensions import Literal  # Python 3.7
 
 
 class Deduplicator:
diff --git a/optunaz/utils/preprocessing/splitter.py b/optunaz/utils/preprocessing/splitter.py
index 3e71b9d..b208bba 100644
--- a/optunaz/utils/preprocessing/splitter.py
+++ b/optunaz/utils/preprocessing/splitter.py
@@ -1,6 +1,6 @@
 import abc
 from dataclasses import dataclass, field
-from typing import Optional, Iterator, Tuple, Union, Dict
+from typing import Optional, Iterator, Tuple, Union, Dict, Literal, Annotated
 
 import numpy as np
 import sklearn
@@ -13,7 +13,6 @@
     PredefinedSplit,
     StratifiedGroupKFold,
 )
-from typing_extensions import Literal, Annotated  # Python 3.7
 
 
 class SklearnSplitter(abc.ABC):
diff --git a/pyproject.toml b/pyproject.toml
index 14e2f22..ce4fdc3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,7 +19,6 @@ jsonpickle = "^2.0"
 xgboost = "^1.3"
 rdkit = ">=2023.3.1"
 scikit-learn = "1.4.0"
-typing-extensions = ">=3.10, <5.0"
 apischema = "^0.17"
 chemprop = "1.6.1"
 descriptastorus = "^2.4"  # Chemprop dependency, but chemprop does not install it itself.