[pre-commit.ci] pre-commit suggestions

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ ci:
 
 repos:
     - repo: https://github.com/pre-commit/pre-commit-hooks
-      rev: v4.5.0
+      rev: v4.6.0
       hooks:
           - id: end-of-file-fixer
             exclude: "setup.cfg"
@@ -48,15 +48,15 @@ repos:
                     )
 
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.2.2
+      rev: v0.6.4
       hooks:
           - id: ruff
             args: ["--fix"]
           - id: ruff-format
           - id: ruff
 
     - repo: https://github.com/pre-commit/mirrors-prettier
-      rev: v4.0.0-alpha.8
+      rev: v3.1.0
       hooks:
           - id: prettier
             files: \.(json|yml|yaml|toml)

examples/PyTorch Tabular with Bank Marketing Dataset.ipynb

@@ -8,10 +8,9 @@
    "outputs": [],
    "source": [
     "import numpy as np\n",
-    "import pandas as pd\n",
     "from sklearn.datasets import fetch_openml\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.metrics import accuracy_score, log_loss"
+    "from sklearn.metrics import accuracy_score, log_loss\n",
+    "from sklearn.model_selection import train_test_split"
    ]
   },
   {
@@ -55,12 +54,23 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "cat_cols = ['job', 'marital', 'education', 'default', 'housing',\n",
-    "       'loan', 'contact', 'day', 'month', 'campaign',\n",
-    "       'previous', 'poutcome']\n",
+    "cat_cols = [\n",
+    "    \"job\",\n",
+    "    \"marital\",\n",
+    "    \"education\",\n",
+    "    \"default\",\n",
+    "    \"housing\",\n",
+    "    \"loan\",\n",
+    "    \"contact\",\n",
+    "    \"day\",\n",
+    "    \"month\",\n",
+    "    \"campaign\",\n",
+    "    \"previous\",\n",
+    "    \"poutcome\",\n",
+    "]\n",
     "\n",
-    "num_cols = ['age', 'balance', 'duration', 'pdays']\n",
-    "target=[\"y\"]"
+    "num_cols = [\"age\", \"balance\", \"duration\", \"pdays\"]\n",
+    "target = [\"y\"]"
    ]
   },
   {
@@ -96,8 +106,8 @@
     "test_enc = test.copy()\n",
     "for col in cat_cols:\n",
     "    enc = OrdinalEncoder(handle_unknown=\"use_encoded_value\", encoded_missing_value=np.nan, unknown_value=np.nan)\n",
-    "    train_enc[col] = enc.fit_transform(train_enc[col].values.reshape(-1,1))\n",
-    "    test_enc[col] = enc.transform(test_enc[col].values.reshape(-1,1))"
+    "    train_enc[col] = enc.fit_transform(train_enc[col].values.reshape(-1, 1))\n",
+    "    test_enc[col] = enc.transform(test_enc[col].values.reshape(-1, 1))"
    ]
   },
   {
@@ -153,15 +163,15 @@
    "outputs": [],
    "source": [
     "from pytorch_tabular import TabularModel\n",
+    "from pytorch_tabular.config import DataConfig, OptimizerConfig, TrainerConfig\n",
     "from pytorch_tabular.models import (\n",
-    "    CategoryEmbeddingModelConfig, \n",
-    "    FTTransformerConfig, \n",
-    "    TabNetModelConfig, \n",
-    "    GatedAdditiveTreeEnsembleConfig, \n",
-    "    TabTransformerConfig, \n",
-    "    AutoIntConfig\n",
+    "    AutoIntConfig,\n",
+    "    CategoryEmbeddingModelConfig,\n",
+    "    FTTransformerConfig,\n",
+    "    GatedAdditiveTreeEnsembleConfig,\n",
+    "    TabNetModelConfig,\n",
+    "    TabTransformerConfig,\n",
     ")\n",
-    "from pytorch_tabular.config import DataConfig, OptimizerConfig, TrainerConfig, ExperimentConfig\n",
     "from pytorch_tabular.models.common.heads import LinearHeadConfig"
    ]
   },
@@ -183,29 +193,29 @@
    "outputs": [],
    "source": [
     "data_config = DataConfig(\n",
-    "    target=target, #target should always be a list.\n",
+    "    target=target,  # target should always be a list.\n",
     "    continuous_cols=num_cols,\n",
     "    categorical_cols=cat_cols,\n",
     ")\n",
     "\n",
     "trainer_config = TrainerConfig(\n",
-    "#     auto_lr_find=True, # Runs the LRFinder to automatically derive a learning rate\n",
+    "    #     auto_lr_find=True, # Runs the LRFinder to automatically derive a learning rate\n",
     "    batch_size=256,\n",
     "    max_epochs=500,\n",
-    "    early_stopping=\"valid_loss\", # Monitor valid_loss for early stopping\n",
-    "    early_stopping_mode = \"min\", # Set the mode as min because for val_loss, lower is better\n",
-    "    early_stopping_patience=5, # No. of epochs of degradation training will wait before terminating\n",
-    "    checkpoints=\"valid_loss\", # Save best checkpoint monitoring val_loss\n",
-    "    load_best=True, # After training, load the best checkpoint\n",
+    "    early_stopping=\"valid_loss\",  # Monitor valid_loss for early stopping\n",
+    "    early_stopping_mode=\"min\",  # Set the mode as min because for val_loss, lower is better\n",
+    "    early_stopping_patience=5,  # No. of epochs of degradation training will wait before terminating\n",
+    "    checkpoints=\"valid_loss\",  # Save best checkpoint monitoring val_loss\n",
+    "    load_best=True,  # After training, load the best checkpoint\n",
     ")\n",
     "\n",
     "optimizer_config = OptimizerConfig()\n",
     "\n",
     "head_config = LinearHeadConfig(\n",
-    "    layers=\"\", # No additional layer in head, just a mapping layer to output_dim\n",
+    "    layers=\"\",  # No additional layer in head, just a mapping layer to output_dim\n",
     "    dropout=0.1,\n",
-    "    initialization=\"kaiming\"\n",
-    ").__dict__ # Convert to dict to pass to the model config (OmegaConf doesn't accept objects)"
+    "    initialization=\"kaiming\",\n",
+    ").__dict__  # Convert to dict to pass to the model config (OmegaConf doesn't accept objects)"
    ]
   },
   {
@@ -442,10 +452,10 @@
     "model_config = CategoryEmbeddingModelConfig(\n",
     "    task=\"classification\",\n",
     "    layers=\"64-32\",  # Number of nodes in each layer\n",
-    "    activation=\"ReLU\", # Activation between each layers\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    activation=\"ReLU\",  # Activation between each layers\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",
@@ -455,7 +465,7 @@
     "    trainer_config=trainer_config,\n",
     ")\n",
     "tabular_model.fit(train=train)\n",
-    "tabular_model.evaluate(test)\n"
+    "tabular_model.evaluate(test)"
    ]
   },
   {
@@ -709,9 +719,9 @@
    "source": [
     "model_config = GatedAdditiveTreeEnsembleConfig(\n",
     "    task=\"classification\",\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",
@@ -983,13 +993,13 @@
    "source": [
     "model_config = GatedAdditiveTreeEnsembleConfig(\n",
     "    task=\"classification\",\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     "    gflu_stages=4,\n",
     "    num_trees=30,\n",
     "    tree_depth=5,\n",
-    "    chain_trees=False\n",
+    "    chain_trees=False,\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",
@@ -1265,9 +1275,9 @@
    "source": [
     "model_config = FTTransformerConfig(\n",
     "    task=\"classification\",\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",
@@ -1543,9 +1553,9 @@
    "source": [
     "model_config = TabTransformerConfig(\n",
     "    task=\"classification\",\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",
@@ -1819,9 +1829,9 @@
    "source": [
     "model_config = AutoIntConfig(\n",
     "    task=\"classification\",\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",
@@ -2095,9 +2105,9 @@
    "source": [
     "model_config = TabNetModelConfig(\n",
     "    task=\"classification\",\n",
-    "    learning_rate = 1e-3,\n",
-    "    head = \"LinearHead\", #Linear Head\n",
-    "    head_config = head_config, # Linear Head Config\n",
+    "    learning_rate=1e-3,\n",
+    "    head=\"LinearHead\",  # Linear Head\n",
+    "    head_config=head_config,  # Linear Head Config\n",
     ")\n",
     "\n",
     "tabular_model = TabularModel(\n",

examples/__only_for_dev__/to_test_classification.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 
 import pandas as pd
+from sklearn.model_selection import train_test_split
 
 # from torch.utils import data
 from pytorch_tabular.config import DataConfig, ExperimentConfig, OptimizerConfig, TrainerConfig
@@ -9,7 +10,6 @@
 
 # import wget
 from pytorch_tabular.utils import get_class_weighted_cross_entropy
-from sklearn.model_selection import train_test_split
 
 # torch.manual_seed(0)
 # np.random.seed(0)

examples/__only_for_dev__/to_test_node.py

@@ -3,10 +3,11 @@
 
 import numpy as np
 import pandas as pd
+from sklearn.datasets import fetch_california_housing, fetch_covtype
+
 from pytorch_tabular.config import DataConfig, OptimizerConfig, TrainerConfig
 from pytorch_tabular.models.node import NodeConfig
 from pytorch_tabular.tabular_model import TabularModel
-from sklearn.datasets import fetch_california_housing, fetch_covtype
 
 
 def regression_data():

examples/__only_for_dev__/to_test_regression.py

@@ -1,9 +1,10 @@
 import pandas as pd
 import torch
+from sklearn.datasets import fetch_california_housing
+
 from pytorch_tabular.config import DataConfig, OptimizerConfig, TrainerConfig
 from pytorch_tabular.models.category_embedding.config import CategoryEmbeddingModelConfig
 from pytorch_tabular.tabular_model import TabularModel
-from sklearn.datasets import fetch_california_housing
 
 # from pytorch_tabular.models.mixture_density import (
 # CategoryEmbeddingMDNConfig,

examples/__only_for_dev__/to_test_regression_custom_models.py

@@ -5,6 +5,8 @@
 import torch
 import torch.nn as nn
 from omegaconf import DictConfig
+from sklearn.datasets import fetch_california_housing
+
 from pytorch_tabular.config import DataConfig, ModelConfig, OptimizerConfig, TrainerConfig
 
 # from pytorch_tabular.models.deep_gmm import (
@@ -14,7 +16,6 @@
 
 # from pytorch_tabular.models.node import utils as utils
 from pytorch_tabular.tabular_model import TabularModel
-from sklearn.datasets import fetch_california_housing
 
 
 @dataclass

examples/covertype_classification.py

@@ -2,11 +2,12 @@
 
 import pandas as pd
 import wget
+from sklearn.model_selection import train_test_split
+
 from pytorch_tabular.config import DataConfig, OptimizerConfig, TrainerConfig
 from pytorch_tabular.models import CategoryEmbeddingModelConfig
 from pytorch_tabular.models.common.heads import LinearHeadConfig
 from pytorch_tabular.tabular_model import TabularModel
-from sklearn.model_selection import train_test_split
 
 BASE_DIR = Path.home().joinpath("data")
 datafile = BASE_DIR.joinpath("covtype.data.gz")

examples/covertype_classification_using_yaml.py

@@ -2,9 +2,10 @@
 
 import pandas as pd
 import wget
-from pytorch_tabular.tabular_model import TabularModel
 from sklearn.model_selection import train_test_split
 
+from pytorch_tabular.tabular_model import TabularModel
+
 BASE_DIR = Path.home().joinpath("data")
 datafile = BASE_DIR.joinpath("covtype.data.gz")
 datafile.parent.mkdir(parents=True, exist_ok=True)

setup.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 
 """The setup script."""
+
 import os
 
 from setuptools import find_packages, setup

src/pytorch_tabular/categorical_encoders.py

@@ -3,6 +3,7 @@
 # For license information, see LICENSE.TXT
 # Modified https://github.com/tcassou/mlencoders/blob/master/mlencoders/base_encoder.py to suit NN encoding
 """Category Encoders."""
+
 from pandas import DataFrame, Series, unique
 
 try:

src/pytorch_tabular/config/config.py

@@ -2,6 +2,7 @@
 # Author: Manu Joseph <manujoseph@gmail.com>
 # For license information, see LICENSE.TXT
 """Config."""
+
 import os
 import re
 from dataclasses import MISSING, dataclass, field

src/pytorch_tabular/models/autoint/autoint.py

@@ -3,6 +3,7 @@
 # For license information, see LICENSE.TXT
 # Inspired by https://github.com/rixwew/pytorch-fm/blob/master/torchfm/model/afi.py
 """AutomaticFeatureInteraction Model."""
+
 import torch
 import torch.nn as nn
 from omegaconf import DictConfig

src/pytorch_tabular/models/autoint/config.py

@@ -2,6 +2,7 @@
 # Author: Manu Joseph <manujoseph@gmail.com>
 # For license information, see LICENSE.TXT
 """AutomaticFeatureInteraction Config."""
+
 from dataclasses import dataclass, field
 from typing import Optional
 

src/pytorch_tabular/models/base_model.py

@@ -2,6 +2,7 @@
 # Author: Manu Joseph <manujoseph@gmail.com>
 # For license information, see LICENSE.TXT
 """Base Model."""
+
 import importlib
 import warnings
 from abc import ABCMeta, abstractmethod

src/pytorch_tabular/models/category_embedding/category_embedding_model.py

@@ -2,6 +2,7 @@
 # Author: Manu Joseph <manujoseph@gmail.com>
 # For license information, see LICENSE.TXT
 """Category Embedding Model."""
+
 import torch
 import torch.nn as nn
 from omegaconf import DictConfig

src/pytorch_tabular/models/category_embedding/config.py

@@ -2,6 +2,7 @@
 # Author: Manu Joseph <manujoseph@gmail.com>
 # For license information, see LICENSE.TXT
 """Category Embedding Model Config."""
+
 from dataclasses import dataclass, field
 
 from pytorch_tabular.config import ModelConfig