adam2392

"""Benchmark categorical split performance on the Amazon Employee dataset.

Usage:
    # Native categorical handling:
    python bench_categorical_tree.py --mode categorical --label cat --output results_cat.csv

    # Ordinal (treat integers as numeric):
    python bench_categorical_tree.py --mode ordinal --label ord --output results_ord.csv

    # One-hot encoding:

adam2392

import numpy as np
import torch
import torch.nn as nn


class ResidualBlock(nn.Module):
    def __init__(self, latent_dim, inner_dim):
        super(ResidualBlock, self).__init__()
        self.fc1 = nn.Linear(latent_dim, inner_dim)
        self.fc2 = nn.Linear(inner_dim, inner_dim)

adam2392

"""Instructions
1. Build this PR and run:

```bash
python bench_missing_extratrees.py bench ~/bench_results pr_no_pythoncheck
```

2. On main run:

```bash

adam2392

"""Instructions
1. Build this PR and run:

```bash
python bench_missing_extraforest.py bench ~/bench_results_forest pr
```

2. On main run:

```bash

adam2392

"""Instructions
1. Build this PR and run:

```bash
python bench_randomforest.py bench ~/bench_results_forest pr
```

2. On main run:

```bash

adam2392

from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification

n_samples = 10_000
n_features = 200
n_estimators = 200

# Generate synthetic classification dataset
X, y = make_classification(n_samples=n_samples, n_features=n_features, n_classes=2, random_state=42)

adam2392

"""Instructions
1. Build this PR and run:

```bash
python bench_missing_extraforest.py bench ~/bench_results_forest pr
```

2. On main run:

```bash

adam2392

"""Instructions
1. Build this PR and run:

```bash
python bench_missing_extratrees.py bench ~/bench_results pr_no_pythoncheck
```

2. On main run:

```bash

adam2392

adam2392