Data Generation

pip install "tabpfn-extensions[unsupervised]"

from tabpfn_extensions import unsupervised
from tabpfn_extensions.unsupervised import experiments
from sklearn.datasets import load_breast_cancer
import torch
from tabpfn_extensions import TabPFNClassifier, TabPFNRegressor

# Load and prepare breast cancer dataset
df = load_breast_cancer(return_X_y=False)
X, y = df["data"], df["target"]
feature_names = df["feature_names"]

# Initialize TabPFN models
model_unsupervised = unsupervised.TabPFNUnsupervisedModel(
    tabpfn_clf=TabPFNClassifier(), 
    tabpfn_reg=TabPFNRegressor()
)

# Select features for synthetic data generation
# Example features: [mean texture, mean area, mean concavity]
feature_indices = [4, 6, 12]

# Run synthetic data generation experiment
experiment = unsupervised.experiments.GenerateSyntheticDataExperiment(
    task_type="unsupervised"
)

results = experiment.run(
    tabpfn=model_unsupervised,
    X=torch.tensor(X),
    y=torch.tensor(y),
    attribute_names=feature_names,
    temp=1.0,                     # Temperature parameter for sampling
    n_samples=X.shape[0] * 2,     # Generate twice as many samples as original data
    indices=feature_indices,
)

import torch
from sklearn.datasets import load_wine
from tabpfn_extensions import TabPFNClassifier, TabPFNRegressor, unsupervised

df = load_wine(return_X_y=False)
X, y = df["data"], df["target"]
attribute_names = df["feature_names"]

# Build a DAG expressed as feature names, then convert to integer indices
wine_dag_by_name = {
    "alcohol": [],
    "malic_acid": [],
    "ash": ["magnesium"],
    "alcalinity_of_ash": ["ash", "magnesium"],
    "magnesium": [],
    "total_phenols": ["flavanoids", "nonflavanoid_phenols", "proanthocyanins"],
    "flavanoids": [],
    "nonflavanoid_phenols": [],
    "proanthocyanins": [],
    "color_intensity": ["flavanoids", "proanthocyanins", "total_phenols"],
    "hue": ["color_intensity"],
    "od280/od315_of_diluted_wines": ["flavanoids", "total_phenols"],
    "proline": ["alcohol", "total_phenols"],
}

name_to_idx = {n: i for i, n in enumerate(attribute_names)}
dag = {
    name_to_idx[child]: [name_to_idx[p] for p in parents]
    for child, parents in wine_dag_by_name.items()
}

model_unsupervised = unsupervised.TabPFNUnsupervisedModel(
    tabpfn_clf=TabPFNClassifier(n_estimators=3),
    tabpfn_reg=TabPFNRegressor(n_estimators=3),
)

experiment = unsupervised.experiments.GenerateSyntheticDataExperiment(task_type="unsupervised")
results = experiment.run(
    tabpfn=model_unsupervised,
    X=torch.tensor(X, dtype=torch.float32),
    y=torch.tensor(y, dtype=torch.float32),
    attribute_names=attribute_names,
    temp=1.0,
    n_samples=X.shape[0] * 3,
    indices=list(range(X.shape[1])),
    dag=dag,
)