TabPFN: 表格数据基础模型 — 结构化数据的 AI 突破

pip install tabpfn

from tabpfn import TabPFNClassifier
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

# 加载数据
X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)

# 初始化并拟合（无需超参数！）
clf = TabPFNClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)
y_prob = clf.predict_proba(X_test)

# 评估
accuracy = (y_pred == y_test).mean()
print(f"准确率: {accuracy:.4f}")

# 自动处理缺失值
clf = TabPFNClassifier()
clf.fit(X_train_with_nans, y_train)

# 处理分类特征
from tabpfn import TabPFNClassifier
import pandas as pd

# TabPFN 处理混合数据类型
df = pd.read_csv('your_data.csv')
X = df.drop('target', axis=1)
y = df['target']

clf = TabPFNClassifier()
clf.fit(X, y)  # 自动检测特征类型

输入特征 → 嵌入层 → Transformer 块 → 输出