from aitraining import TextClassification

trainer = TextClassification(
    model="bert-base-uncased",
    learning_rate=2e-5
)

trainer.train(data)
predictions = trainer.predict(texts)

import pandas as pd
from aitraining import AutoTrainer

# 自定义预处理
data = pd.read_csv("raw_data.csv")
data = clean_and_prepare(data)

# 动态配置
config = {
    "model": get_best_model(data),
    "batch_size": calculate_batch_size(),
    "epochs": 5 if len(data) > 1000 else 10
}

# 使用回调训练
trainer = AutoTrainer(**config)
trainer.train(
    data,
    callbacks=[
        early_stopping,
        checkpoint_best,
        log_to_wandb
    ]
)

# 集成到应用程序
@app.route("/predict")
def predict():
    result = trainer.predict(request.json)
    return jsonify(result)

from flask import Flask
from aitraining import load_model

app = Flask(__name__)
model = load_model("./trained_model")

@app.route("/api/classify", methods=["POST"])
def classify():
    text = request.json["text"]
    result = model.predict(text)
    return {"label": result}

def training_pipeline(df):
    # 自定义清理
    df = remove_outliers(df)
    df = normalize_features(df)

    # 条件训练
    if df.shape[0] > 10000:
        model = "large-model"
    else:
        model = "small-model"

    # 训练
    trainer = AutoTrainer(model=model)
    trainer.train(df)

    return trainer

models = {}

# 训练变体
for config in experiments:
    trainer = create_trainer(config)
    trainer.train(data)
    models[config.name] = trainer

# 比较
results = evaluate_all(models, test_data)
best = select_best(results)

class CustomCallback:
    def on_epoch_end(self, epoch, logs):
        if logs["loss"] < self.threshold:
            send_notification("Training going well!")

        if should_adjust_lr(logs):
            self.trainer.learning_rate *= 0.5

trainer.train(data, callbacks=[CustomCallback()])

# 资源的上下文管理器
with AITraining() as trainer:
    trainer.train(data)
    # 自动清理

# 异步训练
async def train_async():
    await trainer.train_async(data)

# 流式预测
for prediction in trainer.predict_stream(texts):
    process(prediction)

# 模型组合
ensemble = Ensemble([
    model1,
    model2,
    model3
])

# 与 pandas
df = pd.read_csv("data.csv")
trainer.train(df)

# 与 scikit-learn
from sklearn.model_selection import train_test_split
X_train, X_test = train_test_split(data)

# 与 weights & biases
import wandb
wandb.init(project="my-training")
trainer.train(data, callbacks=[WandbCallback()])

# 与 FastAPI
@app.post("/train")
async def train_endpoint(data: TrainingData):
    result = await trainer.train_async(data)
    return {"model_id": result.id}