代码：内置了A股、港股、美股数据的股票量化框架

大模型挖掘因子还在继续开发：

zvt框架的使用：

直接pip安装zvt框架是无法成功的，我尝试了python3.7和python 3.8均是如此。当然这是开源项目的问题，也是咱们星球的核心价值——我把requirements整理了一下。

希望没有代码的，给出代码复现。有代码的，要能够运行起来；另外还需要有数据生态。

dash是plotly出的，金融绘图确实显得更高级一点，与streamlit类似，比streamlit门槛高一些：

这个示例是机器学习预测股票的走势并可视化：

from zvt.domain import Stock, Stock1dHfqKdata
from zvt.ml import MaStockMLMachine
Stock.record_data(provider="em")
entity_ids = ["stock_sz_000001", "stock_sz_000338", "stock_sh_601318"]
Stock1dHfqKdata.record_data(provider="em", entity_ids=entity_ids, sleeping_time=1)
machine = MaStockMLMachine(entity_ids=["stock_sz_000001"], data_provider="em")
machine.train()
machine.predict()
machine.draw_result(entity_id="stock_sz_000001")

zvt这个框架的特别之处在于，内置了很多数据源，有公开的，有jq这样付费的，可以一键使用，而且api看起来非常简洁，值得分析一下。

代码启动后，在用户的目录下，多了很多个sqlite数据库文件：

确实做了大量的数据存储，查询的工作：

这是从东方财富免费接口下载股票30分钟后复权的数据：

龙虎榜的策略代码：

# -*- coding: utf-8 -*-
from typing import List, Union

import pandas as pd

from zvt.contract import IntervalLevel
from zvt.contract.factor import Factor, Transformer, Accumulator
from zvt.domain import Stock, DragonAndTiger
from zvt.trader import StockTrader


class DragonTigerFactor(Factor):
    def __init__(
        self,
        provider: str = "em",
        entity_provider: str = "em",
        entity_ids: List[str] = None,
        exchanges: List[str] = None,
        codes: List[str] = None,
        start_timestamp: Union[str, pd.Timestamp] = None,
        end_timestamp: Union[str, pd.Timestamp] = None,
        columns: List = None,
        filters: List = [DragonAndTiger.dep1 == "机构专用"],
        order: object = None,
        limit: int = None,
        level: Union[str, IntervalLevel] = IntervalLevel.LEVEL_1DAY,
        category_field: str = "entity_id",
        time_field: str = "timestamp",
        keep_window: int = None,
        keep_all_timestamp: bool = False,
        fill_method: str = "ffill",
        effective_number: int = None,
        transformer: Transformer = None,
        accumulator: Accumulator = None,
        need_persist: bool = False,
        only_compute_factor: bool = False,
        factor_name: str = None,
        clear_state: bool = False,
        only_load_factor: bool = False,
    ) -> None:
        super().__init__(
            DragonAndTiger,
            Stock,
            provider,
            entity_provider,
            entity_ids,
            exchanges,
            codes,
            start_timestamp,
            end_timestamp,
            columns,
            filters,
            order,
            limit,
            level,
            category_field,
            time_field,
            keep_window,
            keep_all_timestamp,
            fill_method,
            effective_number,
            transformer,
            accumulator,
            need_persist,
            only_compute_factor,
            factor_name,
            clear_state,
            only_load_factor,
)

    def compute_result(self):
        self.factor_df["filter_result"] = True
        super().compute_result()


class MyTrader(StockTrader):
    def init_factors(
        self, entity_ids, entity_schema, exchanges, codes, start_timestamp, end_timestamp, adjust_type=None
    ):
        return [
            DragonTigerFactor(
                entity_ids=entity_ids,
                exchanges=exchanges,
                codes=codes,
                start_timestamp=start_timestamp,
                end_timestamp=end_timestamp,
            )
        ]


if __name__ == "__main__":
    trader = MyTrader(start_timestamp="2020-01-01", end_timestamp="2022-05-01")
    trader.run()