From 6f150f3fd6f9d48a219e6e9045b285e7fb84c436 Mon Sep 17 00:00:00 2001 From: zhupr Date: Fri, 4 Jun 2021 22:28:42 +0800 Subject: [PATCH 01/14] Add YahooCollector support for extend data --- scripts/data_collector/base.py | 14 +- scripts/data_collector/cn_index/collector.py | 5 +- scripts/data_collector/yahoo/collector.py | 210 ++++++++++++++++++- 3 files changed, 211 insertions(+), 18 deletions(-) diff --git a/scripts/data_collector/base.py b/scripts/data_collector/base.py index 12983f6a5..cb51f9b22 100644 --- a/scripts/data_collector/base.py +++ b/scripts/data_collector/base.py @@ -226,11 +226,7 @@ class BaseCollector(abc.ABC): class BaseNormalize(abc.ABC): - def __init__( - self, - date_field_name: str = "date", - symbol_field_name: str = "symbol", - ): + def __init__(self, date_field_name: str = "date", symbol_field_name: str = "symbol", **kwargs): """ Parameters @@ -265,6 +261,7 @@ class Normalize: max_workers: int = 16, date_field_name: str = "date", symbol_field_name: str = "symbol", + **kwargs, ): """ @@ -291,7 +288,9 @@ class Normalize: self._max_workers = max_workers - self._normalize_obj = normalize_class(date_field_name=date_field_name, symbol_field_name=symbol_field_name) + self._normalize_obj = normalize_class( + date_field_name=date_field_name, symbol_field_name=symbol_field_name, **kwargs + ) def _executor(self, file_path: Path): file_path = Path(file_path) @@ -404,7 +403,7 @@ class BaseRun(abc.ABC): limit_nums=limit_nums, ).collector_data() - def normalize_data(self, date_field_name: str = "date", symbol_field_name: str = "symbol"): + def normalize_data(self, date_field_name: str = "date", symbol_field_name: str = "symbol", **kwargs): """normalize data Parameters @@ -426,5 +425,6 @@ class BaseRun(abc.ABC): max_workers=self.max_workers, date_field_name=date_field_name, symbol_field_name=symbol_field_name, + **kwargs, ) yc.normalize() diff --git a/scripts/data_collector/cn_index/collector.py b/scripts/data_collector/cn_index/collector.py index 5af9785ec..1f8434c58 100644 --- a/scripts/data_collector/cn_index/collector.py +++ b/scripts/data_collector/cn_index/collector.py @@ -24,7 +24,10 @@ from data_collector.utils import get_calendar_list, get_trading_date_by_shift NEW_COMPANIES_URL = "http://www.csindex.com.cn/uploads/file/autofile/cons/{index_code}cons.xls" -INDEX_CHANGES_URL = "http://www.csindex.com.cn/zh-CN/search/total?key=%E5%85%B3%E4%BA%8E%E8%B0%83%E6%95%B4%E6%B2%AA%E6%B7%B1300%E5%92%8C%E4%B8%AD%E8%AF%81%E9%A6%99%E6%B8%AF100%E7%AD%89%E6%8C%87%E6%95%B0%E6%A0%B7%E6%9C%AC%E8%82%A1%E7%9A%84%E5%85%AC%E5%91%8A" + +# INDEX_CHANGES_URL = "http://www.csindex.com.cn/zh-CN/search/total?key=%E5%85%B3%E4%BA%8E%E8%B0%83%E6%95%B4%E6%B2%AA%E6%B7%B1300%E5%92%8C%E4%B8%AD%E8%AF%81%E9%A6%99%E6%B8%AF100%E7%AD%89%E6%8C%87%E6%95%B0%E6%A0%B7%E6%9C%AC%E8%82%A1%E7%9A%84%E5%85%AC%E5%91%8A" +# 2020-11-27 Announcement title change +INDEX_CHANGES_URL = "http://www.csindex.com.cn/zh-CN/search/total?key=%E5%85%B3%E4%BA%8E%E8%B0%83%E6%95%B4%E6%B2%AA%E6%B7%B1300%E5%92%8C%E4%B8%AD%E8%AF%81%E9%A6%99%E6%B8%AF100%E7%AD%89" class CSIIndex(IndexBase): diff --git a/scripts/data_collector/yahoo/collector.py b/scripts/data_collector/yahoo/collector.py index 2cd080199..fcaa9ff92 100644 --- a/scripts/data_collector/yahoo/collector.py +++ b/scripts/data_collector/yahoo/collector.py @@ -23,7 +23,7 @@ from qlib.config import REG_CN as REGION_CN CUR_DIR = Path(__file__).resolve().parent sys.path.append(str(CUR_DIR.parent.parent)) -from data_collector.base import BaseCollector, BaseNormalize, BaseRun +from data_collector.base import BaseCollector, BaseNormalize, BaseRun, Normalize from data_collector.utils import ( get_calendar_list, get_hs_stock_symbols, @@ -297,6 +297,7 @@ class YahooNormalize(BaseNormalize): calendar_list: list = None, date_field_name: str = "date", symbol_field_name: str = "symbol", + last_close: float = None, ): if df.empty: return df @@ -318,7 +319,10 @@ class YahooNormalize(BaseNormalize): df.sort_index(inplace=True) df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]), set(df.columns) - {symbol_field_name}] = np.nan _tmp_series = df["close"].fillna(method="ffill") - df["change"] = _tmp_series / _tmp_series.shift(1) - 1 + _tmp_shift_series = _tmp_series.shift(1) + if last_close is not None and isinstance(last_close, (int, float)): + _tmp_shift_series.iloc[0] = last_close + df["change"] = _tmp_series / _tmp_shift_series - 1 columns += ["change"] df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]), columns] = np.nan @@ -367,6 +371,17 @@ class YahooNormalize1d(YahooNormalize, ABC): df = self._manual_adj_data(df) return df + def _get_first_close(self, df: pd.DataFrame) -> float: + """get first close value + + Notes + ----- + For incremental updates(append) to Yahoo 1D data, user need to use a close that is not 0 on the first trading day of the existing data + """ + df = df.loc[df["close"].first_valid_index() :] + _close = df["close"].iloc[0] + return _close + def _manual_adj_data(self, df: pd.DataFrame) -> pd.DataFrame: """manual adjust data: All fields (except change) are standardized according to the close of the first day""" if df.empty: @@ -374,8 +389,7 @@ class YahooNormalize1d(YahooNormalize, ABC): df = df.copy() df.sort_values(self._date_field_name, inplace=True) df = df.set_index(self._date_field_name) - df = df.loc[df["close"].first_valid_index() :] - _close = df["close"].iloc[0] + _close = self._get_first_close(df) for _col in df.columns: if _col == self._symbol_field_name: continue @@ -388,18 +402,97 @@ class YahooNormalize1d(YahooNormalize, ABC): return df.reset_index() +class YahooNormalize1dExtend(YahooNormalize1d): + def __init__( + self, old_qlib_data_dir: [str, Path], date_field_name: str = "date", symbol_field_name: str = "symbol", **kwargs + ): + """ + + Parameters + ---------- + old_qlib_data_dir: str, Path + the qlib data to be updated for yahoo, usually from: https://github.com/microsoft/qlib/tree/main/scripts#download-cn-data + date_field_name: str + date field name, default is date + symbol_field_name: str + symbol field name, default is symbol + """ + super(YahooNormalize1dExtend, self).__init__(date_field_name, symbol_field_name) + self._end_date, self._old_close = self._get_old_data(old_qlib_data_dir) + self._end_date = pd.Timestamp(self._end_date).strftime(self.DAILY_FORMAT) + + def _get_old_data(self, qlib_data_dir: [str, Path]): + import qlib + from qlib.data import D + + qlib_data_dir = str(Path(qlib_data_dir).expanduser().resolve()) + qlib.init(provider_uri=qlib_data_dir, expression_cache=None, dataset_cache=None) + df = D.features(D.instruments("all"), ["$close/$factor"]) + df.columns = ["close"] + return D.calendar()[-1], df + + def _get_first_close(self, df: pd.DataFrame) -> float: + _symbol = df.iloc[0][self._symbol_field_name] + try: + _df = self._old_close.loc(axis=0)[_symbol.upper()] + _close = _df.loc[_df.first_valid_index()]["close"] + except KeyError: + _close = super(YahooNormalize1dExtend, self)._get_first_close(df) + return _close + + def _get_last_close(self, df: pd.DataFrame) -> float: + _symbol = df.iloc[0][self._symbol_field_name] + try: + _df = self._old_close.loc(axis=0)[_symbol.upper()] + _close = _df.loc[_df.last_valid_index()]["close"] + except KeyError: + _close = None + return _close + + def _get_last_date(self, df: pd.DataFrame) -> pd.Timestamp: + _symbol = df.iloc[0][self._symbol_field_name] + try: + _df = self._old_close.loc(axis=0)[_symbol.upper()] + _date = _df.index.max() + except KeyError: + _date = None + return _date + + def normalize(self, df: pd.DataFrame) -> pd.DataFrame: + _last_close = self._get_last_close(df) + # reindex + _last_date = self._get_last_date(df) + if _last_date is not None: + df = df.set_index(self._date_field_name) + df.index = pd.to_datetime(df.index) + df = df[~df.index.duplicated(keep="first")] + _max_date = df.index.max() + df = df.reindex(self._calendar_list).loc[:_max_date].reset_index() + df = df[df[self._date_field_name] > _last_date] + _si = df["close"].first_valid_index() + if _si > df.index[0]: + logger.warning( + f"{df.iloc[0][self._symbol_field_name]} missing data: {df.loc[:_si][self._date_field_name]}" + ) + # normalize + df = self.normalize_yahoo( + df, self._calendar_list, self._date_field_name, self._symbol_field_name, last_close=_last_close + ) + # adjusted price + df = self.adjusted_price(df) + df = self._manual_adj_data(df) + return df + + class YahooNormalize1min(YahooNormalize, ABC): AM_RANGE = None # type: tuple # eg: ("09:30:00", "11:29:00") PM_RANGE = None # type: tuple # eg: ("13:00:00", "14:59:00") # Whether the trading day of 1min data is consistent with 1d CONSISTENT_1d = False + CALC_PAUSED_NUM = False - def __init__( - self, - date_field_name: str = "date", - symbol_field_name: str = "symbol", - ): + def __init__(self, date_field_name: str = "date", symbol_field_name: str = "symbol", **kwargs): """ Parameters @@ -478,6 +571,54 @@ class YahooNormalize1min(YahooNormalize, ABC): df[_col] = df[_col] / df["factor"] else: df[_col] = df[_col] * df["factor"] + + if self.CALC_PAUSED_NUM: + df = self.calc_paused_num(df) + return df + + def calc_paused_num(self, df: pd.DataFrame): + _symbol = df.iloc[0][self._symbol_field_name] + df = df.copy() + df["date"] = df[self._date_field_name].apply(lambda x: pd.Timestamp(x).date()) + # remove data that starts and ends with `np.nan` all day + all_data = [] + # Record the number of consecutive trading days where the whole day is nan, to remove the last trading day where the whole day is nan + all_nan_nums = 0 + # Record the number of consecutive occurrences of trading days that are not nan throughout the day + not_nan_nums = 0 + for _date, _df in df.groupby(level="date"): + _df["paused"] = 0 + if not _df.loc[_df["volume"] < 0].empty: + logger.warning(f"volume < 0, will fill np.nan: {_date} {_symbol}") + _df.loc[_df["volume"] < 0, "volume"] = np.nan + + check_fields = set(_df.columns) - { + "date", + "paused", + "factor", + self._date_field_name, + self._symbol_field_name, + } + if _df.loc[:, check_fields].isna().values.all() or (_df["volume"] == 0).all(): + all_nan_nums += 1 + not_nan_nums = 0 + _df["paused"] = 1 + if all_data: + _df["paused_num"] = not_nan_nums + all_data.append(_df) + else: + all_nan_nums = 0 + not_nan_nums += 1 + _df["paused_num"] = not_nan_nums + all_data.append(_df) + all_data = all_data[: len(all_data) - all_nan_nums] + if all_data: + df = pd.concat(all_data, sort=False) + else: + logger.warning(f"data is empty: {_symbol}") + df = pd.DataFrame() + return df + del df["date"] return df @abc.abstractmethod @@ -523,11 +664,16 @@ class YahooNormalizeCN1d(YahooNormalizeCN, YahooNormalize1d): pass +class YahooNormalizeCN1dExtend(YahooNormalizeCN, YahooNormalize1dExtend): + pass + + class YahooNormalizeCN1min(YahooNormalizeCN, YahooNormalize1min): AM_RANGE = ("09:30:00", "11:29:00") PM_RANGE = ("13:00:00", "14:59:00") CONSISTENT_1d = True + CALC_PAUSED_NUM = True def _get_calendar_list(self): return self.generate_1min_from_daily(self.calendar_list_1d) @@ -624,10 +770,54 @@ class Run(BaseRun): Examples --------- - $ python collector.py normalize_data --source_dir ~/.qlib/stock_data/source --normalize_dir ~/.qlib/stock_data/normalize --region CN --interval 1d + $ python collector.py normalize_data --source_dir ~/.qlib/stock_data/source --normalize_dir ~/.qlib/stock_data/normalize --region cn --interval 1d """ super(Run, self).normalize_data(date_field_name, symbol_field_name) + def normalize_data_1d_extend( + self, old_qlib_data_dir, date_field_name: str = "date", symbol_field_name: str = "symbol" + ): + """normalize data extend; extending yahoo qlib data(from: https://github.com/microsoft/qlib/tree/main/scripts#download-cn-data) + + Notes + ----- + Steps to extend yahoo qlib data: + + 1. download qlib data: https://github.com/microsoft/qlib/tree/main/scripts#download-cn-data; save to + + 2. collector source data: https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#collector-data; save to + + 3. normalize new source data(from step 2): python scripts/data_collector/yahoo/collector.py normalize_data_1d_extend --old_qlib_dir --source_dir --normalize_dir --region CN --interval 1d + + 4. dump data: python scripts/dump_bin.py dump_update --csv_path --qlib_dir --freq day --date_field_name date --symbol_field_name symbol --exclude_fields symbol,date + + 5. update instrument(eg. csi300): python python scripts/data_collector/cn_index/collector.py --index_name CSI300 --qlib_dir --method parse_instruments + + Parameters + ---------- + old_qlib_data_dir: str + the qlib data to be updated for yahoo, usually from: https://github.com/microsoft/qlib/tree/main/scripts#download-cn-data + date_field_name: str + date field name, default date + symbol_field_name: str + symbol field name, default symbol + + Examples + --------- + $ python collector.py normalize_data_1d_extend --old_qlib_dir ~/.qlib/qlib_data/cn_1d --source_dir ~/.qlib/stock_data/source --normalize_dir ~/.qlib/stock_data/normalize --region CN --interval 1d + """ + _class = getattr(self._cur_module, f"{self.normalize_class_name}Extend") + yc = Normalize( + source_dir=self.source_dir, + target_dir=self.normalize_dir, + normalize_class=_class, + max_workers=self.max_workers, + date_field_name=date_field_name, + symbol_field_name=symbol_field_name, + old_qlib_data_dir=old_qlib_data_dir, + ) + yc.normalize() + if __name__ == "__main__": fire.Fire(Run) From 554b9c78268c6439754e4a9f6fb4b6b35e48cdd4 Mon Sep 17 00:00:00 2001 From: zhupr Date: Sat, 5 Jun 2021 16:01:01 +0800 Subject: [PATCH 02/14] fix YahooCollector getting 1min data occasionally missing --- scripts/data_collector/base.py | 14 ++--- scripts/data_collector/yahoo/collector.py | 63 +++++++++++------------ 2 files changed, 36 insertions(+), 41 deletions(-) diff --git a/scripts/data_collector/base.py b/scripts/data_collector/base.py index cb51f9b22..d261f11cd 100644 --- a/scripts/data_collector/base.py +++ b/scripts/data_collector/base.py @@ -22,9 +22,9 @@ class BaseCollector(abc.ABC): NORMAL_FLAG = "NORMAL" DEFAULT_START_DATETIME_1D = pd.Timestamp("2000-01-01") - DEFAULT_START_DATETIME_1MIN = pd.Timestamp(datetime.datetime.now() - pd.Timedelta(days=5 * 6)) - DEFAULT_END_DATETIME_1D = pd.Timestamp(datetime.datetime.now() + pd.Timedelta(days=1)) - DEFAULT_END_DATETIME_1MIN = pd.Timestamp(datetime.datetime.now() + pd.Timedelta(days=1)) + DEFAULT_START_DATETIME_1MIN = pd.Timestamp(datetime.datetime.now() - pd.Timedelta(days=5 * 6 - 1)).date() + DEFAULT_END_DATETIME_1D = pd.Timestamp(datetime.datetime.now() + pd.Timedelta(days=1)).date() + DEFAULT_END_DATETIME_1MIN = DEFAULT_END_DATETIME_1D INTERVAL_1min = "1min" INTERVAL_1d = "1d" @@ -35,7 +35,7 @@ class BaseCollector(abc.ABC): start=None, end=None, interval="1d", - max_workers=4, + max_workers=1, max_collector_count=2, delay=0, check_data_length: bool = False, @@ -48,7 +48,7 @@ class BaseCollector(abc.ABC): save_dir: str instrument save dir max_workers: int - workers, default 4 + workers, default 1; Concurrent number, default is 1; when collecting data, it is recommended that max_workers be set to 1 max_collector_count: int default 2 delay: float @@ -310,7 +310,7 @@ class Normalize: class BaseRun(abc.ABC): - def __init__(self, source_dir=None, normalize_dir=None, max_workers=4, interval="1d"): + def __init__(self, source_dir=None, normalize_dir=None, max_workers=1, interval="1d"): """ Parameters @@ -320,7 +320,7 @@ class BaseRun(abc.ABC): normalize_dir: str Directory for normalize data, default "Path(__file__).parent/normalize" max_workers: int - Concurrent number, default is 4 + Concurrent number, default is 1; Concurrent number, default is 1; when collecting data, it is recommended that max_workers be set to 1 interval: str freq, value from [1min, 1d], default 1d """ diff --git a/scripts/data_collector/yahoo/collector.py b/scripts/data_collector/yahoo/collector.py index fcaa9ff92..a48c5f16a 100644 --- a/scripts/data_collector/yahoo/collector.py +++ b/scripts/data_collector/yahoo/collector.py @@ -25,6 +25,7 @@ CUR_DIR = Path(__file__).resolve().parent sys.path.append(str(CUR_DIR.parent.parent)) from data_collector.base import BaseCollector, BaseNormalize, BaseRun, Normalize from data_collector.utils import ( + deco_retry, get_calendar_list, get_hs_stock_symbols, get_us_stock_symbols, @@ -92,10 +93,6 @@ class YahooCollector(BaseCollector): else: raise ValueError(f"interval error: {self.interval}") - # using for 1min - self._next_datetime = self.convert_datetime(self.start_datetime.date() + pd.Timedelta(days=1), self._timezone) - self._latest_datetime = self.convert_datetime(self.end_datetime.date(), self._timezone) - self.start_datetime = self.convert_datetime(self.start_datetime, self._timezone) self.end_datetime = self.convert_datetime(self.end_datetime, self._timezone) @@ -140,40 +137,36 @@ class YahooCollector(BaseCollector): def get_data( self, symbol: str, interval: str, start_datetime: pd.Timestamp, end_datetime: pd.Timestamp ) -> pd.DataFrame: + @deco_retry(retry_sleep=1) def _get_simple(start_, end_): self.sleep() _remote_interval = "1m" if interval == self.INTERVAL_1min else interval - return self.get_data_from_remote( + resp = self.get_data_from_remote( symbol, interval=_remote_interval, start=start_, end=end_, ) + if resp is None or resp.empty: + raise ValueError(f"get data error: {symbol}--{start_}--{end_}") + return resp _result = None if interval == self.INTERVAL_1d: _result = _get_simple(start_datetime, end_datetime) elif interval == self.INTERVAL_1min: - if self._next_datetime >= self._latest_datetime: - _result = _get_simple(start_datetime, end_datetime) - else: - _res = [] - - def _get_multi(start_, end_): - _resp = _get_simple(start_, end_) - if _resp is not None and not _resp.empty: - _res.append(_resp) - - for _s, _e in ( - (self.start_datetime, self._next_datetime), - (self._latest_datetime, self.end_datetime), - ): - _get_multi(_s, _e) - for _start in pd.date_range(self._next_datetime, self._latest_datetime, closed="left"): - _end = _start + pd.Timedelta(days=1) - _get_multi(_start, _end) - if _res: - _result = pd.concat(_res, sort=False).sort_values(["symbol", "date"]) + _res = [] + _start = self.start_datetime + while _start < self.end_datetime: + _tmp_end = min(_start + pd.Timedelta(days=7), self.end_datetime) + try: + _resp = _get_simple(_start, _tmp_end) + _res.append(_resp) + except ValueError as e: + pass + _start = _tmp_end + if _res: + _result = pd.concat(_res, sort=False).sort_values(["symbol", "date"]) else: raise ValueError(f"cannot support {self.interval}") return pd.DataFrame() if _result is None else _result @@ -520,6 +513,10 @@ class YahooNormalize1min(YahooNormalize, ABC): calendars, freq="1min", am_range=self.AM_RANGE, pm_range=self.PM_RANGE ) + def get_1d_data(self, symbol: str, start: str, end: str) -> pd.DataFrame: + data_1d = YahooCollector.get_data_from_remote(self.symbol_to_yahoo(symbol), interval="1d", start=start, end=end) + return data_1d + def adjusted_price(self, df: pd.DataFrame) -> pd.DataFrame: # TODO: using daily data factor if df.empty: @@ -529,9 +526,7 @@ class YahooNormalize1min(YahooNormalize, ABC): # get 1d data from yahoo _start = pd.Timestamp(df[self._date_field_name].min()).strftime(self.DAILY_FORMAT) _end = (pd.Timestamp(df[self._date_field_name].max()) + pd.Timedelta(days=1)).strftime(self.DAILY_FORMAT) - data_1d = YahooCollector.get_data_from_remote( - self.symbol_to_yahoo(symbol), interval="1d", start=_start, end=_end - ) + data_1d = self.get_1d_data(symbol, _start, _end) if data_1d is None or data_1d.empty: df["factor"] = 1 # TODO: np.nan or 1 or 0 @@ -579,21 +574,21 @@ class YahooNormalize1min(YahooNormalize, ABC): def calc_paused_num(self, df: pd.DataFrame): _symbol = df.iloc[0][self._symbol_field_name] df = df.copy() - df["date"] = df[self._date_field_name].apply(lambda x: pd.Timestamp(x).date()) + df["_tmp_date"] = df[self._date_field_name].apply(lambda x: pd.Timestamp(x).date()) # remove data that starts and ends with `np.nan` all day all_data = [] # Record the number of consecutive trading days where the whole day is nan, to remove the last trading day where the whole day is nan all_nan_nums = 0 # Record the number of consecutive occurrences of trading days that are not nan throughout the day not_nan_nums = 0 - for _date, _df in df.groupby(level="date"): + for _date, _df in df.groupby("_tmp_date"): _df["paused"] = 0 if not _df.loc[_df["volume"] < 0].empty: logger.warning(f"volume < 0, will fill np.nan: {_date} {_symbol}") _df.loc[_df["volume"] < 0, "volume"] = np.nan check_fields = set(_df.columns) - { - "date", + "_tmp_date", "paused", "factor", self._date_field_name, @@ -618,7 +613,7 @@ class YahooNormalize1min(YahooNormalize, ABC): logger.warning(f"data is empty: {_symbol}") df = pd.DataFrame() return df - del df["date"] + del df["_tmp_date"] return df @abc.abstractmethod @@ -690,7 +685,7 @@ class YahooNormalizeCN1min(YahooNormalizeCN, YahooNormalize1min): class Run(BaseRun): - def __init__(self, source_dir=None, normalize_dir=None, max_workers=4, interval="1d", region=REGION_CN): + def __init__(self, source_dir=None, normalize_dir=None, max_workers=1, interval="1d", region=REGION_CN): """ Parameters @@ -700,7 +695,7 @@ class Run(BaseRun): normalize_dir: str Directory for normalize data, default "Path(__file__).parent/normalize" max_workers: int - Concurrent number, default is 4 + Concurrent number, default is 1; when collecting data, it is recommended that max_workers be set to 1 interval: str freq, value from [1min, 1d], default 1d region: str From a845a2271b3352e410b99843628167c7dce095db Mon Sep 17 00:00:00 2001 From: zhupr Date: Tue, 8 Jun 2021 14:45:20 +0800 Subject: [PATCH 03/14] add normalize 1min to use local data && change the default parameters for collecting 1min --- scripts/data_collector/base.py | 52 ++--- .../contrib/fill_cn_1min_data/README.md | 23 ++ .../fill_cn_1min_data/fill_cn_1min_data.py | 98 +++++++++ .../fill_cn_1min_data/requirements.txt | 5 + .../README.md | 0 .../future_trading_date_collector.py | 2 +- .../requirements.txt | 0 scripts/data_collector/fund/collector.py | 22 +- scripts/data_collector/yahoo/collector.py | 196 +++++++++++++++--- 9 files changed, 328 insertions(+), 70 deletions(-) create mode 100644 scripts/data_collector/contrib/fill_cn_1min_data/README.md create mode 100644 scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py create mode 100644 scripts/data_collector/contrib/fill_cn_1min_data/requirements.txt rename scripts/data_collector/contrib/{ => future_trading_date_collector}/README.md (100%) rename scripts/data_collector/contrib/{ => future_trading_date_collector}/future_trading_date_collector.py (98%) rename scripts/data_collector/contrib/{ => future_trading_date_collector}/requirements.txt (100%) diff --git a/scripts/data_collector/base.py b/scripts/data_collector/base.py index d261f11cd..08e1838a4 100644 --- a/scripts/data_collector/base.py +++ b/scripts/data_collector/base.py @@ -7,7 +7,7 @@ import time import datetime import importlib from pathlib import Path -from typing import Type +from typing import Type, Iterable from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor import pandas as pd @@ -38,7 +38,7 @@ class BaseCollector(abc.ABC): max_workers=1, max_collector_count=2, delay=0, - check_data_length: bool = False, + check_data_length: int = None, limit_nums: int = None, ): """ @@ -59,8 +59,8 @@ class BaseCollector(abc.ABC): start datetime, default None end: str end datetime, default None - check_data_length: bool - check data length, by default False + check_data_length: int + check data length, if not None and greater than 0, each symbol will be considered complete if its data length is greater than or equal to this value, otherwise it will be fetched again, the maximum number of fetches being (max_collector_count). By default None. limit_nums: int using for debug, by default None """ @@ -72,7 +72,7 @@ class BaseCollector(abc.ABC): self.max_collector_count = max_collector_count self.mini_symbol_map = {} self.interval = interval - self.check_small_data = check_data_length + self.check_data_length = max(int(check_data_length) if check_data_length is not None else 0, 0) self.start_datetime = self.normalize_start_datetime(start) self.end_datetime = self.normalize_end_datetime(end) @@ -99,14 +99,6 @@ class BaseCollector(abc.ABC): else getattr(self, f"DEFAULT_END_DATETIME_{self.interval.upper()}") ) - @property - @abc.abstractmethod - def min_numbers_trading(self): - # daily, one year: 252 / 4 - # us 1min, a week: 6.5 * 60 * 5 - # cn 1min, a week: 4 * 60 * 5 - raise NotImplementedError("rewrite min_numbers_trading") - @abc.abstractmethod def get_instrument_list(self): raise NotImplementedError("rewrite get_instrument_list") @@ -132,7 +124,7 @@ class BaseCollector(abc.ABC): Returns --------- - pd.DataFrame, "symbol" in pd.columns + pd.DataFrame, "symbol" and "date"in pd.columns """ raise NotImplementedError("rewrite get_timezone") @@ -151,7 +143,7 @@ class BaseCollector(abc.ABC): self.sleep() df = self.get_data(symbol, self.interval, self.start_datetime, self.end_datetime) _result = self.NORMAL_FLAG - if self.check_small_data: + if self.check_data_length > 0: _result = self.cache_small_data(symbol, df) if _result == self.NORMAL_FLAG: self.save_instrument(symbol, df) @@ -181,8 +173,8 @@ class BaseCollector(abc.ABC): df.to_csv(instrument_path, index=False) def cache_small_data(self, symbol, df): - if len(df) <= self.min_numbers_trading: - logger.warning(f"the number of trading days of {symbol} is less than {self.min_numbers_trading}!") + if len(df) < self.check_data_length: + logger.warning(f"the number of trading days of {symbol} is less than {self.check_data_length}!") _temp = self.mini_symbol_map.setdefault(symbol, []) _temp.append(df.copy()) return self.CACHE_FLAG @@ -194,9 +186,17 @@ class BaseCollector(abc.ABC): def _collector(self, instrument_list): error_symbol = [] - with ThreadPoolExecutor(max_workers=self.max_workers) as executor: - with tqdm(total=len(instrument_list)) as p_bar: - for _symbol, _result in zip(instrument_list, executor.map(self._simple_collector, instrument_list)): + with tqdm(total=len(instrument_list)) as p_bar: + if self.max_workers is not None and self.max_workers > 1: + logger.info(f"concurrent collector, max_workers: {self.max_workers}") + with ThreadPoolExecutor(max_workers=self.max_workers) as executor: + for _symbol, _result in zip(instrument_list, executor.map(self._simple_collector, instrument_list)): + if _result != self.NORMAL_FLAG: + error_symbol.append(_symbol) + p_bar.update() + else: + for _symbol in instrument_list: + _result = self._simple_collector(_symbol) if _result != self.NORMAL_FLAG: error_symbol.append(_symbol) p_bar.update() @@ -217,11 +217,11 @@ class BaseCollector(abc.ABC): instrument_list = self._collector(instrument_list) logger.info(f"{i+1} finish.") for _symbol, _df_list in self.mini_symbol_map.items(): - self.save_instrument( - _symbol, pd.concat(_df_list, sort=False).drop_duplicates(["date"]).sort_values(["date"]) - ) + _df = pd.concat(_df_list, sort=False) + if not _df.empty: + self.save_instrument(_symbol, _df.drop_duplicates(["date"]).sort_values(["date"])) if self.mini_symbol_map: - logger.warning(f"less than {self.min_numbers_trading} instrument list: {list(self.mini_symbol_map.keys())}") + logger.warning(f"less than {self.check_data_length} instrument list: {list(self.mini_symbol_map.keys())}") logger.info(f"total {len(self.instrument_list)}, error: {len(set(instrument_list))}") @@ -247,7 +247,7 @@ class BaseNormalize(abc.ABC): raise NotImplementedError("") @abc.abstractmethod - def _get_calendar_list(self): + def _get_calendar_list(self) -> Iterable[pd.Timestamp]: """Get benchmark calendar""" raise NotImplementedError("") @@ -296,7 +296,7 @@ class Normalize: file_path = Path(file_path) df = pd.read_csv(file_path) df = self._normalize_obj.normalize(df) - if not df.empty: + if df is not None and not df.empty: df.to_csv(self._target_dir.joinpath(file_path.name), index=False) def normalize(self): diff --git a/scripts/data_collector/contrib/fill_cn_1min_data/README.md b/scripts/data_collector/contrib/fill_cn_1min_data/README.md new file mode 100644 index 000000000..c9ff0629c --- /dev/null +++ b/scripts/data_collector/contrib/fill_cn_1min_data/README.md @@ -0,0 +1,23 @@ +# Use 1d data to fill in the missing symbols relative to 1min + + +## Requirements + +```bash +pip install -r requirements.txt +``` + +## fill 1min data + +```bash +python fill_1min_using_1d.py --data_1min_dir ~/.qlib/csv_data/cn_data_1min --qlib_data_1d_dir ~/.qlib/qlib_data/cn_data +``` + +## Parameters + +- ata_1min_dir: csv data +- qlib_data_1d_dir: qlib data directory +- max_workers: `ThreadPoolExecutor(max_workers=max_workers)`, by default *16* +- date_field_name: date field name, by default *date* +- symbol_field_name: symbol field name, by default *symbol* + diff --git a/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py b/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py new file mode 100644 index 000000000..4abca3361 --- /dev/null +++ b/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py @@ -0,0 +1,98 @@ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. + +import sys +from pathlib import Path +from concurrent.futures import ThreadPoolExecutor + +import fire +import qlib +import pandas as pd +from tqdm import tqdm +from qlib.data import D +from loguru import logger + +CUR_DIR = Path(__file__).resolve().parent +sys.path.append(str(CUR_DIR.parent.parent.parent)) +from data_collector.utils import generate_minutes_calendar_from_daily + + +def get_date_range(data_1min_dir: Path, max_workers: int = 16, date_field_name: str = "date"): + csv_files = list(data_1min_dir.glob("*.csv")) + min_date = None + max_date = None + with tqdm(total=len(csv_files)) as p_bar: + with ThreadPoolExecutor(max_workers=max_workers) as executor: + for _file, _result in zip(csv_files, executor.map(pd.read_csv, csv_files)): + if not _result.empty: + _dates = pd.to_datetime(_result[date_field_name]) + + _tmp_min = _dates.min() + min_date = min_date(min_date, _tmp_min) if min_date is not None else _tmp_min + + _tmp_max = _dates.max() + max_date = min_date(max_date, _tmp_max) if max_date is not None else _tmp_max + p_bar.update() + return min_date, max_date + + +def get_symbols(data_1min_dir: Path): + return list(map(lambda x: x.name[:-4].upper(), data_1min_dir.glob("*.csv"))) + + +def fill_1min_using_1d( + data_1min_dir: [str, Path], + qlib_data_1d_dir: [str, Path], + max_workers: int = 16, + date_field_name: str = "date", + symbol_field_name: str = "symbol", +): + """Use 1d data to fill in the missing symbols relative to 1min + + Parameters + ---------- + data_1min_dir: str + 1min data dir + qlib_data_1d_dir: str + 1d qlib data(bin data) dir, from: https://qlib.readthedocs.io/en/latest/component/data.html#converting-csv-format-into-qlib-format + max_workers: int + ThreadPoolExecutor(max_workers), by default 16 + date_field_name: str + date field name, by default date + symbol_field_name: str + symbol field name, by default symbol + + """ + data_1min_dir = Path(data_1min_dir).expanduser().resolve() + qlib_data_1d_dir = Path(qlib_data_1d_dir).expanduser().resolve() + + min_date, max_date = get_date_range(data_1min_dir, max_workers, date_field_name) + symbols_1min = get_symbols(data_1min_dir) + + qlib.init(provider_uri=str(qlib_data_1d_dir)) + data_1d = D.features(D.instruments("all"), ["$close"], min_date, max_date, freq="day") + + miss_symbols = set(data_1d.index.get_level_values(level="instrument").unique()) - set(symbols_1min) + if not miss_symbols: + logger.warning("More symbols in 1min than 1d, no padding required") + return + + logger.info(f"miss_symbols {len(miss_symbols)}: {miss_symbols}") + tmp_df = pd.read_csv(list(data_1min_dir.glob("*.csv"))[0]) + columns = tmp_df.columns + _si = tmp_df[symbol_field_name].first_valid_index() + is_lower = tmp_df.loc[tmp_df][symbol_field_name].islower() + for symbol in tqdm(miss_symbols): + if is_lower: + symbol = symbol.lower() + index_1d = data_1d.loc(axis=0)[symbol.upper()].index + index_1min = generate_minutes_calendar_from_daily(index_1d) + index_1min.name = date_field_name + _df = pd.DataFrame(columns=columns, index=index_1min) + _df.reset_index(inplace=True) + _df[symbol_field_name] = symbol + _df.to_csv(data_1min_dir.joinpath(f"{symbol}.csv"), index=False) + + +if __name__ == "__main__": + fire.Fire(fill_1min_using_1d) diff --git a/scripts/data_collector/contrib/fill_cn_1min_data/requirements.txt b/scripts/data_collector/contrib/fill_cn_1min_data/requirements.txt new file mode 100644 index 000000000..057683685 --- /dev/null +++ b/scripts/data_collector/contrib/fill_cn_1min_data/requirements.txt @@ -0,0 +1,5 @@ +fire +pandas +loguru +tqdm +pyqlib \ No newline at end of file diff --git a/scripts/data_collector/contrib/README.md b/scripts/data_collector/contrib/future_trading_date_collector/README.md similarity index 100% rename from scripts/data_collector/contrib/README.md rename to scripts/data_collector/contrib/future_trading_date_collector/README.md diff --git a/scripts/data_collector/contrib/future_trading_date_collector.py b/scripts/data_collector/contrib/future_trading_date_collector/future_trading_date_collector.py similarity index 98% rename from scripts/data_collector/contrib/future_trading_date_collector.py rename to scripts/data_collector/contrib/future_trading_date_collector/future_trading_date_collector.py index 4da62d465..8df0a4972 100644 --- a/scripts/data_collector/contrib/future_trading_date_collector.py +++ b/scripts/data_collector/contrib/future_trading_date_collector/future_trading_date_collector.py @@ -14,7 +14,7 @@ from loguru import logger import baostock as bs CUR_DIR = Path(__file__).resolve().parent -sys.path.append(str(CUR_DIR.parent.parent)) +sys.path.append(str(CUR_DIR.parent.parent.parent)) from data_collector.utils import generate_minutes_calendar_from_daily diff --git a/scripts/data_collector/contrib/requirements.txt b/scripts/data_collector/contrib/future_trading_date_collector/requirements.txt similarity index 100% rename from scripts/data_collector/contrib/requirements.txt rename to scripts/data_collector/contrib/future_trading_date_collector/requirements.txt diff --git a/scripts/data_collector/fund/collector.py b/scripts/data_collector/fund/collector.py index 10800a7a3..fc06a27e4 100644 --- a/scripts/data_collector/fund/collector.py +++ b/scripts/data_collector/fund/collector.py @@ -3,18 +3,13 @@ import abc import sys -import copy -import time import datetime -import importlib import json from abc import ABC from pathlib import Path -from typing import Iterable, Type import fire import requests -import numpy as np import pandas as pd from loguru import logger from dateutil.tz import tzlocal @@ -38,7 +33,7 @@ class FundCollector(BaseCollector): max_workers=4, max_collector_count=2, delay=0, - check_data_length: bool = False, + check_data_length: int = None, limit_nums: int = None, ): """ @@ -59,8 +54,8 @@ class FundCollector(BaseCollector): start datetime, default None end: str end datetime, default None - check_data_length: bool - check data length, by default False + check_data_length: int + check data length, if not None and greater than 0, each symbol will be considered complete if its data length is greater than or equal to this value, otherwise it will be fetched again, the maximum number of fetches being (max_collector_count). By default None. limit_nums: int using for debug, by default None """ @@ -168,10 +163,7 @@ class FundollectorCN(FundCollector, ABC): class FundCollectorCN1d(FundollectorCN): - @property - def min_numbers_trading(self): - return 252 / 4 - + pass class FundNormalize(BaseNormalize): DAILY_FORMAT = "%Y-%m-%d" @@ -261,7 +253,7 @@ class Run(BaseRun): start=None, end=None, interval="1d", - check_data_length=False, + check_data_length=None, limit_nums=None, ): """download data from Internet @@ -278,8 +270,8 @@ class Run(BaseRun): start datetime, default "2000-01-01" end: str end datetime, default ``pd.Timestamp(datetime.datetime.now() + pd.Timedelta(days=1))`` - check_data_length: bool # if this param useful? - check data length, by default False + check_data_length: int # if this param useful? + check data length, if not None and greater than 0, each symbol will be considered complete if its data length is greater than or equal to this value, otherwise it will be fetched again, the maximum number of fetches being (max_collector_count). By default None. limit_nums: int using for debug, by default None diff --git a/scripts/data_collector/yahoo/collector.py b/scripts/data_collector/yahoo/collector.py index a48c5f16a..16b0a32ba 100644 --- a/scripts/data_collector/yahoo/collector.py +++ b/scripts/data_collector/yahoo/collector.py @@ -137,7 +137,7 @@ class YahooCollector(BaseCollector): def get_data( self, symbol: str, interval: str, start_datetime: pd.Timestamp, end_datetime: pd.Timestamp ) -> pd.DataFrame: - @deco_retry(retry_sleep=1) + @deco_retry(retry_sleep=self.delay) def _get_simple(start_, end_): self.sleep() _remote_interval = "1m" if interval == self.INTERVAL_1min else interval @@ -200,10 +200,6 @@ class YahooCollectorCN(YahooCollector, ABC): class YahooCollectorCN1d(YahooCollectorCN): - @property - def min_numbers_trading(self): - return 252 / 4 - def download_index_data(self): # TODO: from MSN _format = "%Y%m%d" @@ -237,10 +233,6 @@ class YahooCollectorCN1d(YahooCollectorCN): class YahooCollectorCN1min(YahooCollectorCN): - @property - def min_numbers_trading(self): - return 60 * 4 * 5 - def download_index_data(self): # TODO: 1m logger.warning(f"{self.__class__.__name__} {self.interval} does not support: download_index_data") @@ -269,15 +261,11 @@ class YahooCollectorUS(YahooCollector, ABC): class YahooCollectorUS1d(YahooCollectorUS): - @property - def min_numbers_trading(self): - return 252 / 4 + pass class YahooCollectorUS1min(YahooCollectorUS): - @property - def min_numbers_trading(self): - return 60 * 6.5 * 5 + pass class YahooNormalize(BaseNormalize): @@ -514,7 +502,17 @@ class YahooNormalize1min(YahooNormalize, ABC): ) def get_1d_data(self, symbol: str, start: str, end: str) -> pd.DataFrame: + """get 1d data + + Returns + ------ + data_1d: pd.DataFrame + set(data_1d.columns) - set([self._date_field_name, self._symbol_field_name, "paused", "volume", "factor"]) == {} + + """ data_1d = YahooCollector.get_data_from_remote(self.symbol_to_yahoo(symbol), interval="1d", start=start, end=end) + if not (data_1d is None or data_1d.empty): + data_1d = self.data_1d_obj.normalize(data_1d) return data_1d def adjusted_price(self, df: pd.DataFrame) -> pd.DataFrame: @@ -526,13 +524,12 @@ class YahooNormalize1min(YahooNormalize, ABC): # get 1d data from yahoo _start = pd.Timestamp(df[self._date_field_name].min()).strftime(self.DAILY_FORMAT) _end = (pd.Timestamp(df[self._date_field_name].max()) + pd.Timedelta(days=1)).strftime(self.DAILY_FORMAT) - data_1d = self.get_1d_data(symbol, _start, _end) + data_1d: pd.DataFrame = self.get_1d_data(symbol, _start, _end) if data_1d is None or data_1d.empty: df["factor"] = 1 # TODO: np.nan or 1 or 0 df["paused"] = np.nan else: - data_1d = self.data_1d_obj.normalize(data_1d) # type: pd.DataFrame # NOTE: volume is np.nan or volume <= 0, paused = 1 # FIXME: find a more accurate data source data_1d["paused"] = 0 @@ -621,12 +618,12 @@ class YahooNormalize1min(YahooNormalize, ABC): raise NotImplementedError("rewrite symbol_to_yahoo") @abc.abstractmethod - def _get_1d_calendar_list(self): + def _get_1d_calendar_list(self) -> Iterable[pd.Timestamp]: raise NotImplementedError("rewrite _get_1d_calendar_list") class YahooNormalizeUS: - def _get_calendar_list(self): + def _get_calendar_list(self) -> Iterable[pd.Timestamp]: # TODO: from MSN return get_calendar_list("US_ALL") @@ -638,7 +635,7 @@ class YahooNormalizeUS1d(YahooNormalizeUS, YahooNormalize1d): class YahooNormalizeUS1min(YahooNormalizeUS, YahooNormalize1min): CONSISTENT_1d = False - def _get_calendar_list(self): + def _get_calendar_list(self) -> Iterable[pd.Timestamp]: # TODO: support 1min raise ValueError("Does not support 1min") @@ -650,7 +647,7 @@ class YahooNormalizeUS1min(YahooNormalizeUS, YahooNormalize1min): class YahooNormalizeCN: - def _get_calendar_list(self): + def _get_calendar_list(self) -> Iterable[pd.Timestamp]: # TODO: from MSN return get_calendar_list("ALL") @@ -670,7 +667,7 @@ class YahooNormalizeCN1min(YahooNormalizeCN, YahooNormalize1min): CONSISTENT_1d = True CALC_PAUSED_NUM = True - def _get_calendar_list(self): + def _get_calendar_list(self) -> Iterable[pd.Timestamp]: return self.generate_1min_from_daily(self.calendar_list_1d) def symbol_to_yahoo(self, symbol): @@ -680,10 +677,67 @@ class YahooNormalizeCN1min(YahooNormalizeCN, YahooNormalize1min): symbol = symbol[2:] + "." + _exchange return symbol - def _get_1d_calendar_list(self): + def _get_1d_calendar_list(self) -> Iterable[pd.Timestamp]: return get_calendar_list("ALL") +class YahooNormalizeCN1minOffline(YahooNormalizeCN1min): + """Normalised to 1min using local 1d data + 1d data usually from: Normalised to 1min using local 1d data + """ + + def __init__( + self, qlib_data_1d_dir: [str, Path], date_field_name: str = "date", symbol_field_name: str = "symbol", **kwargs + ): + """ + + Parameters + ---------- + qlib_data_1d_dir: str, Path + the qlib data to be updated for yahoo, usually from: Normalised to 1min using local 1d data + date_field_name: str + date field name, default is date + symbol_field_name: str + symbol field name, default is symbol + """ + super(YahooNormalizeCN1minOffline, self).__init__(date_field_name, symbol_field_name) + self.qlib_data_1d_dir = qlib_data_1d_dir + self._all_1d_data = self._get_all_1d_data() + + def _get_1d_calendar_list(self) -> Iterable[pd.Timestamp]: + import qlib + from qlib.data import D + + qlib.init(provider_uri=self.qlib_data_1d_dir) + return list(D.calendar(freq="day")) + + def _get_all_1d_data(self): + import qlib + from qlib.data import D + + qlib.init(provider_uri=self.qlib_data_1d_dir) + df = D.features(D.instruments("all"), ["$paused", "$volume", "$factor"], freq="day") + df.reset_index(inplace=True) + df.rename(columns={"datetime": self._date_field_name, "instrument": self._symbol_field_name}, inplace=True) + df.columns = list(map(lambda x: x[1:] if x.startswith("$") else x, df.columns)) + return df + + def get_1d_data(self, symbol: str, start: str, end: str) -> pd.DataFrame: + """get 1d data + + Returns + ------ + data_1d: pd.DataFrame + set(data_1d.columns) - set([self._date_field_name, self._symbol_field_name, "paused", "volume", "factor"]) == {} + + """ + return self._all_1d_data[ + (self._all_1d_data[self._symbol_field_name] == symbol.upper()) + & (self._all_1d_data[self._date_field_name] >= pd.Timestamp(start)) + & (self._all_1d_data[self._date_field_name] < pd.Timestamp(end)) + ] + + class Run(BaseRun): def __init__(self, source_dir=None, normalize_dir=None, max_workers=1, interval="1d", region=REGION_CN): """ @@ -722,7 +776,7 @@ class Run(BaseRun): delay=0, start=None, end=None, - check_data_length=False, + check_data_length=None, limit_nums=None, ): """download data from Internet @@ -734,14 +788,21 @@ class Run(BaseRun): delay: float time.sleep(delay), default 0 start: str - start datetime, default "2000-01-01" + start datetime, default "2000-01-01"; closed interval(including start) end: str - end datetime, default ``pd.Timestamp(datetime.datetime.now() + pd.Timedelta(days=1))`` - check_data_length: bool - check data length, by default False + end datetime, default ``pd.Timestamp(datetime.datetime.now() + pd.Timedelta(days=1))``; open interval(excluding end) + check_data_length: int + check data length, if not None and greater than 0, each symbol will be considered complete if its data length is greater than or equal to this value, otherwise it will be fetched again, the maximum number of fetches being (max_collector_count). By default None. limit_nums: int using for debug, by default None + Notes + ----- + check_data_length, example: + daily, one year: 252 // 4 + us 1min, a week: 6.5 * 60 * 5 + cn 1min, a week: 4 * 60 * 5 + Examples --------- # get daily data @@ -813,6 +874,85 @@ class Run(BaseRun): ) yc.normalize() + def normalize_data_1min_cn_offline( + self, qlib_data_1d_dir, date_field_name: str = "date", symbol_field_name: str = "symbol" + ): + """Normalised to 1min using local 1d data + + Parameters + ---------- + qlib_data_1d_dir: str + the qlib data to be updated for yahoo, usually from: https://github.com/microsoft/qlib/tree/main/scripts#download-cn-data + date_field_name: str + date field name, default date + symbol_field_name: str + symbol field name, default symbol + + Examples + --------- + $ python collector.py normalize_data_1min_cn_offline --qlib_data_1d_dir ~/.qlib/qlib_data/cn_1d --source_dir ~/.qlib/stock_data/source_cn_1min --normalize_dir ~/.qlib/stock_data/normalize_cn_1min --region CN --interval 1min + """ + _class = getattr(self._cur_module, f"{self.normalize_class_name}Offline") + yc = Normalize( + source_dir=self.source_dir, + target_dir=self.normalize_dir, + normalize_class=_class, + max_workers=self.max_workers, + date_field_name=date_field_name, + symbol_field_name=symbol_field_name, + qlib_data_1d_dir=qlib_data_1d_dir, + ) + yc.normalize() + + def download_today_data( + self, + max_collector_count=2, + delay=0, + check_data_length=None, + limit_nums=None, + ): + """download today data from Internet + + Parameters + ---------- + max_collector_count: int + default 2 + delay: float + time.sleep(delay), default 0 + check_data_length: int + check data length, if not None and greater than 0, each symbol will be considered complete if its data length is greater than or equal to this value, otherwise it will be fetched again, the maximum number of fetches being (max_collector_count). By default None. + limit_nums: int + using for debug, by default None + + Notes + ----- + Download today's data: + start_time = datetime.datetime.now().date(); closed interval(including start) + end_time = pd.Timestamp(start_time + pd.Timedelta(days=1)).date(); open interval(excluding end) + + check_data_length, example: + daily, one year: 252 // 4 + us 1min, a week: 6.5 * 60 * 5 + cn 1min, a week: 4 * 60 * 5 + + Examples + --------- + # get daily data + $ python collector.py download_today_data --source_dir ~/.qlib/stock_data/source --region CN --delay 0.1 --interval 1d + # get 1m data + $ python collector.py download_today_data --source_dir ~/.qlib/stock_data/source --region CN --delay 0.1 --interval 1m + """ + start = datetime.datetime.now().date() + end = pd.Timestamp(start + pd.Timedelta(days=1)).date() + self.download_data( + max_collector_count, + delay, + start.strftime("%Y-%m-%d"), + end.strftime("%Y-%m-%d"), + check_data_length, + limit_nums, + ) + if __name__ == "__main__": fire.Fire(Run) From 03eb0882de52b9c8476fd8456185e99b41e11dc5 Mon Sep 17 00:00:00 2001 From: zhupr Date: Tue, 8 Jun 2021 22:23:05 +0800 Subject: [PATCH 04/14] fix YahooNormalizeCN1minOffline bugs --- .../fill_cn_1min_data/fill_cn_1min_data.py | 10 ++++---- scripts/data_collector/yahoo/collector.py | 23 +++++-------------- 2 files changed, 12 insertions(+), 21 deletions(-) diff --git a/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py b/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py index 4abca3361..0a721298d 100644 --- a/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py +++ b/scripts/data_collector/contrib/fill_cn_1min_data/fill_cn_1min_data.py @@ -28,10 +28,9 @@ def get_date_range(data_1min_dir: Path, max_workers: int = 16, date_field_name: _dates = pd.to_datetime(_result[date_field_name]) _tmp_min = _dates.min() - min_date = min_date(min_date, _tmp_min) if min_date is not None else _tmp_min - + min_date = min(min_date, _tmp_min) if min_date is not None else _tmp_min _tmp_max = _dates.max() - max_date = min_date(max_date, _tmp_max) if max_date is not None else _tmp_max + max_date = max(max_date, _tmp_max) if max_date is not None else _tmp_max p_bar.update() return min_date, max_date @@ -81,7 +80,7 @@ def fill_1min_using_1d( tmp_df = pd.read_csv(list(data_1min_dir.glob("*.csv"))[0]) columns = tmp_df.columns _si = tmp_df[symbol_field_name].first_valid_index() - is_lower = tmp_df.loc[tmp_df][symbol_field_name].islower() + is_lower = tmp_df.loc[_si][symbol_field_name].islower() for symbol in tqdm(miss_symbols): if is_lower: symbol = symbol.lower() @@ -89,8 +88,11 @@ def fill_1min_using_1d( index_1min = generate_minutes_calendar_from_daily(index_1d) index_1min.name = date_field_name _df = pd.DataFrame(columns=columns, index=index_1min) + if date_field_name in _df.columns: + del _df[date_field_name] _df.reset_index(inplace=True) _df[symbol_field_name] = symbol + _df["paused_num"] = 0 _df.to_csv(data_1min_dir.joinpath(f"{symbol}.csv"), index=False) diff --git a/scripts/data_collector/yahoo/collector.py b/scripts/data_collector/yahoo/collector.py index 16b0a32ba..58e1d3009 100644 --- a/scripts/data_collector/yahoo/collector.py +++ b/scripts/data_collector/yahoo/collector.py @@ -473,21 +473,6 @@ class YahooNormalize1min(YahooNormalize, ABC): CONSISTENT_1d = False CALC_PAUSED_NUM = False - def __init__(self, date_field_name: str = "date", symbol_field_name: str = "symbol", **kwargs): - """ - - Parameters - ---------- - date_field_name: str - date field name, default is date - symbol_field_name: str - symbol field name, default is symbol - """ - super(YahooNormalize1min, self).__init__(date_field_name, symbol_field_name) - _class_name = self.__class__.__name__.replace("min", "d") - _class = getattr(importlib.import_module("collector"), _class_name) # type: Type[YahooNormalize] - self.data_1d_obj = _class(self._date_field_name, self._symbol_field_name) - @property def calendar_list_1d(self): calendar_list_1d = getattr(self, "_calendar_list_1d", None) @@ -512,7 +497,10 @@ class YahooNormalize1min(YahooNormalize, ABC): """ data_1d = YahooCollector.get_data_from_remote(self.symbol_to_yahoo(symbol), interval="1d", start=start, end=end) if not (data_1d is None or data_1d.empty): - data_1d = self.data_1d_obj.normalize(data_1d) + _class_name = self.__class__.__name__.replace("min", "d") + _class: type(YahooNormalize) = getattr(importlib.import_module("collector"), _class_name) + data_1d_obj = _class(self._date_field_name, self._symbol_field_name) + data_1d = data_1d_obj.normalize(data_1d) return data_1d def adjusted_price(self, df: pd.DataFrame) -> pd.DataFrame: @@ -525,6 +513,7 @@ class YahooNormalize1min(YahooNormalize, ABC): _start = pd.Timestamp(df[self._date_field_name].min()).strftime(self.DAILY_FORMAT) _end = (pd.Timestamp(df[self._date_field_name].max()) + pd.Timedelta(days=1)).strftime(self.DAILY_FORMAT) data_1d: pd.DataFrame = self.get_1d_data(symbol, _start, _end) + data_1d = data_1d.copy() if data_1d is None or data_1d.empty: df["factor"] = 1 # TODO: np.nan or 1 or 0 @@ -700,8 +689,8 @@ class YahooNormalizeCN1minOffline(YahooNormalizeCN1min): symbol_field_name: str symbol field name, default is symbol """ - super(YahooNormalizeCN1minOffline, self).__init__(date_field_name, symbol_field_name) self.qlib_data_1d_dir = qlib_data_1d_dir + super(YahooNormalizeCN1minOffline, self).__init__(date_field_name, symbol_field_name) self._all_1d_data = self._get_all_1d_data() def _get_1d_calendar_list(self) -> Iterable[pd.Timestamp]: From 9a44fbf9c1e797fe99c9ef283586544347eede0d Mon Sep 17 00:00:00 2001 From: zhupr Date: Tue, 8 Jun 2021 22:52:31 +0800 Subject: [PATCH 05/14] fix PEP8: qlib/scripts/data_collector/fund/collector.py --- scripts/data_collector/fund/collector.py | 1 + 1 file changed, 1 insertion(+) diff --git a/scripts/data_collector/fund/collector.py b/scripts/data_collector/fund/collector.py index fc06a27e4..7b5566f72 100644 --- a/scripts/data_collector/fund/collector.py +++ b/scripts/data_collector/fund/collector.py @@ -165,6 +165,7 @@ class FundollectorCN(FundCollector, ABC): class FundCollectorCN1d(FundollectorCN): pass + class FundNormalize(BaseNormalize): DAILY_FORMAT = "%Y-%m-%d" From b4efbd53b2f8889b984a5f283e8d62cd3ecf1976 Mon Sep 17 00:00:00 2001 From: zhupr Date: Wed, 16 Jun 2021 22:00:43 +0800 Subject: [PATCH 06/14] Fix 'report' compatibility with matplotlib versions --- .../analysis_model_performance.py | 35 ++++++++++++++++--- 1 file changed, 31 insertions(+), 4 deletions(-) diff --git a/qlib/contrib/report/analysis_model/analysis_model_performance.py b/qlib/contrib/report/analysis_model/analysis_model_performance.py index 1cb14d261..1d444b104 100644 --- a/qlib/contrib/report/analysis_model/analysis_model_performance.py +++ b/qlib/contrib/report/analysis_model/analysis_model_performance.py @@ -3,7 +3,6 @@ import pandas as pd -import plotly.tools as tls import plotly.graph_objs as go import statsmodels.api as sm @@ -80,9 +79,37 @@ def _plot_qq(data: pd.Series = None, dist=stats.norm) -> go.Figure: :param dist: :return: """ - fig, ax = plt.subplots(figsize=(8, 5)) - _mpl_fig = sm.qqplot(data.dropna(), dist, fit=True, line="45", ax=ax) - return tls.mpl_to_plotly(_mpl_fig) + _plt_fig = sm.qqplot(data.dropna(), dist=dist, fit=True, line="45") + plt.close(_plt_fig) + qqplot_data = _plt_fig.gca().lines + fig = go.Figure() + + fig.add_trace({ + 'type': 'scatter', + 'x': qqplot_data[0].get_xdata(), + # 'x': [0, 1], + 'y': qqplot_data[0].get_ydata(), + # 'y': [1, 2], + 'mode': 'markers', + 'marker': { + 'color': '#19d3f3' + } + }) + + fig.add_trace({ + 'type': 'scatter', + 'x': qqplot_data[1].get_xdata(), + # 'x': [0, 1], + 'y': qqplot_data[1].get_ydata(), + # 'y': [1, 2], + 'mode': 'lines', + 'line': { + 'color': '#636efa' + } + + }) + del qqplot_data + return fig def _pred_ic(pred_label: pd.DataFrame = None, rank: bool = False, **kwargs) -> tuple: From a4f6e0419943428def7d5bd12958d065d07ecc9f Mon Sep 17 00:00:00 2001 From: zhupr Date: Thu, 17 Jun 2021 22:33:31 +0800 Subject: [PATCH 07/14] modify dump_update starts with the last end date of each symbol --- scripts/dump_bin.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/scripts/dump_bin.py b/scripts/dump_bin.py index b3a18cc90..83daa28bc 100644 --- a/scripts/dump_bin.py +++ b/scripts/dump_bin.py @@ -401,6 +401,8 @@ class DumpDataUpdate(DumpDataBase): ) self._mode = self.UPDATE_MODE self._old_calendar_list = self._read_calendars(self._calendars_dir.joinpath(f"{self.freq}.txt")) + # NOTE: all.txt only exists once for each stock + # NOTE: if a stock corresponds to multiple different time ranges, user need to modify self._update_instruments self._update_instruments = ( self._read_instruments(self._instruments_dir.joinpath(self.INSTRUMENTS_FILE_NAME)) .set_index([self.symbol_field_name]) @@ -409,10 +411,9 @@ class DumpDataUpdate(DumpDataBase): # load all csv files self._all_data = self._load_all_source_data() # type: pd.DataFrame - self._update_calendars = sorted( + self._new_calendar_list = self._old_calendar_list + sorted( filter(lambda x: x > self._old_calendar_list[-1], self._all_data[self.date_field_name].unique()) ) - self._new_calendar_list = self._old_calendar_list + self._update_calendars def _load_all_source_data(self): # NOTE: Need more memory @@ -452,8 +453,16 @@ class DumpDataUpdate(DumpDataBase): if not (isinstance(_start, pd.Timestamp) and isinstance(_end, pd.Timestamp)): continue if _code in self._update_instruments: + # exists stock, will append data + _update_calendars = ( + _df[_df[self.date_field_name] > self._update_instruments[_code][self.INSTRUMENTS_START_FIELD]][ + self.date_field_name + ] + .sort_values() + .to_list() + ) self._update_instruments[_code][self.INSTRUMENTS_END_FIELD] = self._format_datetime(_end) - futures[executor.submit(self._dump_bin, _df, self._update_calendars)] = _code + futures[executor.submit(self._dump_bin, _df, _update_calendars)] = _code else: # new stock _dt_range = self._update_instruments.setdefault(_code, dict()) From b6c31540e8c8bd7559b58bb6e4e268e9f91d32d5 Mon Sep 17 00:00:00 2001 From: zhupr Date: Thu, 17 Jun 2021 23:01:08 +0800 Subject: [PATCH 08/14] add function to automatically update daily frequency data --- README.md | 22 +++++ docs/component/data.rst | 28 ++++++ scripts/data_collector/cn_index/collector.py | 2 +- scripts/data_collector/us_index/collector.py | 2 +- scripts/data_collector/yahoo/README.md | 61 +++++++++++-- scripts/data_collector/yahoo/collector.py | 95 +++++++++++++++++--- 6 files changed, 189 insertions(+), 21 deletions(-) diff --git a/README.md b/README.md index 8276c4951..635b143f4 100644 --- a/README.md +++ b/README.md @@ -159,6 +159,28 @@ Users could create the same dataset with it. *Please pay **ATTENTION** that the data is collected from [Yahoo Finance](https://finance.yahoo.com/lookup), and the data might not be perfect. We recommend users to prepare their own data if they have a high-quality dataset. For more information, users can refer to the [related document](https://qlib.readthedocs.io/en/latest/component/data.html#converting-csv-format-into-qlib-format)*. +### Automatic update of daily frequency data(from yahoo finance) + > It is recommended that users update the data manually once (--trading_date 2021-05-25) and then set it to update automatically. + + > For more information refer to: [yahoo collector](https://github.com/microsoft/qlib/tree/main/scripts/data_collector/yahoo#Automatic-update-of-daily-frequency-data) + + * Automatic update of data to the "qlib" directory each trading day(Linux) + * use *crontab*: `crontab -e` + * set up timed tasks: + + ``` + * * * * 1-5 python