support collecting yahoo 1min data

docs/component/data.rst

@@ -136,7 +136,7 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
     - `volume`
         The trading volume
     - `factor`
-        The Restoration factor
+        The Restoration factor; ``factor = adjusted-close / close``, `adjusted price` reference: `split adjusted <https://www.investopedia.com/terms/s/splitadjusted.asp>`_
 
     In the convention of `Qlib` data processing, `open, close, high, low, volume, money and factor` will be set to NaN if the stock is suspended. 
 

scripts/data_collector/utils.py

@@ -5,6 +5,7 @@
 import time
 import bisect
 import pickle
+import random
 import requests
 import functools
 from pathlib import Path
@@ -17,6 +18,7 @@
 HS_SYMBOLS_URL = "http://app.finance.ifeng.com/hq/list.php?type=stock_a&class={s_type}"
 
 CALENDAR_URL_BASE = "http://push2his.eastmoney.com/api/qt/stock/kline/get?secid={market}.{bench_code}&fields1=f1%2Cf2%2Cf3%2Cf4%2Cf5&fields2=f51%2Cf52%2Cf53%2Cf54%2Cf55%2Cf56%2Cf57%2Cf58&klt=101&fqt=0&beg=19900101&end=20991231"
+SZSE_CALENDAR_URL = "http://www.szse.cn/api/report/exchange/onepersistenthour/monthList?month={month}&random={random}"
 
 CALENDAR_BENCH_URL_MAP = {
     "CSI300": CALENDAR_URL_BASE.format(market=1, bench_code="000300"),
@@ -63,7 +65,29 @@ def _get_calendar(url):
             df = Ticker(CALENDAR_BENCH_URL_MAP[bench_code]).history(interval="1d", period="max")
             calendar = df.index.get_level_values(level="date").map(pd.Timestamp).unique().tolist()
         else:
-            calendar = _get_calendar(CALENDAR_BENCH_URL_MAP[bench_code])
+            if bench_code.upper() == "ALL":
+
+                @deco_retry
+                def _get_calendar(month):
+                    _cal = []
+                    try:
+                        resp = requests.get(SZSE_CALENDAR_URL.format(month=month, random=random.random)).json()
+                        for _r in resp["data"]:
+                            if int(_r["jybz"]):
+                                _cal.append(pd.Timestamp(_r["jyrq"]))
+                    except Exception as e:
+                        raise ValueError(f"{month}-->{e}")
+                    return _cal
+
+                month_range = pd.date_range(start="2000-01", end=pd.Timestamp.now() + pd.Timedelta(days=31), freq="M")
+                calendar = []
+                for _m in month_range:
+                    cal = _get_calendar(_m.strftime("%Y-%m"))
+                    if cal:
+                        calendar += cal
+                calendar = list(filter(lambda x: x <= pd.Timestamp.now(), calendar))
+            else:
+                calendar = _get_calendar(CALENDAR_BENCH_URL_MAP[bench_code])
         _CALENDAR_MAP[bench_code] = calendar
     logger.info(f"end of get calendar list: {bench_code}.")
     return calendar

scripts/data_collector/yahoo/README.md

@@ -18,29 +18,87 @@ pip install -r requirements.txt
 
 ## Collector Data
 
-### Download data and Normalize data
+
+### CN Data
+
+#### 1d
+
 ```bash
-python collector.py collector_data --source_dir ~/.qlib/stock_data/source --region CN --start 2020-11-01 --end 2020-11-10 --delay 0.1 --interval 1d --normalize_dir ~/.qlib/stock_data/normalize
+
+# download from yahoo finance
+python collector.py download_data --source_dir ~/.qlib/stock_data/source/cn_1d --region CN --start 2020-11-01 --end 2020-11-10 --delay 0.1 --interval 1d
+
+# normalize
+python collector.py normalize_data --source_dir ~/.qlib/stock_data/source/cn_1d --normalize_dir ~/.qlib/stock_data/source/cn_1d_nor --region CN --interval 1d
+
+# dump data
+cd qlib/scripts
+python dump_bin.py dump_all --csv_path ~/.qlib/stock_data/source/cn_1d_nor --qlib_dir ~/.qlib/stock_data/source/qlib_cn_1d --freq day --exclude_fields date,adjclose,dividends,splits,symbol
+
+# using
+import qlib
+from qlib.data import D
+
+qlib.init(provider_uri="~/.qlib/stock_data/source/qlib_cn_1d", region="CN")
+df = D.features(D.instruments("all"), ["$close"], freq="day")
+
 ```
 
-### Download Data
+#### 1min
 
 ```bash
-python collector.py download_data --source_dir ~/.qlib/stock_data/source --region CN --start 2020-11-01 --end 2020-11-10 --delay 0.1 --interval 1d
+
+# download from yahoo finance
+python collector.py download_data --source_dir ~/.qlib/stock_data/source/cn_1min --region CN --start 2020-11-01 --end 2020-11-10 --delay 0.1 --interval 1min
+
+# normalize
+python collector.py normalize_data --source_dir ~/.qlib/stock_data/source/cn_1min --normalize_dir ~/.qlib/stock_data/source/cn_1min_nor --region CN --interval 1min
+
+# dump data
+cd qlib/scripts
+python dump_bin.py dump_all --csv_path ~/.qlib/stock_data/source/cn_1min_nor --qlib_dir ~/.qlib/stock_data/source/qlib_cn_1min --freq 1min --exclude_fields date,adjclose,dividends,splits,symbol
+
+# using
+import qlib
+from qlib.data import D
+
+qlib.init(provider_uri="~/.qlib/stock_data/source/qlib_cn_1min", region="CN")
+df = D.features(D.instruments("all"), ["$close"], freq="1min")
+
 ```
 
-### Normalize Data
+### US Data
+
+#### 1d
 
 ```bash
-python collector.py normalize_data --source_dir ~/.qlib/stock_data/source --normalize_dir ~/.qlib/stock_data/normalize --region CN
+
+# download from yahoo finance
+python collector.py download_data --source_dir ~/.qlib/stock_data/source/us_1d --region US --start 2020-11-01 --end 2020-11-10 --delay 0.1 --interval 1d
+
+# normalize
+python collector.py normalize_data --source_dir ~/.qlib/stock_data/source/us_1d --normalize_dir ~/.qlib/stock_data/source/us_1d_nor --region US --interval 1d
+
+# dump data
+cd qlib/scripts
+python dump_bin.py dump_all --csv_path ~/.qlib/stock_data/source/cn_1d_nor --qlib_dir ~/.qlib/stock_data/source/qlib_us_1d --freq day --exclude_fields date,adjclose,dividends,splits,symbol
+
+# using
+import qlib
+from qlib.data import D
+
+qlib.init(provider_uri="~/.qlib/stock_data/source/qlib_us_1d", region="US")
+df = D.features(D.instruments("all"), ["$close"], freq="day")
+
 ```
 
+
 ### Help
 ```bash
 pythono collector.py collector_data --help
 ```
 
 ## Parameters
 
-- interval: 1m or 1d
+- interval: 1min or 1d
 - region: CN or US