def code_classify(code_list, classify_list):
"""
按照code整理其所属的classify
"""
f = h5py.File(conf.HDF5_FILE_CLASSIFY, 'a')
console.write_head(conf.HDF5_OPERATE_ARRANGE, conf.HDF5_RESOURCE_TUSHARE,
conf.HDF5_OTHER_CODE_CLASSIFY)
# 获取classify列表
code_classify_df = tool.init_empty_df(["date", "code", "classify"])
today_str = tradetime.get_today()
for ctype in classify_list:
for classify_name in f[ctype]:
if f[ctype][classify_name].get(conf.HDF5_CLASSIFY_DS_CODE) is None:
console.write_msg(classify_name + "的code列表不存在")
classify_df = tool.df_from_dataset(f[ctype][classify_name],
conf.HDF5_CLASSIFY_DS_CODE,
None)
for index, row in classify_df.iterrows():
code = row[0].astype(str)
if code in code_list:
code_dict = dict()
code_dict["date"] = today_str
code_dict["code"] = code
code_dict["classify"] = classify_name
code_classify_df = code_classify_df.append(
code_dict, ignore_index=True)
console.write_tail()
f.close()
f_other = h5py.File(conf.HDF5_FILE_OTHER, 'a')
tool.delete_dataset(f_other, conf.HDF5_OTHER_CODE_CLASSIFY)
tool.merge_df_dataset(f_other, conf.HDF5_OTHER_CODE_CLASSIFY,
code_classify_df)
f_other.close()
return
def bitmex(symbol, bin_size, count):
"""
bitmex期货数据
"""
console.write_head(conf.HDF5_OPERATE_GET, conf.HDF5_RESOURCE_BITMEX,
symbol + '-' + bin_size)
f = h5py.File(conf.HDF5_FILE_BITMEX, 'a')
if f.get(symbol) is None:
f.create_group(symbol)
# 处理D,5,1数据
if bin_size in [
conf.BINSIZE_ONE_DAY,
conf.BINSIZE_ONE_HOUR,
conf.BINSIZE_FIVE_MINUTE,
conf.BINSIZE_ONE_MINUTE,
]:
df = future.history(symbol, bin_size, count)
# 处理30m数据
elif bin_size in [conf.BINSIZE_THIRTY_MINUTE, conf.BINSIZE_FOUR_HOUR]:
df = future.history_merge(symbol, bin_size, count)
if df is not None and df.empty is not True:
# 存储数据暂时不包括macd的内容
# df = df.set_index(conf.HDF5_SHARE_DATE_INDEX)
# index_df = macd.value(df)
# df = df.merge(index_df, left_index=True, right_index=True, how='left')
# df = df.dropna().reset_index()
tool.merge_df_dataset(f[symbol], bin_size, df)
f.close()
console.write_tail()
return
def all_classify_detail(classify_list, omit_list, start_date):
"""
遍历所有分类，聚合所有code获取分类均值
"""
f = h5py.File(conf.HDF5_FILE_SHARE, 'a')
f_classify = h5py.File(conf.HDF5_FILE_CLASSIFY, 'a')
# 获取classify列表
for ctype in classify_list:
for classify_name in f_classify[ctype]:
console.write_head(conf.HDF5_OPERATE_ARRANGE,
conf.HDF5_RESOURCE_TUSHARE, classify_name)
if f_classify[ctype][classify_name].get(
conf.HDF5_CLASSIFY_DS_CODE) is None:
console.write_msg(classify_name + "的detail文件不存在")
continue
for ktype in conf.HDF5_SHARE_KTYPE:
mean_df = one_classify_detail(
f, f_classify[ctype][classify_name].get(
conf.HDF5_CLASSIFY_DS_CODE), omit_list, ktype,
start_date)
ds_name = ktype
# 如果start_date为空，则重置该数据
if start_date is None:
tool.delete_dataset(f_classify[ctype][classify_name],
ds_name)
if mean_df is not None:
tool.merge_df_dataset(f_classify[ctype][classify_name],
ds_name, mean_df)
console.write_tail()
f_classify.close()
f.close()
return
def all_classify(classify_list, init_flag=True):
"""
获取所有分类的macd与所处均线等指标(依赖分类数据聚合)
"""
f = h5py.File(conf.HDF5_FILE_CLASSIFY, 'a')
# 获取classify列表
for ctype in classify_list:
for classify_name in f[ctype]:
console.write_head(conf.HDF5_OPERATE_INDEX,
conf.HDF5_RESOURCE_TUSHARE, classify_name)
for ktype in conf.HDF5_SHARE_KTYPE:
ds_name = ktype
if f[ctype][classify_name].get(ds_name) is None:
console.write_msg(classify_name + "分类聚合detail不存在")
continue
df = tool.df_from_dataset(f[ctype][classify_name], ds_name,
None)
df["close"] = df["close"].apply(lambda x: round(x, 2))
try:
index_df = one_df(df, init_flag, True)
except Exception as er:
console.write_msg("[" + classify_name + "]" + str(er))
continue
index_ds_name = conf.HDF5_INDEX_DETAIL + "_" + ktype
if init_flag is True:
tool.delete_dataset(f[ctype][classify_name], index_ds_name)
tool.merge_df_dataset(f[ctype][classify_name], index_ds_name,
index_df.reset_index())
console.write_tail()
f.close()
return
def all_classify(classify_list, init_flag=True):
"""
整理分类的缠论k线
"""
f = h5py.File(conf.HDF5_FILE_SHARE, 'a')
f_classify = h5py.File(conf.HDF5_FILE_CLASSIFY, 'a')
# 获取classify列表
for ctype in classify_list:
for classify_name in f_classify[ctype]:
console.write_head(conf.HDF5_OPERATE_WRAP,
conf.HDF5_RESOURCE_TUSHARE, classify_name)
for ktype in conf.HDF5_SHARE_WRAP_KTYPE:
ds_name = conf.HDF5_CLASSIFY_DS_DETAIL + "_" + ktype
if f_classify[ctype][classify_name].get(ds_name) is None:
continue
share_df = tool.df_from_dataset(
f_classify[ctype][classify_name], ds_name, None)
wrap_df = one_df(share_df)
wrap_ds_name = conf.HDF5_INDEX_WRAP + "_" + ktype
if init_flag is True:
tool.delete_dataset(f_classify[ctype][classify_name],
wrap_ds_name)
if wrap_df is not None:
tool.merge_df_dataset(f_classify[ctype][classify_name],
wrap_ds_name, wrap_df)
console.write_tail()
f_classify.close()
f.close()
return
def get_from_remote(ktype, stype, start_date, code, rewrite):
"""
从远端获取最新数据
"""
if stype == conf.STYPE_BITMEX:
count = tradetime.get_barnum_by_date(start_date, ktype)
if ktype in [
conf.BINSIZE_ONE_DAY,
conf.BINSIZE_ONE_HOUR,
conf.BINSIZE_FIVE_MINUTE,
conf.BINSIZE_ONE_MINUTE,
]:
df = future.history(code, ktype, count)
elif ktype in [conf.BINSIZE_THIRTY_MINUTE, conf.BINSIZE_FOUR_HOUR]:
df = future.history_merge(code, ktype, count)
if rewrite:
# 将读取的remote数据写回文件
f = h5py.File(conf.HDF5_FILE_BITMEX, 'a')
path = '/' + code
if f.get(path) is None:
f.create(path)
tool.merge_df_dataset(f[path], ktype, df)
f.close()
elif stype == conf.STYPE_ASHARE:
# TODO (重要)，支持ip池并发获取，要不然多code的高频获取过于缓慢
if rewrite:
# backtest时，将读取的hist数据写回文件
df = ts.get_hist_data(code,
ktype=ktype,
pause=conf.REQUEST_BLANK,
start=start_date)
if code.isdigit():
f = h5py.File(conf.HDF5_FILE_SHARE, 'a')
code_prefix = code[0:3]
path = '/' + code_prefix + '/' + code
df = df[tss.SHARE_COLS]
else:
f = h5py.File(conf.HDF5_FILE_INDEX, 'a')
path = '/' + code
df = df[tss.INDEX_COLS]
df = df.reset_index().sort_values(by=[conf.HDF5_SHARE_DATE_INDEX])
tool.merge_df_dataset(f[path], ktype, df)
f.close
else:
# get_k_data无法获取换手率，但是在线监听时，get_k_data存在时间延迟
df = ts.get_k_data(code,
ktype=ktype,
pause=conf.REQUEST_BLANK,
start=start_date)
time.sleep(conf.REQUEST_BLANK)
else:
raise Exception("数据源不存在或未配置")
if df is None and df.empty is True:
raise Exception("无法获取" + code + "-" + ktype + ":" + start_date +
"以后的数据，休息30秒重新获取")
return df
def merge_batch():
global index
if index in batch_dict and batch_dict[index].empty is not True:
f = h5py.File(conf.HDF5_FILE_ERROR)
if f.get(index) is None:
tool.create_df_dataset(f, index, batch_dict[index])
else:
tool.merge_df_dataset(f, index, batch_dict[index])
batch_dict[index].drop(batch_dict[index].index, inplace=True)
return
def get_sz_margins(f, reset_flag=False):
"""
获取深市的融资融券
"""
df = ts.sz_margins(pause=conf.REQUEST_BLANK)
df = df.sort_values(by=["opDate"])
if reset_flag is False:
tool.merge_df_dataset(f, conf.HDF5_FUNDAMENTAL_SZ_MARGINS, df)
else:
tool.create_df_dataset(f, conf.HDF5_FUNDAMENTAL_SZ_MARGINS, df)
return
def get_ipo(f, reset_flag=False):
"""
获取ipo数据
"""
df = ts.new_stocks(pause=conf.REQUEST_BLANK)
df = df.drop("name", axis=1)
df = df.sort_values(by=["ipo_date"])
if reset_flag is False:
tool.merge_df_dataset(f, conf.HDF5_FUNDAMENTAL_IPO, df)
else:
tool.create_df_dataset(f, conf.HDF5_FUNDAMENTAL_IPO, df)
return
def code_detail(code_list, start_date):
"""
将code的basic内容，整理至share文件下
"""
# 获取basic所有日期的detail，并遍历读取详细信息
f = h5py.File(conf.HDF5_FILE_BASIC, 'a')
f_share = h5py.File(conf.HDF5_FILE_SHARE, 'a')
console.write_head(conf.HDF5_OPERATE_ARRANGE, conf.HDF5_RESOURCE_TUSHARE,
conf.HDF5_BASIC_DETAIL)
path = '/' + conf.HDF5_BASIC_DETAIL
if f.get(path) is None:
return
code_basic_dict = dict()
for date in f[path]:
if start_date is not None and date < start_date:
console.write_msg(start_date + "起始日期大于基本数据的最大日期")
continue
df = tool.df_from_dataset(f[path], date, None)
df["code"] = df["code"].str.decode("utf-8")
df = df.set_index("code")
for code in df.index:
if code not in code_list:
continue
if code not in code_basic_dict:
code_basic_dict[code] = tool.init_empty_df(df.columns)
code_basic_dict[code].loc[date] = df.loc[code, :]
for code, code_df in code_basic_dict.items():
code_df.index.name = conf.HDF5_SHARE_DATE_INDEX
code_df = code_df.reset_index().sort_values(
by=[conf.HDF5_SHARE_DATE_INDEX])
code_prefix = code[0:3]
code_group_path = '/' + code_prefix + '/' + code
if f_share.get(code_group_path) is None:
console.write_msg(code + "的detail文件不存在")
continue
if start_date is None:
tool.delete_dataset(f_share[code_group_path],
conf.HDF5_BASIC_DETAIL)
tool.merge_df_dataset(f_share[code_group_path], conf.HDF5_BASIC_DETAIL,
code_df)
console.write_exec()
console.write_blank()
console.write_tail()
f_share.close()
f.close()
return
def all_index(init_flag=True):
"""
整理指数的缠论k线
"""
f = h5py.File(conf.HDF5_FILE_INDEX, 'a')
for code in f:
console.write_head(conf.HDF5_OPERATE_WRAP, conf.HDF5_RESOURCE_TUSHARE,
code)
for ktype in conf.HDF5_SHARE_WRAP_KTYPE:
if f[code].get(ktype) is None:
continue
share_df = tool.df_from_dataset(f[code], ktype, None)
wrap_df = one_df(share_df)
wrap_ds_name = conf.HDF5_INDEX_WRAP + "_" + ktype
if init_flag is True:
tool.delete_dataset(f[code], wrap_ds_name)
if wrap_df is not None:
tool.merge_df_dataset(f[code], wrap_ds_name, wrap_df)
console.write_tail()
f.close()
return
def all_share(omit_list, init_flag=True):
"""
获取所有股票的macd与所处均线等指标
"""
f = h5py.File(conf.HDF5_FILE_SHARE, 'a')
for code_prefix in f:
if code_prefix in omit_list:
continue
console.write_head(conf.HDF5_OPERATE_INDEX, conf.HDF5_RESOURCE_TUSHARE,
code_prefix)
for code in f[code_prefix]:
# 忽略停牌、退市、无法获取的情况
if f[code_prefix][code].attrs.get(
conf.HDF5_BASIC_QUIT) is not None:
continue
if f[code_prefix][code].attrs.get(conf.HDF5_BASIC_ST) is not None:
continue
code_group_path = '/' + code_prefix + '/' + code
for ktype in conf.HDF5_SHARE_KTYPE:
try:
if f.get(code_group_path) is None or f[code_prefix][
code].get(ktype) is None:
console.write_msg(code + "-" + ktype + "的detail不存在")
continue
df = tool.df_from_dataset(f[code_prefix][code], ktype,
None)
index_df = one_df(df, init_flag)
ds_name = conf.HDF5_INDEX_DETAIL + "_" + ktype
if init_flag is True:
tool.delete_dataset(f[code_prefix][code], ds_name)
tool.merge_df_dataset(f[code_prefix][code], ds_name,
index_df.reset_index())
except Exception as er:
print(str(er))
console.write_exec()
console.write_blank()
console.write_tail()
f.close()
return
def all_index(init_flag=True):
"""
处理所有指数的均线与macd
"""
f = h5py.File(conf.HDF5_FILE_INDEX, 'a')
for code in f:
console.write_head(conf.HDF5_OPERATE_INDEX, conf.HDF5_RESOURCE_TUSHARE,
code)
for ktype in conf.HDF5_SHARE_KTYPE:
if f[code].get(ktype) is None:
console.write_msg(code + "-" + ktype + "的detail不存在")
continue
df = tool.df_from_dataset(f[code], ktype, None)
index_df = one_df(df, init_flag)
index_ds_name = conf.HDF5_INDEX_DETAIL + "_" + ktype
if init_flag is True:
tool.delete_dataset(f[code], index_ds_name)
tool.merge_df_dataset(f[code], index_ds_name,
index_df.reset_index())
console.write_tail()
f.close()
return
def all_exec(omit_list):
"""
筛选出存在背离的股票
"""
# 筛选记录内容如下:
# 1. 月线macd趋势
# 2. 周线macd趋势
# 3. 日线macd趋势，是否背离，数值差距
# 4. 30min的macd趋势，是否背离，数值差距，震荡中枢数量
# 5. 5min的macd趋势，是否背离，数值差距，震荡中枢数量
console.write_head(conf.HDF5_OPERATE_SCREEN, conf.HDF5_RESOURCE_TUSHARE,
conf.STRATEGY_TREND_AND_REVERSE)
f = h5py.File(conf.HDF5_FILE_SHARE, 'a')
filter_df = tool.init_empty_df(_ini_filter_columns())
for code_prefix in f:
if code_prefix in omit_list:
continue
for code in f[code_prefix]:
code_group_path = '/' + code_prefix + '/' + code
if f.get(code_group_path) is None:
console.write_blank()
console.write_msg(code + "的tushare数据不存在")
continue
# 忽略停牌、退市、无法获取的情况
if f[code_prefix][code].attrs.get(
conf.HDF5_BASIC_QUIT
) is not None or f[code_prefix][code].attrs.get(
conf.HDF5_BASIC_ST) is not None:
console.write_blank()
console.write_msg(code + "已退市或停牌")
continue
try:
code_dict = code_exec(f, code)
if code_dict is None:
console.write_pass()
continue
else:
console.write_exec()
filter_df = filter_df.append(code_dict, ignore_index=True)
except Exception as er:
console.write_msg("[" + code + "]" + str(er))
f.close()
f_screen = h5py.File(conf.HDF5_FILE_SCREEN, 'a')
if f_screen.get(conf.STRATEGY_TREND_AND_REVERSE) is None:
f_screen.create_group(conf.STRATEGY_TREND_AND_REVERSE)
if f_screen[conf.STRATEGY_TREND_AND_REVERSE].get(
conf.SCREEN_SHARE_FILTER) is None:
f_screen[conf.STRATEGY_TREND_AND_REVERSE].create_group(
conf.SCREEN_SHARE_FILTER)
today_str = tradetime.get_today()
tool.delete_dataset(
f_screen[conf.STRATEGY_TREND_AND_REVERSE][conf.SCREEN_SHARE_FILTER],
today_str)
tool.merge_df_dataset(
f_screen[conf.STRATEGY_TREND_AND_REVERSE][conf.SCREEN_SHARE_FILTER],
today_str, filter_df)
f_screen.close()
console.write_blank()
console.write_tail()
return
def mark_grade(today_str=None):
"""
对筛选结果进行打分
"""
console.write_head(conf.HDF5_OPERATE_SCREEN, conf.HDF5_RESOURCE_TUSHARE,
conf.SCREEN_SHARE_GRADE)
f = h5py.File(conf.HDF5_FILE_SCREEN, 'a')
f_share = h5py.File(conf.HDF5_FILE_SHARE, 'a')
if today_str is None:
today_str = tradetime.get_today()
if f[conf.STRATEGY_TREND_AND_REVERSE][conf.SCREEN_SHARE_FILTER].get(
today_str) is None:
console.write_msg(today_str + "个股筛选结果不存在")
return
grade_df = tool.init_empty_df([
"code", "status", "d_price_space", "d_price_per", "30_price_space",
"30_price_per", "d_macd", "30_macd"
])
screen_df = tool.df_from_dataset(
f[conf.STRATEGY_TREND_AND_REVERSE][conf.SCREEN_SHARE_FILTER],
today_str, None)
screen_df["d_m_status"] = screen_df["d_m_status"].str.decode("utf-8")
screen_df["w_m_status"] = screen_df["w_m_status"].str.decode("utf-8")
screen_df["m_m_status"] = screen_df["m_m_status"].str.decode("utf-8")
screen_df["code"] = screen_df["code"].str.decode("utf-8")
for index, row in screen_df.iterrows():
code = row["code"]
grade_dict = dict()
grade_dict["code"] = code
grade_dict["status"] = 0
grade_dict["status"] += _status_grade(row["d_m_status"])
grade_dict["status"] += _status_grade(row["w_m_status"])
grade_dict["status"] += _status_grade(row["m_m_status"])
code_prefix = code[0:3]
code_group_path = '/' + code_prefix + '/' + code
for ktype in ["D", "30"]:
detail_ds_name = ktype
index_ds_name = conf.HDF5_INDEX_DETAIL + "_" + ktype
if f_share[code_group_path].get(detail_ds_name) is None:
console.write_msg(code + "的detail数据不存在")
continue
if f_share[code_group_path].get(index_ds_name) is None:
console.write_msg(code + "的index数据不存在")
continue
detail_df = tool.df_from_dataset(f_share[code_group_path],
detail_ds_name, None)
index_df = tool.df_from_dataset(f_share[code_group_path],
index_ds_name, None)
latest_price = detail_df.tail(1)["close"].values[0]
latest_macd = index_df.tail(1)["macd"].values[0]
diverse_price_start = row[str.lower(ktype) +
INDEX_MACD_DIVERSE_PRICE_START]
if diverse_price_start == 0:
grade_dict[str.lower(ktype) + "_price_space"] = 0
grade_dict[str.lower(ktype) + "_price_per"] = 0
else:
grade_dict[str.lower(ktype) + "_price_space"] = round(
diverse_price_start - latest_price, 2)
grade_dict[str.lower(ktype) + "_price_per"] = round(
grade_dict[str.lower(ktype) + "_price_space"] * 100 /
diverse_price_start, 2)
grade_dict[str.lower(ktype) + "_macd"] = latest_macd
grade_df = grade_df.append(grade_dict, ignore_index=True)
if f[conf.STRATEGY_TREND_AND_REVERSE].get(conf.SCREEN_SHARE_GRADE) is None:
f[conf.STRATEGY_TREND_AND_REVERSE].create_group(
conf.SCREEN_SHARE_GRADE)
tool.delete_dataset(
f[conf.STRATEGY_TREND_AND_REVERSE][conf.SCREEN_SHARE_GRADE], today_str)
tool.merge_df_dataset(
f[conf.STRATEGY_TREND_AND_REVERSE][conf.SCREEN_SHARE_GRADE], today_str,
grade_df)
f_share.close()
f.close()
console.write_tail()
return
