def predict_data_process(trigger_file, role_file, schema_file, save_path):
"""predict_data_process"""
pred_ret = []
trigger_datas = read_by_lines(trigger_file)
role_data = read_by_lines(role_file)
schema_datas = read_by_lines(schema_file)
print("trigger predict {} load from {}".format(len(trigger_datas),
trigger_file))
print("role predict {} load from {}".format(len(role_data), role_file))
print("schema {} load from {}".format(len(schema_datas), schema_file))
schema = {}
for s in schema_datas:
d_json = json.loads(s)
schema[d_json["event_type"]] = [r["role"] for r in d_json["role_list"]]
# process the role data
sent_role_mapping = {}
for d in role_data:
d_json = json.loads(d)
r_ret = extract_result(d_json["text"], d_json["pred"]["labels"])
role_ret = {}
for r in r_ret:
role_type = r["type"]
if role_type not in role_ret:
role_ret[role_type] = []
role_ret[role_type].append("".join(r["text"]))
sent_role_mapping[d_json["id"]] = role_ret
for d in trigger_datas:
d_json = json.loads(d)
t_ret = extract_result(d_json["text"], d_json["pred"]["labels"])
pred_event_types = list(set([t["type"] for t in t_ret]))
event_list = []
for event_type in pred_event_types:
role_list = schema[event_type]
arguments = []
for role_type, ags in sent_role_mapping[d_json["id"]].items():
if role_type not in role_list:
continue
for arg in ags:
if len(arg) == 1:
continue
arguments.append({"role": role_type, "argument": arg})
event = {"event_type": event_type, "arguments": arguments}
event_list.append(event)
pred_ret.append({
"id": d_json["id"],
"text": d_json["text"],
"event_list": event_list
})
pred_ret = [json.dumps(r, ensure_ascii=False) for r in pred_ret]
print("submit data {} save to {}".format(len(pred_ret), save_path))
write_by_lines(save_path, pred_ret)
def subscribe(self, symbol, func=None, fields="", data_format=""):
"""Subscribe securites
This function adds new securities to subscribed list on the server. If
success, return subscribed codes.
If securities is empty, return current subscribed codes.
"""
r, msg = self._check_session()
if not r:
return (r, msg)
if func:
self._on_jsq_callback = func
rpc_params = {"symbol": symbol, "fields": fields}
cr = self._remote.call("jsq.subscribe", rpc_params)
rsp, msg = utils.extract_result(cr,
data_format="",
class_name="SubRsp")
if not rsp:
return (rsp, msg)
new_codes = [x.strip() for x in symbol.split(',') if x]
self._subscribed_set = self._subscribed_set.union(set(new_codes))
self._schema_id = rsp['schema_id']
self._schema = rsp['schema']
self._sub_hash = rsp['sub_hash']
return (rsp['securities'], msg)
def _do_subscribe(self):
"""Subscribe again when reconnected or hash_code is not same"""
if not self._subscribed_set: return
codes = list(self._subscribed_set)
codes.sort()
# XXX subscribe with default fields!
rpc_params = {"symbol": ",".join(codes), "fields": ""}
cr = self._remote.call("jsq.subscribe", rpc_params)
rsp, msg = utils.extract_result(cr,
data_format="",
class_name="SubRsp")
if not rsp:
#return (rsp, msg)
return
self._schema_id = rsp['schema_id']
self._schema = rsp['schema']
self._sub_hash = rsp['sub_hash']
#return (rsp.securities, msg)
self._make_schema_map()
def batch_order(self, orders, algo="", algo_param={}, userdata=""):
"""
orders format:
[ {"security": "000001.SZ", "action": "Buy", "price": 10.0, "size" : 100}, ... ]
return (result, message)
if result is None, message contains error information
"""
if not orders or not isinstance(orders, (list, tuple)):
return (None, "empty order")
if isinstance(orders[0], EntrustOrder):
tmp = []
for o in orders:
tmp.append({
"security": o.security,
"price": o.price,
"size": int(o.size)
})
orders = tmp
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {
"orders": orders,
"algo": algo,
"algo_param": json.dumps(algo_param),
"user": self._username,
"userdata": userdata
}
cr = self._remote.call("oms.batch_order", rpc_params)
return utils.extract_result(cr)
def place_order(self,
security,
action,
price,
size,
algo="",
algo_param={},
userdata=""):
"""
return (result, message)
if result is None, message contains error information
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {
"security": security,
"action": action,
"price": price,
"size": int(size),
"algo": algo,
"algo_param": json.dumps(algo_param),
"user": self._username,
"userdata": userdata
}
cr = self._remote.call("oms.place_order", rpc_params)
return utils.extract_result(cr)
def basket_order(self, orders, algo="", algo_param={}, userdata=""):
"""
orders format:
[ {"security": "000001.SZ", "ref_price": 10.0, "inc_size" : 100}, ...]
return (result, message)
if result is None, message contains error information
"""
r, msg = self._check_session()
if not r: return (False, msg)
if type(orders) is pd.core.frame.DataFrame:
tmp = []
for i in xrange(0, len(orders)):
tmp.append({
'security': orders.index[i],
'ref_price': float(orders['ref_price'][i]),
"inc_size": int(orders['inc_size'][i])
})
orders = tmp
rpc_params = {
"orders": orders,
"algo": algo,
"algo_param": json.dumps(algo_param),
"user": self._username,
"userdata": userdata
}
cr = self._remote.call("pms.basket_order", rpc_params)
return utils.extract_result(cr)
def logout(self):
self._loggined = None
rpc_params = {}
cr = self._remote.call("auth.logout", rpc_params)
return utils.extract_result(cr)
def logout(self):
"""
Logout to stop using the data api or switch users.
"""
self._loggined = None
rpc_params = {}
cr = self._remote.call("auth.logout", rpc_params)
return utils.extract_result(cr)
def _do_use_strategy(self):
if self._strategy_id:
rpc_params = {"account_id": self._strategy_id}
cr = self._remote.call("auth.use_strategy", rpc_params)
r, msg = utils.extract_result(cr)
self._strategy_selected = r
return (r, msg)
else:
return (False, "-1,no strategy_id was specified")
def stop_portfolio(self):
"""
return (result, message)
if result is None, message contains error information
"""
r, msg = self._check_session()
if not r: return (False, msg)
rpc_params = {}
cr = self._remote.call("pms.stop_portfolio", rpc_params)
return utils.extract_result(cr)
def cancel_order(self, task_id):
"""
return (result, message)
if result is None, message contains error information
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {"task_id": task_id}
cr = self._remote.call("oms.cancel_order", rpc_params)
return utils.extract_result(cr)
def use_strategy(self, strategy_id):
if strategy_id:
self._strategy_id = strategy_id
return self._do_use_strategy()
else:
# Query
rpc_params = {"account_id": 0}
cr = self._remote.call("auth.use_strategy", rpc_params)
r, msg = utils.extract_result(cr)
self._strategy_selected = r
return (r, msg)
def query_universe(self, format=""):
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {}
data_format = self._get_format(format, "pandas")
if data_format == "pandas":
rpc_params["format"] = "columnset"
cr = self._remote.call("oms.query_universe", rpc_params)
return utils.extract_result(cr,
format=data_format,
class_name="UniverseItem")
def _call_rpc(self, method, data_format, data_class, **kwargs):
r, msg = self._check_session()
if not r:
return (r, msg)
rpc_params = {}
for kw in kwargs.items():
rpc_params[str(kw[0])] = kw[1]
cr = self._remote.call(method, rpc_params)
return utils.extract_result(cr,
data_format=data_format,
class_name=data_class)
def query_repo_contract(self, format=""):
"""
securities: seperate by ","
return pd.dataframe
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {}
cr = self._remote.call("oms.query_repo_contract", rpc_params)
return utils.extract_result(cr,
format=self._get_format(format, "pandas"),
class_name="RepoContract")
def _do_login(self, format=""):
# Shouldn't check connected flag here. ZMQ is a mesageq queue!
# if !self._connected :
# return (False, "-1,no connection")
if self._username and self._password:
rpc_params = {
"username": self._username,
"password": self._password
}
cr = self._remote.call("auth.login", rpc_params)
f = self._get_format(format, "")
if f != "obj" and f != "":
f = ""
return utils.extract_result(cr, format=f, class_name="UserInfo")
else:
return (False, "-1,empty username or password")
def query_trade(self, task_id=-1, format=""):
"""
task_id: -1 -- all
return pd.dataframe
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {"task_id": task_id}
data_format = self._get_format(format, "pandas")
if data_format == "pandas":
rpc_params["format"] = "columnset"
cr = self._remote.call("oms.query_trade", rpc_params)
return utils.extract_result(cr, format=data_format, class_name="Trade")
def query_account(self, format=""):
"""
return pd.dataframe
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {}
data_format = self._get_format(format, "pandas")
if data_format == "pandas":
rpc_params["format"] = "columnset"
cr = self._remote.call("oms.query_account", rpc_params)
return utils.extract_result(cr,
format=data_format,
class_name="Account")
def _call_rpc(self, method, data_format, data_class, **kwargs):
r, msg = self._check_session()
if not r:
return (r, msg)
index_column = None
rpc_params = {}
for kw in kwargs.items():
if str(kw[0]) == "_index_column":
index_column = kw[1]
else:
rpc_params[str(kw[0])] = kw[1]
cr = self._remote.call(method, rpc_params, timeout=self._timeout)
return utils.extract_result(cr,
data_format=data_format,
index_column=index_column,
class_name=data_class)
def _do_login(self):
# Shouldn't check connected flag here. ZMQ is a mesageq queue!
# if !self._connected :
# return (False, "-1,no connection")
if self._username and self._password:
rpc_params = {
"username": self._username,
"password": self._password
}
cr = self._remote.call("auth.login", rpc_params)
r, msg = utils.extract_result(cr,
data_format="",
class_name="UserInfo")
self._loggined = r
return (r, msg)
else:
self._loggined = None
return (False, "-1,empty username or password")
def query_net_position(self, mode="all", securities="", format=""):
"""
securities: seperate by ","
return pd.dataframe
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {"mode": mode, "security": securities}
data_format = self._get_format(format, "pandas")
if data_format == "pandas":
rpc_params["format"] = "columnset"
cr = self._remote.call("oms.query_net_position", rpc_params)
return utils.extract_result(cr,
format=data_format,
class_name="NetPosition")
def query_portfolio(self, format=""):
"""
return pd.dataframe
"""
r, msg = self._check_session()
if not r: return (None, msg)
rpc_params = {}
data_format = self._get_format(format, "pandas")
if data_format == "pandas":
rpc_params["format"] = "columnset"
cr = self._remote.call("pms.query_portfolio", rpc_params)
return utils.extract_result(cr,
index_column="security",
format=data_format,
class_name="NetPosition")
def predict_data_process(trigger_file, role_file, schema_file, save_path):
"""predict_data_process"""
pred_ret = []
trigger_datas = read_by_lines(trigger_file)
role_data = read_by_lines(role_file)
schema_datas = read_by_lines(schema_file)
print("trigger predict {} load from {}".format(len(trigger_datas),
trigger_file))
print("role predict {} load from {}".format(len(role_data), role_file))
print("schema {} load from {}".format(len(schema_datas), schema_file))
schema = {}
for s in schema_datas:
d_json = json.loads(s)
schema[d_json["event_type"]] = [
r["role"] for r in d_json["role_list"]
] # 字典：key-event_type，value-role_list， {event_type: [role1, role2, ...]}
# process the role data
sent_role_mapping = {}
for d in role_data:
d_json = json.loads(d)
r_ret = extract_result(d_json["text"], d_json["pred"]["labels"])
role_ret = {}
for r in r_ret: # 对每个预测到的论元组，即字典{'start': , 'text': , 'type': }
role_type = r["type"] # 获取预测的role
if role_type not in role_ret:
role_ret[role_type] = []
role_ret[role_type].append(
"".join(r["text"])
) # 汇集论元对应的实例化的词，即{'role_type': [role_arg1, role_arg2, ...]}
sent_role_mapping[d_json[
"id"]] = role_ret # 当前句子的{id : {'role_type': [role_arg1, role_arg2, ...]}}
for d in trigger_datas:
d_json = json.loads(d)
t_ret = extract_result(
d_json["text"],
d_json["pred"]["labels"]) # [{'start': , 'text': , 'type': }, ...]
pred_event_types = list(set([
t["type"] for t in t_ret
])) # 获取预测的trigger类型，即事件类型。利用触发词来拿到事件类型，一个句子可以有多个事件类型，所以用了序列标注的方法
event_list = []
for event_type in pred_event_types:
role_list = schema[event_type]
arguments = []
for role_type, ags in sent_role_mapping[d_json["id"]].items():
if role_type not in role_list: # 这里的判断可以排除理应不在本事件类型中出现的论元；我们只关心本事件类型出现的论元是否被预测到
continue
for arg in ags:
if len(arg) == 1:
continue
arguments.append({"role": role_type, "argument": arg})
event = {"event_type": event_type, "arguments": arguments}
event_list.append(event)
pred_ret.append({
"id": d_json["id"],
"text": d_json["text"],
"event_list": event_list
})
pred_ret = [
json.dumps(r, ensure_ascii=False) for r in pred_ret
] # 最后的预测数据里的event_list是没有index的，只有event_type, {role, argument}
print("submit data {} save to {}".format(len(pred_ret), save_path))
write_by_lines(save_path, pred_ret)
def predict_data_process(trigger_file, role_file, enum_file, schema_file,
save_path):
"""predict_data_process"""
pred_ret = []
trigger_data = read_by_lines(trigger_file)
role_data = read_by_lines(role_file)
enum_data = read_by_lines(enum_file)
schema_data = read_by_lines(schema_file)
print("trigger predict {} load from {}".format(len(trigger_data),
trigger_file))
print("role predict {} load from {}".format(len(role_data), role_file))
print("enum predict {} load from {}".format(len(enum_data), enum_file))
print("schema {} load from {}".format(len(schema_data), schema_file))
schema, sent_role_mapping, sent_enum_mapping = {}, {}, {}
for s in schema_data:
d_json = json.loads(s)
schema[d_json["event_type"]] = [r["role"] for r in d_json["role_list"]]
# role depends on id and sent_id
for d in role_data:
d_json = json.loads(d)
r_ret = extract_result(d_json["text"], d_json["pred"]["labels"])
role_ret = {}
for r in r_ret:
role_type = r["type"]
if role_type not in role_ret:
role_ret[role_type] = []
role_ret[role_type].append("".join(r["text"]))
_id = "{}\t{}".format(d_json["id"], d_json["sent_id"])
sent_role_mapping[_id] = role_ret
# process the enum_role data
for d in enum_data:
d_json = json.loads(d)
_id = "{}\t{}".format(d_json["id"], d_json["sent_id"])
label = d_json["pred"]["label"]
sent_enum_mapping[_id] = label
# process trigger data
for d in trigger_data:
d_json = json.loads(d)
t_ret = extract_result(d_json["text"], d_json["pred"]["labels"])
pred_event_types = list(set([t["type"] for t in t_ret]))
event_list = []
_id = "{}\t{}".format(d_json["id"], d_json["sent_id"])
for event_type in pred_event_types:
role_list = schema[event_type]
arguments = []
for role_type, ags in sent_role_mapping[_id].items():
if role_type not in role_list:
continue
for arg in ags:
arguments.append({"role": role_type, "argument": arg})
# 特殊处理环节
if event_type == enum_event_type:
arguments.append({
"role": enum_role,
"argument": sent_enum_mapping[_id]
})
event = {
"event_type": event_type,
"arguments": arguments,
"text": d_json["text"]
}
event_list.append(event)
pred_ret.append({
"id": d_json["id"],
"sent_id": d_json["sent_id"],
"text": d_json["text"],
"event_list": event_list
})
doc_pred = {}
for d in pred_ret:
if d["id"] not in doc_pred:
doc_pred[d["id"]] = {"id": d["id"], "event_list": []}
doc_pred[d["id"]]["event_list"].extend(d["event_list"])
# unfiy the all prediction results and save them
doc_pred = [
json.dumps(event_normalization(r), ensure_ascii=False)
for r in doc_pred.values()
]
print("submit data {} save to {}".format(len(doc_pred), save_path))
write_by_lines(save_path, doc_pred)
