def divide_manually():
boundary = request.form.get("boundary")
variable_name = request.form.get("variable_name")
branch = request.form.get("branch")
model_name = request.form.get("model_name")
type = request.form.get("type")
df_map = global_value.get_value(model_name + "_" + branch)
df_train = df_map['df_train']
boundary_list = []
if type == "true":
for s in boundary.split(","):
temp = []
temp.extend(map(cmm.transfer, s.split("|")))
boundary_list.append(temp)
columns = ['bin_num', variable_name, 'bads', 'goods', 'total', 'total_perc', 'bad_rate', 'woe',
'type']
else:
for s in boundary.split(","):
boundary_list.append(float(s))
columns = ['bin_num', 'min', 'max', 'min_boundary', 'max_boundary', 'bads', 'goods', 'total', 'total_perc',
'bad_rate', 'woe',
'type']
target = tool_model_service.load_model(model_name=model_name, model_branch=branch)[0]["model_target"]
result = bf.adjust_bin(df_train, type == "true", variable_name, boundary_list
, target=target, expected_column={variable_name})
iv = result['IV'].sum()
df = pd.DataFrame(result,
columns=columns)
data = generate_response(variable_name, df, iv)
return rest.responseto(data=data)
def init():
"""
初始化binning record
:return: dict
格式:
{variable_name1
-var_table
-var_params(province,goods,bads...)
-is_selected
-iv
variable_name2...}
"""
name = request.form.get("modelName")
branch = request.form.get("branch")
# 根据key从内存中获取已上传文件的相关参数
df_map = global_value.get_value(name + "_" + branch)
result = tool_model_service.load_model(model_name=name, model_branch=branch)
# selected_list在数据库中是json格式,在python中是一个dict,格式为:select_variable:index(变量的位置)
selected_list_json = json.loads(result[0].selected_list)
selected_list = selected_list_json.keys()
min_val = 0
df = df_map['df_train']
init_result = get_init(df, target=result[0].model_target, valid=selected_list)
# 根据init_result获得变量的区间
out = get_boundary(init_result, min_val)
# 根据iv排序
out_sorted_iv = sort_iv(out)
return rest.responseto(data=out_sorted_iv)
def init_model_name():
"""
training文件变量初始化页面,将会初始化各个模型的条目供用户选择
:return: [model_name1,model_name2,model_name3]
"""
result = tool_model_service.load_model(is_deleted=0)
# only get model_name form result
result = list(set(map(lambda x: x.model_name, result)))
return rest.responseto(result)
def get_branch_name():
"""
根据模型名称获得分支信息和文件路径
:param: model_name
:return: model_name file_path
"""
model_name = request.args.get("modelName")
result = tool_model_service.load_model(model_name=model_name)
# get model_branch and file_path from result
result = list(map(lambda x: x.model_branch, result))
return rest.responseto(result)
def create_model_name():
model_name = request.args.get("model_name")
if tool_model_service.load_model(model_name=model_name,
model_branch="master") is None:
if tool_model_service.create_branch():
return rest.responseto({
"model_name": model_name,
"model_branch": "master"
})
else:
return rest.responseto("create fail", success=False)
return rest.responseto("name exist", success=False)
def parse():
# 对train文件进行转换,分析
model_name = request.form.get("modelName")
branch = request.form.get("branch")
# 用户指定的文件相对路径
file_path = request.form.get("filePath")
target = request.form.get("target")
root_path = app.config["ROOT_PATH"]
path = root_path + "/" + file_path
# 以模型名称和分支名作为唯一的key
key = model_name + "_" + branch
# df_train = None
# 流程继续下去的前提就是路径是真实存在的
if os.path.exists(path):
# 检查是否已经加载过了
if global_value.has_key(key) is False:
# 重新加载资源
df_all = pd.read_excel(path)
df_train = df_all[df_all['dev_ind'] == 1]
df_test = df_all[df_all['dev_ind'] == 0]
df_map = {
model_name + "_" + branch: {
"df_all": df_all,
"df_train": df_train,
"df_test": df_test
}
}
global_value.set_value(**df_map)
else:
df_map = global_value.get_value(key)
df_train = df_map['df_train']
df = ba.get_df_summary(df_train)
# 得到df_train,将dataframe转换为用于展示前端展示的数据
data_map = cmm.df_for_html(df)
result = tool_model_service.load_model(model_name=model_name,
model_branch=branch)
branches = []
v = result[0]
for n in result:
branches.append(n.model_branch)
# data_map["current_model"] = model_name
data_map["branches"] = branches
data_map["selected_list"] = v.selected_list
data_map["target"] = v.model_target
return rest.responseto(data=data_map)
else:
return rest.responseto(message="file not exist", success=False)
def checkout():
model_name = request.values.get("model_name")
branch = request.values.get("branch")
result = tool_model_service.load_model(model_name=model_name, model_branch = branch)
return rest.responseto(data=result[0])
def get_branch_info():
"""
根据模型名称和分支名称获得target和文件路径
:param:model_name
:return:
"""
model_name = request.args.get("modelName")
branch = request.args.get("branch")
original_branch = request.args.get("originalBranch")
result = tool_model_service.load_model(model_name=model_name,
model_branch=branch)
##数据库找不到对应当前分支的数据,用户希望创建一个新分支
if result.first() == None:
try:
# tool_model_service.create_branch(model_name=model_name, model_branch=branch)
result = tool_model_service.load_binning_record(
model_name, original_branch)
list = []
for record in result:
obj = ModelContent(model_name=model_name,
model_branch=branch,
variable_name=record["variable_name"],
variable_iv=record["variable_iv"],
binning_record=record["binning_record"],
is_selected=record["is_selected"])
list.append(obj)
record = tool_model_service.load_model(
model_name=model_name, model_branch=original_branch)[0]
result = [record]
if tool_model_service.create_branch(
model_name=model_name,
model_branch=branch,
model_target=record["model_target"],
remove_list=record["remove_list"],
selected_list=record["selected_list"]):
tool_model_service.save_binning_record(list)
except Exception:
return rest.responseto(success=False, data="添加分支失败")
target = result.first().model_target
path = result.first().file_path
# df_map = global_value.get_value(model_name+"_"+branch)
selected_file = None
# if path is not None and \
# global_value.has_key(model_name+"_"+branch) is not True\
# and os.path.exists(path):
# df_all = pd.read_excel(path)
# df_train = df_all[df_all['dev_ind'] == 1]
# df_test = df_all[df_all['dev_ind'] == 0]
# df_map = {model_name + "_" + branch:
# {"df_all": df_all,
# "df_train": df_train,
# "df_test": df_test}}
# global_value.set_value(**df_map)
if path is not None:
selected_file = path.replace(app.config["ROOT_PATH"] + "/", "")
files = simple_util.listFile(app.config["ROOT_PATH"], absolute=False)
data = {"target": target, "selected_file": selected_file, "files": files}
return responseto(data)