447 lines
22 KiB
Python
447 lines
22 KiB
Python
import json
|
|
import time
|
|
import requests
|
|
|
|
import pandas as pd
|
|
|
|
from common.scripts import file_path, read_json_file, sub_dict, df_iterrows
|
|
from company.db import find_data_in_tyc, insert_data_to_tfse, find_data_in_tfse
|
|
from rating.scripts.risk_detail import associate_risk_detail, change_log_detail
|
|
|
|
|
|
def drag_company_data_request(company_name):
|
|
"""
|
|
从天眼查接口获取企业数据
|
|
Parameters:
|
|
company_name: 企业名称
|
|
Returns:
|
|
-
|
|
"""
|
|
url = "http://139.9.249.34:51009/api/tyc/drag_data"
|
|
headers = {'token': "uzdq51N4!I0%HY4sCaQ!aeCSIDIVIdAM"}
|
|
data = {"企业名称": company_name}
|
|
res = requests.post(url=url, headers=headers, data=json.dumps(data))
|
|
if res.status_code == 200:
|
|
return "企业数据拉取成功"
|
|
else:
|
|
return "企业数据拉取失败"
|
|
|
|
|
|
def basic_info_etl(cid, company_name):
|
|
"""
|
|
根据企业名称，查询天眼查数据库
|
|
将数据按规定格式存储到股交企业数据库中
|
|
Parameters:
|
|
cid: 企业ID
|
|
company_name: 企业名称
|
|
Returns:
|
|
-
|
|
"""
|
|
# Params
|
|
basic_info = find_data_in_tyc('公司背景', '基本信息', {"企业名称": company_name})
|
|
holder_info = find_data_in_tyc('公司背景', '企业股东', {"企业名称": company_name})
|
|
member_info = find_data_in_tyc('公司背景', '主要人员', {"企业名称": company_name})
|
|
|
|
# Returns
|
|
data = read_json_file(file_path('/company/static/template/基本信息.json'))
|
|
|
|
# 处理工商信息
|
|
def business_data():
|
|
data['企业ID'] = cid
|
|
data['更新日期'] = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
|
|
data['企业名称'] = basic_info[0]['企业名称']
|
|
data['工商信息']['企业状态'] = basic_info[0]['基本信息']['regStatus']
|
|
data['工商信息']['法定代表人'] = basic_info[0]['基本信息']['legalPersonName']
|
|
data['工商信息']['企业类型'] = basic_info[0]['基本信息']['companyOrgType']
|
|
data['工商信息']['纳税人识别号'] = basic_info[0]['基本信息']['taxNumber']
|
|
data['工商信息']['经营范围'] = basic_info[0]['基本信息']['businessScope']
|
|
data['工商信息']['注册资本'] = basic_info[0]['基本信息']['regCapital']
|
|
data['工商信息']['实缴资本'] = basic_info[0]['基本信息']['actualCapital']
|
|
data['工商信息']['注册地址'] = basic_info[0]['基本信息']['regLocation']
|
|
data['工商信息']['登记机关'] = basic_info[0]['基本信息']['regInstitute']
|
|
data['工商信息']['行业'] = basic_info[0]['基本信息']['industry']
|
|
data['工商信息']['人员规模'] = basic_info[0]['基本信息']['staffNumRange']
|
|
data['工商信息']['参保人数'] = basic_info[0]['基本信息']['socialStaffNum']
|
|
data['工商信息']['小微企业'] = "是" if basic_info[0]['基本信息']['regStatus'] == 1 else "否"
|
|
|
|
# 处理股东信息
|
|
def share_holders():
|
|
data['股东信息'] = []
|
|
for holder in holder_info[0]['企业股东']['result']:
|
|
info = dict()
|
|
info['股东'] = holder['name']
|
|
info['股东类型'] = "公司" if holder['type'] == 1 else ("个人" if holder['type'] == 2 else "其他")
|
|
|
|
if holder['capital']:
|
|
info['持股比例'] = None if holder['capital'][0]['percent'] == '' else holder['capital'][0]['percent']
|
|
info['认缴金额'] = None if holder['capital'][0]['amomon'] == '' else holder['capital'][0]['amomon']
|
|
info['认缴日期'] = None if holder['capital'][0]['time'] == '' else holder['capital'][0]['time']
|
|
else:
|
|
info['持股比例'] = None
|
|
info['认缴金额'] = None
|
|
info['认缴日期'] = None
|
|
|
|
if holder['capitalActl']:
|
|
info['实缴金额'] = []
|
|
info['实缴方式'] = []
|
|
info['实缴时间'] = []
|
|
for capital_actl in holder['capitalActl']:
|
|
info['实缴金额'].append(capital_actl['amomon'])
|
|
info['实缴方式'].append(capital_actl['paymet'])
|
|
info['实缴时间'].append(capital_actl['time'])
|
|
else:
|
|
info['实缴金额'] = []
|
|
info['实缴方式'] = []
|
|
info['实缴时间'] = []
|
|
|
|
data['股东信息'].append(info)
|
|
|
|
# 处理主要成员信息
|
|
def main_members():
|
|
data['主要成员'] = []
|
|
for member in member_info[0]['主要人员']['result']:
|
|
info = dict()
|
|
info['姓名'] = member['name']
|
|
info['职务'] = member['typeJoin']
|
|
data['主要成员'].append(info)
|
|
|
|
# 保存处理后的数据
|
|
def save_result():
|
|
insert_data_to_tfse('企业', '公司基本信息', data)
|
|
|
|
# 执行方法
|
|
business_data()
|
|
share_holders()
|
|
main_members()
|
|
save_result()
|
|
|
|
|
|
def general_rating_etl(rid):
|
|
"""
|
|
执行综合信用评价信息数据清洗程序
|
|
Parameters:
|
|
rid: str 评价ID
|
|
Returns:
|
|
res: desc
|
|
"""
|
|
|
|
# Parameters
|
|
rating_result = find_data_in_tfse('评价', '评价结果', {"评价ID": rid})[0]
|
|
rating_record = find_data_in_tfse('评价', '评价结果', {"企业ID": rating_result['企业ID']})
|
|
df_records = pd.DataFrame(rating_record).sort_values('评价时间', ascending=False)
|
|
|
|
# Returns
|
|
result = dict()
|
|
|
|
# 根据rid 查询评价日期、信用等级、信用分数
|
|
result['企业ID'] = rating_result['企业ID']
|
|
result['企业名称'] = rating_result['企业名称']
|
|
result['更新时间'] = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
|
|
|
|
# 综合信用等级数据
|
|
result_general = result['综合信用等级'] = dict()
|
|
result_general['评价时间'] = rating_result['评价时间']
|
|
result_general['信用等级'] = rating_result['信用等级']
|
|
result_general['信用评分'] = rating_result['信用评分']
|
|
|
|
# 评级历史数据
|
|
df_records['变化趋势'] = (df_records['信用评分'] - df_records['信用评分'].shift(-1)).apply(lambda x: '下降' if x < 0 else ('上升' if x > 0 else ('维持' if x == 0 else '-')))
|
|
result['历史级别'] = list(json.loads(df_records[['信用等级', "信用评分", '评价时间', "评价方式", "变化趋势"]].T.to_json()).values())
|
|
|
|
# 生成雷达图数据
|
|
rating_score = dict()
|
|
rating_score["环境"] = rating_result['经营评分']["环境"]
|
|
rating_score["社会责任"] = rating_result['经营评分']["社会责任"]
|
|
rating_score["公司治理"] = rating_result['经营评分']["公司治理"]
|
|
rating_score["盈利能力"] = rating_result['财务评分']["盈利能力"]['合计']
|
|
rating_score["资产质量"] = rating_result['财务评分']["资产质量"]['合计']
|
|
rating_score["债务风险"] = rating_result['财务评分']["债务风险"]['合计']
|
|
rating_score["经营增长"] = rating_result['财务评分']["经营增长"]['合计']
|
|
rating_score["合规风险"] = 43 - rating_result['风险评分']["合规风险"]
|
|
rating_score["经营风险"] = 10 - rating_result['风险评分']["经营风险"]['合计']
|
|
rating_score["关联风险"] = 10 - rating_result['风险评分']["关联风险"]['合计']
|
|
|
|
score_max = {
|
|
"环境": 10,
|
|
"社会责任": 10,
|
|
"公司治理": 10,
|
|
"盈利能力": 16,
|
|
"资产质量": 18,
|
|
"债务风险": 18,
|
|
"经营增长": 18,
|
|
"合规风险": 43,
|
|
"经营风险": 10,
|
|
"关联风险": 10
|
|
}
|
|
|
|
result['综合信用表现'] = dict()
|
|
result['综合信用表现']['指标雷达'] = dict()
|
|
result['综合信用表现']['指标雷达']['指标得分'] = rating_score
|
|
result['综合信用表现']['指标雷达']['最大分数'] = score_max
|
|
|
|
# 生成指标表格数据
|
|
result['指标表格'] = dict()
|
|
|
|
result['指标表格']['财务指标'] = dict()
|
|
result['指标表格']['风险指标'] = dict()
|
|
|
|
df_operate = pd.DataFrame({'实际值': sub_dict(rating_result['经营评分'], ['环境', '社会责任', '公司治理']), '最大值': {'环境': 10, '社会责任': 10, '公司治理': 10}})
|
|
result['指标表格']['经营指标'] = json.loads((df_operate['实际值'] / df_operate['最大值']).apply(lambda x: '优' if x >= 1 else ('良' if x >= 0.75 else ('中' if x >= 0.5 else ('低' if x >= 0.25 else '差')))).to_json())
|
|
|
|
financial = dict()
|
|
financial['盈利能力'] = rating_result['财务评分']['盈利能力']['合计']
|
|
financial['资产质量'] = rating_result['财务评分']['资产质量']['合计']
|
|
financial['债务风险'] = rating_result['财务评分']['债务风险']['合计']
|
|
financial['经营增长'] = rating_result['财务评分']['经营增长']['合计']
|
|
df_financial = pd.DataFrame({'实际值': financial, '最大值': {"盈利能力": 16, "资产质量": 18, "债务风险": 18, "经营增长": 18}})
|
|
result['指标表格']['财务指标'] = json.loads((df_financial['实际值'] / df_financial['最大值']).apply(lambda x: '优' if x >= 1 else ('良' if x >= 0.75 else ('中' if x >= 0.5 else ('低' if x >= 0.25 else '差')))).to_json())
|
|
|
|
risks = dict()
|
|
risks['合规风险'] = 43 - rating_result['风险评分']['合规风险']
|
|
risks['经营风险'] = 10 - rating_result['风险评分']['经营风险']['合计']
|
|
risks['关联风险'] = 10 - rating_result['风险评分']['关联风险']['合计']
|
|
df_risks = pd.DataFrame({'实际值': risks, '最大值': {"合规风险": 43, "经营风险": 10, "关联风险": 10}})
|
|
result['指标表格']['风险指标'] = json.loads((df_risks['实际值'] / df_risks['最大值']).apply(lambda x: '优' if x >= 1 else ('良' if x >= 0.75 else ('中' if x >= 0.5 else ('低' if x >= 0.25 else '差')))).to_json())
|
|
|
|
# 生成信用分析数据
|
|
result['信用分析'] = dict()
|
|
result['信用分析']['经营分析'] = '经营分析是利用会计核算、统计核算、业务以及其他方面提供的数据信息，。。。。'
|
|
result['信用分析']['财务分析'] = '财务分析是以会计核算和报表资料及其他相关资料为依据，采用一系列专门的分析技术和方法，对企业等经济组织过去和现在有关筹资活动、投资活动、经营活动、分配活动的盈利能力、营运能力、偿债能力和增长能力状况等进行分析与评价的经济管理活动。'
|
|
result['信用分析']['风险分析'] = '风险分析有狭义和广义两种，狭义的风险分析是指通过定量分析的方法给出完成任务所需的费用、进度、性能三个随机变量的可实现值的概率分布。 而广义的风险分析则是一种识别和测算风险，开发、选择和管理方案来解决这些风险的有组织的手段。 它包括风险识别、风险评估和风险管理三方面的内容。 本文中论及风险分析时，都采用后一种定义。'
|
|
result['信用分析']['评价意见'] = '评价意见是指在掌握大量数据资料的基础上，对经过筛选后的少数方案再具体化，通过进一步的调查、研究和评价，最后选出最令人满意的方案，其评价结论是方案审批的依据。'
|
|
result['信用分析']['查看报告'] = '/file/get_company_report?file_id=61bc4c4733120000ce000695'
|
|
|
|
insert_data_to_tfse('企业', '综合评价分析', result)
|
|
|
|
|
|
def financial_analysis(rid):
|
|
"""
|
|
Notes
|
|
Parameters:
|
|
-
|
|
Returns:
|
|
res: desc
|
|
"""
|
|
|
|
# Parameters
|
|
rating_result = find_data_in_tfse('评价', '评价结果', {"评价ID": rid})[0]
|
|
rating_input = find_data_in_tfse('评价', '综合评价填报', {"评价ID": rid})[0]
|
|
industry = rating_input['行业选择']
|
|
periods = list(pd.DataFrame(rating_input['财务填报']['资产负债表']).sort_values('报告期', ascending=False)['报告期'][0:2].values)
|
|
df_recent_2year = pd.DataFrame(find_data_in_tfse('企业', '指标明细', {'企业ID': rating_result['企业ID']})).sort_values('年报期', ascending=False)[0:2]
|
|
df_this = df_recent_2year[0:1]
|
|
df_last = df_recent_2year[1:2]
|
|
|
|
# Returns
|
|
result = dict()
|
|
result['企业ID'] = rating_result['企业ID']
|
|
# 财报期
|
|
result['财报期'] = periods[0]
|
|
# 更新日期
|
|
result['更新日期'] = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
|
|
|
|
# 与行业平均对比
|
|
score_avg = {
|
|
"盈利能力": 8,
|
|
"资产质量": 9,
|
|
"债务风险": 9,
|
|
"经营增长": 9
|
|
}
|
|
score_actl = {
|
|
"盈利能力": rating_result['财务评分']['盈利能力']['合计'],
|
|
"资产质量": rating_result['财务评分']['资产质量']['合计'],
|
|
"债务风险": rating_result['财务评分']['债务风险']['合计'],
|
|
"经营增长": rating_result['财务评分']['经营增长']['合计']
|
|
}
|
|
|
|
# 与去年对比
|
|
data_last = list(json.loads(df_last[['净资产收益率', '存货周转率', '已获利息倍数', '应收账款周转率', '总资产周转率', '总资产增长率', '总资产报酬率', '技术投入比率', '营业增长率', '资产负债率', '速动比率']].T.to_json()).values())
|
|
url = "http://139.9.249.34:51012/tfse_rating/rating/financial_score"
|
|
headers = {'token': "X0gSlC!YE8jmr2jJr&ilcjS83j!tsoh5", "content-type": "application/json"}
|
|
data = {"财务指标": data_last, "所属行业": industry}
|
|
score_last_origin = json.loads(requests.post(url=url, headers=headers, data=json.dumps(data)).text)['result']
|
|
score_last = {
|
|
"盈利能力": score_last_origin['盈利能力']['合计'],
|
|
"资产质量": score_last_origin['资产质量']['合计'],
|
|
"债务风险": score_last_origin['债务风险']['合计'],
|
|
"经营增长": score_last_origin['经营增长']['合计']
|
|
}
|
|
|
|
df = pd.DataFrame({'今年值': score_actl, '去年值': score_last, "平均值": score_avg})
|
|
|
|
# 同行对比图
|
|
df1 = df[['今年值', '平均值']]
|
|
df1 = df1.rename(columns={'今年值': '公司水平', '平均值': '平均水平'})
|
|
result['同行对比图'] = json.loads(df1.to_json())
|
|
|
|
# 去年对比图
|
|
df2 = df[['今年值', '去年值']]
|
|
df2 = df2.rename(columns={'今年值': periods[0], '去年值': periods[1]})
|
|
result['去年对比图'] = json.loads(df2.to_json())
|
|
|
|
# 去年对比表
|
|
result['去年对比表'] = json.loads((df['今年值']/df['去年值']-1).apply(lambda x: '{}%'.format(round(x*100, 2))).T.to_json())
|
|
|
|
# 同行对比表
|
|
result['同行对比表'] = json.loads((df['今年值']/df['平均值']-1).apply(lambda x: '{}%'.format(round(x * 100, 2))).T.to_json())
|
|
|
|
# 指标详情
|
|
index_value = json.loads(df_this[['净资产收益率', '总资产报酬率', '总资产周转率', '应收账款周转率', '存货周转率', '资产负债率', '已获利息倍数', '速动比率', '营业增长率', '总资产增长率', '技术投入比率']].apply(lambda x: '{}%'.format(x.values[0]) if '率' in x.name else x.values[0]).T.to_json())
|
|
rate = dict()
|
|
rate['净资产收益率'] = rating_result['财务评分']['盈利能力']['净资产收益率']/8
|
|
rate['总资产报酬率'] = rating_result['财务评分']['盈利能力']['总资产报酬率']/8
|
|
rate['总资产周转率'] = rating_result['财务评分']['资产质量']['总资产周转率']/6
|
|
rate['存货周转率'] = rating_result['财务评分']['资产质量']['存货周转率']/6
|
|
rate['应收账款周转率'] = rating_result['财务评分']['资产质量']['应收账款周转率']/6
|
|
rate['资产负债率'] = rating_result['财务评分']['债务风险']['资产负债率']/8
|
|
rate['已获利息倍数'] = rating_result['财务评分']['债务风险']['已获利息倍数']/5
|
|
rate['速动比率'] = rating_result['财务评分']['债务风险']['速动比率']/5
|
|
rate['营业增长率'] = rating_result['财务评分']['经营增长']['营业增长率']/8
|
|
rate['总资产增长率'] = rating_result['财务评分']['经营增长']['总资产增长率']/5
|
|
rate['技术投入比率'] = rating_result['财务评分']['经营增长']['技术投入比率']/5
|
|
df_rate = pd.DataFrame([rate])
|
|
index_level = json.loads(df_rate.apply(lambda x: '优' if x.values[0] >= 1 else ('良' if x.values[0] >= 0.75 else ('中' if x.values[0] >= 0.5 else ('低' if x.values[0] >= 0.25 else '差')))).to_json())
|
|
df_index = pd.DataFrame({'值': index_value, "级别": index_level})
|
|
result['指标详情'] = df_iterrows(df_index)
|
|
insert_data_to_tfse('企业', '财务要素分析', result)
|
|
|
|
|
|
def risk_analysis_etl(rid):
|
|
"""
|
|
风险要素分析
|
|
Parameters:
|
|
rid str 评价ID
|
|
Returns:
|
|
-
|
|
"""
|
|
# Params
|
|
rating_result = find_data_in_tfse('评价', '评价结果', {"评价ID": rid})[0]
|
|
risk_data = find_data_in_tfse('评价', '风险数据', {"评价ID": rid})[0]
|
|
|
|
# Returns
|
|
result = dict()
|
|
|
|
# 计算风险分数
|
|
def risk_relative_score():
|
|
risk_score = rating_result['风险评分']['合计']
|
|
relative_score = 100 if risk_score/43 >= 1 else round(risk_score/43*100, 2)
|
|
return relative_score
|
|
|
|
# 计算风险级别
|
|
def risk_level():
|
|
risk_score = rating_result['风险评分']['合计']
|
|
if risk_score >= 43:
|
|
level = '高'
|
|
elif risk_score >= 33:
|
|
level = '较高'
|
|
elif risk_score >= 23:
|
|
level = '中等'
|
|
elif risk_score >= 10:
|
|
level = '警示'
|
|
else:
|
|
level = '低'
|
|
return level
|
|
|
|
# 统计风险数量
|
|
def stat_risk_num():
|
|
return sum(risk_data['合规风险'].values()) + sum(risk_data['经营风险'].values())
|
|
|
|
# 判断失信人
|
|
def is_break_trust():
|
|
return '是' if risk_data['合规风险']['失信人'] >= 1 else '否'
|
|
|
|
# 合规风险表格
|
|
def eligibility_risk():
|
|
|
|
def degree_of_impact(param):
|
|
if param.name in ['失信人', '严重违法']:
|
|
impact = '严重'
|
|
elif param.name in ['经营异常', '欠税公告', '税收违法']:
|
|
impact = '异常'
|
|
elif param.name in ['立案信息', '行政处罚', '环保处罚']:
|
|
impact = '中等'
|
|
else:
|
|
impact = ''
|
|
return impact
|
|
|
|
df = pd.DataFrame({'合规风险': risk_data['合规风险']})
|
|
df = df.drop(df[df['合规风险'] == 0].index)
|
|
df['影响程度'] = df.T.apply(lambda x: degree_of_impact(x))
|
|
|
|
return df_iterrows(df)
|
|
|
|
# 经营风险表格
|
|
def operating_risk():
|
|
def degree_of_impact(param):
|
|
if param.name in ['开庭公告', '法院公告', '诉讼', '送达公告'] and param.values[0] >= 50:
|
|
impact = '异常'
|
|
elif param.name in ['开庭公告', '法院公告', '诉讼', '送达公告'] and param.values[0] >= 25:
|
|
impact = '中等'
|
|
elif param.name in ['开庭公告', '法院公告', '诉讼', '送达公告'] and param.values[0] >= 10:
|
|
impact = '警示'
|
|
elif param.name in ['被执行人'] and param.values[0] >= 30:
|
|
impact = '异常'
|
|
elif param.name in ['被执行人'] and param.values[0] >= 15:
|
|
impact = '中等'
|
|
elif param.name in ['被执行人'] and param.values[0] >= 6:
|
|
impact = '警示'
|
|
elif param.name in ['股权出质'] and param.values[0] >= 10:
|
|
impact = '异常'
|
|
elif param.name in ['股权出质'] and param.values[0] >= 5:
|
|
impact = '中等'
|
|
elif param.name in ['股权出质'] and param.values[0] >= 3:
|
|
impact = '警示'
|
|
else:
|
|
impact = '轻微'
|
|
return impact
|
|
|
|
df = pd.DataFrame({'经营风险': risk_data['经营风险']})
|
|
df = df.drop(df[df['经营风险'] == 0].index)
|
|
df['影响程度'] = df.T.apply(lambda x: degree_of_impact(x))
|
|
|
|
return df_iterrows(df)
|
|
|
|
# 关联风险表格
|
|
def associate_risk():
|
|
data = associate_risk_detail(rating_result['企业名称'])
|
|
return df_iterrows(pd.DataFrame(data).sort_values('total', ascending=False).set_index('title'))
|
|
|
|
# 变更记录表格
|
|
def change_log():
|
|
data = change_log_detail(rating_result['企业名称'])
|
|
|
|
def degree_of_impact(param):
|
|
if param.name in ['法定代表人变更', '主要人员变更'] and param.values[0] >= 20:
|
|
impact = '异常'
|
|
elif param.name in ['法定代表人变更', '主要人员变更'] and param.values[0] >= 10:
|
|
impact = '中等'
|
|
elif param.name in ['法定代表人变更', '主要人员变更'] and param.values[0] >= 4:
|
|
impact = '警示'
|
|
else:
|
|
impact = '轻微'
|
|
return impact
|
|
|
|
df = pd.DataFrame(data).sort_values('total', ascending=False).set_index('title')
|
|
df['影响程度'] = df.T.apply(lambda x: degree_of_impact(x))
|
|
|
|
return df_iterrows(df[['total', '影响程度']])
|
|
|
|
# 汇总数据处理结果
|
|
result['企业ID'] = rating_result['企业ID']
|
|
result['更新日期'] = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
|
|
result['风险分数'] = risk_relative_score()
|
|
result['风险级别'] = risk_level()
|
|
result['风险数量'] = stat_risk_num()
|
|
result['列入失信名单'] = is_break_trust()
|
|
result['合规风险'] = eligibility_risk()
|
|
result['经营风险'] = operating_risk()
|
|
result['周边风险'] = associate_risk()
|
|
result['变更记录'] = change_log()
|
|
insert_data_to_tfse('企业', '风险要素分析', result)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# general_rating_etl("kSVoCeJ1")
|
|
# financial_analysis("bR2n0mV0")
|
|
risk_analysis_etl("bR2n0mV0")
|