def equity_interest_pledge_too_high(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry, context: AnalysisContext) -> AnalysisResult:
nop(database)
nop(context)
query_fields = ['质押次数', '无限售股质押数量', '限售股份质押数量', '总股本', '质押比例']
if not data_hub.get_data_center().check_readable_name(query_fields):
return AnalysisResult(securities, AnalysisResult.SCORE_NOT_APPLIED, 'Unknown readable name detect.')
df = data_hub.get_data_center().query('Stockholder.PledgeStatus', securities, (years_ago(2), now()),
fields=query_fields + ['stock_identity', 'due_date'], readable=True)
if df is None or len(df) == 0:
return AnalysisResult(securities, AnalysisResult.SCORE_NOT_APPLIED, 'No data for ' + str(securities))
df = df.sort_values('due_date', ascending=False)
score = 100
reason = []
for index, row in df.iterrows():
due_date = row['due_date']
pledge_rate = row['质押比例']
if pledge_rate > 0.5:
score = 0
if pledge_rate > 0.1:
reason.append('%s: 质押比例：%.2f%%' % (str(due_date), pledge_rate * 100))
return AnalysisResult(securities, score, reason)
def analysis_finance_report_sign(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry,
context: AnalysisContext) -> AnalysisResult:
nop(database)
if context.cache.get('finance_audit', None) is None:
context.cache['finance_audit'] = data_hub.get_data_center().query(
'Finance.Audit')
df = context.cache.get('finance_audit', None)
error_report = check_gen_report_when_data_missing(
df, securities, 'Finance.Audit',
['stock_identity', 'period', 'conclusion'])
if error_report is not None:
return error_report
df_slice = df[df['stock_identity'] == securities]
df_slice_in_4_years = df_slice[df_slice['period'] > years_ago(4)]
score = 100
reason = []
for index, row in df_slice_in_4_years.iterrows():
period = row['period']
conclusion = row['conclusion']
if conclusion != '标准无保留意见':
score = 0
reason.append(date2text(period) + ' : ' + conclusion)
if len(reason) == 0:
reason.append('近四年均为标准无保留意见')
return AnalysisResult(securities, score, reason)
def analysis_dispersed_ownership(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry,
context: AnalysisContext) -> AnalysisResult:
nop(database, context)
df = data_hub.get_data_center().query(
'Stockholder.Statistics',
securities,
(years_ago(3), now()),
)
if df is None or len(df) == 0:
return AnalysisResult(securities, AnalysisResult.SCORE_NOT_APPLIED,
'没有数据')
df = df[df['period'].dt.month == 12]
df = df.sort_values('period', ascending=False)
score = 100
reason = []
applied = False
for index, row in df.iterrows():
period = row['period']
stockholder_top10 = row['stockholder_top10']
stockholder_top10_nt = row['stockholder_top10_nt']
if not isinstance(stockholder_top10, (list, tuple)):
continue
if len(stockholder_top10) != 10:
continue
largest_ratio = 0.0
biggest_holder = ''
for stockholder_data in stockholder_top10:
if 'hold_ratio' not in stockholder_data.keys(
) or 'holder_name' not in stockholder_data.keys():
break
applied = True
hold_ratio = stockholder_data.get('hold_ratio')
holder_name = stockholder_data.get('holder_name')
if hold_ratio > largest_ratio:
largest_ratio = hold_ratio
biggest_holder = holder_name
if largest_ratio == 0.0:
return AnalysisResult(securities, AnalysisResult.SCORE_NOT_APPLIED,
'缺少必要数据，请确保数据包含tushare pro数据源')
if largest_ratio < 0.1:
score = 0
reason.append('%s: 最大股东 %s 持股比例为%.2f%%，小于10%%' %
(str(period), biggest_holder, largest_ratio * 100))
else:
reason.append('%s: 最大股东 %s 持股比例为%.2f%%' %
(str(period), biggest_holder, largest_ratio * 100))
if len(reason) == 0:
reason.append('没有数据')
return AnalysisResult(securities, score, reason) if applied else \
AnalysisResult(securities, AnalysisResult.SCORE_NOT_APPLIED, reason)
def analysis_location_limitation(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry, context: AnalysisContext) -> AnalysisResult:
nop(database)
if context.cache.get('securities_info', None) is None:
context.cache['securities_info'] = data_hub.get_data_center().query('Market.SecuritiesInfo')
df = context.cache.get('securities_info', None)
df_slice = df[df['stock_identity'] == securities]
area = get_dataframe_slice_item(df_slice, 'area', 0, '')
exclude = area in ['黑龙江', '辽宁', '吉林']
reason = securities + '地域为' + str(area)
return AnalysisResult(securities, not exclude, reason)
def analysis_less_than_3_years(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry, context: AnalysisContext) -> AnalysisResult:
nop(database)
if context.cache.get('securities_info', None) is None:
context.cache['securities_info'] = data_hub.get_data_center().query('Market.SecuritiesInfo')
df = context.cache.get('securities_info', None)
df_slice = df[df['stock_identity'] == securities]
listing_date = get_dataframe_slice_item(df_slice, 'listing_date', 0, now())
exclude = now().year - listing_date.year < 3
reason = '上市日期' + str(listing_date) + ('小于三年' if exclude else '大于三年')
return AnalysisResult(securities, not exclude, reason)
def analysis_exclude_industries(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry, context: AnalysisContext) -> AnalysisResult:
nop(database)
if context.cache.get('securities_info', None) is None:
context.cache['securities_info'] = data_hub.get_data_center().query('Market.SecuritiesInfo')
df = context.cache.get('securities_info', None)
df_slice = df[df['stock_identity'] == securities]
industry = get_dataframe_slice_item(df_slice, 'industry', 0, '')
exclude = industry in ['种植业', '渔业', '林业', '畜禽养殖', '农业综合']
reason = '所在行业[' + str(industry) + (']属于农林牧渔' if exclude else ']不属于农林牧渔')
return AnalysisResult(securities, not exclude, reason)
def check_industry_in(securities: str, industries: [str],
data_hub: DataHubEntry, database: DatabaseEntry,
context: AnalysisContext) -> bool:
nop(database)
if context.cache.get('securities_info', None) is None:
context.cache['securities_info'] = data_hub.get_data_center().query(
'Market.SecuritiesInfo')
df_info = context.cache.get('securities_info', None)
df_slice = df_info[df_info['stock_identity'] == securities]
industry = get_dataframe_slice_item(df_slice, 'industry', 0, '')
return industry in industries
def query_finance_pattern(data_hub: DataHubEntry, identity: str,
time_serial: tuple, fields: list, mapping: dict) -> pd.DataFrame:
query_fields = [mapping.get(f, f) for f in fields]
query_fields = list(set(query_fields))
if 'period' in query_fields:
query_fields.remove('period')
if 'stock_identity' in query_fields:
query_fields.remove('stock_identity')
data_utility = data_hub.get_data_utility()
df = data_utility.auto_query(identity, time_serial, query_fields, join_on=['stock_identity', 'period'])
df.fillna(0.0, inplace=True)
df = df.sort_values('period', ascending=False)
inv_dict = {v: k for k, v in mapping.items()}
df = df.rename(inv_dict, axis='columns')
return df
def analysis_investigation(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry,
context: AnalysisContext) -> AnalysisResult:
nop(database)
if context.cache.get('investigation', None) is None:
context.cache['investigation'] = data_hub.get_data_center().query(
'Market.Investigation')
df = context.cache.get('investigation', None)
error_report = check_gen_report_when_data_missing(
df, securities, 'Market.Investigation', [
'stock_identity', 'investigate_date', 'investigate_topic',
'investigate_reason'
])
if error_report is not None:
return error_report
df_slice = df[df['stock_identity'] == securities]
df_slice_in_4_years = df_slice[df_slice['investigate_date'] > years_ago(5)]
score = 100
reason = []
for index, row in df_slice_in_4_years.iterrows():
score = 0
investigate_date = row['investigate_date']
investigate_topic = row['investigate_topic']
investigate_reason = row['investigate_reason']
reason.append('%s: <<%s>> -- %s' %
(date2text(investigate_date), investigate_topic,
investigate_reason))
if len(reason) == 0:
reason.append('近四年无立案调查记录')
return AnalysisResult(securities, score, reason)
def analysis_inquiry(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry,
context: AnalysisContext) -> AnalysisResult:
nop(database)
df = data_hub.get_data_center().query('Market.Enquiries', securities)
if df is None or len(df) == 0:
return AnalysisResult(securities, AnalysisResult.SCORE_PASS,
'四年内无问询记录（也可能是数据缺失）')
error_report = check_gen_report_when_data_missing(
df, securities, 'Market.Enquiries',
['stock_identity', 'enquiry_date', 'enquiry_topic'])
if error_report is not None:
return error_report
df_slice = df[df['stock_identity'] == securities]
df_slice_in_4_years = df_slice[df_slice['enquiry_date'] > years_ago(5)]
score = 100
reason = []
for index, row in df_slice_in_4_years.iterrows():
enquiry_date = row['enquiry_date']
enquiry_topic = row['enquiry_topic']
enquiry_title = row['enquiry_title']
if '问询函' in enquiry_topic or '关注函' in enquiry_topic:
score = 59
reason.append(
'%s: <<%s>> -- %s' %
(date2text(enquiry_date), enquiry_topic, enquiry_title))
if len(reason) == 0:
reason.append('近四年无敏感问询')
return AnalysisResult(securities, score, reason)
def analysis_finance_report_sign(securities: str, data_hub: DataHubEntry,
database: DatabaseEntry, context: AnalysisContext) -> AnalysisResult:
nop(database)
if context.cache.get('finance_audit', None) is None:
context.cache['finance_audit'] = data_hub.get_data_center().query('Finance.Audit')
df = context.cache.get('finance_audit', None)
error_report = check_gen_report_when_data_missing(df, securities, 'Finance.IncomeStatement',
['stock_identity', 'period', 'conclusion'])
if error_report is not None:
return error_report
df_slice = df[df['stock_identity'] == securities]
df_slice_in_4_years = df_slice[df_slice['period'] > years_ago(4)]
score = 100
reason = []
for index, row in df_slice_in_4_years.iterrows():
period = row['period']
conclusion = row['conclusion']
if conclusion != '标准无保留意见':
score = 0
reason.append(date2text(period) + ' : ' + conclusion)
if len(reason) == 0:
reason.append('近四年均为标准无保留意见')
# df_slice.sort_values('period', ascending=True)
#
# if len(df_slice) == 1:
# print('Too less record: ' + securities)
# df_slice_in_3_years = df_slice[df_slice['period'] > years_ago(3)]
#
# conclusion_all = df_slice['conclusion']
# conclusion_all_list = conclusion_all.to_list()
#
# conclusion_3_years = df_slice_in_3_years['conclusion']
# conclusion_3_years_list = conclusion_3_years.to_list()
# ok_count = 0
# nok_count = 0
# for conclusion in conclusion_all_list:
# if conclusion != '标准无保留意见':
# nok_count += 1
# else:
# ok_count += 1
# score = 100 * ok_count / (ok_count + nok_count) if (ok_count + nok_count) > 0 else 100
#
# for conclusion in conclusion_3_years_list:
# if conclusion != '标准无保留意见':
# score = 0
# break
# agency = get_dataframe_slice_item(df_slice, 'agency', 0, '')
# sign = get_dataframe_slice_item(df_slice, 'sign', 0, '')
# reason = '标准无保留意见' if score == 100 else '存在非标意见'
return AnalysisResult(securities, score, reason)