def update_static_info(force=False):
now = datetime.datetime.now()
t = None
rf = open(StaticInfo.storage_update_date, "r")
line = rf.read()
rf.close()
wf = open(StaticInfo.storage_update_date, "w")
if line:
t = parser.parse(line)
else:
wf.write(str(now))
delta_day = (now - t).days
if delta_day > 0 or force:
wf.write(str(now))
print "static info need to update"
ts.get_industry_classified().to_csv(
StaticInfo.data_type["industry"], index=False)
ts.get_concept_classified().to_csv(StaticInfo.data_type["concept"],
index=False)
ts.get_area_classified().to_csv(StaticInfo.data_type["area"],
index=False)
InitStaticInfo._get_stock_hist_data(
StaticInfo.get_stock_pool().keys())
wf.close()
def 下载板块数据(self):
# 获取不同分类数据
ts.get_industry_classified().to_csv('./股票数据/基本信息/行业分类.csv')
ts.get_concept_classified().to_csv('./股票数据/基本信息/概念分类.csv')
ts.get_area_classified().to_csv('./股票数据/基本信息/地域分类.csv')
ts.get_sme_classified().to_csv('./股票数据/基本信息/中小板.csv')
ts.get_gem_classified().to_csv('./股票数据/基本信息/创业板.csv')
ts.get_st_classified().to_csv('./股票数据/基本信息/风险警示板.csv')
ts.get_hs300s().to_csv('./股票数据/基本信息/沪深300.csv')
ts.get_sz50s().to_csv('./股票数据/基本信息/上证50.csv')
ts.get_zz500s().to_csv('./股票数据/基本信息/中证500.csv')
def regionData(self):
table = 'stock_etl.stock_region'
column = 'ticker,tickerName,tickerType'
result = ts.get_area_classified()
sql = SqlBuildUtil.SqlBuildUtil.insertBuildts(table, column, result.values)
EtlDao.EtlDao().delAllDate(table)
EtlDao.EtlDao().save(sql)
def save_area_classified():
'''
获取地域分类信息
:return:
'''
cur = mysql_connect.cursor()
try:
sta = cur.execute("delete from py_db.gp_area_classified")
print(sta)
print("删除地域分类gp_area_classified:", sta, "条数据完成")
except Exception as e:
print(e)
mysql_connect.commit()
cur.close()
df = tushare.get_area_classified()
try:
pd.io.sql.to_sql(df,
'gp_area_classified',
yconnect,
schema='py_db',
if_exists='append',
index=df['code'])
print("地域分类", len(df), "更新完成")
return len(df)
except ValueError as e:
print(e)
return False
return -1
def fetch_classification(self): # 数据来源自新浪财经的行业分类/概念分类/地域分类 print( "Trying: get_today_all" ) today_all = ts.get_today_all() #一次性获取今日全部股价 set_today_all = set(today_all.T.values[0]) print( "Trying: get_industry_classified" ) industry_classified = ts.get_industry_classified() set_industry_classified = set(industry_classified.T.values[0]) print( "Trying: get_area_classified" ) area_classified = ts.get_area_classified() set_area_classified = set(area_classified.T.values[0]) print( "Trying: get_concept_classified" ) concept_classified = ts.get_concept_classified() set_concept_classified = set(concept_classified.T.values[0]) print( "Trying: get_sme_classified" ) sme_classified = ts.get_sme_classified() set_sme_classified = set(sme_classified.T.values[0]) return [ today_all , set_today_all , industry_classified , set_industry_classified , area_classified , set_area_classified , concept_classified , set_concept_classified , sme_classified , set_sme_classified ]
def get_arealist_info():
# 地域分类
df = ts.get_area_classified()
res = df.to_sql(all_area_table, engine, if_exists='replace')
msg = 'ok' if res is None else res
print('获取地域分类: ' + msg + '\n')
print(msg)
def classify_info_to_sql():
create_classify_table()
a = ts.get_industry_classified()
a.columns = ['code', 'name', 'industry']
b = ts.get_area_classified()
c = ts.get_sz50s()
c = c.iloc[:,1::]
c['sz50'] = '1'
d = ts.get_hs300s()
d = d.iloc[:,1::]
d.columns = ['code','name','hs300_weight']
e = ts.get_zz500s()
e = e.iloc[:,1::]
e.columns = ['code','name','zz500_weight']
result = pd.merge(a, b, how='left', on=None, left_on=None, right_on=None,
left_index=False, right_index=False, sort=True,
suffixes=('_x', '_y'), copy=True, indicator=False)
result = pd.merge(result, c, how='left', on=None, left_on=None, right_on=None,
left_index=False, right_index=False, sort=True,
suffixes=('_x', '_y'), copy=True, indicator=False)
result = pd.merge(result, d, how='left', on=None, left_on=None, right_on=None,
left_index=False, right_index=False, sort=True,
suffixes=('_x', '_y'), copy=True, indicator=False)
result = pd.merge(result, e, how='left', on=None, left_on=None, right_on=None,
left_index=False, right_index=False, sort=True,
suffixes=('_x', '_y'), copy=True, indicator=False)
df_to_mysql('anack_classify',result)
def get_area_classified():
'''
Return the area classified DataFrame
:return: the DataFrame
'''
content = ts.get_area_classified()
return content
def fetch_classification(self):
# 数据来源自新浪财经的行业分类/概念分类/地域分类
print("Trying: get_today_all")
today_all = ts.get_today_all() #一次性获取今日全部股价
set_today_all = set(today_all.T.values[0])
print("Trying: get_industry_classified")
industry_classified = ts.get_industry_classified()
set_industry_classified = set(industry_classified.T.values[0])
print("Trying: get_area_classified")
area_classified = ts.get_area_classified()
set_area_classified = set(area_classified.T.values[0])
print("Trying: get_concept_classified")
concept_classified = ts.get_concept_classified()
set_concept_classified = set(concept_classified.T.values[0])
print("Trying: get_sme_classified")
sme_classified = ts.get_sme_classified()
set_sme_classified = set(sme_classified.T.values[0])
return [
today_all, set_today_all, industry_classified,
set_industry_classified, area_classified, set_area_classified,
concept_classified, set_concept_classified, sme_classified,
set_sme_classified
]
def get_stock_basic() -> list:
nodes, links = [], []
Node = namedtuple("Node", "name type source")
Link = namedtuple("Link", "head link tail source")
df = ts.get_stock_basics()
df.reset_index(inplace=True)
data = df.to_dict(orient="records")
industry_mapper = ts.get_industry_classified().groupby(
["code"])["c_name"].apply(lambda x: x.tolist()).to_dict()
concept_mapper = ts.get_concept_classified().groupby(
["code"])["c_name"].apply(lambda x: x.tolist()).to_dict()
area_mapper = ts.get_area_classified().groupby(
["code"])["area"].apply(lambda x: x.tolist()).to_dict()
for d in data:
nodes.append(Node(d["code"], "公司", "tu"))
nodes.append(Node(d["name"], "公司", "tu"))
links.append(Link(d["code"], "等于", d["name"], "tu"))
for k in set(industry_mapper.get(d["code"], []) + [d["industry"]]):
nodes.append(Node(k, "行业", "tu"))
links.append(Link(d["code"], "属于", k, "tu"))
for k in concept_mapper.get(d["code"], []):
nodes.append(Node(k, "概念", "tu"))
links.append(Link(d["code"], "属于", k, "tu"))
for k in set(area_mapper.get(d["code"], []) + [d["area"]]):
nodes.append(Node(k, "区域", "tu"))
links.append(Link(d["code"], "属于", k, "tu"))
del d["industry"], d["area"]
nodes = list(set(nodes))
return nodes, links, data
def update_stock_basic() -> None:
df = ts.get_stock_basics()
df.reset_index(inplace=True)
data = df.to_dict(orient="records")
# update industry
industry_df = ts.get_industry_classified()
industry_df = industry_df.groupby(["code"])["c_name"].apply(lambda x: x.tolist()).reset_index()
industry_mapper = dict([(d["code"], d["c_name"]) for
d in industry_df.to_dict(orient="records")])
# update concept
concept_df = ts.get_concept_classified()
concept_df = concept_df.groupby(["code"])["c_name"].apply(lambda x: x.tolist()).reset_index()
concept_mapper = dict([(d["code"], d["c_name"]) for
d in concept_df.to_dict(orient="records")])
# update area
area_df = ts.get_area_classified()
area_df = area_df.groupby(["code"])["area"].apply(lambda x: x.tolist()).reset_index()
area_mapper = dict([(d["code"], d["area"]) for
d in area_df.to_dict(orient="records")])
bar = ProgressBar(total=len(data))
for d in data:
d["industry"] = list(set(industry_mapper.get(d["code"], []) + [d["industry"]]))
d["concept"] = concept_mapper.get(d["code"], [])
d["area"] = list(set(area_mapper.get(d["code"], []) + [d["area"]]))
bar.move()
db.stock_basics.update({"code": d["code"]}, {"$set": d}, True)
bar.log("code: {} name: {} industry {} concept {} area {}"
.format(d["code"], d["name"], d["industry"], d["concept"], d["area"]))
def fetch_stock_area():
'''
获取股票 地区数据
:return:
'''
df = ts.get_area_classified()
return df
def classification(class_types):
if class_types == 'industry':
industry_classified = ts.get_industry_classified()
industry_classified.to_csv('D:\\ts\\classification\\industry_classified.csv', encoding='gbk')
elif class_types == 'concept':
concept_classified = ts.get_concept_classified()
concept_classified.to_csv('D:\\ts\\classification\\concept_classified.csv', encoding='gbk')
elif class_types == 'area':
area_classified = ts.get_area_classified()
area_classified.to_csv('D:\\ts\\classification\\area_classified.csv', encoding='gbk')
elif class_types == 'sme':
sme_classified = ts.get_sme_classified()
sme_classified.to_csv('D:\\ts\\classification\\sme_classified.csv', encoding='gbk')
elif class_types == 'gem':
gem_classified = ts.get_gem_classified()
gem_classified.to_csv('D:\\ts\\classification\\gem_classified.csv', encoding='gbk')
elif class_types == 'st':
st_classified = ts.get_st_classified()
st_classified.to_csv('D:\\ts\\classification\\st_classified.csv', encoding='gbk')
elif class_types == 'hs300':
hs300s = ts.get_hs300s()
hs300s.to_csv('D:\\ts\\classification\\hs300s.csv', encoding='gbk')
elif class_types == 'sz50':
sz50s = ts.get_sz50s()
sz50s.to_csv('D:\\ts\\classification\\sz50s.csv', encoding='gbk')
elif class_types == 'zz500':
zz500s = ts.get_zz500s()
zz500s.to_csv('D:\\ts\\classification\\zz500s.csv', encoding='gbk')
elif class_types == 'terminated':
terminated = ts.get_terminated()
terminated.to_csv('D:\\ts\\classification\\terminated.csv', encoding='gbk')
elif class_types == 'suspended':
suspended = ts.get_suspended()
suspended.to_csv('D:\\ts\\classification\\suspended.csv', encoding='gbk')
def core_function(self, func):
self.set_data()
mongo = MongoClient("127.0.0.1", 27017)
if (func == "industry_classified"):
df = ts.get_industry_classified()
elif (func == "concept_classified"):
df = ts.get_concept_classified()
elif (func == "area_classified"):
df = ts.get_area_classified()
elif (func == "gem_classified"):
df = ts.get_gem_classified()
elif (func == "sme_classified"):
df = ts.get_sme_classified()
elif (func == "st_classified"):
df = ts.get_st_classified()
elif (func == "hs300s"):
df = ts.get_hs300s()
elif (func == "sz50s"):
df = ts.get_sz50s()
elif (func == "zz500s"):
df = ts.get_zz500s()
print(df)
elif (func == "terminated"):
df = ts.get_terminated()
else:
df = {}
insert_string = df.to_json(orient='records')
items = json.loads(insert_string)
coll = mongo.classify[func]
coll.insert(items)
def get_area_classified():
try:
df = ts.get_area_classified();
engine = create_engine('mysql://*****:*****@127.0.0.1/stock?charset=utf8')
# df.insert(0,'code','600848')
df.to_sql('area_classified', engine, if_exists='append')
except Exception, e:
e.message
def regionData(self):
table = 'stock_etl.stock_region'
column = 'ticker,tickerName,tickerType'
result = ts.get_area_classified()
sql = SqlBuildUtil.SqlBuildUtil.insertBuildts(table, column,
result.values)
EtlDao.EtlDao().delAllDate(table)
EtlDao.EtlDao().save(sql)
def get_area_classified():
try:
logger.info('get area data starting...')
df = ts.get_area_classified()
logger.info('get area data end...')
except:
logger.exception('some errors between get area data end...')
return df
def get_area_classified(self):
"""
地域分类
"""
area = ts.get_area_classified()
area = area[['code','area']]
area.columns = ['code','areaName']
self.data = pd.merge(self.data,area,on=['code'],how='outer')
def ini_classfication():
Industry = ts.get_industry_classified()
Concept = ts.get_concept_classified()
Area = ts.get_area_classified()
_Codelist = Area[['code']]
Codelist = []
for i in range(len(_Codelist)):
Codelist.append(_Codelist.ix[i, 0])
return [Codelist, Area, Concept, Industry]
def get_area_classification():
filename = 'area_classification'
filepath = os.path.join(rootDir, 'StockBasis', filename + '.csv')
if (os.path.exists(filepath)):
data = pd.read_csv(filepath, encoding='gbk')
else:
data = ts.get_area_classified()
data.to_csv(filepath)
return data
def area_classified(request):
try:
data = ts.get_area_classified()
res = {
'columns': ['股票代码', '股票名称', '地域名称'],
'data': json.loads(json.dumps(data.values, cls=DateEncoder))
}
except (BaseException):
return HttpResponse(BaseException)
else:
return HttpResponse(json.dumps(res), content_type="application/json")
def getAreaClassified():
'''
获取地域分类。按地域对股票进行分类，即查找出哪些股票属于哪个省份。
参数说明：
file_path:文件路径，默认为None即由TuShare提供，可以设定自己的股票文件路径。
返回值说明：
code：股票代码
name：股票名称
area：地域名称
'''
return ts.get_area_classified()
def getstockclassifieddata():
mylogger = getmylogger()
print("start")
scdict = {
'industry': '行业分类',
'concept': '概念分类',
'area': '地域分类',
'sme': '中小板分类',
'gem': '创业板分类',
'st': '风险警示板分类',
'hs300s': '沪深300成份及权重',
'sz50s': '上证50成份股',
'zz500s': '中证500成份股',
'terminated': '终止上市股票列表',
'suspended': '暂停上市股票列表'
}
for sc in scdict:
sctbname = sc
scinfo = scdict[sctbname]
try:
if sc == "industry":
df = ts.get_industry_classified()
elif sc == "concept":
df = ts.get_concept_classified()
elif sc == "area":
df = ts.get_area_classified()
elif sc == "sme":
df = ts.get_sme_classified()
elif sc == "gem":
df = ts.get_gem_classified()
elif sc == "st":
df = ts.get_st_classified()
elif sc == "hs300s":
df = ts.get_hs300s()
elif sc == "zz500s":
df = ts.get_zz500s()
elif sc == "sz50s":
df = ts.get_sz50s()
elif sc == "terminated":
df = ts.get_terminated()
elif sc == "suspended":
df = ts.get_suspended()
else:
mylogger.info("没有执行命令。")
if df is not None:
tosql(df, sctbname, "replace", scinfo, mylogger)
else:
mylogger.info("没有%s数据。" % scinfo)
except Exception:
tracelog = traceback.format_exc()
mylogger.info("获取数据异常。")
mylogger.info(tracelog)
def load_data():
try:
rs = ts.get_area_classified()
pd.DataFrame.to_sql(rs,
table_name,
con=conn,
flavor='mysql',
if_exists='replace',
index=True)
except Exception as e:
print(e.message)
print("公司地域分类信息数据出错")
def classReport():
'''
股票分类报告
'''
class_industry = ts.get_industry_classified()
class_industry['code'] = class_industry['code'].astype(str)
class_industry = class_industry.drop(['name'], axis=1)
print " "
class_area = ts.get_area_classified()
class_area['code'] = class_area['code'].astype(str)
class_area = class_area.drop(['name'], axis=1)
return class_industry, class_area
def load_data():
try:
rs = ts.get_area_classified()
pd.DataFrame.to_sql(rs,
name=table_name,
con=con,
schema=db,
if_exists='replace',
index=True)
except Exception as e:
print(e)
print("公司地域分类信息数据出错")
def ts_to_csv():
stock_data = ts.get_stock_basics()
# stock_data.to_csv('stock.csv',columns=['name'])
stock_edges = pd.DataFrame(columns=['fromID', 'toID', 'type'])
block_nodes = {}
begin_code = int(900001);
# industry
block_industry = ts.get_industry_classified()
for row in block_industry.iterrows():
if row[1]['c_name'] not in block_nodes:
block_nodes[row[1]['c_name']] = begin_code
begin_code += 1
stock_edges = stock_edges.append({'fromID': row[1]['code'], 'toID': str(block_nodes[row[1]['c_name']]), 'type': '属于'},
ignore_index=True)
# block_industry.to_csv('block_industry.csv',index=None)
# concept
block_concept = ts.get_concept_classified()
for row in block_concept.iterrows():
if row[1]['c_name'] not in block_nodes:
block_nodes[row[1]['c_name']] = begin_code
begin_code += 1
stock_edges = stock_edges.append({'fromID': row[1]['code'], 'toID': str(block_nodes[row[1]['c_name']]), 'type': '属于'}, ignore_index=True)
# block_concept.to_csv('block_concept.csv',index=None)
# area
block_area =ts.get_area_classified()
for row in block_area.iterrows():
if row[1]['area'] not in block_nodes:
block_nodes[row[1]['area']] = begin_code
begin_code += 1
stock_edges = stock_edges.append({'fromID': row[1]['code'], 'toID': str(block_nodes[row[1]['area']]), 'type': '属于'}, ignore_index=True)
# block_area.to_csv('block_area.csv',index=None)
# print(stock_edges)
stock_edges.to_csv('stock_edges.csv',index=None, encoding="utf-8");
#to csv
# 1. 创建文件对象
block_df = pd.DataFrame(columns=['code', 'name'])
for k,v in block_nodes.items():
# print(k)
block_df = block_df.append({'code': str(v), 'name': k}, ignore_index=True)
block_df = block_df.set_index('code')
block_df = block_df.append(stock_data)
block_df.to_csv('stock_nodes.csv',columns=['name'], encoding="utf-8")
def main():
dbclient = SqliteClient(base=Base, url='sqlite:///./share.db')
# get_report_data(2017, 3, engine)
# rep = ts.cap_tops()
print(datetime.now())
areas = ts.get_area_classified()
print(datetime.now())
areas = tushareTable.pandaToORM(areas, areaClassified)
print(datetime.now())
dbclient.save_all(areas)
print(datetime.now())
return
def refresh_baseinfo_table():
print("Fetching area data (地域分类)... ", end='')
df = ts.get_area_classified()
sql = "INSERT INTO baseinfo(code, name, area) VALUES(?, ?, ?)"
rss = np.array(df).tolist()
db.conn().exem(sql, rss)
print("is done! And saved data to table [baseinfo] success.")
def update_baseinfo(df, field):
sql = "UPDATE baseinfo SET " + field + "=1 WHERE code=?"
# css = np.array(df[['code']]).tolist()
css = list(df.code)
db.conn().exem(sql, css)
print("is done! And update table [baseinfo] success.")
def list(self, stock_block_type):
stock_block = None
if stock_block_type == self.industry:
stock_block = db.get(STOCK_BLOCK_INDUSTRY)
if stock_block is None:
stock_block = ts.get_industry_classified()
db.save(STOCK_BLOCK_INDUSTRY, stock_block)
elif stock_block_type == self.concept:
stock_block = db.get(STOCK_BLOCK_CONCEPT)
if stock_block is None:
stock_block = ts.get_concept_classified()
db.save(STOCK_BLOCK_CONCEPT, stock_block)
elif stock_block_type == self.area:
stock_block = db.get(STOCK_BLOCK_AREA)
if stock_block is None:
stock_block = ts.get_area_classified()
db.save(STOCK_BLOCK_AREA, stock_block)
elif stock_block_type == self.sme:
stock_block = db.get(STOCK_BLOCK_SME)
if stock_block is None:
stock_block = ts.get_sme_classified()
db.save(STOCK_BLOCK_SME, stock_block)
elif stock_block_type == self.gem:
stock_block = db.get(STOCK_BLOCK_GEM)
if stock_block is None:
stock_block = ts.get_gem_classified()
db.save(STOCK_BLOCK_GEM, stock_block)
elif stock_block_type == self.st:
stock_block = db.get(STOCK_BLOCK_ST)
if stock_block is None:
stock_block = ts.get_st_classified()
db.save(STOCK_BLOCK_ST, stock_block)
elif stock_block_type == self.hs300s:
stock_block = db.get(STOCK_BLOCK_HS300S)
if stock_block is None:
stock_block = ts.get_hs300s()
db.save(STOCK_BLOCK_HS300S, stock_block)
elif stock_block_type == self.sz50s:
stock_block = db.get(STOCK_BLOCK_SZ50S)
if stock_block is None:
stock_block = ts.get_sz50s()
db.save(STOCK_BLOCK_SZ50S, stock_block)
elif stock_block_type == self.zz500s:
stock_block = db.get(STOCK_BLOCK_ZZ500S)
if stock_block is None:
stock_block = ts.get_zz500s()
db.save(STOCK_BLOCK_ZZ500S, stock_block)
else:
return None
return stock_block
def update_area(request):
'''更新地域数据'''
stock_area.objects.all().delete()
rltobj = ts.get_area_classified()
objlist = []
for i in range(len(rltobj)):
tmpobj = stock_area(code=rltobj.loc[i]['code'],
name=rltobj.loc[i]['name'],
a_name=rltobj.loc[i]['area'])
objlist.append(tmpobj)
stock_area.objects.bulk_create(objlist)
return HttpResponse('succ.{0}条!'.format(len(objlist)))
def save_area_classified():
"""按地域对股票进行分类，即查找出哪些股票属于哪个省份。"""
logger.info('Begin get and save area clssified.')
try:
data_df = ts.get_area_classified()
if data_df is not None and not data_df.empty:
data = data_df.values
data_dicts = [{
'code': row[0],
'name': row[1],
'area': row[2]
} for row in data]
AreaClassified.insert_many(data_dicts).execute()
logger.info('Success get and save area clssified.')
else:
logger.warn('Empty get and save area clssified.')
except Exception as e:
logger.exception('Error get and save area clssified.')
def preload():
stock_block = ts.get_industry_classified()
db.save(STOCK_BLOCK_INDUSTRY, stock_block)
stock_block = ts.get_concept_classified()
db.save(STOCK_BLOCK_CONCEPT, stock_block)
stock_block = ts.get_area_classified()
db.save(STOCK_BLOCK_AREA, stock_block)
stock_block = ts.get_sme_classified()
db.save(STOCK_BLOCK_SME, stock_block)
stock_block = ts.get_gem_classified()
db.save(STOCK_BLOCK_GEM, stock_block)
stock_block = ts.get_st_classified()
db.save(STOCK_BLOCK_ST, stock_block)
stock_block = ts.get_hs300s()
db.save(STOCK_BLOCK_HS300S, stock_block)
stock_block = ts.get_sz50s()
db.save(STOCK_BLOCK_SZ50S, stock_block)
stock_block = ts.get_zz500s()
db.save(STOCK_BLOCK_ZZ500S, stock_block)
def getStockClassfied():
filepath = 'f:\\stockdata\\股票分类数据\\'
index = 0
# 行业分类
df = ts.get_industry_classified()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 概念分类
df = ts.get_concept_classified()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 地域分类
df = ts.get_area_classified()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 中小板分类
df = ts.get_sme_classified()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 创业板分类
df = ts.get_gem_classified()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 风险警示板分类
df = ts.get_st_classified()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 沪深300成份及权重
df = ts.get_hs300s()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 上证50成份股
df = ts.get_sz50s()
saveCsv(df, filepath, stockClassList, index)
index += 1
# 中证500成份股
df = ts.get_zz500s()
saveCsv(df, filepath, stockClassList, index)
index += 1
def get_area_classified(force=False):
cache_file = cache_path + 'area_class_{date}.csv'.format(
date=datetime.now().strftime('%Y%m%d'))
if force is False and os.path.exists(cache_file):
return pd.read_csv(cache_file, dtype={'code': str}, index_col=0)
area_cls_df = ts.get_area_classified()
area_names = area_cls_df['area'].unique()
area_codes = range(1, 1 + len(area_cls_df['area'].unique()))
area = pd.DataFrame(np.full((len(area_names), 2), np.nan),
columns=['area', 'area_code'])
area['area'] = area_names
area['area_code'] = area_codes
area_cls_df = pd.merge(area_cls_df, area, on='area')
area_cls_df.to_csv(cache_file)
return area_cls_df
def get_area():
'''
函数功能：
--------
获取沪深上市公司所属的地域信息。
输入参数：
--------
无
输出参数：
--------
DataFrame
code,代码
name,名称
area,所属地域
'''
# Download data
area = ts.get_area_classified()
# Return Dataframe
return area
def get_area(self, year):
i = ts.get_area_classified()[['code', 'area']]
j = pd.read_csv('profit_data_%d.csv'%year, dtype={'code':str})[['code', 'roe', 'net_profit_ratio']]
j = j[(j.net_profit_ratio>-100)&(j.net_profit_ratio<100)&(j.roe>-100)&(j.roe<100)]
data = pd.merge(i, j, on='code').groupby(by='area').mean()
return data
#!/usr/bin/python
from sqlalchemy import create_engine
import tushare as ts
import os
#result=ts.get_industry_classified()
engine=create_engine('mysql://*****:*****@127.0.0.1/stock?charset=utf8',echo=True)
#result.to_sql('industry',engine)
result=ts.get_area_classified()
result.to_sql('area',engine)
#result.to_excel('/Users/xzp/industry.xlsx')
def typearea(): global dftypearea dftypearea = ts.get_area_classified() dftypearea.insert(0,'uploadtime',nowtime) typearea_tosql()
def getIndustry():
df = ts.get_area_classified()
df.to_csv('area.csv', encoding='gbk')
print(df)
def load_company_industry_info():
#下载加载行业分类数据
try:
rs=ts.get_industry_classified()
sql.write_frame(rs, "company_industry_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载公司行业分类信息ok")
except:
print("下载公司行业分类信息出错")
#下载加载概念分类数据
try:
rs=ts.get_concept_classified()
sql.write_frame(rs, "company_concept_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("载公司概念分类信息ok")
except:
print("下载公司概念分类信息出错")
#下载加载地域分类数据
try:
rs=ts.get_area_classified()
sql.write_frame(rs, "company_area_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载公司区域分类信息ok")
except:
print("下载公司区域分类信息出错")
#下载加载中小板分类数据
try:
rs=ts.get_sme_classified()
sql.write_frame(rs, "company_sme_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载中小板分类数据ok")
except:
print("下载中小板分类数据出错")
#下载加载创业板分类数据
try:
rs=ts.get_gem_classified()
sql.write_frame(rs, "company_gem_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载创业板分类数据ok")
except:
print("下载创业板分类数据出错")
#下载加载st板分类数据
try:
rs=ts.get_st_classified()
sql.write_frame(rs, "company_st_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载st板分类数据ok")
except:
print("下载st板分类数据出错")
#下载加载沪深300板分类数据
try:
rs=ts.get_hs300s()
sql.write_frame(rs, "company_hs300_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载加载沪深300板分类数据ok")
except:
print("下载加载沪深300板分类数据出错")
#下载加载上证50板分类数据
try:
rs=ts.get_sz50s()
sql.write_frame(rs, "company_sz50_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载加载上证50板分类数据ok")
except:
print("下载加载上证50板分类数据出错")
#下载加载中证500板分类数据
try:
rs=ts.get_zz500s()
sql.write_frame(rs, "company_zz500_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载加载中证500板分类数据ok")
except:
print("下载加载中证500板分类数据出错")
#下载加载终止上市分类数据
try:
rs=ts.get_terminated()
sql.write_frame(rs, "company_terminated_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载加载终止上市分类数据ok")
except:
print("下载加载终止上市分类数据出错")
#下载加载暂停上市分类数据
try:
rs=ts.get_suspended()
sql.write_frame(rs, "company_suspended_classified", con=conn_company_classified , flavor='mysql', if_exists='replace',index=True)
print("下载加载暂停上市分类数据ok")
except:
print("下载加载暂停上市分类数据出错")
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 31 14:41:27 2016
@author: colec
"""
import tushare as ts
import csv
file_csv = open('AreaStatistic.csv', 'wb+')
spamwriter = csv.writer(file_csv,dialect='excel')
spamwriter.writerow(['code', 'name', 'area'])
all_stock = ts.get_area_classified()
for code, stockRow in all_stock.iterrows():
areaName = str(stockRow["area"])
if (areaName.find("天津") != -1):
spamwriter.writerow([code, stockRow["name"].decode('utf-8').encode('gb2312'), stockRow["area"].decode('utf-8').encode('gb2312')])
file_csv.close()
def get_location(self):
df = ts.get_area_classified()
print df
# df.to_excel('location.xls')
self.save_to_excel(df,'location.xls')
#coding=utf-8 ''' Created on 2015年6月4日 @author: Administrator ''' import tushare as ts # 行业分类 ts.get_industry_classified() # 概念分类 ts.get_concept_classified() # 地域分类 ts.get_area_classified() # 获取沪深300当前成份股及所占权重 ts.get_hs300s() # 获取中小板股票数据，即查找所有002开头的股票 ts.get_sme_classified() # 获取创业板股票数据，即查找所有300开头的股票 ts.get_gem_classified() # 获取风险警示板股票数据，即查找所有st股票 ts.get_st_classified() # 获取上证50成份股 ts.get_sz50s()
#!/usr/bin/env python
#coding=utf-8
import tushare as ts
import pandas as pd
import time
# 行业分类
inds = ts.get_industry_classified()
inds.columns = ('code', 'name', 'industry')
time.sleep(1)
# 概念分类
concepts = ts.get_concept_classified()
concepts.columns = ('code', 'name', 'concept')
time.sleep(1)
# 地域分类
areas = ts.get_area_classified()
areas.columns = ('code', 'name', 'area')
time.sleep(1)
# 中小板块
smalls = ts.get_sme_classified()
time.sleep(1)
# 创业版
news = ts.get_gem_classified()
time.sleep(1)
# st版块
sts = ts.get_st_classified()
time.sleep(1)
