def bi_pruning(q_id, q, k, index, cache):
IO = 0
partitions = list(common.partitions(q, index.space, 6))
region_list = list()
points = index.points
vd = index.voronoi_diagram
for partition in partitions:
h = MinHeap()
h.push((0, q_id, q))
visited = {q_id}
knn = list()
while len(h) > 0 and len(knn) < k:
dist, o, p = h.pop()
if o != q_id and partition.intersects(p):
knn.append((o, p, dist))
for neighbor in vd.neighbors(o):
if neighbor not in visited:
visited.add(neighbor)
if neighbor in cache:
neighbor_p = cache[neighbor]
else:
neighbor_p = points[neighbor]
cache[neighbor] = neighbor_p
IO += 1
if partition.intersects(vd.cell(neighbor)):
h.push((neighbor_p.distance(q), neighbor, neighbor_p))
if len(knn) > 0:
r = knn[-1][2]
if r > 0:
region_list.append(
common.sector(q, r, partition.angles).buffer(0.01))
region = reduce(lambda x, y: x.union(y), region_list)
return region, IO
def pruning(q_id, q, k, index, partition_num):
partitions = common.partitions(q, index.space, partition_num)
sigLists = [[] for i in range(partition_num)]
upper_arc_radius_heaps = [common.MaxHeap() for i in range(partition_num)]
shaded_areas = [calculate_shaded_area(partition, partition.r) for partition in partitions]
h = common.MinHeap()
IO = 0
h.push((0, index.root))
while len(h) > 0:
e_dist, e = h.pop()
if may_contains_significant_facility(e, shaded_areas):
if e.is_data_node:
pruneSpace(q_id, e, k, partitions, sigLists, upper_arc_radius_heaps, shaded_areas)
else:
for child in e.children:
h.push((child.geom.distance(q), child))
IO += 1
unpruned_area_list = list()
for i in range(partition_num):
r_b = min(upper_arc_radius_heaps[i].first(), partitions[i].r)
angles = [2 * pi / partition_num * i, 2 * pi / partition_num * (i + 1)]
if r_b > 0:
unpruned_area_list.append(common.sector(q, r_b, angles).buffer(0.01))
unpruned_area = reduce(lambda x, y: x.union(y), unpruned_area_list)
return sigLists, unpruned_area, IO
def calculate_shaded_area(partition, bounding_arc_radius):
if bounding_arc_radius == 0:
return partition.origin
if bounding_arc_radius == float('inf'):
bounding_arc_radius = partition.r
sector = common.sector(partition.o, bounding_arc_radius * 2, partition.angles)
m, n = get_M_N(partition, bounding_arc_radius)
circle_m = common.circle(m, bounding_arc_radius)
circle_n = common.circle(n, bounding_arc_radius)
return sector.union(circle_m).union(circle_n)
def bi_pruning(q_id, q, k, index, cache):
IO = 0
partitions = list(common.partitions(q, index.space, 6))
region_list = list()
points = index.points
vd = index.voronoi_diagram
visited = {q_id}
H = common.MinHeap()
S = [common.MaxHeap() for i in range(6)]
for neighbor_id in vd.neighbors(q_id):
if neighbor_id in cache:
neighbor_p = cache[neighbor_id]
else:
neighbor_p = points[neighbor_id]
cache[neighbor_id] = neighbor_p
IO += 1
H.push((1, neighbor_id, neighbor_p))
visited.add(neighbor_id)
while len(H) > 0:
gd_p, p_id, p = H.pop()
for i in range(6):
if partitions[i].intersects(p):
if len(S[i]) < k:
dist_bound = float('inf')
else:
dist_bound = S[i].first()[0]
dist_p = p.distance(q)
if gd_p <= k and dist_p < dist_bound:
S[i].push((dist_p, p_id, p))
for neighbor_id in vd.neighbors(p_id):
if neighbor_id not in visited:
if neighbor_id in cache:
neighbor_p = cache[neighbor_id]
else:
neighbor_p = points[neighbor_id]
cache[neighbor_id] = neighbor_p
IO += 1
gd_neighbor = gd_p + 1
visited.add(neighbor_id)
H.push((gd_neighbor, neighbor_id, neighbor_p))
for i in range(6):
s = sorted(S[i])
if len(s) >= k:
r = s[k - 1][0]
elif len(s) > 0:
r = s[-1][0]
else:
r = 0
if r > 0:
region_list.append(
common.sector(q, r, partitions[i].angles).buffer(0.01))
region = reduce(lambda x, y: x.union(y), region_list)
return region, IO
def hindenburgomen():
tcode={}
codenumber=[]
xcode,k,X,Y=[],[],[],[]
Rsq=pd.DataFrame()
index='000001'#上证指数
sectorcode="2000032255"#上证A股成分
startdate='20160101'#起始日期
enddate='20161231'#截止日期
#后推30日获取
Ndate=c.getdate(enddate,30)
enddateN30=Ndate.Dates[0]
date=c.tradedates(startdate,enddateN30)
#获取上证A股的板块成分，每日新增的代码也获取对应的收盘价数据
for i in range(len(date.Dates)-30):
if(i==0):
code = c.sector(sectorcode, date.Dates[i])
data=c.csd(code.Codes,"CLOSE",startdate,enddateN30,'Period=1,ispandas=1')
codenumber=code.Codes
code2=code
else:
code1=c.sector(sectorcode, date.Dates[i])
addcode = [i for i in code1.Codes if i not in code2.Codes]
if(len(addcode)!=0):
adddata=c.csd(addcode,"CLOSE",startdate,enddateN30,'Period=1,ispandas=1')
data=data.append(adddata)
codenumber=codenumber+addcode
code2 = code1
data.to_csv('data.csv')
data=pd.read_csv('data.csv')
data=data.set_index('CODES')
#获取对比指数收盘价数据
indexdata=c.csd(index,"CLOSE",startdate,enddateN30,'Period=1,ispandas=1,rowindex=1')
#板块成分和指数线性回归，并计算30日间隔的Rsq系数
for i in range(len(codenumber)):
for x, y in zip(data.ix[codenumber[i],"CLOSE"], indexdata["CLOSE"]):
X.append([float(x)])
Y.append(float(y))
for j in range(0,len(Y)):
try:
regr = linear_model.LinearRegression()
regr=regr.fit(X[j:j+30], Y[j:j+30])
regr=regr.score(X[j:j + 30], Y[j:j + 30])
xcode.append(regr)
if(j+30>=len(Y)-1):
break
except:
xcode.append(0)
tcode[codenumber[i]]=xcode
xcode=[]
X=[]
Y=[]
Rsq=pd.DataFrame(tcode)
Rsq.to_csv('rsq.csv',index=None)
Rsq=pd.read_csv('rsq.csv')
#求每日Rsq系数的均值
FORMAT ='%d/%02d/%02d'
Rsq=Rsq.T
mean=pd.DataFrame(Rsq.mean(),columns=['MEAN'])
for i in range(Rsq.columns.size):
mean['MEAN']=mean['MEAN']*len(Rsq)/len(Rsq[Rsq[i]!=0.0])
mean['DATE']=date.Dates[30:]
#求每日Rsq系数的均值间隔3日变动幅度超过30%的日期进行标记
for i in range(len(mean)-33):
x=(mean.ix[i,'MEAN']-mean.ix[i+3,'MEAN'])/mean.ix[i,'MEAN']
if (x >0.3 or x<-0.3):
k.append(mean.ix[i + 3, 'DATE'])
list1=mean.ix[i + 3, 'DATE'].split("/")
list1=FORMAT % (int(list1[0]), int(list1[1]), int(list1[2]))
indexdata.ix[indexdata['DATES']==list1, 'MARKER'] = 1
else:
pass
#绘制指数收盘价
indexdata=indexdata.set_index('DATES')
indexdata.index=pd.to_datetime(indexdata.index)
#标记吉登堡凶兆所标记的时间点
for i in range(0,len(indexdata.ix[indexdata["MARKER"]==1,"CLOSE"])):
plt.scatter(pd.to_datetime((indexdata.ix[indexdata["MARKER"]==1,"CLOSE"]).index)[i],indexdata.ix[indexdata["MARKER"]==1,"CLOSE"][i], color='red',marker='o')
indexdata['CLOSE'].plot(figsize=(10,8))
plt.xlabel("date")
plt.ylabel("close")
plt.title(u"000001.SH")
plt.show()