优化
This commit is contained in:
+2
-2
@@ -6,8 +6,8 @@ import sell_price.zhuge0118A as sellPrice
|
|||||||
s = time.time()
|
s = time.time()
|
||||||
|
|
||||||
ct = '上海'
|
ct = '上海'
|
||||||
rl = '闵行'
|
rl = '嘉定'
|
||||||
lk = '上海康城'
|
lk = '莱茵北郡'
|
||||||
weekend = datetime.datetime.strptime("2018-03-11", "%Y-%m-%d")
|
weekend = datetime.datetime.strptime("2018-03-11", "%Y-%m-%d")
|
||||||
|
|
||||||
sellPrice.out_put_price(ct, rl, lk, weekend)
|
sellPrice.out_put_price(ct, rl, lk, weekend)
|
||||||
|
|||||||
+274
-344
@@ -11,23 +11,11 @@ import numpy
|
|||||||
import collections
|
import collections
|
||||||
import re
|
import re
|
||||||
from fangjia import timer
|
from fangjia import timer
|
||||||
@timer
|
|
||||||
def url_lable(dmi1):
|
|
||||||
|
|
||||||
company_list=['lianjia','zhuge','5i5j','iwjw','fangdd','centanet', 'cityhouse','baixing','ganji','anjuke','58']
|
|
||||||
##有Bug
|
|
||||||
for p in company_list:
|
|
||||||
for k in dmi1.index:
|
|
||||||
ff=dmi1['url'][k]
|
|
||||||
if type(ff)==str:
|
|
||||||
if p in dmi1['url'][k]:
|
|
||||||
dmi1.loc[k,'url']=p
|
|
||||||
return dmi1
|
|
||||||
|
|
||||||
|
|
||||||
def url_to_root(url):
|
def url_to_root(url):
|
||||||
company_list = ['lianjia', 'zhuge', '5i5j', 'iwjw', 'fangdd', 'centanet', 'cityhouse', 'baixing', 'ganji',
|
company_list = ['lianjia', 'zhuge', '5i5j', 'iwjw', 'fangdd', 'centanet', 'cityhouse', 'baixing', 'ganji',
|
||||||
'anjuke', '58']
|
'anjuke', '58.com']
|
||||||
for c in company_list:
|
for c in company_list:
|
||||||
if c in url:
|
if c in url:
|
||||||
return c
|
return c
|
||||||
@@ -35,370 +23,334 @@ def url_to_root(url):
|
|||||||
return url
|
return url
|
||||||
|
|
||||||
|
|
||||||
# @timer
|
@timer
|
||||||
# def url_lable(dmi1):
|
def url_lable(dmi1):
|
||||||
#
|
house_list = dmi1.to_dict('records')
|
||||||
# house_list = dmi1.to_dict('records')
|
for h in house_list:
|
||||||
# for h in house_list:
|
h["url"] = url_to_root(h["url"])
|
||||||
# h["url"] = url_to_root(h["url"])
|
dmi1 = pandas.DataFrame(house_list)
|
||||||
# dmi1 = pandas.DataFrame(house_list)
|
return dmi1
|
||||||
# return dmi1
|
|
||||||
|
|
||||||
|
|
||||||
def drop_rubbish(dd1):
|
def drop_rubbish(dd1):
|
||||||
|
for i in dd1.index:
|
||||||
for i in dd1.index:
|
pp = dd1['url'][i]
|
||||||
pp=dd1['url'][i]
|
|
||||||
|
|
||||||
# print(pp)
|
|
||||||
|
|
||||||
if type(pp)==str:
|
|
||||||
|
|
||||||
if len(pp)>12 :
|
|
||||||
dd1=dd1.drop(i)
|
|
||||||
return dd1
|
|
||||||
|
|
||||||
|
|
||||||
#dd=drop_rubbish(dd1)
|
# print(pp)
|
||||||
|
|
||||||
|
if type(pp) == str:
|
||||||
|
|
||||||
|
if len(pp) > 12:
|
||||||
|
dd1 = dd1.drop(i)
|
||||||
|
return dd1
|
||||||
|
|
||||||
|
|
||||||
|
# dd=drop_rubbish(dd1)
|
||||||
|
|
||||||
|
|
||||||
@timer
|
@timer
|
||||||
def zhuge_out(ddd):
|
def zhuge_out(ddd):
|
||||||
|
# print('我在诸葛文件内',ddd)
|
||||||
#print('我在诸葛文件内',ddd)
|
|
||||||
|
def k_means(pp, clus):
|
||||||
def k_means(pp,clus):
|
|
||||||
from sklearn.cluster import KMeans
|
from sklearn.cluster import KMeans
|
||||||
pv=list(pp)
|
pv = list(pp)
|
||||||
if len(set(pv))>clus:
|
if len(set(pv)) > clus:
|
||||||
gf=numpy.array([pv]).T
|
gf = numpy.array([pv]).T
|
||||||
estimator = KMeans(n_clusters=clus)#构造聚类器
|
estimator = KMeans(n_clusters=clus) # 构造聚类器
|
||||||
estimator.fit(gf)#聚类
|
estimator.fit(gf) # 聚类
|
||||||
label_pred = estimator.labels_ #获取聚类标签
|
label_pred = estimator.labels_ # 获取聚类标签
|
||||||
|
|
||||||
aa=collections.Counter(label_pred)
|
aa = collections.Counter(label_pred)
|
||||||
|
|
||||||
#print('aa=',aa)
|
# print('aa=',aa)
|
||||||
v=pandas.Series(aa)
|
v = pandas.Series(aa)
|
||||||
gg=list(v)
|
gg = list(v)
|
||||||
index_max=gg.index(max(gg))
|
index_max = gg.index(max(gg))
|
||||||
|
|
||||||
centroids = estimator.cluster_centers_ #获取聚类中心
|
centroids = estimator.cluster_centers_ # 获取聚类中心
|
||||||
#inertia = estimator.inertia_ # 获取聚类准则的总和
|
# inertia = estimator.inertia_ # 获取聚类准则的总和
|
||||||
center=centroids[index_max][0]
|
center = centroids[index_max][0]
|
||||||
return int(center)
|
return int(center)
|
||||||
else:
|
else:
|
||||||
return int(pp.mean())
|
return int(pp.mean())
|
||||||
|
|
||||||
def spilit_number_from_string(dd):
|
def spilit_number_from_string(dd):
|
||||||
|
|
||||||
for pl in dd.index:
|
for pl in dd.index:
|
||||||
bte=dd['build_date'][pl]
|
bte = dd['build_date'][pl]
|
||||||
if bte!=None:
|
if bte != None:
|
||||||
dd['build_date'][pl]=re.sub("\D", "", str(bte))
|
dd['build_date'][pl] = re.sub("\D", "", str(bte))
|
||||||
|
|
||||||
most_build=Counter(dd['build_date']).most_common(1)
|
most_build = Counter(dd['build_date']).most_common(1)
|
||||||
dd['build_date']=dd['build_date'].fillna(most_build[0][0])
|
dd['build_date'] = dd['build_date'].fillna(most_build[0][0])
|
||||||
|
|
||||||
return dd[dd['build_date']==most_build[0][0]]
|
return dd[dd['build_date'] == most_build[0][0]]
|
||||||
|
|
||||||
def lower_dimention(dd):
|
def lower_dimention(dd):
|
||||||
|
|
||||||
url_set=list( set(dd['url']) )
|
url_set = list(set(dd['url']))
|
||||||
|
|
||||||
url_price=pandas.Series()
|
url_price = pandas.Series()
|
||||||
|
|
||||||
index_list=[]
|
index_list = []
|
||||||
for i in url_set:
|
for i in url_set:
|
||||||
dd1=dd[dd['url']==i]
|
dd1 = dd[dd['url'] == i]
|
||||||
if dd1.shape[0]<=2:
|
if dd1.shape[0] <= 2:
|
||||||
index_list.extend(list(dd1.index))
|
index_list.extend(list(dd1.index))
|
||||||
else:
|
else:
|
||||||
most_price=k_means(dd1['total_price'],3)*1.0
|
most_price = k_means(dd1['total_price'], 3) * 1.0
|
||||||
|
|
||||||
url_price[i]=round(most_price,2)
|
url_price[i] = round(most_price, 2)
|
||||||
|
|
||||||
for j in index_list:
|
for j in index_list:
|
||||||
url_price[dd['url'][j]]=dd['total_price'][j]
|
url_price[dd['url'][j]] = dd['total_price'][j]
|
||||||
|
|
||||||
return url_price
|
return url_price
|
||||||
|
|
||||||
|
def k_means_ratio(pp, clus):
|
||||||
def k_means_ratio(pp,clus):
|
|
||||||
from sklearn.cluster import KMeans
|
from sklearn.cluster import KMeans
|
||||||
pv=list(pp)
|
pv = list(pp)
|
||||||
if len(set(pv))>3:
|
if len(set(pv)) > 3:
|
||||||
gf=numpy.array([pv]).T
|
gf = numpy.array([pv]).T
|
||||||
estimator = KMeans(n_clusters=clus)#构造聚类器
|
estimator = KMeans(n_clusters=clus) # 构造聚类器
|
||||||
estimator.fit(gf)#聚类
|
estimator.fit(gf) # 聚类
|
||||||
label_pred = estimator.labels_ #获取聚类标签
|
label_pred = estimator.labels_ # 获取聚类标签
|
||||||
|
|
||||||
aa=collections.Counter(label_pred)
|
aa = collections.Counter(label_pred)
|
||||||
|
|
||||||
#print('aa=',aa)
|
# print('aa=',aa)
|
||||||
v=pandas.Series(aa)
|
v = pandas.Series(aa)
|
||||||
v=v.sort_values(ascending=False)
|
v = v.sort_values(ascending=False)
|
||||||
|
|
||||||
ratio=v.iloc[0]/v.iloc[1]
|
ratio = v.iloc[0] / v.iloc[1]
|
||||||
|
|
||||||
return round(ratio,2)
|
return round(ratio, 2)
|
||||||
else:
|
else:
|
||||||
return 1
|
return 1
|
||||||
|
|
||||||
|
def popo(dmi, columns):
|
||||||
def popo(dmi,columns):
|
|
||||||
|
most = Counter(dmi[columns]).most_common(1)
|
||||||
most=Counter(dmi[columns]).most_common(1)
|
# print(dmi)
|
||||||
#print(dmi)
|
dmi2 = dmi[dmi[columns] == most[0][0]]
|
||||||
dmi2=dmi[dmi[columns]==most[0][0]]
|
# print('dmi2=',dmi2)
|
||||||
#print('dmi2=',dmi2)
|
|
||||||
|
dmiy = lower_dimention(dmi2)
|
||||||
dmiy=lower_dimention(dmi2)
|
# print(dmiy)
|
||||||
#print(dmiy)
|
ratio2 = (dmiy.max() - dmiy.min()) / dmiy.mean()
|
||||||
ratio2=(dmiy.max()-dmiy.min())/dmiy.mean()
|
ww1 = round(k_means(dmiy, 3), 2)
|
||||||
ww1=round(k_means( dmiy ,3 ),2)
|
ww2 = round(k_means(dmi2['area'].dropna(), 3), 2)
|
||||||
ww2=round(k_means(dmi2['area'].dropna(),3),2)
|
ww3 = round(k_means(dmi2['room'].dropna(), 3), 2)
|
||||||
ww3=round(k_means(dmi2['room'].dropna(),3),2)
|
ww4 = list(dmiy.index)
|
||||||
ww4=list(dmiy.index)
|
|
||||||
|
# ww5=round(k_means_ratio(dmi['total_price'].dropna(),3),2)
|
||||||
#ww5=round(k_means_ratio(dmi['total_price'].dropna(),3),2)
|
ww5 = round(k_means_ratio(dmiy, 3), 2)
|
||||||
ww5=round(k_means_ratio(dmiy,3),2)
|
# print('dmi2=',dmi2)
|
||||||
#print('dmi2=',dmi2)
|
|
||||||
|
if (ratio2 < 0.15 and len(dmiy) > 1) or (ratio2 > 1.2 and len(dmiy) > 1):
|
||||||
if (ratio2<0.15 and len(dmiy)>1) or (ratio2>1.2 and len(dmiy)>1) :
|
return [round(ww1, 2), round(ww2, 2), round(ww3, 2), round(100, 2), ww4, ww5]
|
||||||
|
|
||||||
return [round(ww1,2),round(ww2,2),round(ww3,2),round(100,2),ww4,ww5]
|
# print('area_filter',dd)
|
||||||
|
|
||||||
#print('area_filter',dd)
|
|
||||||
"""
|
"""
|
||||||
else:
|
else:
|
||||||
return [round(ww1,2),round(ww2,2),round(ww3,2),round(len(dmiy),2),ww4,ww5]
|
return [round(ww1,2),round(ww2,2),round(ww3,2),round(len(dmiy),2),ww4,ww5]
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
def room_define(dd, j):
|
||||||
|
|
||||||
|
pdd = numpy.array([[None, None, None, None, None, None],
|
||||||
def room_define(dd,j):
|
[None, None, None, None, None, None],
|
||||||
|
[None, None, None, None, None, None]])
|
||||||
pdd=numpy.array([[None,None,None,None,None,None],
|
|
||||||
[None,None,None,None,None,None],
|
d4 = dd[dd['room'] == j]
|
||||||
[None,None,None,None,None,None]])
|
|
||||||
|
# print('room=',j,'的样本个数为',d4.shape[0])
|
||||||
|
|
||||||
d4=dd[dd['room']==j]
|
pdd[0] = popo(d4, 'room')
|
||||||
|
|
||||||
#print('room=',j,'的样本个数为',d4.shape[0])
|
most_area = Counter(d4['area']).most_common(1)
|
||||||
|
|
||||||
pdd[0]=popo(d4,'room')
|
if most_area[0][1] >= 2:
|
||||||
|
|
||||||
most_area=Counter(d4['area']).most_common(1)
|
d4area = d4[d4['area'] == most_area[0][0]]
|
||||||
|
|
||||||
|
pdd[1] = popo(d4area, 'area')
|
||||||
|
|
||||||
if most_area[0][1]>=2:
|
most_floor = Counter(d4area['floor']).most_common(1)
|
||||||
|
|
||||||
d4area=d4[d4['area']==most_area[0][0]]
|
if most_floor[0][1] >= 2:
|
||||||
|
d4floor = d4area[d4area['floor'] == most_floor[0][0]]
|
||||||
pdd[1]=popo(d4area,'area')
|
# print('d4floor=',d4floor)
|
||||||
|
pdd[2] = popo(d4floor, 'floor')
|
||||||
most_floor=Counter(d4area['floor']).most_common(1)
|
|
||||||
|
return (pdd)
|
||||||
if most_floor[0][1]>=2:
|
|
||||||
d4floor=d4area[d4area['floor']==most_floor[0][0]]
|
def dout(room_pair, dd):
|
||||||
#print('d4floor=',d4floor)
|
|
||||||
pdd[2]=popo(d4floor,'floor')
|
bbb = []
|
||||||
|
# print('room_pair=',room_pair)
|
||||||
return ( pdd )
|
# print('dd=',dd)
|
||||||
|
|
||||||
|
|
||||||
def dout(room_pair,dd):
|
|
||||||
|
|
||||||
bbb=[]
|
|
||||||
#print('room_pair=',room_pair)
|
|
||||||
#print('dd=',dd)
|
|
||||||
for j in room_pair.index:
|
for j in room_pair.index:
|
||||||
|
kgg = pandas.DataFrame(room_define(dd, j),
|
||||||
kgg=pandas.DataFrame(room_define(dd,j),
|
columns=['total_price', 'area', 'room', 'credit', 'url_list', 'choose_index'])
|
||||||
columns=['total_price','area','room','credit','url_list','choose_index'])
|
kgg['avg_price'] = kgg['total_price'] / kgg['area']
|
||||||
kgg['avg_price']=kgg['total_price']/kgg['area']
|
|
||||||
|
# print('kgg=',kgg)
|
||||||
#print('kgg=',kgg)
|
|
||||||
|
bbb.append(kgg)
|
||||||
bbb.append(kgg)
|
|
||||||
return bbb
|
return bbb
|
||||||
|
|
||||||
|
def dsf_average_price(ct, rl, lk, timd, timm):
|
||||||
|
|
||||||
|
client = pymongo.MongoClient('192.168.0.136', 27017) # '192.168.0.65',27777
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
def dsf_average_price(ct,rl,lk,timd,timm):
|
|
||||||
|
|
||||||
client = pymongo.MongoClient('192.168.0.136',27017) #'192.168.0.65',27777
|
|
||||||
db = client.fangjia
|
db = client.fangjia
|
||||||
seawater = db.average_statistics
|
seawater = db.average_statistics
|
||||||
|
|
||||||
timd1=timd//100
|
timd1 = timd // 100
|
||||||
timm1=timm//100
|
timm1 = timm // 100
|
||||||
|
|
||||||
query = {"city":ct,"region":rl,
|
query = {"city": ct, "region": rl,
|
||||||
"name":{"$in":lk},
|
"name": {"$in": lk},
|
||||||
"s_date":{"$gt":timd1,"$lt":timm1}}
|
"s_date": {"$gt": timd1, "$lt": timm1}}
|
||||||
#lt= seawater.count(query)
|
# lt= seawater.count(query)
|
||||||
#print(lt)
|
# print(lt)
|
||||||
pos = list(seawater.find(query).limit(3000))
|
pos = list(seawater.find(query).limit(3000))
|
||||||
|
|
||||||
data=pandas.DataFrame(pos)
|
data = pandas.DataFrame(pos)
|
||||||
del pos
|
del pos
|
||||||
return data
|
return data
|
||||||
|
|
||||||
|
dsf_name_list = {'soufang_new_price', 'soufang_esf_price',
|
||||||
dsf_name_list={'soufang_new_price','soufang_esf_price',
|
'anjuke_new_price', 'anjuke_esf_price',
|
||||||
'anjuke_new_price','anjuke_esf_price',
|
'sina_new_price', 'sina_esf_price',
|
||||||
'sina_new_price','sina_esf_price',
|
'ganji_esf_price', 'cric_new_price',
|
||||||
'ganji_esf_price','cric_new_price',
|
'cric_esf_price',
|
||||||
'cric_esf_price',
|
'lianjia_esf_price', 'zhugezhaofang_esf_price'
|
||||||
'lianjia_esf_price','zhugezhaofang_esf_price'
|
|
||||||
|
'fanggugu_esf_price', 'yungujia_esf_price'
|
||||||
'fanggugu_esf_price','yungujia_esf_price'
|
}
|
||||||
}
|
|
||||||
|
company_list = ['lianjia', 'zhuge', '5i5j', 'iwjw', 'fangdd', 'centanet',
|
||||||
|
'cityhouse', 'baixing', 'ganji', 'anjuke', '58']
|
||||||
|
|
||||||
|
company_name = ['链家', '诸葛找房', '我爱我家', '爱屋吉屋', '房多多', '中原',
|
||||||
|
'城市房产', '百姓', '赶集', '安居客', '58同城']
|
||||||
|
company_values = [10, 10, 5, 5, 3, 2,
|
||||||
company_list=['lianjia','zhuge','5i5j','iwjw','fangdd','centanet',
|
1, 1, 1, 1, 1]
|
||||||
'cityhouse','baixing','ganji','anjuke','58']
|
|
||||||
|
# companypp=[]
|
||||||
company_name=['链家','诸葛找房','我爱我家','爱屋吉屋','房多多','中原',
|
|
||||||
'城市房产','百姓','赶集','安居客','58同城']
|
|
||||||
company_values=[10, 10, 5, 5, 3, 2,
|
|
||||||
1 , 1, 1, 1, 1]
|
|
||||||
|
|
||||||
#companypp=[]
|
|
||||||
import numpy as np
|
import numpy as np
|
||||||
|
|
||||||
a=np.array([company_name,company_values])
|
a = np.array([company_name, company_values])
|
||||||
|
|
||||||
company_pandas=pandas.DataFrame(a.T,columns=['name','values'],index=company_list)
|
company_pandas = pandas.DataFrame(a.T, columns=['name', 'values'], index=company_list)
|
||||||
name_pair=pandas.Series(company_list,index=company_name)
|
name_pair = pandas.Series(company_list, index=company_name)
|
||||||
|
|
||||||
|
|
||||||
def add_floor(ppd):
|
def add_floor(ppd):
|
||||||
if 'floor' not in ppd.columns:
|
if 'floor' not in ppd.columns:
|
||||||
ppd['floor']= 6
|
ppd['floor'] = 6
|
||||||
return ppd
|
return ppd
|
||||||
|
|
||||||
#ddd=url_lable(company_list,ddd)
|
|
||||||
|
|
||||||
|
|
||||||
@timer
|
|
||||||
def opfm(ddo,fm):
|
|
||||||
|
|
||||||
floor_column=ddo[fm].dropna()
|
# ddd=url_lable(company_list,ddd)
|
||||||
if len(floor_column)>0:
|
|
||||||
|
@timer
|
||||||
#print('floor_column=',floor_column)
|
def opfm(ddo, fm):
|
||||||
most_floor=Counter(floor_column).most_common(1)
|
|
||||||
#print('floor=',ddo['floor'])
|
floor_column = ddo[fm].dropna()
|
||||||
ddo[fm]=ddo[fm].fillna(most_floor[0][0])
|
if len(floor_column) > 0:
|
||||||
|
|
||||||
|
# print('floor_column=',floor_column)
|
||||||
|
most_floor = Counter(floor_column).most_common(1)
|
||||||
|
# print('floor=',ddo['floor'])
|
||||||
|
ddo[fm] = ddo[fm].fillna(most_floor[0][0])
|
||||||
return ddo
|
return ddo
|
||||||
else:
|
else:
|
||||||
ddo[fm]=ddo[fm].fillna(2)
|
ddo[fm] = ddo[fm].fillna(2)
|
||||||
return ddo
|
return ddo
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
@timer
|
@timer
|
||||||
def export_pp(ddd):
|
def export_pp(ddd):
|
||||||
|
|
||||||
ddo=ddd
|
|
||||||
#ddo=ddo.drop(0)
|
|
||||||
#print('ddo=',ddo)
|
|
||||||
ddo=add_floor(ddo)
|
|
||||||
#print('ddo=',ddo)
|
|
||||||
|
|
||||||
if ddo.shape[0]>1:
|
|
||||||
|
|
||||||
|
|
||||||
ddo=opfm(ddo,'floor')
|
|
||||||
ddo=opfm(ddo,'room')
|
|
||||||
|
|
||||||
|
|
||||||
|
ddo = ddd
|
||||||
ddo['area']=(ddo['area']//2)*2+1
|
# ddo=ddo.drop(0)
|
||||||
|
# print('ddo=',ddo)
|
||||||
#dd1=url_lable(company_list,ddo)
|
ddo = add_floor(ddo)
|
||||||
|
# print('ddo=',ddo)
|
||||||
#dd=drop_rubbish(dd1)
|
|
||||||
|
if ddo.shape[0] > 1:
|
||||||
#print(Counter(dd['url']))
|
|
||||||
dd=ddo
|
ddo = opfm(ddo, 'floor')
|
||||||
mr=Counter(dd['room'])
|
ddo = opfm(ddo, 'room')
|
||||||
room_pair=pandas.Series(mr)
|
|
||||||
room_pair1=room_pair.sort_values(ascending=False)
|
ddo['area'] = (ddo['area'] // 2) * 2 + 1
|
||||||
room_pair=room_pair1.iloc[:3]
|
|
||||||
opt=dout(room_pair,dd)
|
# dd1=url_lable(company_list,ddo)
|
||||||
|
|
||||||
|
# dd=drop_rubbish(dd1)
|
||||||
|
|
||||||
|
# print(Counter(dd['url']))
|
||||||
|
dd = ddo
|
||||||
|
mr = Counter(dd['room'])
|
||||||
|
room_pair = pandas.Series(mr)
|
||||||
|
room_pair1 = room_pair.sort_values(ascending=False)
|
||||||
|
room_pair = room_pair1.iloc[:3]
|
||||||
|
opt = dout(room_pair, dd)
|
||||||
return opt
|
return opt
|
||||||
else:
|
else:
|
||||||
return pandas.DataFrame()
|
return pandas.DataFrame()
|
||||||
|
|
||||||
opt=export_pp(ddd)
|
opt = export_pp(ddd)
|
||||||
|
|
||||||
#print('opt=',opt)
|
# print('opt=',opt)
|
||||||
|
|
||||||
def k_means22(pp,clus):
|
def k_means22(pp, clus):
|
||||||
from sklearn.cluster import KMeans
|
from sklearn.cluster import KMeans
|
||||||
pv=list(pp)
|
pv = list(pp)
|
||||||
if len(set(pv))>1:
|
if len(set(pv)) > 1:
|
||||||
gf=numpy.array([pv]).T
|
gf = numpy.array([pv]).T
|
||||||
estimator = KMeans(n_clusters=clus)#构造聚类器
|
estimator = KMeans(n_clusters=clus) # 构造聚类器
|
||||||
estimator.fit(gf)#聚类
|
estimator.fit(gf) # 聚类
|
||||||
label_pred = estimator.labels_ #获取聚类标签
|
label_pred = estimator.labels_ # 获取聚类标签
|
||||||
|
|
||||||
aa=collections.Counter(label_pred)
|
aa = collections.Counter(label_pred)
|
||||||
|
|
||||||
#print('aa=',aa)
|
# print('aa=',aa)
|
||||||
v=pandas.Series(aa)
|
v = pandas.Series(aa)
|
||||||
gg=list(v)
|
gg = list(v)
|
||||||
index_max=gg.index(max(gg))
|
index_max = gg.index(max(gg))
|
||||||
|
|
||||||
centroids = estimator.cluster_centers_ #获取聚类中心
|
centroids = estimator.cluster_centers_ # 获取聚类中心
|
||||||
#inertia = estimator.inertia_ # 获取聚类准则的总和
|
# inertia = estimator.inertia_ # 获取聚类准则的总和
|
||||||
center=centroids[index_max][0]
|
center = centroids[index_max][0]
|
||||||
return round(center,2)
|
return round(center, 2)
|
||||||
else:
|
else:
|
||||||
return pp.mean()
|
return pp.mean()
|
||||||
|
|
||||||
|
|
||||||
def out_put_price(opt):
|
def out_put_price(opt):
|
||||||
|
|
||||||
re = pandas.concat(opt)
|
re = pandas.concat(opt)
|
||||||
|
|
||||||
#print(re)
|
# print(re)
|
||||||
|
|
||||||
oo=re[re['credit']==100]
|
oo = re[re['credit'] == 100]
|
||||||
oo1=re.dropna()
|
oo1 = re.dropna()
|
||||||
|
|
||||||
#print(oo)
|
# print(oo)
|
||||||
if oo.shape[0]>1:
|
if oo.shape[0] > 1:
|
||||||
return round(k_means22( oo['avg_price'] ,2 ),2)
|
return round(k_means22(oo['avg_price'], 2), 2)
|
||||||
elif oo1.shape[0]>0:
|
elif oo1.shape[0] > 0:
|
||||||
|
|
||||||
re1=re.sort_values(by='credit',ascending=False)
|
re1 = re.sort_values(by='credit', ascending=False)
|
||||||
re2=re1.sort_values(by='choose_index',ascending=False)
|
re2 = re1.sort_values(by='choose_index', ascending=False)
|
||||||
#print(re2)
|
# print(re2)
|
||||||
#print('#'*20)
|
# print('#'*20)
|
||||||
return (re2['avg_price'].iloc[0])
|
return (re2['avg_price'].iloc[0])
|
||||||
else:
|
else:
|
||||||
#print(ddd['avg'].dropna())
|
# print(ddd['avg'].dropna())
|
||||||
kkm=k_means(ddd['avg'].dropna(),2)
|
kkm = k_means(ddd['avg'].dropna(), 2)
|
||||||
return kkm
|
return kkm
|
||||||
|
|
||||||
return int(out_put_price(opt))
|
return int(out_put_price(opt))
|
||||||
|
|
||||||
|
|
||||||
@@ -435,25 +387,3 @@ ddd=some_district_information(ct,rl,lk,timd,timm)
|
|||||||
|
|
||||||
df=zhuge_out(ddd)
|
df=zhuge_out(ddd)
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user