def LDM(PreStartYear,
PreEndYear,
buildingarea,
loaddensity,
pretype="全社会用电量",
city="云南省"):
def Density(n, Dlist, Plist):
#n为所画片区，Dlist为对应的负荷密度，Plist为对应的建筑面积
load = 0
for i in range(n):
load = Dlist[i] * Plist[i] + load
return load
data1 = pd.read_csv(buildingarea, encoding="UTF-8")
data2 = pd.read_csv(loaddensity, encoding="UTF-8")
columns = data1.columns
columns2 = data2.columns
if len(columns) != len(columns2):
raise ValueError("负荷密度和建筑密度列表不匹配，请重新上传")
elif not (data1[columns[0]].values == data2[columns2[0]].values).all():
raise ValueError("负荷密度和建筑密度列表不匹配，请重新上传")
else:
StartYear = str(data1[columns[0]].values[0])
EndYear = str(data1[columns[0]].values[-1])
#预测建筑用地数据
building = predict.pre(data1.loc[:, [columns[0], columns[1]]],
columns[1], int(PreStartYear), int(PreEndYear))
for i in range(2, len(columns)):
c = predict.pre(data1.loc[:, [columns[0], columns[i]]], columns[i],
int(PreStartYear), int(PreEndYear))
building = pd.merge(building, c, on=columns[0])
#预测负荷密度
density = predict.pre(data2.loc[:, [columns2[0], columns2[1]]],
columns2[1], int(PreStartYear), int(PreEndYear))
for i in range(2, len(columns2)):
c = predict.pre(data2.loc[:, [columns2[0], columns2[i]]],
columns2[i], int(PreStartYear), int(PreEndYear))
density = pd.merge(density, c, on=columns2[0])
#读取历史负荷数据
period = int(EndYear) - int(StartYear) + 1
finaldata = []
name = [pretype]
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
trainx = []
start = 0 #训练集的起始位置
for i in range(start, period):
d = [building[columns[-1]].values[i]]
b = [density[columns[-1]].values[i]]
trainx.append(Density(1, d, b))
trainy = []
trainyear = []
for j in range(period):
if int(final.index.values[j]) in data1["year"].values[start:]:
trainy.append(final[pretype].values[j])
trainyear.append(final.index.values[j])
prex = []
for a in range(period, len(building.values)):
d = [building[columns[-1]].values[a]]
b = [density[columns[-1]].values[a]]
prex.append(Density(1, d, b))
trainx = np.array(trainx).reshape(-1, 1)
trainy = np.array(trainy).reshape(-1, 1)
prex = np.array(prex).reshape(-1, 1)
#训练模型
reg = LinearRegression().fit(trainx, trainy)
prey = [x * reg.coef_[0][0] + reg.intercept_[0] for x in prex]
pretrainy = [tx * reg.coef_[0][0] + reg.intercept_[0] for tx in trainx]
ypre = np.array(prey).reshape(1, -1).squeeze()
ytrain = np.array(pretrainy).reshape(1, -1)
mape = MAPE(pretrainy, trainx)
rmse = RMSE(pretrainy, trainx)
#返回结果
result = {
"trainfromyear": StartYear,
"traintoyear": EndYear,
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
def PCAIndustry(StartYear,EndYear,PreStartYear,PreEndYear,pretype,econamelist,city="云南省"):
if city=="云南省":
name=[pretype]
finaldata=[]
period=int(PreEndYear)-int(PreStartYear)+1
historyyear=np.arange(int(StartYear),int(EndYear)+1)
#读取历史负荷数据
datajson=getData("云南省_year_电力电量类-行业", pretype, StartYear, EndYear)
# print(datajson)
data=json.loads(datajson)
finaldata.append(data)
#读取经济数据
for i in range(len(econamelist)):
ecodatajson=getData("云南省_year_社会经济类", econamelist[i], StartYear, EndYear)
ecodata=json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final=pd.DataFrame(finaldata,index=name)
final=final.T
final["Year"]=historyyear
#预测经济数据
# print(logfinal[econamelist[0]].to_frame().column)
eco=preeco.pre(final,econamelist[0],PreStartYear,PreEndYear)
for j in range(1,len(econamelist)):
c=preeco.pre(final,econamelist[j],PreStartYear,PreEndYear)
eco=pd.merge(eco,c,on="year")
Index=eco.columns[1:].tolist()#经济特征名称
##对特征数据进行归一化处理
scaler = StandardScaler()
scaler.fit(eco[Index].values)
Data_eco_scaler = scaler.transform(eco[Index].values)
Data_eco_scaler=pd.DataFrame(data=Data_eco_scaler,columns=Index)
Data_eco_scaler["Year"]=eco["year"].values#归一化后的特征数据
#获得训练数据集合测试数据集
train_start_year=int(StartYear)
train_end_year=int(StartYear)+math.ceil(len(historyyear)*0.7)
test_start_year=int(StartYear)+math.ceil(len(historyyear)*0.7)
test_end_year=int(EndYear)
x_train=Data_eco_scaler.loc[Data_eco_scaler["Year"].isin(range(train_start_year,train_end_year+1))]
y_train=final.loc[final["Year"].isin(range(train_start_year,train_end_year+1))]
x_test=Data_eco_scaler.loc[Data_eco_scaler["Year"].isin(range(test_start_year,test_end_year+1))]
y_test=final.loc[final["Year"].isin(range(test_start_year,test_end_year+1))]
#获取合适的PCA维度
pca = PCA(0.9)
principalComponents = pca.fit_transform(Data_eco_scaler[Index].values)
n_components = pca.n_components_#得到PCA的维度
#print("n_components = ",pca.n_components_)
#进行PCA分析
pca = PCA(n_components)
pca.fit(x_train[Index].values)
x_train_pca=pca.transform(x_train[Index].values)
y_train_pca=y_train[pretype]
x_test_pca=pca.transform(x_test[Index].values)
y_test_pca=y_test[pretype]
#建立线性回归
pca_model = LinearRegression()
pca_model.fit(x_train_pca, y_train_pca)
pca_predict = pca_model.predict(x_test_pca)
#评价指标
rmse = RMSE(pca_predict,y_test_pca)
mape = MAPE(pca_predict,y_test_pca)
#保存训练结果
# trainyear=[]
# for t in y_test_pca:
# for d in final.values:
# if t>d[1]-5 and t<d[1]+5:
# trainyear.append(d[0])
# break
trainyear=[]
for t in y_test_pca:
count=-1
for d in final[pretype]:
count+=1
if t>d-5 and t<d+5:
# print("yes")
trainyear.append(final.index[count])
break
#预测
predata=Data_eco_scaler.loc[Data_eco_scaler["Year"].isin(range(int(PreStartYear),int(PreEndYear)+1))]
predatatrain=pca.transform(predata[Index].values)
predict=pca_model.predict(predatatrain)
#PCA线性模型参数
#pca_coef = pca_model.coef_
#存储
ytrain=pca_predict.tolist()
ypre=np.array(predict).squeeze().tolist()
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":ytrain,"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre,"MAPE":mape,"RMSE":rmse}
return result
def Growth(StartYear,
EndYear,
PreStartYear,
PreEndYear,
pretype="全社会用电量",
econamelist="GDP",
city="云南省",
planflag=1,
plan=1,
pro=1):
"""
Parameters
----------
StartYear : TYPE
DESCRIPTION.
EndYear : TYPE
DESCRIPTION.
PreStartYear : TYPE
DESCRIPTION.
PreEndYear : TYPE
DESCRIPTION.
pretype : TYPE
DESCRIPTION.
econamelist : TYPE
DESCRIPTION.
city : TYPE, optional
DESCRIPTION. The default is "云南省".
planflag : TYPE, optional
DESCRIPTION. The default is 0.
plan : TYPE, optional
DESCRIPTION. The default is 0.
Returns
-------
TYPE
DESCRIPTION.
"""
def func3(params, x):
a, b, c = params
return np.exp(a / x + b) + c
def error3(params, x, y):
return func3(params, x) - y
def slovePara3(x, y):
p0 = [1, 0.02, 0]
Para = leastsq(error3, p0, args=(x, y))
return Para
econamelist = [econamelist]
if len(econamelist) != 1:
raise ValueError("仅支持选择一个因素变量")
elif city == "云南省":
name = [pretype]
finaldata = []
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
#读取经济数据
ecodatajson = getData("云南省_year_社会经济类", econamelist[0], StartYear,
EndYear)
ecodata = json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[0])
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
x = final[econamelist[0]].values
y = final[pretype].values #load
x = x.reshape(-1, 1)
y = y.reshape(-1, 1)
#区分训练数据和预测数据
num = len(x)
testyear = math.floor(num / 5)
trainx = x[:num - testyear].squeeze()
trainy = y[:num - testyear].squeeze()
testx = x[num - testyear:]
testy = y[num - testyear:]
#建立模型
Para = slovePara3(trainx, trainy)
a, b, c = Para[0]
testp = ic.getpred(testx, testyear, planflag, plan, pro)
testp = np.array(testp).T
testpm = []
for i in range(51):
testpm.append(np.mean(testp[i]))
testpmm = testpm.index(np.median(testpm))
testpredx = testp[testpmm]
testpredx = [k * testx[-1] for k in testpredx]
testpredy = [np.exp(a / x + b) + c for x in testpredx]
trainyear = []
for t in testy:
count = -1
for d in final[pretype]:
count += 1
if t > d - 5 and t < d + 5:
# print("yes")
trainyear.append(final.index[count])
break
#误差
mape = MAPE(testpredy, testy)
rmse = RMSE(testpredy, testy)
#预测
x = x.squeeze()
y = y.squeeze()
Parapre = slovePara3(x, y)
ap, bp, cp = Parapre[0]
preyear = np.arange(int(PreStartYear), int(PreEndYear) + 1)
year = len(preyear)
p = ic.getpred(x, year, planflag, plan, pro)
p = np.array(p).T
pm = []
for i in range(51):
pm.append(np.mean(p[i]))
pmm = pm.index(np.median(pm))
predx = p[pmm]
predx = [k * x[-1] for k in predx]
predy = [np.exp(ap / x0 + bp) + cp for x0 in predx]
predy = np.array(predy).squeeze()
#存储
ytrain = np.array(testpredy).squeeze()
ypre = np.array(predy).squeeze()
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
def BPNNIndustry(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep,
pretype,
city="云南省",
hidden=[24, 12],
learningrate=0.005,
epoch=1000):
"""
Parameters
----------
StartYear : TYPE
DESCRIPTION.
EndYear : TYPE
DESCRIPTION.
PreStartYear : TYPE
DESCRIPTION.
PreEndYear : TYPE
DESCRIPTION.
timestep : TYPE
DESCRIPTION.
pretype : TYPE, optional
DESCRIPTION. The default is "consumption".
city : TYPE, optional
DESCRIPTION. The default is "云南省".
hidden : TYPE, optional
神经网络的隐藏层, list, 几个元素代表几层，每层神经元个数为list元素值. The default is [24,12].
learningrate : TYPE, optional
神经网络学习率. The default is 0.005.
epoch : TYPE, optional
训练学习次数. The default is 1000.
Returns
-------
None.
"""
def bpnn(timestep, outputlen, x_train, y_train, x_test, y_test, x_pre,
hiddenneron, lr, epoch):
x = tf.placeholder(tf.float32, shape=[None, timestep], name="Input")
y = tf.placeholder(tf.float32, shape=[None, outputlen], name="Onput")
hlen = len(hiddenneron)
f = locals()
for i in range(hlen + 1):
if i == 0:
f["f%s" % (i + 1)] = tf.contrib.layers.fully_connected(
x, hiddenneron[i])
else:
if i == hlen:
pre = tf.contrib.layers.fully_connected(
f["f%s" % (i)], outputlen)
else:
f["f%s" % (i + 1)] = tf.contrib.layers.fully_connected(
f["f%s" % (i)], hiddenneron[i])
loss = tf.losses.mean_squared_error(y, pre)
train_op = tf.train.AdamOptimizer(lr).minimize(loss)
saver = tf.train.Saver()
with tf.Session() as sess:
init = tf.initialize_all_variables()
sess.run(init)
for i in range(epoch):
sess.run(train_op, feed_dict={x: x_train, y: y_train})
lossz = sess.run(loss, feed_dict={x: x_train, y: y_train})
if i % 50 == 0:
print(lossz)
y_train_pre = sess.run(pre, feed_dict={x: x_train})
y_test_pre = sess.run(pre, feed_dict={x: x_test})
y_pre = sess.run(pre, feed_dict={x: x_pre})
training = np.array(y_train_pre).squeeze()
predictions = np.array(y_test_pre).squeeze()
labels = np.array(y_test).squeeze()
# saver.save(sess, "D:/lab/Yunnan_Pre/result/yunnan_shortterm_钢铁_BPNN/")
return predictions, labels, y_pre, training
if timestep > (int(EndYear) - int(StartYear) + 1) * 0.5:
raise ValueError("训练步长过大，请调整后重试")
elif int(EndYear) - int(StartYear) < (int(PreEndYear) - int(PreStartYear) +
timestep):
raise ValueError("历史时间长度小于预测时间长度与训练步长之和, 请调整后重试")
else:
#读取数据，确定参数
name = [pretype]
finaldata = []
outputlen = int(PreEndYear) - int(PreStartYear) + 1
datajson = getData("云南省_year_电力电量类-行业", pretype, StartYear, EndYear)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
test_size = 0 #测试数据集应当取0才可以
X, y = generate_data(final,
timestep,
outputlen,
test_size=test_size,
if_norm="no")
testdata = final[pretype].values
testinput = []
testoutput = []
num = len(X["train"])
selet = int(np.floor(num / 2))
testinput = X["train"][selet:, :]
testoutput = y["train"][selet:, :]
x_pre = np.array(np.flipud(testdata[-1:-(timestep + 1):-1])).reshape(
1, -1)
test_pre, test_label, pre, training = bpnn(
timestep, outputlen, X["train"][:-1, :], y["train"][:-1, :],
testinput, testoutput, x_pre, hidden, learningrate, epoch)
mape = MAPE(test_pre, test_label)
rmse = RMSE(test_pre, test_label)
#保存训练结果,年份上可能有问题
#trainingtrue=y["train"][:-1,:].flatten()
trainingtrue = y["train"][-1, :]
trainyear = []
for t in trainingtrue:
count = -1
for d in final[pretype]:
count += 1
if t > d - 5 and t < d + 5:
# print("yes")
trainyear.append(final.index[count])
break
ytrain = training[-1]
ypre = pre.flatten()
#trainsave.to_csv("D:/lab/Yunnan_Pre/result/yunnan_shortterm_consumption_BPNN_training.csv")
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
#保存
return result
def LSTMpre(StartYear,EndYear,PreStartYear,PreEndYear,timestep,pretype="全社会用电量",city="云南省", hidden_size=24,hidden_layer=1, learningrate=0.005,epoch=1000):
#搭建LSTM模块
def LSTM(x,y,outputlen,is_training,hidden_size,num_layers,lr,optimizer,keep_pro):
cell=tf.nn.rnn_cell.BasicLSTMCell
if is_training and keep_pro<1:
lstmcell=tf.nn.rnn_cell.MultiRNNCell([tf.nn.rnn_cell.DropoutWrapper(cell(hidden_size,activation=tf.nn.softsign),output_keep_prob=keep_pro) for _ in range(num_layers)])
else:
lstmcell=tf.nn.rnn_cell.MultiRNNCell([cell(hidden_size) for _ in range(num_layers)])
x=tf.expand_dims(x,axis=2)
outputs,current_state=tf.nn.dynamic_rnn(lstmcell,x,dtype=tf.float32)
output=outputs[:,-1,:]
predictions=tf.contrib.layers.fully_connected(output,outputlen)
if not is_training:
return predictions,None,None
loss=tf.losses.absolute_difference(labels=y,predictions=predictions)
train_op=tf.contrib.layers.optimize_loss(loss,tf.train.get_global_step(),optimizer=optimizer,learning_rate=lr)
return predictions,loss,train_op
#训练模型模块
def trainmodel(sess,outputlen,train_x,train_y,hidden_size,num_layers,lr,optimizer,keep_pro,batch_size,training_step):
ds=tf.data.Dataset.from_tensor_slices((train_x,train_y))
ds=ds.repeat().shuffle(100).batch(batch_size)
x,y=ds.make_one_shot_iterator().get_next()
prediction,loss,train_op=LSTM(x,y,outputlen,True,hidden_size,num_layers,lr,optimizer,keep_pro)
losses=[]
sess.run(tf.global_variables_initializer())
ytrain=[]
for j in range(training_step):
y,p,l=sess.run([prediction,train_op,loss])
ytrain.append(y)
return ytrain
#测试模型模块
def runmodel(sess,outputlen,test_x,test_y,hidden_size,num_layers,lr,optimizer,keep_pro,batch_size,training_step):
ds=tf.data.Dataset.from_tensor_slices((test_x,test_y))
ds=ds.batch(1)
x,y=ds.make_one_shot_iterator().get_next()
prediction,_,_=LSTM(x,[0.0],outputlen,False,hidden_size,num_layers,lr,optimizer,keep_pro)
pre=[]
label=[]
for j in range(len(test_y)):
p,l=sess.run([prediction,y])
pre.append(p)
label.append(l)
pre=np.array(pre).squeeze()
labels=np.array(label).squeeze()
return pre,labels
#预测模型模块
def premodel(sess,outputlen,test_x,test_y,hidden_size,num_layers,lr,optimizer,keep_pro,batch_size,training_step):
prediction,_,_=LSTM(test_x,[0.0],outputlen,False,hidden_size,num_layers,lr,optimizer,keep_pro)
finalpre=sess.run(prediction)
return finalpre
#设置参数
if timestep > (int(EndYear)-int(StartYear)+1)*0.5:
raise ValueError("训练步长过大，请调整后重试")
elif int(EndYear)-int(StartYear)<(int(PreEndYear)-int(PreStartYear)+timestep):
raise ValueError("历史时间长度小于 预测时间长度与训练步长之和，请调整后重试")
else:
optimizer="Adam"
keep_pro=0.9
batch_size=16
#读取数据，确定参数
name=[pretype]
finaldata=[]
outputlen=int(PreEndYear)-int(PreStartYear)+1
datajson=getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
data=json.loads(datajson)
finaldata.append(data)
final=pd.DataFrame(finaldata,index=name)
final=final.T
test_size=0#测试数据集应当取0才可以
X,y=generate_data(final,timestep,outputlen,test_size=test_size,if_norm="no")
testdata=final[pretype].values
testinput=[]
testoutput=[]
num=len(X["train"])
selet=int(np.floor(num/2))
testinput=X["train"][selet:,:]
testoutput=y["train"][selet:,:]
#最终预测需要的数据
x_pre=testdata[-1:-(timestep+1):-1].reshape(1,-1)
x_pre=np.array(x_pre, dtype = np.float32)
#训练模型并预测结果
tf.reset_default_graph()
with tf.Session() as sess:
with tf.variable_scope("LSTM"):
ytrain=trainmodel(sess,outputlen,X["train"][:-1,:],y["train"][:-1,:],hidden_size,hidden_layer,learningrate,optimizer,keep_pro,batch_size,epoch)
with tf.variable_scope("LSTM",reuse=True):
test_pre,test_label=runmodel(sess,outputlen,testinput,testoutput,hidden_size,hidden_layer,learningrate,optimizer,keep_pro,batch_size,epoch)
with tf.variable_scope("LSTM",reuse=True):
ypre=premodel(sess,outputlen,x_pre,x_pre,hidden_size,hidden_layer,learningrate,optimizer,keep_pro,batch_size,epoch)
mape=MAPE(test_pre,test_label)
rmse=RMSE(test_pre,test_label)
trainyear=[]
trainingtrue=y["train"][-1,:]
for t in trainingtrue:
count=-1
for d in final[pretype]:
count+=1
if t>d-5 and t<d+5:
# print("yes")
trainyear.append(final.index[count])
break
ypre=np.array(ypre).squeeze()
result={"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre.tolist(),"MAPE":mape,"RMSE":rmse}
return result
def EEMDIndustry(StartYear,
EndYear,
PreStartYear,
PreEndYear,
pretype,
city="云南省"):
#判定当前的时间序列是否是单调序列
#读取年度数据
yeardatajson = getData("云南省_year_电力电量类-行业", pretype, StartYear, EndYear)
yeardata = json.loads(yeardatajson)
pdyeardata = pd.DataFrame(yeardata, index=[pretype])
pdyeardata = pdyeardata.T
totalyear = int(EndYear) - int(StartYear) + 1
timestep = int(PreEndYear) - int(PreStartYear) + 1
trainyear = math.floor(totalyear - totalyear * 0.4)
delay = math.floor((totalyear - trainyear - timestep) * 0.7)
testyear = trainyear + delay
if testyear + timestep > totalyear or delay < 1:
raise ValueError("历史数据时间间隔过短或预测年份过长")
else:
train_x = pdyeardata[pretype].values[:trainyear]
train_y = pdyeardata[pretype].values[trainyear:trainyear + timestep]
train_x = train_x.reshape(1, -1)
train_y = train_y.reshape(1, -1)
test_x = pdyeardata[pretype].values[delay:testyear]
test_y = pdyeardata[pretype].values[testyear:testyear + timestep]
test_x = test_x.reshape(1, -1)
test_y = test_y.reshape(1, -1)
testdata = pdyeardata[pretype].values
finalpre = np.array(np.flipud(
testdata[-1:-(trainyear + 1):-1])).reshape(1, -1)
eemd = EMD()
IMFs = eemd(train_x.squeeze())[-1].reshape(1, -1)
testIMFs = eemd(test_x.squeeze())[-1].reshape(1, -1)
preIMFs = eemd(finalpre.squeeze())[-1].reshape(1, -1)
gbdt = xgb.XGBRegressor(max_depth=5,
learning_rate=0.1,
n_estimators=100,
silent=True,
objective='reg:linear',
booster='gblinear',
n_jobs=50,
nthread=None,
gamma=0,
min_child_weight=1,
max_delta_step=0,
subsample=1,
colsample_bytree=1,
colsample_bylevel=1,
reg_alpha=0,
reg_lambda=1,
scale_pos_weight=1,
base_score=0.5,
random_state=0,
seed=None,
missing=None,
importance_type='gain') #
multi_model = MultiOutputRegressor(gbdt)
# svr=SVR(kernel="poly",gamma="scale",C= 0.001)#kernel="linear","poly"
# multi_model = MultiOutputRegressor(svr)
multi_model.fit(IMFs, train_y)
testpredict = multi_model.predict(testIMFs)
ypre = multi_model.predict(preIMFs)
print(testpredict, test_y)
mape = MAPE(testpredict, test_y)
rmse = RMSE(testpredict, test_y)
teststarty = int(StartYear) + testyear - 1
testendy = teststarty + timestep - 1
ytrain = testpredict.flatten()
ypre = ypre.reshape(-1, 1).squeeze()
result = {
"trainfromyear": teststarty,
"traintoyear": testendy,
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
def Combination(PreStartYear,
PreEndYear,
pretype,
singleresult,
city="云南省",
comtype="等权组合"):
"""
Parameters
----------
PreStartYear : TYPE
DESCRIPTION.
PreEndYear : TYPE
DESCRIPTION.
pretype : TYPE
DESCRIPTION.
singleresult : list
单预测模型的结果,list形式,每个元素为dict.
city_or_industry : TYPE, optional
DESCRIPTION. The default is "云南省".
comtype : TYPE, optional
选择组合方法，有"等权组合","加权组合" 和 "递阶组合"可选. The default is "等权组合".
Returns
-------
None.
"""
def findtrain(alldata):
n = len(alldata)
start = "0"
end = "9999999999"
for i in range(n):
data = alldata[i]
startyear = data.get("trainfromyear")
endyear = data.get("traintoyear")
if int(startyear) > int(start):
start = str(startyear)
if int(endyear) < int(end):
end = str(endyear)
if int(end) - int(start) < 0:
return None, None
else:
return start, end
def normalization(index):
#根据评价指标权重
indexsum = sum(index)
weight = []
for i in range(len(index)):
w = 1 - index[i] / indexsum
weight.append(w)
weightsum = sum(weight)
finalweight = [x / weightsum for x in weight]
return finalweight
#检查模型是否可以组合
for tag in singleresult:
r = getAlgorithmResult(tag)
data = json.loads(json.loads(r)["results"][0][1])
print(tag)
if ("PreStartYear" or "PreEndtYear") not in data["arg"].keys():
raise ValueError("%s 并非预测模型，不适用于组合预测模型" % tag)
if "pretype" in data["arg"].keys():
if data["arg"]["pretype"] != pretype:
raise ValueError("%s 的预测目标与组合预测的预测目标不符" % tag)
if "pretype*" in data["arg"].keys():
if data["arg"]["pretype*"] != pretype:
raise ValueError("%s 的预测目标与组合预测的预测目标不符" % tag)
if data["arg"]["PreStartYear"] != int(PreStartYear):
raise ValueError("%s 的预测起始年份与所选预测起始年份不符" % tag)
elif data["arg"]["PreEndYear"] != int(PreEndYear):
raise ValueError("%s 的预测起始年份与所选预测终止年份不符" % tag)
elif "trainresult" not in data["result"].keys():
raise ValueError("%s 不适用于组合预测模型" % tag)
#读取各个模型的数据
alldata = []
for tag in singleresult:
r = getAlgorithmResult(tag)
data = json.loads(json.loads(r)["results"][0][1])
alldata.append(data["result"])
trainyear = [0, 0]
trainyear[0], trainyear[1] = findtrain(alldata)
#构建训练数据集，numpy格式,同时获取预测数据集，numpy格式
if trainyear[0] != None:
traindata = []
predata = []
singlermse = []
singlemape = []
for i in range(len(alldata)):
d = alldata[i]
StartYear = d.get("trainfromyear")
EndYear = d.get("traintoyear")
realyear = np.arange(int(StartYear), int(EndYear) + 1)
a = np.where(realyear == int(trainyear[0]))[0][0]
b = np.where(realyear == int(trainyear[1]))[0][0]
tdata = d.get("trainresult")[a:b + 1]
pdata = d.get("preresult")
traindata.append(tdata)
predata.append(pdata)
singlermse.append(d.get("RMSE"))
singlemape.append(d.get("MAPE"))
traindata = np.array(traindata)
predata = np.array(predata)
#获取训练数据对应的真实数据
datajson = getData("云南省_year_电力电量类", pretype, trainyear[0], trainyear[1])
data = json.loads(datajson)
realtraindata = []
for i in data.values():
realtraindata.append(i)
realtraindata = np.array(realtraindata)
if comtype == "等权组合":
meancombination = predata.mean(axis=0)
trainmeancombination = traindata.mean(axis=0)
rmse = RMSE(trainmeancombination, realtraindata)
mape = MAPE(trainmeancombination, realtraindata)
ytrain = trainmeancombination.tolist()
ypre = meancombination.tolist()
elif comtype == "加权组合":
weight = normalization(singlermse)
weightcombination = np.average(predata, weights=weight, axis=0)
trainweightcombination = np.average(traindata, weights=weight, axis=0)
rmse = RMSE(trainweightcombination, realtraindata)
mape = MAPE(trainweightcombination, realtraindata)
ytrain = trainweightcombination.tolist()
ypre = weightcombination.tolist()
elif comtype == "递阶组合":
againdata = copy.deepcopy(predata)
againtrain = copy.deepcopy(traindata)
for k in range(10):
weight = normalization(singlermse)
# print(weight)
reweightcombination = np.average(againdata, weights=weight, axis=0)
retrainweightcombination = np.average(againtrain,
weights=weight,
axis=0)
r = RMSE(retrainweightcombination, realtraindata)
if min(weight) > 1 / (len(predata)):
break
#比较权重，进行数据代替
dex = 0
replace = 0
for w in range(len(singlermse)):
if singlermse[w] > r:
if singlermse[w] > replace:
dex = w
replace = singlermse[w]
singlermse[dex] = r
againdata[dex] = reweightcombination
againtrain[dex] = retrainweightcombination
rmse = RMSE(retrainweightcombination, realtraindata)
mape = MAPE(retrainweightcombination, realtraindata)
ytrain = retrainweightcombination.tolist()
ypre = reweightcombination.tolist()
cname = copy.deepcopy(singleresult)
cmape = copy.deepcopy(singlemape)
crmse = copy.deepcopy(singlermse)
cpre = copy.deepcopy(predata).tolist()
cname.append(comtype)
cmape.append(mape)
crmse.append(rmse)
cpre.append(ypre)
#result = {"trainfromyear":trainyear[0],"traintoyear":trainyear[1],"trainresult":ytrain,"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre,"MAPE":mape,"RMSE":rmse}
result = {
"name": cname,
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": cpre,
"MAPE": cmape,
"RMSE": crmse
}
return result
def Logarithm(StartYear,EndYear,PreStartYear,PreEndYear,pretype="全社会用电量",econamelist="GDP",city="云南省",planflag=1,plan=1,pro=1):
"""对数函数"""
def func5(params, x):
a, b = params
return a * np.log(x) + b
def error5(params, x, y):
return func5(params, x) - y
def slovePara5(x,y):
p0 = [1, 0.02]
Para = leastsq(error5, p0, args=(x, y))
return Para
econamelist=[econamelist]
if len(econamelist) !=1:
raise ValueError("仅支持选择一个因素变量")
elif city=="云南省":
name=[pretype]
finaldata=[]
#读取历史负荷数据
datajson=getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data=json.loads(datajson)
finaldata.append(data)
#读取经济数据
ecodatajson=getData("云南省_year_社会经济类", econamelist[0], StartYear, EndYear)
ecodata=json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[0])
#获取最终数据DataFrame
final=pd.DataFrame(finaldata,index=name)
final=final.T
x = final[econamelist[0]].values
y = final[pretype].values #load
x = x.reshape(-1,1)
y = y.reshape(-1,1)
#区分训练数据和预测数据
num=len(x)
testyear=math.floor(num/5)
trainx=x[:num-testyear].squeeze()
trainy=y[:num-testyear].squeeze()
testx=x[num-testyear:]
testy=y[num-testyear:]
Para = slovePara5(trainx,trainy)
a, b = Para[0]
testp = ic.getpred(testx,testyear,planflag,plan,pro)
testp = np.array(testp).T
testpm = []
for i in range(51):
testpm.append(np.mean(testp[i]))
testpmm = testpm.index(np.median(testpm))
testpredx = testp[testpmm]
testpredx = [k * testx[-1] for k in testpredx]
testpredy = [a*np.log (x) + b for x in testpredx]
trainyear=[]
for t in testy:
count=-1
for d in final[pretype]:
count+=1
if t>d-5 and t<d+5:
# print("yes")
trainyear.append(final.index[count])
break
mape=MAPE(testpredy,testy)
rmse=RMSE(testpredy,testy)
x=x.squeeze()
y=y.squeeze()
Parapre = slovePara5(x,y)
ap, bp = Parapre[0]
preyear = np.arange(int(PreStartYear),int(PreEndYear)+1)
year=len(preyear)
p = ic.getpred(x,year,planflag,plan,pro)
p = np.array(p).T
pm = []
for i in range(51):
pm.append(np.mean(p[i]))
pmm = pm.index(np.median(pm))
predx = p[pmm]
predx = [k * x[-1] for k in predx]
predy = [ap*np.log (x0) + bp for x0 in predx]
predy=np.array(predy).squeeze()
#存储
ytrain=np.array(testpredy).squeeze()
ypre=np.array(predy).squeeze()
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":ytrain.tolist(),"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre.tolist(),"MAPE":mape,"RMSE":rmse}
return result
def GPRM(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep,
pretype="全社会用电量",
city="云南省"):
def improve_GM(x, n):
'''
改进灰色预测
x：序列，numpy对象
n:需要往后预测的个数
'''
x1 = x.cumsum() #一次累加
z1 = (x1[:len(x1) - 1] + x1[1:]) / 2.0 #紧邻均值
z1 = z1.reshape((len(z1), 1))
B = np.append(-z1, np.ones_like(z1), axis=1)
Y = x[1:].reshape((len(x) - 1, 1))
#a为发展系数 b为灰色作用量
try:
[[a], [b]] = np.dot(np.dot(np.linalg.inv(np.dot(B.T, B)), B.T),
Y) #计算参数
except:
raise ValueError("中间矩阵不可逆，请重新调整历史数据时间或步长")
#result = (x[0]-b/a)*np.exp(-a*(n-1))-(x[0]-b/a)*np.exp(-a*(n-2))
S1_2 = x.var() #原序列方差
e = list() #残差序列
for index in range(1, x.shape[0] + 1):
predict = (x[0] - b / a) * np.exp(
-a * (index - 1)) - (x[0] - b / a) * np.exp(-a * (index - 2))
e.append(x[index - 1] - predict)
S2_2 = np.array(e).var() #残差方差
C = S2_2 / S1_2 #后验差比
if C <= 0.35:
assess = '后验差比<=0.35，模型精度等级为好'
elif C <= 0.5:
assess = '后验差比<=0.5，模型精度等级为合格'
elif C <= 0.65:
assess = '后验差比<=0.65，模型精度等级为勉强'
else:
assess = '后验差比>0.65，模型精度等级为不合格'
#预测数据
predict = list()
for index in range(x.shape[0] + 1, x.shape[0] + n + 1):
predict.append((x[0] - b / a) * np.exp(-a * (index - 1)) -
(x[0] - b / a) * np.exp(-a * (index - 2)))
predict = np.array(predict)
return predict, a, b, assess
def GMpre(x, n, a, b):
predict = list()
for index in range(x.shape[0] + 1, x.shape[0] + n + 1):
predict.append((x[0] - b / a) * np.exp(-a * (index - 1)) -
(x[0] - b / a) * np.exp(-a * (index - 2)))
predict = np.array(predict)
return predict
if timestep > (int(EndYear) - int(StartYear) + 1):
raise ValueError("训练步长过大，请调整后重试.")
# elif int(PreEndYear)-int(PreStartYear)<1:
# raise ValueError("该算法不支持一年及一年内的预测.")
elif timestep < (int(PreEndYear) - int(PreStartYear) + 2):
raise ValueError("训练步长小于预测年份区间长度，请增加训练步长.")
else:
"""负荷预测"""
name = [pretype]
finaldata = []
datayear = np.arange(int(StartYear), int(EndYear) + 1)
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
datafinalyear = int(EndYear)
trainyear = timestep
testyear = int(PreEndYear) - int(PreStartYear) + 1
y = final.values
y = y.reshape(-1, 1)
#区分训练数据和预测数据
num = len(y)
#训练集
trainx = y[num - testyear - 1 - trainyear:num - testyear - 1].squeeze()
trainy = y[num - testyear - 1:num - 1].squeeze()
#测试集
testx = y[num - testyear - trainyear:num - testyear].squeeze()
testy = y[num - testyear:]
if len(testy) > 1:
testy = testy.squeeze()
#开始训练
trainpre, a, b, assess = improve_GM(trainx, testyear)
#获得测试结果
testpre = GMpre(testx, testyear, a, b)
#获得最终预测
testpredx = np.array(np.flipud(y[-1:-(trainyear + 1):-1]))
finalpre = GMpre(testpredx, testyear, a, b)
mape = MAPE(testpre, testy)
rmse = RMSE(testpre, testy)
ypre = finalpre.reshape(1, -1).squeeze()
trainyear = datayear[num - testyear:]
# for t in testy:
# count=-1
# for d in final[pretype]:
# count+=1
# if t>d-5 and t<d+5:
# # print("yes")
# trainyear.append(final.index[count])
# break
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": trainpre.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
#保存
return result
def FER(StartYear,EndYear,PreStartYear,PreEndYear,timestep,pretype="全社会用电量",city="云南省"):
"""
Parameters
----------
StartYear : TYPE
DESCRIPTION.
EndYear : TYPE
DESCRIPTION.
PreStartYear : TYPE
DESCRIPTION.
PreEndYear : TYPE
DESCRIPTION.
timestep : TYPE, optional
DESCRIPTION. The default is 15.
pretype : TYPE, optional
DESCRIPTION. The default is "consumption".
city : TYPE, optional
DESCRIPTION. The default is "云南省".
Returns
-------
result : TYPE
DESCRIPTION.
"""
def exponential_smoothing(series, alpha):
#一次指数平滑
result = [series[0]] # first value is same as series
for n in range(1, len(series)):
result.append(alpha * series[n] + (1 - alpha) * result[n-1])
return result
def double_exponential_smoothing(series, alpha, beta):
#二次指数平滑
result = [series[0]]
for n in range(1, len(series)):
if n == 1: # initialize
level, trend = series[0], series[1] - series[0]
if n >= len(series): # we are forecasting
value = result[-1]
else:
value = series[n]
last_level, level = level, alpha*value + (1-alpha)*(level+trend) # a-hat at t
trend = beta*(level-last_level) + (1-beta)*trend # b-hat at t
final=level+trend
result.append(final)
return result
if timestep > (int(EndYear)-int(StartYear)+1):
raise ValueError("训练步长过大，请调整后重试.")
elif int(PreEndYear)-int(PreStartYear)<1:
raise ValueError("该算法不支持一年及一年内的预测.")
elif timestep<(int(PreEndYear)-int(PreStartYear)+2):
raise ValueError("训练步长小于预测年份区间长度，请增加训练步长.")
else:
#读取数据
datajson=getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
data=json.loads(datajson)
name=[pretype]
finaldata=[]
finaldata.append(data)
final=pd.DataFrame(finaldata,index=name)
period=int(PreEndYear)-int(PreStartYear)+1
econamelist=["第一产业GDP","第二产业GDP","第三产业GDP"]
#读取经济数据
for i in range(len(econamelist)):
ecodatajson=getData("云南省_year_社会经济类", econamelist[i], StartYear, EndYear)
ecodata=json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final=pd.DataFrame(finaldata,index=name)
final=final.T
#获取训练所用的数据集
data1=final.iloc[len(final.values)-timestep:]
num=len(data1.values)
#预测经济数据
eco=predict.pre(data1,econamelist[0],PreStartYear,PreEndYear)
for j in range(1,len(econamelist)):
c=predict.pre(data1,econamelist[j],PreStartYear,PreEndYear)
eco=pd.merge(eco,c,on="year")
#获得训练集和测试集
trainx=eco.loc[:,econamelist]
trainy=data1.loc[:,pretype]
prex=eco.loc[num:,econamelist]
#创建模糊控制变量
GDP1=ctrl.Antecedent(np.arange( 100, 15000, 20 ), "gdp1" )
GDP2=ctrl.Antecedent(np.arange( 150, 20000, 20 ), "gdp2" )
# GDP3=ctrl.Antecedent(np.arange( 100, 25000, 20 ), "gdp3" )
fuload=ctrl.Consequent(np.arange( 100, 8000, 1 ), "futureload" )
#定义模糊集和其隶属度函数
GDP1[ "very low" ] = fuzz.trimf( GDP1.universe, [ 100, 300, 500 ] )
GDP1[ "low" ] = fuzz.trimf( GDP1.universe, [ 400, 850, 1250 ] )
GDP1[ "medium" ] = fuzz.trimf( GDP1.universe, [ 1000, 2500, 4000 ] )
GDP1[ "high" ] = fuzz.trimf( GDP1.universe, [ 3700, 5500, 7500] )
GDP1[ "very high" ] = fuzz.trimf( GDP1.universe, [ 7300, 12000, 15000] )
GDP2[ "very low" ] = fuzz.trimf(GDP2.universe, [ 100, 500, 900 ] )
GDP2[ "low" ] = fuzz.trimf(GDP2.universe, [ 500, 1450, 2600 ] )
GDP2[ "medium" ] = fuzz.trimf(GDP2.universe, [ 2500, 6500, 10500 ] )
GDP2[ "high" ] = fuzz.trimf(GDP2.universe, [ 9500, 12000, 14000] )
GDP2[ "very high" ] = fuzz.trimf(GDP2.universe, [ 13500, 16000, 20000] )
# GDP3[ "very low" ] = fuzz.trimf(GDP3.universe, [ 100, 400, 700 ] )
# GDP3[ "low" ] = fuzz.trimf(GDP3.universe, [ 650, 1400, 2750 ] )
# GDP3[ "medium" ] = fuzz.trimf(GDP3.universe, [ 2600, 6000, 13000 ] )
# GDP3[ "high" ] = fuzz.trimf(GDP3.universe, [ 12000, 15000, 18000] )
# GDP3[ "very high" ] = fuzz.trimf(GDP3.universe, [ 17000, 21000, 25000] )
fuload[ "very low" ] = fuzz.trimf( fuload.universe, [ 100, 200, 300 ] )
fuload[ "low" ] = fuzz.trimf( fuload.universe, [ 250, 550, 1100 ] )
fuload[ "medium" ] = fuzz.trimf( fuload.universe, [ 1050, 1900, 3000 ] )
fuload[ "high" ] = fuzz.trimf( fuload.universe, [ 2750, 3500, 5100 ] )
fuload[ "very high" ] = fuzz.trimf(fuload.universe, [ 5000, 8000, 8000 ] )
# #定义模糊规则
rule=locals()
rule1 = ctrl.Rule(GDP1[ "very low" ]&GDP2[ "very low" ], fuload[ "very low" ] )
rule2 = ctrl.Rule(GDP1[ "very low" ]&GDP2[ "low" ], fuload[ "very low" ] )
rule3 = ctrl.Rule(GDP1[ "very low" ]&GDP2[ "medium" ], fuload[ "low" ] )
rule4 = ctrl.Rule(GDP1[ "very low" ]&GDP2[ "high" ], fuload[ "medium" ] )
rule5 = ctrl.Rule(GDP1[ "very low" ]&GDP2[ "very high" ], fuload[ "medium" ] )
rule6 = ctrl.Rule(GDP1[ "low" ]&GDP2[ "very low" ], fuload["very low" ] )
rule7 = ctrl.Rule(GDP1[ "low" ]&GDP2[ "low" ], fuload[ "low" ] )
rule8 = ctrl.Rule(GDP1[ "low" ]&GDP2[ "medium" ], fuload[ "low" ] )
rule9 = ctrl.Rule(GDP1[ "low" ]&GDP2[ "high" ], fuload["medium" ] )
rule10 = ctrl.Rule(GDP1[ "low" ]&GDP2[ "very high" ], fuload["medium" ] )
rule11 = ctrl.Rule(GDP1[ "medium" ]&GDP2[ "very low" ], fuload["low" ] )
rule12 = ctrl.Rule(GDP1[ "medium" ]&GDP2[ "low" ], fuload["low" ] )
rule13 = ctrl.Rule(GDP1[ "medium" ]&GDP2[ "medium" ], fuload["medium" ] )
rule14 = ctrl.Rule(GDP1[ "medium" ]&GDP2[ "high" ], fuload["high" ] )
rule15 = ctrl.Rule(GDP1[ "medium" ]&GDP2[ "very high" ], fuload["medium" ] )
rule16 = ctrl.Rule(GDP1[ "high" ]&GDP2[ "very low" ], fuload["low" ] )
rule17 = ctrl.Rule(GDP1[ "high" ]&GDP2[ "low" ], fuload["medium" ] )
rule18 = ctrl.Rule(GDP1[ "high" ]&GDP2[ "medium" ], fuload["high"] )
rule19 = ctrl.Rule(GDP1[ "high" ]&GDP2[ "high" ], fuload["high" ] )
rule20 = ctrl.Rule(GDP1[ "high" ]&GDP2[ "very high" ], fuload["very high" ] )
rule21 = ctrl.Rule(GDP1[ "very high" ]&GDP2[ "very low" ], fuload["low" ] )
rule22 = ctrl.Rule(GDP1[ "very high" ]&GDP2[ "low" ], fuload["low" ] )
rule23 = ctrl.Rule(GDP1[ "very high" ]&GDP2[ "medium" ], fuload["medium" ] )
rule24 = ctrl.Rule(GDP1[ "very high" ]&GDP2[ "high" ], fuload["high" ] )
rule25 = ctrl.Rule(GDP1[ "very high" ]&GDP2[ "very high" ], fuload["very high" ] )
fuzzy_ctrl = ctrl.ControlSystem([ rule1, rule2, rule3, rule4, rule5,rule6, rule7, rule8, rule9, rule10,
rule11, rule12, rule13, rule14, rule15, rule16, rule17, rule18, rule19, rule20,
rule21, rule22, rule23, rule24, rule25])
consumptionSystem = ctrl.ControlSystemSimulation( fuzzy_ctrl )
#评估
trainn=len(trainx)
systemoutput=np.zeros(trainn, dtype=np.float64 )
for i in range(trainn):
consumptionSystem.input["gdp1"] = trainx.loc[i,econamelist[0]]
consumptionSystem.input["gdp2"] = trainx.loc[i,econamelist[1]]
consumptionSystem.compute()
systemoutput[i] = consumptionSystem.output["futureload"]
alpha=0.9
beta=1
#对结果进行二次指数平滑
allexsystemoutput=double_exponential_smoothing(systemoutput[:num], alpha, beta)
exsystemoutput=double_exponential_smoothing(systemoutput[num-period:num], alpha, beta)
exprey=double_exponential_smoothing(systemoutput[num:], alpha, beta)
mape=MAPE(exsystemoutput,trainy.values[num-period:num])
rmse=RMSE(exsystemoutput,trainy.values[num-period:num])
#保存结果
trainyear=data1.index
ytrain=np.array(allexsystemoutput).reshape(1,-1).squeeze()
ypre=np.array(exprey).reshape(1,-1).squeeze()
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":ytrain.tolist(),"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre.tolist(),"MAPE":mape,"RMSE":rmse}
return result
def GPRM(StartYear,EndYear,PreStartYear,PreEndYear,timestep=15,pretype="consumption",city="云南省"):
def improve_GM(x,n):
'''
改进灰色预测
x：序列，numpy对象
n:需要往后预测的个数
'''
x1 = x.cumsum()#一次累加
z1 = (x1[:len(x1) - 1] + x1[1:])/2.0#紧邻均值
z1 = z1.reshape((len(z1),1))
B = np.append(-z1,np.ones_like(z1),axis=1)
Y = x[1:].reshape((len(x) - 1,1))
#a为发展系数 b为灰色作用量
[[a],[b]] = np.dot(np.dot(np.linalg.inv(np.dot(B.T, B)), B.T), Y)#计算参数
result = (x[0]-b/a)*np.exp(-a*(n-1))-(x[0]-b/a)*np.exp(-a*(n-2))
S1_2 = x.var()#原序列方差
e = list()#残差序列
for index in range(1,x.shape[0]+1):
predict = (x[0]-b/a)*np.exp(-a*(index-1))-(x[0]-b/a)*np.exp(-a*(index-2))
e.append(x[index-1]-predict)
S2_2 = np.array(e).var()#残差方差
C = S2_2/S1_2#后验差比
if C<=0.35:
assess = '后验差比<=0.35，模型精度等级为好'
elif C<=0.5:
assess = '后验差比<=0.5，模型精度等级为合格'
elif C<=0.65:
assess = '后验差比<=0.65，模型精度等级为勉强'
else:
assess = '后验差比>0.65，模型精度等级为不合格'
#预测数据
predict = list()
for index in range(x.shape[0]+1,x.shape[0]+n+1):
predict.append((x[0]-b/a)*np.exp(-a*(index-1))-(x[0]-b/a)*np.exp(-a*(index-2)))
predict = np.array(predict)
return predict,a,b,assess
def GMpre(x,n,a,b):
predict = list()
for index in range(x.shape[0]+1,x.shape[0]+n+1):
predict.append((x[0]-b/a)*np.exp(-a*(index-1))-(x[0]-b/a)*np.exp(-a*(index-2)))
predict = np.array(predict)
return predict
"""负荷预测"""
name=[pretype]
finaldata=[]
outputlen=int(PreEndYear)-int(PreStartYear)+1
#读取历史负荷数据
datajson=getData("yunnan_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data=json.loads(datajson)
finaldata.append(data)
final=pd.DataFrame(finaldata,index=name)
final=final.T
datafinalyear=int(EndYear)
trainyear=timestep
testyear=int(PreEndYear)-int(PreStartYear)+1
y = final.values
y = y.reshape(-1,1)
#区分训练数据和预测数据
num=len(y)
#训练集
trainx=y[num-testyear-1-trainyear:num-testyear-1].squeeze()
trainy=y[num-testyear-1:].squeeze()
#测试集
testx=y[num-testyear-trainyear:num-testyear].squeeze()
testy=y[num-testyear:].squeeze()
#开始训练
trainpre,a,b,assess=improve_GM(trainx,testyear)
#获得测试结果
testpre=GMpre(testx,testyear,a,b)
#获得最终预测
testpredx=np.array(np.flipud(y[-1:-(trainyear+1):-1]))
finalpre=GMpre(testpredx,testyear,a,b)
mape=MAPE(testpre,testy)
rmse=RMSE(testpre,testy)
ypre=finalpre.squeeze().reshape(1,-1)
trainyear=[]
for t in testy:
count=-1
for d in final[pretype]:
count+=1
if t>d-5 and t<d+5:
# print("yes")
trainyear.append(final.index[count])
break
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":trainpre,"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre,"MAPE":mape,"RMSE":rmse}
#保存
return result
def Binarylinear(StartYear,EndYear,PreStartYear,PreEndYear,econamelist,pretype="全社会用电量",city="云南省",planflag1=1,plan1=1,pro1=1,planflag2=1,plan2=1,pro2=1):
"""
Parameters
----------
StartYear : TYPE
DESCRIPTION.
EndYear : TYPE
DESCRIPTION.
PreStartYear : TYPE
DESCRIPTION.
PreEndYear : TYPE
DESCRIPTION.
pretype : TYPE
DESCRIPTION.
econamelist : TYPE
DESCRIPTION.
city : TYPE, optional
DESCRIPTION. The default is "云南省".
planflag1 : TYPE, optional
DESCRIPTION. The default is 0.
plan1 : TYPE, optional
DESCRIPTION. The default is 0.
planflag2 : TYPE, optional
DESCRIPTION. The default is 0.
plan2 : TYPE, optional
DESCRIPTION. The default is 0.
Returns
-------
TYPE
DESCRIPTION.
"""
def madd(X,Y):
Z = []
lenX = len(X)
for i in range(lenX):
Z.append(X[i][0]+Y[i][0])
return Z
if len(econamelist) !=2:
return {"False":"请重新选择两个经济变量."}
elif city=="云南省":
name=[pretype]
finaldata=[]
period=int(PreEndYear)-int(PreStartYear)+1
#读取历史负荷数据
datajson=getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data=json.loads(datajson)
finaldata.append(data)
#读取经济数据
for i in range(2):
ecodatajson=getData("云南省_year_社会经济类", econamelist[i], StartYear, EndYear)
ecodata=json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final=pd.DataFrame(finaldata,index=name)
final=final.T
x1 = final[econamelist[0]].values
x2 = final[econamelist[1]].values
y = final[pretype].values #load
x1 = x1.reshape(-1,1)
x2 = x2.reshape(-1,1)
xx=np.concatenate((x1,x2),axis=1)
y = y.reshape(-1,1)
#区分训练数据和预测数据
num=len(y)
testyear=math.floor(num/5)
trainx=xx[:num-testyear]
trainy=y[:num-testyear]
testx=xx[num-testyear:]
testy=y[num-testyear:]
# reg = LinearRegression().fit(trainx, trainy)
reg = LinearRegression().fit(xx, y)
testp1 = ic.getpred(testx[:,0],testyear,planflag1,plan1,pro1)
testp1 = np.array(testp1).T
testpm1 = []
for i in range(51):
testpm1.append(np.mean(testp1[i]))
testpmm1 = testpm1.index(np.median(testpm1))
testpredx1 = testp1[testpmm1]
testpredx1 = [k * testx[:,0][-1] for k in testpredx1]
print(testpredx1)
testpredy1 = [testx[:,0] * reg.coef_[0][0] + reg.intercept_[0] for testx[:,0] in testpredx1]
testp2 = ic.getpred(testx[:,1],testyear,planflag2,plan2,pro2)
testp2 = np.array(testp2).T
testpm2 = []
for i in range(51):
testpm2.append(np.mean(testp2[i]))
testpmm2 = testpm2.index(np.median(testpm2))
testpredx2 = testp2[testpmm2]
testpredx2 = [k * testx[:,1][-1] for k in testpredx2]
testpredy2 = [testx[:,1] * reg.coef_[0][1] for testx[:,1] in testpredx2]
testpredy = madd(testpredy1 , testpredy2)
# testpredy=np.array(testpredy).squeeze()
# loadp = reg.predict(testx)#趋势外推
mape=MAPE(testpredy,testy)
rmse=RMSE(testpredy,testy)
trainyear=[]
for t in testy:
count=-1
for d in final[pretype]:
count+=1
if t>d-5 and t<d+5:
# print("yes")
trainyear.append(final.index[count])
break
"""预测"""
preyear = np.arange(int(PreStartYear),int(PreEndYear)+1)
year=len(preyear)
p1 = ic.getpred(xx[:,0],year,planflag1,plan1,pro1)
p1 = np.array(p1).T
pm1 = []
for i in range(51):
pm1.append(np.mean(p1[i]))
pmm1 = pm1.index(np.median(pm1))
predx1 = p1[pmm1]
predx1 = [k * xx[:,0][-1] for k in predx1]
predy1 = [xx[:,0] * reg.coef_[0][0] + reg.intercept_[0] for xx[:,0] in predx1]
p2 = ic.getpred(xx[:,1],year,planflag2,plan2,pro2)
p2 = np.array(p2).T
pm2 = []
for i in range(51):
pm2.append(np.mean(p2[i]))
pmm2 = pm2.index(np.median(pm2))
predx2 = p2[pmm2]
predx2 = [k * xx[:,1][-1] for k in predx2]
predy2 = [xx[:,1] * reg.coef_[0][1] for xx[:,1] in predx2]
predy = madd(predy1 , predy2)
predy=np.array(predy).squeeze()
#存储
ytrain=np.array(testpredy).squeeze()
ypre=np.array(predy).squeeze()
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":ytrain.tolist(),"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre.tolist(),"MAPE":mape,"RMSE":rmse}
return result
def QuantileRegression(StartYear,
EndYear,
PreStartYear,
PreEndYear,
quatile=0.95,
pretype="全社会用电量",
econamelist=["GDP"],
city="云南省"):
#首先需要回归得到未来的经济数据
def get_coef(data, xnamelist, yname, quatile):
#获得分位数回归线性关系
#注意xnamelist 最多只能容纳5个变量,yname是str
n = len(xnamelist)
print(yname, xnamelist)
if n == 1:
mod = smf.quantreg('%s ~ %s' % (yname, xnamelist[0]), data)
elif n == 2:
mod = smf.quantreg(
'%s ~ %s+%s' % (yname, xnamelist[0], xnamelist[1]), data)
elif n == 3:
mod = smf.quantreg(
'%s ~ %s+%s+%s' %
(yname, xnamelist[0], xnamelist[1], xnamelist[2]), data)
elif n == 4:
mod = smf.quantreg(
'%s ~ %s+%s+%s+%s' % (yname, xnamelist[0], xnamelist[1],
xnamelist[2], xnamelist[3]), data)
elif n == 5:
mod = smf.quantreg(
'%s ~ %s+%s+%s+%s+%s' %
(yname, xnamelist[0], xnamelist[1], xnamelist[2], xnamelist[3],
xnamelist[4]), data)
res = mod.fit(q=quatile)
print(res.summary())
#返回分位点，截距，各个参数系数 和 各个参数lb,ub
return quatile, res.params['Intercept'], res.params[
xnamelist], res.conf_int().loc[xnamelist]
def predict(data, intercept, coef, quatile, xnamelist):
#这里的data只有x没有y
n = len(xnamelist)
pre = [intercept] * len(data.values)
for i in range(n):
pre = pre + coef[xnamelist[i]] * data[xnamelist[i]].values
return pre
#判断经济因素数量是否合适
if len(econamelist) > 5:
delnum = len(econamelist) - 5
raise ValueError("经济因素选取不应超出 5 个，请删去 %s 个，再重新预测" % delnum)
elif int(PreEndYear) - int(PreStartYear) < 1:
raise ValueError("该算法不支持一年及一年内的预测")
elif (int(EndYear) - int(StartYear) + 1) < 5:
raise ValueError("历史年份区间过短，建议历史年份区间在 5 年以上")
elif city == "云南省":
name = [pretype]
finaldata = []
period = int(PreEndYear) - int(PreStartYear) + 1
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
#读取经济数据
for i in range(len(econamelist)):
ecodatajson = getData("云南省_year_社会经济类", econamelist[i], StartYear,
EndYear)
ecodata = json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
#预测经济数据
# print(logfinal[econamelist[0]].to_frame().column)
eco = preeco.pre(final, econamelist[0], PreStartYear, PreEndYear)
for j in range(1, len(econamelist)):
c = preeco.pre(final, econamelist[j], PreStartYear, PreEndYear)
eco = pd.merge(eco, c, on="year")
q, b, k, lbub = get_coef(final, econamelist, pretype, 0.95)
y = predict(eco, b, k, q, econamelist)
#求mape，rmse
ytrain = y[:len(y) - period]
ytraintrue = final[pretype].values[:len(y) - period]
mape = MAPE(ytrain, ytraintrue)
rmse = RMSE(ytrain, ytraintrue)
ypre = y[len(y) - period:]
#返回结果
result = {
"trainfromyear": StartYear,
"traintoyear": EndYear,
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
else:
raise ValueError("暂不支持其他地区预测")
def ESQRM(StartYear,
EndYear,
PreStartYear,
PreEndYear,
quatile=0.95,
pretype="全社会用电量",
econamelist=["GDP"],
city="云南省"):
"""
Parameters
----------
StartYear : str
历史数据起始年份
EndYear : str
历史数据终止年份
PreStartYear : str
预测起始年份
PreEndYear : str
预测终止年份
pretype : str
预测类型："consumption"、"load"
quatile : float
分位数,默认为0.95
econamelist : list
选取的经济数据名称列表
city : str
选择城市，默认云南省
Returns
-------
"trainfromyear":StartYear
"traintoyear":EndYear
"trainresult":ytrain, array
训练结果
"prefromyear":PreStartYear
"pretoyear":PreEndYear
"preresult":ypre, array
预测结果
"MAPE":mape, float
"RMSE":rmse, float
"""
def get_coef(data, pretype, econamelist, quatile):
#获得分位数回归线性关系
#注意econamelist 最多只能容纳5个变量,yname是str
n = len(econamelist)
# print("num",n)
if n == 1:
mod = smf.quantreg('%s ~ %s' % (pretype, econamelist[0]), data)
elif n == 2:
mod = smf.quantreg(
'%s ~ %s+%s' % (pretype, econamelist[0], econamelist[1]), data)
elif n == 3:
mod = smf.quantreg(
'%s ~ %s+%s+%s' %
(pretype, econamelist[0], econamelist[1], econamelist[2]),
data)
elif n == 4:
mod = smf.quantreg(
'%s ~ %s+%s+%s+%s' % (pretype, econamelist[0], econamelist[1],
econamelist[2], econamelist[3]), data)
elif n == 5:
mod = smf.quantreg(
'%s ~ %s+%s+%s+%s+%s' %
(pretype, econamelist[0], econamelist[1], econamelist[2],
econamelist[3], econamelist[4]), data)
res = mod.fit(q=quatile)
# print(res.summary())
#返回分位点，截距，各个参数系数 和 各个参数lb,ub
return quatile, res.params['Intercept'], res.params[
econamelist], res.conf_int().loc[econamelist]
def predict(data, intercept, coef, quatile, econamelist):
#这里的data只有x没有y
n = len(econamelist)
pre = [intercept] * len(data.values)
for i in range(n):
pre = pre + coef[econamelist[i]] * data[econamelist[i]].values
pre = np.exp(pre)
return pre
#判断经济因素数量是否合适
if len(econamelist) > 5:
delnum = len(econamelist) - 5
raise ValueError("经济因素选取不应超出 5 个,请删去 %s 个,再重新预测" % delnum)
elif int(PreEndYear) - int(PreStartYear) < 1:
raise ValueError("该算法不支持一年及一年内的预测")
elif (int(EndYear) - int(StartYear) + 1) < 5:
raise ValueError("历史年份区间过短，建议历史年份区间在 5 年以上")
elif city == "云南省":
name = [pretype]
finaldata = []
period = int(PreEndYear) - int(PreStartYear) + 1
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
#读取经济数据
for i in range(len(econamelist)):
ecodatajson = getData("云南省_year_社会经济类", econamelist[i], StartYear,
EndYear)
ecodata = json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
#取对数
logfinal = final.apply(np.log)
#预测经济数据
# print(logfinal[econamelist[0]].to_frame().column)
eco = preeco.pre(logfinal, econamelist[0], PreStartYear, PreEndYear)
for j in range(1, len(econamelist)):
c = preeco.pre(logfinal, econamelist[j], PreStartYear, PreEndYear)
eco = pd.merge(eco, c, on="year")
#预测
q, b, k, lbub = get_coef(logfinal, pretype, econamelist, quatile)
y = predict(eco, b, k, q, econamelist)
#求训练集误差mape，rmse
ytrain = y[:len(y) - period]
ytraintrue = final[pretype].values[:len(y) - period]
mape = MAPE(ytrain, ytraintrue)
rmse = RMSE(ytrain, ytraintrue)
ypre = y[len(y) - period:]
#返回结果
result = {
"trainfromyear": StartYear,
"traintoyear": EndYear,
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
else:
raise ValueError("暂不支持其他地区预测")
def FLR(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep=15,
pretype="consumption",
city="云南省"):
"""
Parameters
----------
StartYear : TYPE
DESCRIPTION.
EndYear : TYPE
DESCRIPTION.
PreStartYear : TYPE
DESCRIPTION.
PreEndYear : TYPE
DESCRIPTION.
timestep : TYPE
DESCRIPTION.
pretype : TYPE, optional
DESCRIPTION. The default is "consumption".
city : TYPE, optional
DESCRIPTION. The default is "云南省".
Returns
-------
None.
"""
#读取数据
datajson = getData("yunnan_year_电力电量类", pretype, StartYear, EndYear)
data = json.loads(datajson)
name = [pretype]
finaldata = []
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
period = int(PreEndYear) - int(PreStartYear) + 1
econamelist = ["GDP1", "GDP2", "GDP3"]
#读取经济数据
for i in range(len(econamelist)):
ecodatajson = getData("yunnan_year_社会经济类", econamelist[i], StartYear,
EndYear)
ecodata = json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
#获取训练所用的数据集
data1 = final.iloc[len(final.values) - timestep:]
num = len(data1.values)
#预测经济数据
eco = predict.pre(data1, econamelist[0], PreStartYear, PreEndYear)
for j in range(1, len(econamelist)):
c = predict.pre(data1, econamelist[j], PreStartYear, PreEndYear)
eco = pd.merge(eco, c, on="year")
#获得训练集和测试集
trainx = eco.loc[:, econamelist]
trainy = data1.loc[:, pretype]
prex = eco.loc[num:, econamelist]
#创建模糊控制变量
GDP1 = ctrl.Antecedent(np.arange(100, 15000, 20), "gdp1")
GDP2 = ctrl.Antecedent(np.arange(150, 20000, 20), "gdp2")
# GDP3=ctrl.Antecedent(np.arange( 100, 25000, 20 ), "gdp3" )
fuload = ctrl.Consequent(np.arange(100, 8000, 1), "futureload")
#定义模糊集和其隶属度函数
GDP1["very low"] = fuzz.trimf(GDP1.universe, [100, 300, 500])
GDP1["low"] = fuzz.trimf(GDP1.universe, [400, 850, 1250])
GDP1["medium"] = fuzz.trimf(GDP1.universe, [1000, 2500, 4000])
GDP1["high"] = fuzz.trimf(GDP1.universe, [3700, 5500, 7500])
GDP1["very high"] = fuzz.trimf(GDP1.universe, [7300, 12000, 15000])
GDP2["very low"] = fuzz.trimf(GDP2.universe, [100, 500, 900])
GDP2["low"] = fuzz.trimf(GDP2.universe, [500, 1450, 2600])
GDP2["medium"] = fuzz.trimf(GDP2.universe, [2500, 6500, 10500])
GDP2["high"] = fuzz.trimf(GDP2.universe, [9500, 12000, 14000])
GDP2["very high"] = fuzz.trimf(GDP2.universe, [13500, 16000, 20000])
# GDP3[ "very low" ] = fuzz.trimf(GDP3.universe, [ 100, 400, 700 ] )
# GDP3[ "low" ] = fuzz.trimf(GDP3.universe, [ 650, 1400, 2750 ] )
# GDP3[ "medium" ] = fuzz.trimf(GDP3.universe, [ 2600, 6000, 13000 ] )
# GDP3[ "high" ] = fuzz.trimf(GDP3.universe, [ 12000, 15000, 18000] )
# GDP3[ "very high" ] = fuzz.trimf(GDP3.universe, [ 17000, 21000, 25000] )
fuload["very low"] = fuzz.trimf(fuload.universe, [100, 200, 300])
fuload["low"] = fuzz.trimf(fuload.universe, [250, 550, 1100])
fuload["medium"] = fuzz.trimf(fuload.universe, [1050, 1900, 3000])
fuload["high"] = fuzz.trimf(fuload.universe, [2750, 3500, 5100])
fuload["very high"] = fuzz.trimf(fuload.universe, [5000, 8000, 8000])
# #定义模糊规则
rule = locals()
rule1 = ctrl.Rule(GDP1["very low"] & GDP2["very low"], fuload["very low"])
rule2 = ctrl.Rule(GDP1["very low"] & GDP2["low"], fuload["very low"])
rule3 = ctrl.Rule(GDP1["very low"] & GDP2["medium"], fuload["low"])
rule4 = ctrl.Rule(GDP1["very low"] & GDP2["high"], fuload["medium"])
rule5 = ctrl.Rule(GDP1["very low"] & GDP2["very high"], fuload["medium"])
rule6 = ctrl.Rule(GDP1["low"] & GDP2["very low"], fuload["very low"])
rule7 = ctrl.Rule(GDP1["low"] & GDP2["low"], fuload["low"])
rule8 = ctrl.Rule(GDP1["low"] & GDP2["medium"], fuload["low"])
rule9 = ctrl.Rule(GDP1["low"] & GDP2["high"], fuload["medium"])
rule10 = ctrl.Rule(GDP1["low"] & GDP2["very high"], fuload["medium"])
rule11 = ctrl.Rule(GDP1["medium"] & GDP2["very low"], fuload["low"])
rule12 = ctrl.Rule(GDP1["medium"] & GDP2["low"], fuload["low"])
rule13 = ctrl.Rule(GDP1["medium"] & GDP2["medium"], fuload["medium"])
rule14 = ctrl.Rule(GDP1["medium"] & GDP2["high"], fuload["high"])
rule15 = ctrl.Rule(GDP1["medium"] & GDP2["very high"], fuload["medium"])
rule16 = ctrl.Rule(GDP1["high"] & GDP2["very low"], fuload["low"])
rule17 = ctrl.Rule(GDP1["high"] & GDP2["low"], fuload["medium"])
rule18 = ctrl.Rule(GDP1["high"] & GDP2["medium"], fuload["high"])
rule19 = ctrl.Rule(GDP1["high"] & GDP2["high"], fuload["high"])
rule20 = ctrl.Rule(GDP1["high"] & GDP2["very high"], fuload["very high"])
rule21 = ctrl.Rule(GDP1["very high"] & GDP2["very low"], fuload["low"])
rule22 = ctrl.Rule(GDP1["very high"] & GDP2["low"], fuload["low"])
rule23 = ctrl.Rule(GDP1["very high"] & GDP2["medium"], fuload["medium"])
rule24 = ctrl.Rule(GDP1["very high"] & GDP2["high"], fuload["high"])
rule25 = ctrl.Rule(GDP1["very high"] & GDP2["very high"],
fuload["very high"])
fuzzy_ctrl = ctrl.ControlSystem([
rule1, rule2, rule3, rule4, rule5, rule6, rule7, rule8, rule9, rule10,
rule11, rule12, rule13, rule14, rule15, rule16, rule17, rule18, rule19,
rule20, rule21, rule22, rule23, rule24, rule25
])
consumptionSystem = ctrl.ControlSystemSimulation(fuzzy_ctrl)
#评估
trainn = len(trainx)
systemoutput = np.zeros(trainn, dtype=np.float64)
for i in range(trainn):
consumptionSystem.input["gdp1"] = trainx.loc[i, econamelist[0]]
consumptionSystem.input["gdp2"] = trainx.loc[i, econamelist[1]]
consumptionSystem.compute()
systemoutput[i] = consumptionSystem.output["futureload"]
mape = MAPE(systemoutput[num - period:num],
trainy.values[num - period:num])
rmse = RMSE(systemoutput[num - period:num],
trainy.values[num - period:num])
#保存结果
trainyear = data1.index
ytrain = systemoutput[:num]
ypre = np.array(systemoutput[num:]).reshape(1, -1)
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain,
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre,
"MAPE": mape,
"RMSE": rmse
}
return result
def GM(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep,
pretype="全社会用电量",
city="云南省"):
def RGM(x, n):
'''
x为原始序列
n为往后预测的个数
'''
x1 = x.cumsum() #一次累加
z1 = (x1[:len(x1) - 1] + x1[1:]) / 2.0 #紧邻均值
z1 = z1.reshape((len(z1), 1))
B = np.append(-z1, np.ones_like(z1), axis=1)
Y = x[1:].reshape((len(x) - 1, 1))
#a为发展系数 b为灰色作用量
try:
[[a], [b]] = np.dot(np.dot(np.linalg.inv(np.dot(B.T, B)), B.T),
Y) #计算参数
except:
raise ValueError("中间矩阵不可逆，请重新调整历史数据时间或步长")
imitate = list()
predict = list()
der = list()
for index in range(0, x.shape[0]):
imitate.append((x[0] - b / a) * np.exp(-a * (index)) * (-a))
for index in range(x.shape[0] + 1, x.shape[0] + n + 1):
predict.append((x[0] - b / a) * np.exp(-a * (index - 1)) * (-a))
for index in range(0, x.shape[0] + n):
der.append((x[0] - b / a) * np.exp(-a * index) * (pow(a, 2)))
# return {
# 'a':{'value':a,'desc':'发展系数'},
# 'b':{'value':b,'desc':'灰色作用量'},
# 'imitate':{'value':imitate,'desc':'模拟值'},
# 'predict':{'value':predict,'desc':'预测值'},
# 'der':{'value':der,'desc':'x0斜率'}
# }
return predict, a, b
def RGMpre(x, n, a, b):
predict = list()
for index in range(x.shape[0] + 1, x.shape[0] + n + 1):
predict.append((x[0] - b / a) * np.exp(-a * (index - 1)) * (-a))
predict = np.array(predict)
return predict
if timestep > (int(EndYear) - int(StartYear) + 1):
raise ValueError("训练步长过大，请调整后重试.")
elif timestep < (int(PreEndYear) - int(PreStartYear) + 2):
raise ValueError("训练步长小于预测年份区间长度，请增加训练步长.")
else:
"""负荷预测"""
name = [pretype]
finaldata = []
datayear = np.arange(int(StartYear), int(EndYear) + 1)
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
datafinalyear = int(EndYear)
trainyear = timestep
testyear = int(PreEndYear) - int(PreStartYear) + 1
y = final.values
y = y.reshape(-1, 1)
#区分训练数据和预测数据
num = len(y)
#训练集
trainx = y[num - testyear - 1 - trainyear:num - testyear - 1].squeeze()
trainy = y[num - testyear - 1:num - 1].squeeze()
#测试集
testx = y[num - testyear - trainyear:num - testyear].squeeze()
testy = y[num - testyear:].squeeze()
#开始训练
trainpre, a, b = RGM(trainx, testyear)
#获得测试结果
testpre = RGMpre(testx, testyear, a, b)
#获得最终预测
testpredx = np.array(np.flipud(y[-1:-(trainyear + 1):-1]))
finalpre = RGMpre(testpredx, testyear, a, b)
mape = MAPE(testpre, testy)
rmse = RMSE(testpre, testy)
ypre = finalpre.reshape(1, -1).squeeze()
trainyear = datayear[num - testyear:]
# for t in testy:
# count=-1
# for d in final[pretype]:
# count+=1
# if t>d-5 and t<d+5:
# # print("yes")
# trainyear.append(final.index[count])
# break
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": trainpre,
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
#保存
return result
def QRsolow(hisfromyear,
histoyear,
fromyear,
toyear,
quatile=0.95,
pretype="consumption",
econamelist=["GDP"],
city="云南省"):
"""
Parameters
----------
hisfromyear : str
历史数据起始年份
histoyear : str
历史数据终止年份
fromyear : str
预测起始年份
toyear : str
预测终止年份
pretype : str
预测类型："consumption"、"load"
quatile : float
分位数,默认为0.95
econamelist : list
选取的经济数据名称列表
city : str
选择城市，默认云南省
Returns
-------
"trainfromyear":hisfromyear
"traintoyear":histoyear
"trainresult":ytrain, array
训练结果
"prefromyear":fromyear
"pretoyear":toyear
"preresult":ypre, array
预测结果
"MAPE":mape, float
"RMSE":rmse, float
"""
def get_coef(data, pretype, econamelist, quatile):
#获得分位数回归线性关系
#注意xnamelist 最多只能容纳5个变量,yname是str
#n=len(xnamelist)
n = len(econamelist)
if n == 1:
mod = smf.quantreg('%s ~ %s' % (pretype, econamelist[0]), data)
elif n == 2:
mod = smf.quantreg(
'%s ~ %s+%s' % (pretype, econamelist[0], econamelist[1]), data)
elif n == 3:
mod = smf.quantreg(
'%s ~ %s+%s+%s' %
(pretype, econamelist[0], econamelist[1], econamelist[2]),
data)
elif n == 4:
mod = smf.quantreg(
'%s ~ %s+%s+%s+%s' % (pretype, econamelist[0], econamelist[1],
econamelist[2], econamelist[3]), data)
elif n == 5:
mod = smf.quantreg(
'%s ~ %s+%s+%s+%s+%s' %
(pretype, econamelist[0], econamelist[1], econamelist[2],
econamelist[3], econamelist[4]), data)
res = mod.fit(q=quatile)
# print(res.summary())
#返回分位点，截距，各个参数系数 和 各个参数lb,ub
return quatile, res.params['Intercept'], res.params[
econamelist], res.conf_int().loc[econamelist]
def predict(data, intercept, coef, quatile, econamelist):
#这里的data只有x没有y
n = len(econamelist)
pre = [intercept] * len(data.values)
for i in range(n):
pre = pre + coef[econamelist[i]] * data[econamelist[i]].values
pre = np.exp(pre)
return pre
#判断经济因素数量是否合适
if len(econamelist) > 5:
delnum = len(econamelist) - 5
print("经济因素选取不应超出5个,请删去%s个,再重新预测。" % delnum)
elif city == "云南省":
name = [pretype]
finaldata = []
period = toyear - fromyear + 1
#读取历史负荷数据
datajson = getData("yunnan_year", pretype, hisfromyear, histoyear)
data = json.loads(datajson)
finaldata.append(data)
#读取经济数据
for i in range(len(econamelist)):
ecodatajson = getData("yunnan_year", econamelist[i], hisfromyear,
histoyear)
ecodata = json.loads(ecodata)
finaldata.append(ecodata)
name.append(econamelist[i])
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
#取对数
logfinal = data.apply(np.log)
#预测经济数据
eco = predict.pre(logfinal.loc[:, econamelist[0]], econamelist[0],
fromyear, toyear)
for j in range(1, len(econamelist)):
c = predict.pre(logfinal.loc[:, econamelist[j]], econamelist[j],
fromyear, toyear)
eco = pd.merge(eco, c, on="year")
#预测
q, b, k, lbub = get_coef(logfinal, name, pretype, quatile)
y = predict(eco, b, k, q, econamelist)
#求训练集误差mape，rmse
ytrain = y[:len(y) - period]
ytraintrue = data[pretype].values[:len(y) - period]
mape = MAPE(ytrain, ytraintrue)
rmse = RMSE(ytrain, ytraintrue)
print("MAPE=", mape)
print("RMSE=", rmse)
ypre = y[len(y) - period:]
#返回结果
return {
"trainfromyear": hisfromyear,
"traintoyear": histoyear,
"trainresult": ytrain,
"prefromyear": fromyear,
"pretoyear": toyear,
"preresult": ypre,
"MAPE": mape,
"RMSE": rmse
}
else:
return {"False": "暂不支持其他地区预测"}
def GBDT(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep,
pretype="全社会用电量",
city="云南省",
LearningRate=0.5,
MaxDepth=20,
NumberofEstimators=500):
if timestep > (int(EndYear) - int(StartYear) + 1):
raise ValueError("训练步长过大，请调整后重试.")
elif int(EndYear) - int(StartYear) < (int(PreEndYear) - int(PreStartYear) +
timestep):
raise ValueError("历史时间长度小于预测时间长度,请增加历史时间长度或减小预测时间长度.")
else:
#读取数据，确定参数
name = [pretype]
finaldata = []
outputlen = int(PreEndYear) - int(PreStartYear) + 1
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
test_size = 0 #测试数据集应当取0.3才可以
X, y = generate_data(final,
timestep,
outputlen,
test_size=test_size,
if_norm="no")
gbdt = xgb.XGBRegressor(max_depth=MaxDepth,
learning_rate=LearningRate,
n_estimators=NumberofEstimators,
silent=True,
objective='reg:linear',
booster='gblinear',
n_jobs=50,
nthread=None,
gamma=0,
min_child_weight=1,
max_delta_step=0,
subsample=1,
colsample_bytree=1,
colsample_bylevel=1,
reg_alpha=0,
reg_lambda=1,
scale_pos_weight=1,
base_score=0.5,
random_state=0,
seed=None,
missing=None,
importance_type='gain') #
multi_model = MultiOutputRegressor(gbdt)
multi_model.fit(X["train"], y["train"])
testdata = final.values
num = len(X["train"])
selet = int(np.floor(num / 2))
testinput = X["train"][selet:, :]
testoutput = y["train"][selet:, :]
x_pre = np.array(np.flipud(testdata[-1:-(timestep + 1):-1])).reshape(
1, -1)
y1_gbdt = multi_model.predict(testinput)
y1_gbdt_real = np.array(y1_gbdt).reshape(-1, 1)
y1_real = np.array(testoutput).reshape(-1, 1)
mape = MAPE(y1_gbdt_real, y1_real)
rmse = RMSE(y1_gbdt_real, y1_real)
ytrain = y1_gbdt[-1]
trainyear = []
for t in testoutput[-1]:
count = -1
for d in final[pretype]:
count += 1
if t > d - 1 and t < d + 1:
trainyear.append(final.index[count])
break
pre = multi_model.predict(x_pre)
ypre = np.array(pre).flatten().tolist()
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre,
"MAPE": mape,
"RMSE": rmse
}
#保存
return result
def SARIMAIndustry(StartYear,EndYear,PreStartYear,PreEndYear,pretype,city="云南省"):
StartMonth="%s/1"%(StartYear)
EndMonth="%s/12"%(EndYear)
#读取月度数据
monthdatajson=getData("云南省_month_电力电量类-行业", pretype, StartMonth, EndMonth)
monthdata=json.loads(monthdatajson)
pdmonthdata=pd.DataFrame(monthdata,index=[pretype])
pdmonthdata=pdmonthdata.T
#读取年度数据
yeardatajson=getData("云南省_year_电力电量类-行业", pretype, StartYear, EndYear)
yeardata=json.loads(yeardatajson)
pdyeardata=pd.DataFrame(yeardata,index=[pretype])
pdyeardata=pdyeardata.T
totalyear=int(EndYear)-int(StartYear)+1
trainyear=math.floor(totalyear-totalyear*0.3)#2or5，意味着短期or中期
train_num=trainyear*12
train_data=pdmonthdata[pretype].values[:train_num]
test_data=pdmonthdata[pretype].values[train_num:]
mean = sum(train_data)/len(train_data) # 计算均值
data_mean = [data - mean for data in train_data] # 得到去均值后的序列
data_mean=np.array(data_mean)
#做一阶差分差分，变量序列平稳.
df_mean = pd.DataFrame(data_mean,index=pdmonthdata[pretype].values[:train_num],columns=['mean value'])
df_mean_1 = np.diff(data_mean,1)
# plt.plot(df_mean_1)
# plt.show()
# 进行ADF检验并打印结果
adf_summary = ts.adfuller(np.array(df_mean_1).reshape(-1))
# print(adf_summary)
###SARIMA-----ARIMA(p,d,q)(P,D,Q)s
### (p, d, q)是上述非季节性参数.(P, D, Q)遵循相同的定义.但适用于时间序列的季节分量. 术语s是时间序列的周期（季度为4 ,年度为12 ,等等）.
###https://blog.csdn.net/weixin_39479282/article/details/89513624
##select the best parameter proup of SARIMA, using AIC （Akaike信息标准）
# Define the p, d and q parameters to take any value between 0 and 2
p=q=P=Q=range(0,2)#短期取得是（0,3）
d=D=1#短期取得是1
parameters = itertools.product(p,q,P,Q)
parameters_list = list(parameters)
warnings.filterwarnings("ignore")
# param_best=tuple()
# param_seasonal_best=tuple()
result = []
best_aic = float("inf")
for parameters in parameters_list:
try:
model = sm.tsa.statespace.SARIMAX(df_mean_1,
order=(parameters[0],d,parameters[1]),
seasonal_order=(parameters[2], D, parameters[3], 12)).fit(disp=-1)
# print('ARIMA{}x{}12 - AIC:{}'.format(param, param_seasonal, results.aic))
except:
continue
aic = model.aic
if aic < best_aic:
best_aic = aic
best_param = parameters
result.append([parameters, model.aic])
# result_table = pd.DataFrame(result)
# result_table.columns = ['parameters', 'aic']
# print(result_table.sort_values(by='aic', ascending=True).head())
###prediction
best_model=sm.tsa.statespace.SARIMAX(train_data,
order=(best_param[0],d,best_param[1]),
seasonal_order=(best_param[2], D, best_param[3], 12)).fit(disp=-1)
test_predict=best_model.forecast(steps=len(test_data))
#将月度数据转化为年度数据
def month_to_year(test_predict):
finalpredict=[]
loadsum=0
for i in range(len(test_predict)):
if ((i+1)%12==0) and loadsum!=0:
loadsum=loadsum+test_predict[i]
finalpredict.append(loadsum)
loadsum=0
else:
loadsum=loadsum+test_predict[i]
finalpredict=np.array(finalpredict)
return finalpredict
finalpredict=month_to_year(test_predict)
finaltrue=np.flipud(pdyeardata[pretype].values[-1:-(len(finalpredict)+1):-1])
mape=MAPE(finalpredict,finaltrue)
rmse=RMSE(finalpredict,finaltrue)
trainyear=[]
for t in finaltrue:
for year, data in pdyeardata.iterrows():
if t>data[pretype]-5 and t<data[pretype]+5:
trainyear.append(year)
break
ytrain=np.array(finalpredict)
#预测
outputlen=int(PreEndYear)-int(PreStartYear)+1
traindata=pdmonthdata[pretype].values
best_model=sm.tsa.statespace.SARIMAX(traindata,
order=(best_param[0],d,best_param[1]),
seasonal_order=(best_param[2], D, best_param[3], 12)).fit(disp=-1)
predict=best_model.forecast(steps=outputlen*12)
finalpredict=month_to_year(predict)
ypre=np.array(finalpredict)
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":ytrain.tolist(),"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre.tolist(),"MAPE":mape,"RMSE":rmse}
return result
def UnarylinearTime(StartYear,
EndYear,
PreStartYear,
PreEndYear,
pretype="全社会用电量",
city="云南省",
planflag=0,
plan=0):
"""一元一次外推"""
if city == "云南省":
name = [pretype]
finaldata = []
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
realyear = np.arange(int(StartYear), int(EndYear) + 1)
final["time"] = realyear
x = final["time"].values * (1 + plan * 0.01)
y = final[pretype].values #load
x = x.reshape(-1, 1)
y = y.reshape(-1, 1)
preyear = np.arange(int(PreStartYear), int(PreEndYear) + 1)
year = len(preyear)
#区分训练数据和预测数据
num = len(x)
if num < 2 + year:
raise ValueError("历史数据过少或预测年份过长，请重新选择")
elif year < 2:
raise ValueError("该算法不支持两年以下的预测")
else:
trainx = x[num - 2 - year:num - 2]
trainy = y[num - 2 - year:num - 2]
testx = x[num - 1 - year:num - 1]
testy = y[num - 1 - year:num - 1]
# trainp = ic.getpred(trainx,year,planflag,plan)
# trainp = np.array(trainp).T
# trainpm = []
# for i in range(51):
# trainpm.append(np.mean(trainp[i]))
# trainpmm = trainpm.index(np.median(trainpm))
# trainpredx = trainp[trainpmm]
# trainpredx = [k * trainx[-1] for k in trainpredx]
# print(trainx)
# print(trainpredx)
reg = LinearRegression().fit(trainx, trainy)
# reg = LinearRegression().fit(x, y)
# testp = ic.getpred(testx,year,planflag,plan)
# testp = np.array(testp).T
# testpm = []
# for i in range(51):
# testpm.append(np.mean(testp[i]))
# testpmm = testpm.index(np.median(testpm))
# testpredx = testp[testpmm]
# testpredx = [k * testx[-1] for k in testpredx]
testpredy = [
testx * reg.coef_[0][0] + reg.intercept_[0] for testx in testx
]
# loadp = reg.predict(testx)#趋势外推
mape = MAPE(testpredy, testy)
rmse = RMSE(testpredy, testy)
trainyear = realyear[num - 1 - year:num - 1]
preyear = np.arange(int(PreStartYear),
int(PreEndYear) + 1) * (1 + plan * 0.01)
reg1 = LinearRegression().fit(x, y)
# p = ic.getpred(preyear,year,planflag,plan)
# p = np.array(p).T
# pm = []
# for i in range(51):
# pm.append(np.mean(p[i]))
# pmm = pm.index(np.median(pm))
# predx = p[pmm]
# predx = [k * x[-1] for k in predx]
predy = [
x * reg1.coef_[0][0] + reg1.intercept_[0] for x in preyear
]
predy = np.array(predy).squeeze()
#存储
ytrain = np.array(testpredy).squeeze()
ypre = np.array(predy).squeeze()
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
def LogarithmTime(StartYear,EndYear,PreStartYear,PreEndYear,pretype="全社会用电量",city="云南省",planflag=0,plan=0):
"""对数函数"""
def func5(params, x):
a, b = params
return a * np.log(x) + b
def error5(params, x, y):
return func5(params, x) - y
def slovePara5(x,y):
p0 = [1, 0.02]
Para = leastsq(error5, p0, args=(x, y))
return Para
if city=="云南省":
name=[pretype]
finaldata=[]
#读取历史负荷数据
datajson=getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data=json.loads(datajson)
finaldata.append(data)
#获取最终数据DataFrame
final=pd.DataFrame(finaldata,index=name)
final=final.T
realyear = np.arange(int(StartYear),int(EndYear)+1)
final["time"]=realyear
x = final["time"].values*(1+plan*0.01)
y = final[pretype].values #load
x = x.reshape(-1,1)
y = y.reshape(-1,1)
#区分训练数据和预测数据
preyear = np.arange(int(PreStartYear),int(PreEndYear)+1)*(1+plan*0.01)
year=len(preyear)
#区分训练数据和预测数据
num=len(x)
if num<3+year:
raise ValueError("历史数据过少或预测年份过长，请重新选择")
elif year<2:
raise ValueError("该算法不支持两年以下的预测")
else:
trainx=x[num-2-year-1:num-2].squeeze()
trainy=y[num-2-year-1:num-2].squeeze()
testx=x[num-1-year:num].squeeze()
testy=y[num-1-year:num].squeeze()
Para = slovePara5(trainx,trainy)
a, b = Para[0]
testp = ic.getpred(testx,year+1,planflag,plan)
testp = np.array(testp).T
testpm = []
for i in range(51):
testpm.append(np.mean(testp[i]))
testpmm = testpm.index(np.median(testpm))
testpredx = testp[testpmm]
testpredx = [k * testx[-1] for k in testpredx]
testpredy = [a*np.log (x) + b for x in testx]
trainyear=realyear[num-1-year:num]
mape=MAPE(testpredy,testy)
rmse=RMSE(testpredy,testy)
x=x.squeeze()
y=y.squeeze()
Parapre = slovePara5(x,y)
ap, bp = Parapre[0]
p = ic.getpred(preyear,year,planflag,plan)
p = np.array(p).T
pm = []
for i in range(51):
pm.append(np.mean(p[i]))
pmm = pm.index(np.median(pm))
predx = p[pmm]
predx = [k * x[-1] for k in predx]
predy = [ap*np.log (x0) + bp for x0 in preyear]
predy=np.array(predy).squeeze()
#存储
ytrain=np.array(testpredy).squeeze()
ypre=np.array(predy).squeeze()
result={"trainfromyear":trainyear[0],"traintoyear":trainyear[-1],"trainresult":ytrain.tolist(),"prefromyear":PreStartYear,"pretoyear":PreEndYear,"preresult":ypre.tolist(),"MAPE":mape,"RMSE":rmse}
return result
def Unarylinear(StartYear,
EndYear,
PreStartYear,
PreEndYear,
pretype="全社会用电量",
econamelist="GDP",
city="云南省",
planflag=1,
plan=1,
pro=1):
"""
Parameters
----------
StartYear : str
历史数据起始年份
EndYear : str
历史数据终止年份
PreStartYear : str
预测起始年份
PreEndYear : str
预测终止年份
pretype : str
预测类型："consumption"、"load"
econamelist : list
用到的社会经济类数据名称, e.g., ["GDP","人口"].
city : str, optional
预测城市. The default is "云南省".
planflag : TYPE, optional
是否有规划值，1代表有，0代表没有. The default is 0.
plan : TYPE, optional
规划指数值. The default is 0.
Returns
-------
None.
"""
econamelist = [econamelist]
if len(econamelist) != 1:
raise ValueError("仅支持选择一个因素变量")
elif city == "云南省":
name = [pretype]
finaldata = []
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
#读取经济数据
ecodatajson = getData("云南省_year_社会经济类", econamelist[0], StartYear,
EndYear)
ecodata = json.loads(ecodatajson)
finaldata.append(ecodata)
name.append(econamelist[0])
#获取最终数据DataFrame
final = pd.DataFrame(finaldata, index=name)
final = final.T
x = final[econamelist[0]].values
y = final[pretype].values #load
x = x.reshape(-1, 1)
y = y.reshape(-1, 1)
#区分训练数据和预测数据
num = len(x)
testyear = math.ceil(num / 8)
if testyear < 2:
raise ValueError("历史数据过少或预测年份过长，请重新选择")
# if testyear<3:
# raise ValueError("历史数据过少或预测年份过长，请重新选择")
else:
trainx = x[:num - testyear]
trainy = y[:num - testyear]
testx = x[num - testyear:]
testy = y[num - testyear:]
reg = LinearRegression().fit(trainx, trainy)
# reg = LinearRegression().fit(x, y)
testp = ic.getpred(testx, testyear, planflag, plan, pro)
testp = np.array(testp).T
testpm = []
for i in range(51):
testpm.append(np.mean(testp[i]))
testpmm = testpm.index(np.median(testpm))
testpredx = testp[testpmm]
testpredx = [k * testx[-1] for k in testpredx]
testpredy = [
testx * reg.coef_[0][0] + reg.intercept_[0]
for testx in testpredx
]
# loadp = reg.predict(testx)#趋势外推
mape = MAPE(testpredy, testy)
rmse = RMSE(testpredy, testy)
historyyear = np.arange(int(StartYear), int(EndYear) + 1)
trainyear = historyyear[num - testyear:]
# for t in testy:
# count=-1
# for d in final[pretype]:
# count+=1
# if t>d-5 and t<d+5:
# # print("yes")
# trainyear.append(final.index[count])
# break
preyear = np.arange(int(PreStartYear), int(PreEndYear) + 1)
year = len(preyear)
p = ic.getpred(x, year, planflag, plan, pro)
p = np.array(p).T
pm = []
for i in range(51):
pm.append(np.mean(p[i]))
pmm = pm.index(np.median(pm))
predx = p[pmm]
predx = [k * x[-1] for k in predx]
predy = [x * reg.coef_[0][0] + reg.intercept_[0] for x in predx]
predy = np.array(predy).squeeze()
#存储
ytrain = np.array(testpredy).squeeze()
ypre = np.array(predy).squeeze()
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
def RFIndustry(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep,
pretype,
n_estimators=50,
city="云南省"):
"""
Parameters
----------
StartYear : str
历史数据起始年份
EndYear : str
历史数据终止年份
PreStartYear : str
预测起始年份
PreEndYear : str
预测终止年份
timestep : int
训练数据步长, 常常大于预测时间段的2倍
n_estimators : int
随机森林数目个数. The default is 50.
pretype : str, optional
预测类型："consumption"、"load". The default is "consumption".
city : str, optional
选择城市. The default is "云南省".
Returns
-------
"trainfromyear":StartYear
"traintoyear":EndYear
"trainresult":ytrain, array
训练结果
"prefromyear":PreStartYear
"pretoyear":PreEndYear
"preresult":ypre, array
预测结果
"MAPE":mape, float
"RMSE":rmse, float
"""
if timestep > (int(EndYear) - int(StartYear) + 1):
raise ValueError("训练步长过大，请调整后重试")
elif int(EndYear) - int(StartYear) < (int(PreEndYear) - int(PreStartYear) +
timestep):
raise ValueError("历史时间长度小于预测时间长度，请增加历史时间长度或减小预测时间长度")
else:
name = [pretype]
finaldata = []
outputlen = int(PreEndYear) - int(PreStartYear) + 1
#读取历史负荷数据
datajson = getData("云南省_year_电力电量类-行业", pretype, StartYear, EndYear)
# print(datajson)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
test_size = 0
X, y = generate_data(final,
timestep,
outputlen,
test_size=test_size,
if_norm="no")
y["train"].ravel()
#构建随机森林模型
rf = RandomForestRegressor(n_estimators) #n_estimators：森林个数
rf.fit(X["train"], y["train"])
testdata = final[pretype].values
testinput = []
testoutput = []
num = len(X["train"])
selet = int(np.floor(num / 2))
testinput = X["train"][selet:, :]
testoutput = y["train"][selet:, :]
#训练结果
y_rf = rf.predict(testinput)
y_rf_real = np.array(y_rf).reshape(-1, 1) #训练数据预测结果
y_real = np.array(testoutput).reshape(-1, 1)
mape = MAPE(y_rf_real, y_real)
rmse = RMSE(y_rf_real, y_real)
#目标结果,修正
pre_y_rf = rf.predict(
np.array(np.flipud(testdata[-1:-(timestep + 1):-1])).reshape(
1, -1)) + 500
#保存训练结果
trainyear = []
for t in y_real:
count = -1
for d in final[pretype]:
count += 1
if t > d - 5 and t < d + 5:
# print("yes")
trainyear.append(final.index[count])
break
ytrain = y_rf_real.flatten()
ypre = pre_y_rf.flatten()
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
return result
def SVM(StartYear,
EndYear,
PreStartYear,
PreEndYear,
timestep,
pretype="全社会用电量",
city="云南省"):
#读取数据，确定参数
if timestep > (int(EndYear) - int(StartYear) + 1):
raise ValueError("训练步长过大，请调整后重试")
elif int(EndYear) - int(StartYear) < (int(PreEndYear) - int(PreStartYear) +
timestep):
raise ValueError("历史时间长度小于预测时间长度与训练步长之和，请调整后重试")
else:
name = [pretype]
finaldata = []
outputlen = int(PreEndYear) - int(PreStartYear) + 1
datajson = getData("云南省_year_电力电量类", pretype, StartYear, EndYear)
data = json.loads(datajson)
finaldata.append(data)
final = pd.DataFrame(finaldata, index=name)
final = final.T
test_size = 0 #测试数据集应当取0才可以
X, y = generate_data(final,
timestep,
outputlen,
test_size=test_size,
if_norm="no")
testdata = final[pretype].values
testinput = []
testoutput = []
X, y = generate_data(final,
timestep,
outputlen,
test_size=test_size,
if_norm="no")
svr = SVR(kernel="poly", gamma="scale", C=0.1) #kernel="linear","poly"
multi_model = MultiOutputRegressor(svr)
multi_model.fit(X["train"], y["train"])
testdata = final.values
num = len(X["train"])
selet = int(np.floor(num / 2))
testinput = X["train"][selet:, :]
testoutput = y["train"][selet:, :]
y_svr = multi_model.predict(testinput)
y_svr_real = np.array(y_svr).reshape(-1, 1)
y_real = np.array(testoutput).reshape(-1, 1)
mape = MAPE(y_svr_real, y_real)
rmse = RMSE(y_svr_real, y_real)
pre = multi_model.predict(
np.array(np.flipud(testdata[-1:-(timestep + 1):-1])).reshape(
1, -1))
ytrain = y_svr[-1]
trainyear = []
for t in testoutput[-1]:
count = -1
for d in final[pretype]:
count += 1
if t > d - 1 and t < d + 1:
trainyear.append(final.index[count])
break
ypre = np.array(pre).flatten()
result = {
"trainfromyear": trainyear[0],
"traintoyear": trainyear[-1],
"trainresult": ytrain.tolist(),
"prefromyear": PreStartYear,
"pretoyear": PreEndYear,
"preresult": ypre.tolist(),
"MAPE": mape,
"RMSE": rmse
}
#保存
return result