补充9月数据

main
鸽子 1 year ago
parent e4eb5e5e50
commit 8d14ef8691

@ -0,0 +1,14 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="PublishConfigData" remoteFilesAllowedToDisappearOnAutoupload="false">
<serverData>
<paths name="root@192.168.89.11:22 password">
<serverdata>
<mappings>
<mapping local="$PROJECT_DIR$" web="/" />
</mappings>
</serverdata>
</paths>
</serverData>
</component>
</project>

@ -1,4 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="pytorch_gpu" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="C:\anaconda\envs\pytorch" project-jdk-type="Python SDK" />
</project>

@ -2,7 +2,7 @@
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="pytorch_gpu" jdkType="Python SDK" />
<orderEntry type="jdk" jdkName="C:\anaconda\envs\pytorch" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="NimToolchainService">
<option name="rootPaths">
<list />
</option>
</component>
</project>

@ -1,79 +1,79 @@
import pandas as pd
import datetime
from sklearn.preprocessing import LabelEncoder
import os
import math
import chinese_calendar as cc
is_holiday = cc.is_workday(datetime.date(2023, 10, 7))
print(is_holiday)
def holiday_work(x):
if cc.is_workday(x):
return 0
if cc.is_holiday(x):
return 1
tq_df = pd.read_excel(r'C:\Users\鸽子\Desktop\杭州\杭州气象数据.xlsx',sheet_name=0)
pd.set_option('display.width',None)
tq_df.columns = tq_df.columns.map(lambda x:x.strip())
tq_df = tq_df[['city_name','dtdate','tem_max','tem_min','rh','rh_max','rh_min','pre','prs','prs_max','prs_min','win_s_max','win_s_min']]
tq_df.drop_duplicates(subset='dtdate',inplace=True)
tq_df = tq_df.sort_values(by='dtdate',ascending=True)
tq_df.reset_index(inplace=True,drop=True)
tq_df['dtdate'] = pd.to_datetime(tq_df['dtdate'],format='%Y%m%d')
tq_df['holiday'] = tq_df['dtdate'].apply(holiday_work)
print(tq_df.columns)
print(tq_df.head())
print(tq_df.info())
def jq(y,x):
a=365.242 * (y - 1900) + 6.2 + 15.22 * x - 1.9 * math.sin(0.262 * x)
return datetime.date(1899,12,31)+datetime.timedelta(days=int(a))
# print(jq(2020,0))
jq_list=['小寒', '大寒', '立春', '雨水', '惊蛰', '春分', '清明', '谷雨', '立夏', '小满', '芒种', '夏至', '小暑', '大暑', '立秋', '处暑', '白露', '秋分', '寒露', '霜降', '立冬', '小雪', '大雪','冬至']
jq_dict={}
for j in range(2019,2024):
for i in range(24):
jq_dict[jq(j,i).strftime('%Y-%m-%d')]=jq_list[i]
# print(jq_dict)
tq_df['24ST']=tq_df.dtdate
tq_df['24ST']=tq_df['24ST'].astype('string').map(jq_dict)
tq_df['24ST'].fillna(method='ffill',inplace=True)
tq_df['24ST'].fillna('冬至',inplace=True)
# data为数据集 product_tags为需要编码的特征列(假设为第一列)
le = LabelEncoder()
tq_df['24ST'] = le.fit_transform(tq_df['24ST'])
print(tq_df)
file2=os.getcwd()+'/气象数据.csv'
try:
tq_df.to_csv(file2,encoding='gbk')
except:
tq_df.to_csv(file2,encoding='utf-8')
elec_df = pd.read_excel(r'C:\Users\鸽子\Desktop\杭州\杭州日电量.xlsx')
elec_df['售电量'] = (elec_df['售电量']/10000).map(lambda x:round(x,2))
print(elec_df.columns)
elec_df.sort_values(by='',ascending=True,inplace=True)
elec_df[''] = pd.to_datetime(elec_df[''],format='%Y%m%d')
print(elec_df.info())
print(elec_df)
df = pd.merge(tq_df,elec_df,left_on='dtdate',right_on='')
df.drop(columns='',inplace=True)
df.set_index('dtdate',inplace=True,drop=True)
print(df)
df.to_csv(os.getcwd()+'\入模数据.csv',encoding='gbk')
import pandas as pd
import datetime
from sklearn.preprocessing import LabelEncoder
import os
import math
import chinese_calendar as cc
is_holiday = cc.is_workday(datetime.date(2023, 10, 7))
print(is_holiday)
def holiday_work(x):
if cc.is_workday(x):
return 0
if cc.is_holiday(x):
return 1
tq_df = pd.read_excel(r'C:\Users\鸽子\Desktop\杭州\杭州气象数据.xlsx',sheet_name=0)
pd.set_option('display.width',None)
tq_df.columns = tq_df.columns.map(lambda x:x.strip())
tq_df = tq_df[['city_name','dtdate','tem_max','tem_min','rh','rh_max','rh_min','pre','prs','prs_max','prs_min','win_s_max','win_s_min']]
tq_df.drop_duplicates(subset='dtdate',inplace=True)
tq_df = tq_df.sort_values(by='dtdate',ascending=True)
tq_df.reset_index(inplace=True,drop=True)
tq_df['dtdate'] = pd.to_datetime(tq_df['dtdate'],format='%Y%m%d')
tq_df['holiday'] = tq_df['dtdate'].apply(holiday_work)
print(tq_df.columns)
print(tq_df.head())
print(tq_df.info())
def jq(y,x):
a=365.242 * (y - 1900) + 6.2 + 15.22 * x - 1.9 * math.sin(0.262 * x)
return datetime.date(1899,12,31)+datetime.timedelta(days=int(a))
# print(jq(2020,0))
jq_list=['小寒', '大寒', '立春', '雨水', '惊蛰', '春分', '清明', '谷雨', '立夏', '小满', '芒种', '夏至', '小暑', '大暑', '立秋', '处暑', '白露', '秋分', '寒露', '霜降', '立冬', '小雪', '大雪','冬至']
jq_dict={}
for j in range(2019,2024):
for i in range(24):
jq_dict[jq(j,i).strftime('%Y-%m-%d')]=jq_list[i]
print(jq_dict)
tq_df['24ST']=tq_df.dtdate
tq_df['24ST']=tq_df['24ST'].astype('string').map(jq_dict)
tq_df['24ST'].fillna(method='ffill',inplace=True)
tq_df['24ST'].fillna('冬至',inplace=True)
# data为数据集 product_tags为需要编码的特征列(假设为第一列)
le = LabelEncoder()
tq_df['24ST'] = le.fit_transform(tq_df['24ST'])
print(tq_df)
file2=os.getcwd()+'/气象数据.csv'
try:
tq_df.to_csv(file2,encoding='gbk')
except:
tq_df.to_csv(file2,encoding='utf-8')
elec_df = pd.read_excel(r'C:\Users\鸽子\Desktop\杭州\杭州日电量.xlsx')
elec_df['售电量'] = (elec_df['售电量']/10000).map(lambda x:round(x,2))
print(elec_df.columns)
elec_df.sort_values(by='',ascending=True,inplace=True)
elec_df[''] = pd.to_datetime(elec_df[''],format='%Y%m%d')
print(elec_df.info())
print(elec_df)
df = pd.merge(tq_df,elec_df,left_on='dtdate',right_on='')
df.drop(columns='',inplace=True)
df.set_index('dtdate',inplace=True,drop=True)
print(df)
df.to_csv(os.getcwd()+'\入模数据.csv',encoding='gbk')

@ -0,0 +1,160 @@
import numpy as np
import pandas as pd
import torch
from torch import nn
from multiprocessing import Pool
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
DAYS_FOR_TRAIN = 10
torch.manual_seed(42)
class LSTM_Regression(nn.Module):
def __init__(self, input_size, hidden_size, output_size=1, num_layers=2):
super().__init__()
self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
self.fc = nn.Linear(hidden_size, output_size)
def forward(self, _x):
x, _ = self.lstm(_x) # _x is input, size (seq_len, batch, input_size)
s, b, h = x.shape # x is output, size (seq_len, batch, hidden_size)
x = x.view(s * b, h)
x = self.fc(x)
x = x.view(s, b, -1) # 把形状改回来
return x
def create_dataset(data, days_for_train=5) -> (np.array, np.array):
dataset_x, dataset_y = [], []
for i in range(len(data) - days_for_train-3):
_x = data[i:(i + days_for_train)]
dataset_x.append(_x)
dataset_y.append(data[i + days_for_train:i + days_for_train+3])
return (np.array(dataset_x), np.array(dataset_y))
def normal(nd):
high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%'])
low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
return nd[(nd<high)&(nd>low)]
def run(file_dir,excel):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date ')
data.columns = data.columns.map(lambda x: x.strip())
data.index = pd.to_datetime(data.index,format='%Y%m%d')
data.sort_index(inplace=True)
print(data.head())
data = data.loc['2021-01':'2023-09']
data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True) # 去除0值列
print('len(data):', len(data))
for industry in data.columns:
df = data[industry]
df = df[df.values != 0] # 去除0值行
df = normal(df)
df = df.astype('float32').values # 转换数据类型
# 标准化到0~1
max_value = np.max(df)
min_value = np.min(df)
df = (df - min_value) / (max_value - min_value)
dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
print('len(dataset_x:)', len(dataset_x))
# 划分训练集和测试集
train_size = len(dataset_x) - 3
train_x = dataset_x[:train_size]
train_y = dataset_y[:train_size]
# 将数据改变形状RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
train_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
train_y = train_y.reshape(-1, 1, 3)
# 转为pytorch的tensor对象
train_x = torch.from_numpy(train_x).to(device)
train_y = torch.from_numpy(train_y).to(device)
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(device) # 导入模型并设置模型的参数输入输出层、隐藏层等
train_loss = []
loss_function = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
for i in range(1500):
out = model(train_x)
loss = loss_function(out, train_y)
loss.backward()
optimizer.step()
optimizer.zero_grad()
train_loss.append(loss.item())
# print(loss)
# 保存模型
# torch.save(model.state_dict(),save_filename)
# torch.save(model.state_dict(),os.path.join(model_save_dir,model_file))
# for test
model = model.eval() # 转换成测试模式
# model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file))) # 读取参数
dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN) # (seq_size, batch_size, feature_size)
dataset_x = torch.from_numpy(dataset_x).to(device)
pred_test = model(dataset_x) # 全量训练集
# 模型输出 (seq_size, batch_size, output_size)
pred_test = pred_test.view(-1)
pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
# plt.plot(pred_test, 'r', label='prediction')
# plt.plot(df, 'b', label='real')
# plt.plot((train_size, train_size), (0, 1), 'g--') # 分割线 左边是训练数据 右边是测试数据的输出
# plt.legend(loc='best')
# plt.show()
# 创建测试集
result_list = []
# 以x为基础实际数据滚动预测未来3天
x = torch.from_numpy(df[-14:-4]).to(device)
pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).detach().numpy()
# for i in range(3):
# next_1_8 = x[1:]
# next_9 = model(x.reshape(-1,1,DAYS_FOR_TRAIN))
# # print(next_9,next_1_8)
# x = torch.concatenate((next_1_8, next_9.view(-1)))
# result_list.append(next_9.view(-1).item())
# 反归一化
pred = pred * (max_value - min_value) + min_value
df = df * (max_value - min_value) + min_value
print(pred)
# 打印指标
print(abs(pred - df[-3:]).mean() / df[-3:].mean())
result_eight = pd.DataFrame({'pred': np.round(pred,1),'real': df[-3:]})
target = (result_eight['pred'].sum() - result_eight['real'].sum()) / df[-31:].sum()
result_eight['loss_rate'] = round(target, 5)
print(target)
print(result_eight)
# result_eight.to_csv(f'./月底预测结果/9月{excel[:2]}.txt', sep='\t', mode='a')
# with open(fr'./偏差/9月底偏差率.txt', 'a', encoding='utf-8') as f:
# f.write(f'{excel[:2]}{industry}:{round(target, 5)}\n')
if __name__ == '__main__':
file_dir = r'C:\python-project\pytorch3\浙江行业电量\浙江所有地市133行业数据'
run(file_dir,'丽水133行业数据.xlsx')
# p = Pool(4)
# for excel in os.listdir(file_dir):
# p.apply_async(func=run,args=(file_dir,excel))
# p.close()
# p.join()
Loading…
Cancel
Save