补充9月数据

各地级市日电量模型/丽水.py

@@ -24,12 +24,10 @@ print(len(df_eval),len(df_train),len(data))
 
 df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
 
-
 # IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
 # high = df['售电量'].describe()['75%'] + 1.5*IQR
 # low = df['售电量'].describe()['25%'] - 1.5*IQR
 # print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
 # df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
 
 

文档处理.py

@@ -0,0 +1,24 @@
+import pandas as pd
+import os
+import re
+file_dir1 = r'C:\Users\鸽子\Desktop\一版结果\电压等级电量预测结果\偏差率'
+file_dir2 = r'C:\Users\鸽子\Desktop\一版结果\电压等级电量预测结果\月底3天预测结果'
+file_dir3 = r'C:\Users\鸽子\Desktop\一版结果\行业电量预测结果\偏差'
+print(os.listdir(file_dir3))
+str1 = '丽水电压等级10kv以下月底偏差率:0.00229'
+
+print(re.split('电压等级|月底偏差率:',str1))
+with open(os.path.join(file_dir3,'9月底偏差率.txt'),'r',encoding='utf-8') as f:
+    lines = f.readlines()
+    list_city = []
+    list_industry = []
+    list_loss = []
+    for i in lines:
+        i = re.split(':|：|其中', i)
+        print(i)
+        list_city.append(i[0][:2])
+        list_industry.append(i[-2].replace(i[0][:2],''))
+        list_loss.append(i[-1][:-2])
+df_level = pd.DataFrame({'城市':list_city,'行业':list_industry,'偏差':list_loss})
+df_level.to_csv(os.path.join(file_dir3,'9月底偏差率.csv'),encoding='gbk')
+print(df_level)

浙江行业电量/杭州日电量数据预处理.py

@@ -27,7 +27,6 @@ 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)

浙江行业电量/浙江总行业.py

@@ -0,0 +1,158 @@
+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):
+        _x = data[i:(i + days_for_train)]
+        dataset_x.append(_x)
+        dataset_y.append(data[i + days_for_train])
+    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)]
+
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+data = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江133行业日电量数据.xlsx', 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))
+
+
+df_result = pd.DataFrame({'预测值':[],'实际值':[],'偏差率':[],'行业':[]})
+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, 1)
+
+    # 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=1, 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(2000):
+        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)
+    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 = np.array(result_list) * (max_value - min_value) + min_value
+
+    df = df * (max_value - min_value) + min_value
+
+
+    # 打印指标
+    # print(abs(pred - df[-3:]).mean() / df[-3:].mean())
+
+    result_eight = pd.DataFrame({'预测值': np.round(pred,1),'实际值': df[-3:]})
+    target = (result_eight['预测值'].sum() - result_eight['实际值'].sum()) / df[-31:].sum()
+    result_eight['偏差率'] = round(target, 5)
+    result_eight['行业'] = industry
+
+    df_result = pd.concat((df_result,result_eight))
+    print(df_result)
+
+
+
+
+
+    # result_eight.to_csv(f'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')
+