diff --git a/入模数据/1.py b/入模数据/1.py deleted file mode 100644 index f382c45..0000000 --- a/入模数据/1.py +++ /dev/null @@ -1,120 +0,0 @@ -import xgboost as xgb -import pandas as pd -import os -from sklearn.metrics import r2_score -from sklearn.model_selection import train_test_split -import matplotlib as mpl -import matplotlib.pyplot as plt -mpl.rcParams['font.sans-serif']=['kaiti'] - -pd.set_option('display.width',None) - -def hf_season(x): - list1= [] - for i in range(1,13): - if x.loc[f'2021-{i}'].mean() >= x.describe()['75%']: - list1.append(i) - return list1 - - -def season(x): - if str(x)[5:7] in ('06','07','08','12','01','02'): - return 1 - else: - return 0 -def month(x): - if str(x)[5:7] in ('08','09','10','12','01','02'): - return 1 - else: - return 0 -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[(ndlow)] - - -data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate') -data.index = pd.to_datetime(data.index,format='%Y-%m-%d') -data = data.loc[normal(data['售电量']).index] -# for i in range(1,13): -# plt.plot(range(len(data['售电量'][f'2022-{i}'])),data['售电量'][f'2022-{i}']) -# plt.show() -print(data['售电量']['2022-9']) -plt.plot(range(len(data['售电量']['2022-7'])),data['售电量']['2022-7']) -plt.plot(range(len(data['售电量']['2022-7']),len(data['售电量']['2022-7'])+len(data['售电量']['2023-7'])),data['售电量']['2023-7']) -# plt.plot(range(len(data['售电量'][['2022-9','2023-9']])),data['售电量'][['2022-9','2023-9']]) -plt.show() - -# print(hf_season(data.loc['2021']['售电量'])) - -data['month'] = data.index.strftime('%Y-%m-%d').str[6] -data['month'] = data['month'].astype('int') -data['season'] = data.index.map(season) -print(data.head(50)) - -df_eval = data.loc['2023-7'] -df_train = data.loc['2021-1':'2023-6'] -# df_train = df[500:850] -print(len(df_eval),len(df_train),len(data)) - -print(data.drop(columns='city_name').corr(method='pearson')['售电量']) - -df_train = df_train[['tem_max','tem_min','24ST','rh','rh_max','prs','prs_max','prs_min','售电量','month','holiday','season']] - - -# 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)] - - -X = df_train[['tem_max','tem_min','24ST','holiday','season']] -X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']] -y = df_train['售电量'] -print(y.describe()) -# best_goal = 1 -# best_i = {} -# for i in range(400): - -x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,random_state=42) -model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150) -model.fit(x_train,y_train) - -y_pred = model.predict(x_test) -result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index) - -# 指标打印 -print(abs(y_test - y_pred).mean() / y_test.mean()) -eval_pred = model.predict(X_eval) - -result_eval = pd.DataFrame({'eval':df_eval['售电量'],'pred':eval_pred},index=df_eval['售电量'].index) - -print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum()) - -goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum() -print('goal:',goal) - -goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum() - -print('goal2:',goal2) -print(result_eval) -print('r2:',r2_score(y_test,y_pred)) - # if abs(goal) < best_goal: - # best_goal = abs(goal) - # best_i['best_i'] = i - # x = goal2 -# print(best_i,best_goal,x) - - - -# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\杭州.csv') -# with open(r'C:\Users\user\Desktop\9月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f: -# f.write(f'杭州月末3天偏差率：{round(goal,5)},9号-月底偏差率：{round(goal2,5)}\n') -# # 保存模型 -# model.save_model('hangzhou.bin') -# loaded_model = xgb.XGBRegressor() -# loaded_model.load_model('hangzhou.bin') -# model.predict(X_eval) - diff --git a/入模数据/丽水.xlsx b/入模数据/丽水.xlsx new file mode 100644 index 0000000..1156441 Binary files /dev/null and b/入模数据/丽水.xlsx differ diff --git a/入模数据/丽水数据.xlsx b/入模数据/丽水数据.xlsx deleted file mode 100644 index 0566dfd..0000000 Binary files a/入模数据/丽水数据.xlsx and /dev/null differ diff --git a/入模数据/台州.xlsx b/入模数据/台州.xlsx new file mode 100644 index 0000000..5bd6d74 Binary files /dev/null and b/入模数据/台州.xlsx differ diff --git a/入模数据/台州数据(1).xlsx b/入模数据/台州数据(1).xlsx deleted file mode 100644 index 08d6913..0000000 Binary files a/入模数据/台州数据(1).xlsx and /dev/null differ diff --git a/入模数据/嘉兴.xlsx b/入模数据/嘉兴.xlsx new file mode 100644 index 0000000..7dcf86c Binary files /dev/null and b/入模数据/嘉兴.xlsx differ diff --git a/入模数据/嘉兴数据.xlsx b/入模数据/嘉兴数据.xlsx deleted file mode 100644 index 09ee922..0000000 Binary files a/入模数据/嘉兴数据.xlsx and /dev/null differ diff --git a/入模数据/宁波.xlsx b/入模数据/宁波.xlsx new file mode 100644 index 0000000..c613a4a Binary files /dev/null and b/入模数据/宁波.xlsx differ diff --git a/入模数据/宁波数据.xlsx b/入模数据/宁波数据.xlsx deleted file mode 100644 index aa29744..0000000 Binary files a/入模数据/宁波数据.xlsx and /dev/null differ diff --git a/入模数据/杭州.xlsx b/入模数据/杭州.xlsx new file mode 100644 index 0000000..5eb8239 Binary files /dev/null and b/入模数据/杭州.xlsx differ diff --git a/入模数据/杭州数据.xlsx b/入模数据/杭州数据.xlsx deleted file mode 100644 index 044de43..0000000 Binary files a/入模数据/杭州数据.xlsx and /dev/null differ diff --git a/入模数据/温州.xlsx b/入模数据/温州.xlsx new file mode 100644 index 0000000..d4613d7 Binary files /dev/null and b/入模数据/温州.xlsx differ diff --git a/入模数据/温州数据(1).xlsx b/入模数据/温州数据(1).xlsx deleted file mode 100644 index 47aad76..0000000 Binary files a/入模数据/温州数据(1).xlsx and /dev/null differ diff --git a/入模数据/湖州.xlsx b/入模数据/湖州.xlsx new file mode 100644 index 0000000..6cbc6b1 Binary files /dev/null and b/入模数据/湖州.xlsx differ diff --git a/入模数据/湖州数据.xlsx b/入模数据/湖州数据.xlsx deleted file mode 100644 index 0cc47e4..0000000 Binary files a/入模数据/湖州数据.xlsx and /dev/null differ diff --git a/入模数据/绍兴.xlsx b/入模数据/绍兴.xlsx new file mode 100644 index 0000000..0a498b1 Binary files /dev/null and b/入模数据/绍兴.xlsx differ diff --git a/入模数据/绍兴数据(1).xlsx b/入模数据/绍兴数据(1).xlsx deleted file mode 100644 index 3426aae..0000000 Binary files a/入模数据/绍兴数据(1).xlsx and /dev/null differ diff --git a/入模数据/舟山.xlsx b/入模数据/舟山.xlsx new file mode 100644 index 0000000..2ba7a65 Binary files /dev/null and b/入模数据/舟山.xlsx differ diff --git a/入模数据/舟山数据(1).xlsx b/入模数据/舟山数据(1).xlsx deleted file mode 100644 index ebce5e2..0000000 Binary files a/入模数据/舟山数据(1).xlsx and /dev/null differ diff --git a/入模数据/衢州.xlsx b/入模数据/衢州.xlsx new file mode 100644 index 0000000..ef453eb Binary files /dev/null and b/入模数据/衢州.xlsx differ diff --git a/入模数据/衢州数据.xlsx b/入模数据/衢州数据.xlsx deleted file mode 100644 index f3bfdf2..0000000 Binary files a/入模数据/衢州数据.xlsx and /dev/null differ diff --git a/入模数据/金华.csv b/入模数据/金华.csv deleted file mode 100644 index 8e9061e..0000000 --- a/入模数据/金华.csv +++ /dev/null @@ -1,32 +0,0 @@ -dtdate,eval,pred -2023-08-01,4781.72,4638.4565 -2023-08-02,5264.18,4224.5635 -2023-08-03,5308.39,5036.8037 -2023-08-04,5531.27,5441.4995 -2023-08-05,5989.36,6265.5225 -2023-08-06,6373.8,5753.8174 -2023-08-07,5688.18,4972.277 -2023-08-08,5287.83,4424.5815 -2023-08-09,5560.11,4310.7837 -2023-08-10,5706.55,4657.085 -2023-08-11,5923.97,5702.3916 -2023-08-12,6238.88,5897.044 -2023-08-13,5961.14,4939.6694 -2023-08-14,5316.45,3566.0615 -2023-08-15,4802.99,3005.286 -2023-08-16,4908.05,3805.3303 -2023-08-17,4792.48,3044.6094 -2023-08-18,4380.25,3086.1318 -2023-08-19,4490.53,4237.0283 -2023-08-20,4577.54,3911.61 -2023-08-21,4784.33,4044.5312 -2023-08-22,4517.86,3943.1465 -2023-08-23,4327.74,4588.3257 -2023-08-24,4736.04,4383.0825 -2023-08-25,4981.34,4765.4146 -2023-08-26,4967.04,4744.9272 -2023-08-27,5044.84,4771.1987 -2023-08-28,4919.99,4644.142 -2023-08-29,3611.24,3359.0356 -2023-08-30,3184.04,3217.3503 -2023-08-31,3026.0,3217.8718 diff --git a/入模数据/金华.xlsx b/入模数据/金华.xlsx new file mode 100644 index 0000000..012b81b Binary files /dev/null and b/入模数据/金华.xlsx differ diff --git a/入模数据/金华数据.xlsx b/入模数据/金华数据.xlsx deleted file mode 100644 index 780af6d..0000000 Binary files a/入模数据/金华数据.xlsx and /dev/null differ diff --git a/区域电量19年至今数据.py b/区域电量19年至今数据.py index e2ce2ae..bed20b7 100644 --- a/区域电量19年至今数据.py +++ b/区域电量19年至今数据.py @@ -12,10 +12,6 @@ mpl.rcParams['font.sans-serif']=['kaiti'] pd.set_option('display.width',None) - - - - def season(x): if str(x)[5:7] in ['07', '08']: return 2 diff --git a/浙江电压等级电量/电压等级_输出为5.py b/浙江电压等级电量/电压等级_输出为5.py index 7ffbbac..9767442 100644 --- a/浙江电压等级电量/电压等级_输出为5.py +++ b/浙江电压等级电量/电压等级_输出为5.py @@ -17,8 +17,8 @@ class LSTM_Regression(nn.Module): 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) 一批多少条样本 多少批样本 每一个样本的输入特征大小（10） - s, b, h = x.shape # x is output, size (seq_len, batch, hidden_size) 经过lstm计算后输出为隐藏层大小 + 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 @@ -52,133 +52,110 @@ def data_preprocessing(data): return data -if __name__ == '__main__': - # 拼接数据集 - file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据' - excel = os.listdir(file_dir)[0] +# 拼接数据集 +file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据' +excel = os.listdir(file_dir)[0] - data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col=' stat_date ') +data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col=' stat_date ') - data = data_preprocessing(data) - - df = data[data.columns[0]] - df.dropna(inplace = True) - dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN) - - for level in data.columns[1:]: - df = data[level] - df.dropna(inplace=True) - x, y = create_dataset(df, DAYS_FOR_TRAIN) - dataset_x = np.concatenate((dataset_x, x)) - dataset_y = np.concatenate((dataset_y, y)) - - - for excel in os.listdir(file_dir)[1:]: - data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date ') - data = data_preprocessing(data) - - for level in data.columns: - df = data[level] - df.dropna(inplace=True) - x,y = create_dataset(df,DAYS_FOR_TRAIN) - dataset_x = np.concatenate((dataset_x,x)) - dataset_y = np.concatenate((dataset_y,y)) - - print(dataset_x,dataset_y,dataset_x.shape,dataset_y.shape) - - # 训练 - device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') - - # 标准化到0~1 - max_value = np.max(dataset_x) - min_value = np.min(dataset_x) - dataset_x = (dataset_x - min_value) / (max_value - min_value) - dataset_y = (dataset_y - min_value) / (max_value - min_value) - - # 划分训练集和测试集 - train_size = int(len(dataset_x)*0.7) - - 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, 5) - - # 转为pytorch的tensor对象 - train_x = torch.from_numpy(train_x).to(device).type(torch.float32) - train_y = torch.from_numpy(train_y).to(device).type(torch.float32) - - model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, 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(),'dy5.pth') - - - model.load_state_dict(torch.load('dy5.pth')) - - # 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).type(torch.float32) - - 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.reshape(-1), 'r', label='prediction') - # plt.plot(dataset_y.reshape(-1), 'b', label='real') - # plt.plot((train_size*5, train_size*5), (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() +data = data_preprocessing(data) +df = data[data.columns[0]] +df.dropna(inplace = True) +dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN) +for level in data.columns[1:]: + df = data[level] + df.dropna(inplace=True) + x, y = create_dataset(df, DAYS_FOR_TRAIN) + dataset_x = np.concatenate((dataset_x, x)) + dataset_y = np.concatenate((dataset_y, y)) +for excel in os.listdir(file_dir)[1:]: + data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date ') + data = data_preprocessing(data) + for level in data.columns: + df = data[level] + df.dropna(inplace=True) + x,y = create_dataset(df,DAYS_FOR_TRAIN) + dataset_x = np.concatenate((dataset_x,x)) + dataset_y = np.concatenate((dataset_y,y)) + +print(dataset_x,dataset_y,dataset_x.shape,dataset_y.shape) + +# 训练 +device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') + +# 标准化到0~1 +max_value = np.max(dataset_x) +min_value = np.min(dataset_x) +dataset_x = (dataset_x - min_value) / (max_value - min_value) +dataset_y = (dataset_y - min_value) / (max_value - min_value) + +# 划分训练集和测试集 +train_size = len(dataset_x)*0.7 +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, 5) + +# 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(),'dy5.pth') + + +# 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 -df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江各地市分电压日电量数据\杭州.xlsx',index_col=' stat_date ') -df_eval.columns = df_eval.columns.map(lambda x:x.strip()) -df_eval.index = pd.to_datetime(df_eval.index) - -x,y = create_dataset(df_eval.loc['2023-7']['10kv以下'],10) - -x = (x - min_value) / (max_value - min_value) -x = x.reshape(-1,1,10) - -x = torch.from_numpy(x).type(torch.float32).to(device) -pred = model(x) +# x = torch.from_numpy(df[-14:-4]).to(device) +# pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).detach().numpy() # 反归一化 -pred = pred * (max_value - min_value) + min_value +# pred = pred * (max_value - min_value) + min_value # df = df * (max_value - min_value) + min_value -print(pred,y) -df = pd.DataFrame({'real':y.reshape(-1),'pred':pred.view(-1).cpu().detach().numpy()}) -df.to_csv('7月预测.csv',encoding='gbk') - -# 打印指标 +# 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()