diff --git a/.idea/deployment.xml b/.idea/deployment.xml new file mode 100644 index 0000000..4de79b3 --- /dev/null +++ b/.idea/deployment.xml @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml index 695b918..3141537 100644 --- a/.idea/misc.xml +++ b/.idea/misc.xml @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/.idea/pytorch2.iml b/.idea/pytorch2.iml index 5cfdc49..719cec4 100644 --- a/.idea/pytorch2.iml +++ b/.idea/pytorch2.iml @@ -2,7 +2,7 @@ - + \ No newline at end of file diff --git a/.idea/toolchains.xml b/.idea/toolchains.xml new file mode 100644 index 0000000..4581420 --- /dev/null +++ b/.idea/toolchains.xml @@ -0,0 +1,8 @@ + + + + + + \ No newline at end of file diff --git a/杭州日电量/浙江所有地市133行业数据/丽水133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/丽水133行业数据（全）.xlsx deleted file mode 100644 index 9b90065..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/丽水133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/台州133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/台州133行业数据（全）.xlsx deleted file mode 100644 index 21df9fa..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/台州133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/嘉兴133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/嘉兴133行业数据（全）.xlsx deleted file mode 100644 index 6144b56..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/嘉兴133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/宁波133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/宁波133行业数据（全）.xlsx deleted file mode 100644 index f90e8ac..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/宁波133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/杭州133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/杭州133行业数据（全）.xlsx deleted file mode 100644 index a894cef..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/杭州133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/温州133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/温州133行业数据（全）.xlsx deleted file mode 100644 index 12e4bfa..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/温州133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/湖州133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/湖州133行业数据（全）.xlsx deleted file mode 100644 index 14f27eb..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/湖州133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/绍兴133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/绍兴133行业数据（全）.xlsx deleted file mode 100644 index 7c7e04b..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/绍兴133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/舟山133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/舟山133行业数据（全）.xlsx deleted file mode 100644 index 97d56b9..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/舟山133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/浙江所有地市133行业数据/衢州133行业数据（全）.xlsx b/杭州日电量/浙江所有地市133行业数据/衢州133行业数据（全）.xlsx deleted file mode 100644 index e03d91f..0000000 Binary files a/杭州日电量/浙江所有地市133行业数据/衢州133行业数据（全）.xlsx and /dev/null differ diff --git a/杭州日电量/industry_elec.py b/浙江行业电量/industry_elec.py similarity index 100% rename from 杭州日电量/industry_elec.py rename to 浙江行业电量/industry_elec.py diff --git a/杭州日电量/industry_elec_cws.py b/浙江行业电量/industry_elec_cws.py similarity index 100% rename from 杭州日电量/industry_elec_cws.py rename to 浙江行业电量/industry_elec_cws.py diff --git a/杭州日电量/偏差/7月底偏差率.txt b/浙江行业电量/偏差/7月底偏差率.txt similarity index 100% rename from 杭州日电量/偏差/7月底偏差率.txt rename to 浙江行业电量/偏差/7月底偏差率.txt diff --git a/杭州日电量/偏差/8月底偏差率.txt b/浙江行业电量/偏差/8月底偏差率.txt similarity index 100% rename from 杭州日电量/偏差/8月底偏差率.txt rename to 浙江行业电量/偏差/8月底偏差率.txt diff --git a/杭州日电量/偏差/9月底偏差率.txt b/浙江行业电量/偏差/9月底偏差率.txt similarity index 100% rename from 杭州日电量/偏差/9月底偏差率.txt rename to 浙江行业电量/偏差/9月底偏差率.txt diff --git a/杭州日电量/月底预测结果/7月丽水.txt b/浙江行业电量/月底预测结果/7月丽水.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月丽水.txt rename to 浙江行业电量/月底预测结果/7月丽水.txt diff --git a/杭州日电量/月底预测结果/7月台州.txt b/浙江行业电量/月底预测结果/7月台州.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月台州.txt rename to 浙江行业电量/月底预测结果/7月台州.txt diff --git a/杭州日电量/月底预测结果/7月嘉兴.txt b/浙江行业电量/月底预测结果/7月嘉兴.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月嘉兴.txt rename to 浙江行业电量/月底预测结果/7月嘉兴.txt diff --git a/杭州日电量/月底预测结果/7月宁波.txt b/浙江行业电量/月底预测结果/7月宁波.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月宁波.txt rename to 浙江行业电量/月底预测结果/7月宁波.txt diff --git a/杭州日电量/月底预测结果/7月杭州.txt b/浙江行业电量/月底预测结果/7月杭州.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月杭州.txt rename to 浙江行业电量/月底预测结果/7月杭州.txt diff --git a/杭州日电量/月底预测结果/7月温州.txt b/浙江行业电量/月底预测结果/7月温州.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月温州.txt rename to 浙江行业电量/月底预测结果/7月温州.txt diff --git a/杭州日电量/月底预测结果/7月湖州.txt b/浙江行业电量/月底预测结果/7月湖州.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月湖州.txt rename to 浙江行业电量/月底预测结果/7月湖州.txt diff --git a/杭州日电量/月底预测结果/7月绍兴.txt b/浙江行业电量/月底预测结果/7月绍兴.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月绍兴.txt rename to 浙江行业电量/月底预测结果/7月绍兴.txt diff --git a/杭州日电量/月底预测结果/7月舟山.txt b/浙江行业电量/月底预测结果/7月舟山.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月舟山.txt rename to 浙江行业电量/月底预测结果/7月舟山.txt diff --git a/杭州日电量/月底预测结果/7月衢州.txt b/浙江行业电量/月底预测结果/7月衢州.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月衢州.txt rename to 浙江行业电量/月底预测结果/7月衢州.txt diff --git a/杭州日电量/月底预测结果/7月金华.txt b/浙江行业电量/月底预测结果/7月金华.txt similarity index 100% rename from 杭州日电量/月底预测结果/7月金华.txt rename to 浙江行业电量/月底预测结果/7月金华.txt diff --git a/杭州日电量/月底预测结果/8月丽水.txt b/浙江行业电量/月底预测结果/8月丽水.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月丽水.txt rename to 浙江行业电量/月底预测结果/8月丽水.txt diff --git a/杭州日电量/月底预测结果/8月台州.txt b/浙江行业电量/月底预测结果/8月台州.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月台州.txt rename to 浙江行业电量/月底预测结果/8月台州.txt diff --git a/杭州日电量/月底预测结果/8月嘉兴.txt b/浙江行业电量/月底预测结果/8月嘉兴.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月嘉兴.txt rename to 浙江行业电量/月底预测结果/8月嘉兴.txt diff --git a/杭州日电量/月底预测结果/8月宁波.txt b/浙江行业电量/月底预测结果/8月宁波.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月宁波.txt rename to 浙江行业电量/月底预测结果/8月宁波.txt diff --git a/杭州日电量/月底预测结果/8月杭州.txt b/浙江行业电量/月底预测结果/8月杭州.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月杭州.txt rename to 浙江行业电量/月底预测结果/8月杭州.txt diff --git a/杭州日电量/月底预测结果/8月温州.txt b/浙江行业电量/月底预测结果/8月温州.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月温州.txt rename to 浙江行业电量/月底预测结果/8月温州.txt diff --git a/杭州日电量/月底预测结果/8月湖州.txt b/浙江行业电量/月底预测结果/8月湖州.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月湖州.txt rename to 浙江行业电量/月底预测结果/8月湖州.txt diff --git a/杭州日电量/月底预测结果/8月绍兴.txt b/浙江行业电量/月底预测结果/8月绍兴.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月绍兴.txt rename to 浙江行业电量/月底预测结果/8月绍兴.txt diff --git a/杭州日电量/月底预测结果/8月舟山.txt b/浙江行业电量/月底预测结果/8月舟山.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月舟山.txt rename to 浙江行业电量/月底预测结果/8月舟山.txt diff --git a/杭州日电量/月底预测结果/8月衢州.txt b/浙江行业电量/月底预测结果/8月衢州.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月衢州.txt rename to 浙江行业电量/月底预测结果/8月衢州.txt diff --git a/杭州日电量/月底预测结果/8月金华.txt b/浙江行业电量/月底预测结果/8月金华.txt similarity index 100% rename from 杭州日电量/月底预测结果/8月金华.txt rename to 浙江行业电量/月底预测结果/8月金华.txt diff --git a/杭州日电量/月底预测结果/9月丽水.txt b/浙江行业电量/月底预测结果/9月丽水.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月丽水.txt rename to 浙江行业电量/月底预测结果/9月丽水.txt diff --git a/杭州日电量/月底预测结果/9月台州.txt b/浙江行业电量/月底预测结果/9月台州.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月台州.txt rename to 浙江行业电量/月底预测结果/9月台州.txt diff --git a/杭州日电量/月底预测结果/9月嘉兴.txt b/浙江行业电量/月底预测结果/9月嘉兴.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月嘉兴.txt rename to 浙江行业电量/月底预测结果/9月嘉兴.txt diff --git a/杭州日电量/月底预测结果/9月宁波.txt b/浙江行业电量/月底预测结果/9月宁波.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月宁波.txt rename to 浙江行业电量/月底预测结果/9月宁波.txt diff --git a/杭州日电量/月底预测结果/9月杭州.txt b/浙江行业电量/月底预测结果/9月杭州.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月杭州.txt rename to 浙江行业电量/月底预测结果/9月杭州.txt diff --git a/杭州日电量/月底预测结果/9月温州.txt b/浙江行业电量/月底预测结果/9月温州.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月温州.txt rename to 浙江行业电量/月底预测结果/9月温州.txt diff --git a/杭州日电量/月底预测结果/9月湖州.txt b/浙江行业电量/月底预测结果/9月湖州.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月湖州.txt rename to 浙江行业电量/月底预测结果/9月湖州.txt diff --git a/杭州日电量/月底预测结果/9月绍兴.txt b/浙江行业电量/月底预测结果/9月绍兴.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月绍兴.txt rename to 浙江行业电量/月底预测结果/9月绍兴.txt diff --git a/杭州日电量/月底预测结果/9月舟山.txt b/浙江行业电量/月底预测结果/9月舟山.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月舟山.txt rename to 浙江行业电量/月底预测结果/9月舟山.txt diff --git a/杭州日电量/月底预测结果/9月衢州.txt b/浙江行业电量/月底预测结果/9月衢州.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月衢州.txt rename to 浙江行业电量/月底预测结果/9月衢州.txt diff --git a/杭州日电量/月底预测结果/9月金华.txt b/浙江行业电量/月底预测结果/9月金华.txt similarity index 100% rename from 杭州日电量/月底预测结果/9月金华.txt rename to 浙江行业电量/月底预测结果/9月金华.txt diff --git a/杭州日电量/杭州日电量数据预处理.py b/浙江行业电量/杭州日电量数据预处理.py similarity index 96% rename from 杭州日电量/杭州日电量数据预处理.py rename to 浙江行业电量/杭州日电量数据预处理.py index aaa6555..d6937de 100644 --- a/杭州日电量/杭州日电量数据预处理.py +++ b/浙江行业电量/杭州日电量数据预处理.py @@ -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=' 天 ',ascending=True,inplace=True) -elec_df[' 天 '] = pd.to_datetime(elec_df[' 天 '],format='%Y%m%d') -print(elec_df.info()) -print(elec_df) - -df = pd.merge(tq_df,elec_df,left_on='dtdate',right_on=' 天 ') -df.drop(columns=' 天 ',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=' 天 ',ascending=True,inplace=True) +elec_df[' 天 '] = pd.to_datetime(elec_df[' 天 '],format='%Y%m%d') +print(elec_df.info()) +print(elec_df) + +df = pd.merge(tq_df,elec_df,left_on='dtdate',right_on=' 天 ') +df.drop(columns=' 天 ',inplace=True) + +df.set_index('dtdate',inplace=True,drop=True) +print(df) +df.to_csv(os.getcwd()+'\入模数据.csv',encoding='gbk') + + + + + diff --git a/浙江行业电量/浙江所有地市133行业数据/丽水133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/丽水133行业数据（全）.xlsx new file mode 100644 index 0000000..802bea9 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/丽水133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/台州133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/台州133行业数据（全）.xlsx new file mode 100644 index 0000000..abf88f4 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/台州133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/嘉兴133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/嘉兴133行业数据（全）.xlsx new file mode 100644 index 0000000..d050fe1 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/嘉兴133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/宁波133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/宁波133行业数据（全）.xlsx new file mode 100644 index 0000000..e57dd5c Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/宁波133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/杭州133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/杭州133行业数据（全）.xlsx new file mode 100644 index 0000000..9d29e5e Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/杭州133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/温州133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/温州133行业数据（全）.xlsx new file mode 100644 index 0000000..ad8cab4 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/温州133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/湖州133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/湖州133行业数据（全）.xlsx new file mode 100644 index 0000000..7972a34 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/湖州133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/绍兴133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/绍兴133行业数据（全）.xlsx new file mode 100644 index 0000000..81696d1 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/绍兴133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/舟山133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/舟山133行业数据（全）.xlsx new file mode 100644 index 0000000..2601aa5 Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/舟山133行业数据（全）.xlsx differ diff --git a/浙江行业电量/浙江所有地市133行业数据/衢州133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/衢州133行业数据（全）.xlsx new file mode 100644 index 0000000..61b975f Binary files /dev/null and b/浙江行业电量/浙江所有地市133行业数据/衢州133行业数据（全）.xlsx differ diff --git a/杭州日电量/浙江所有地市133行业数据/金华133行业数据（全）.xlsx b/浙江行业电量/浙江所有地市133行业数据/金华133行业数据（全）.xlsx similarity index 85% rename from 杭州日电量/浙江所有地市133行业数据/金华133行业数据（全）.xlsx rename to 浙江行业电量/浙江所有地市133行业数据/金华133行业数据（全）.xlsx index 4222aee..f59214c 100644 Binary files a/杭州日电量/浙江所有地市133行业数据/金华133行业数据（全）.xlsx and b/浙江行业电量/浙江所有地市133行业数据/金华133行业数据（全）.xlsx differ diff --git a/杭州日电量/滚动预测.py b/浙江行业电量/滚动预测.py similarity index 100% rename from 杭州日电量/滚动预测.py rename to 浙江行业电量/滚动预测.py diff --git a/浙江行业电量/输出为3.py b/浙江行业电量/输出为3.py new file mode 100644 index 0000000..de6655c --- /dev/null +++ b/浙江行业电量/输出为3.py @@ -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[(ndlow)] + +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（全）.xlsx') + # p = Pool(4) + # for excel in os.listdir(file_dir): + # p.apply_async(func=run,args=(file_dir,excel)) + # p.close() + # p.join() \ No newline at end of file