补充9月数据

文档处理.py

@@ -4,21 +4,59 @@ 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)
+import numpy as np
+np.set_printoptions(threshold=np.inf)
+
+# 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)
+file_dir = r'C:\python-project\pytorch3\浙江行业电量\浙江所有地市133行业数据'
+# print(os.listdir(file_dir))
+dict1 = {}
+
+for file in os.listdir(file_dir):
+
+    df = pd.read_excel(os.path.join(file_dir,file),index_col=' stat_date ')
+
+    col_list = df.drop(columns=[i for i in df.columns if (df[i] == 0).sum() / len(df) >= 0.5]).columns
+    dict1[file[:2]] = col_list
+    print(dict1)
+
+    # print(len(df.drop(columns=[i for i in df.columns if (df[i] == 0).sum() / len(df) >= 0.5]).columns))
+
+read_path = r'C:\Users\鸽子\Desktop\一版结果\行业电量预测结果\月底预测结果'
+list1 = []
+for i in os.listdir(read_path):
     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)
+    data = pd.read_csv(os.path.join(read_path, i), sep='\t',header=None)
+    data = data[data.columns[1:]]
+
+
+    for j,step in enumerate(range(0, len(data), 4)):
+        df = data.iloc[step+1:step + 4, :]
+        df.columns = ['预测值', '实际值', '偏差率']
+        try:
+            df['行业'] = dict1[i[2:4]][j]
+        except:
+            pass
+        df['城市'] = i[2:4]
+        list1.append(df)
+        print(df)
+df = pd.concat(list1,ignore_index=True)
+df.to_csv('各市行业电量预测结果.csv',encoding='gbk')
+print(df)