删除重复数据集

浙江行业电量/test1.py

@@ -9,7 +9,7 @@ n2 = np.array([]).reshape(3,-1)
 
 print(np.max([[1,2,3],[4,5,6]]))
 
-file_dir = r'./浙江各地市分电压日电量数据'
+file_dir = r'../浙江电压等级电量/浙江各地市分电压日电量数据'
 excel = os.listdir(file_dir)[0]
 df = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date')
 df.columns = df.columns.map(lambda x:x.strip())
@@ -38,4 +38,45 @@ print(df.tail())
 #     df1['stat_date'] = pd.to_datetime(df1['stat_date'],format='%Y%m%d')
 #     df2 = pd.concat((df2,df1),ignore_index=True)
 #     df2.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市行业电量数据\{city}.xlsx')
+pd.set_option('display.width',None)
+def normal(df):
+    drop_col = [x for x in df.columns if len(df[df[x]==0])/len(df) >= 0.5]
+    df.drop(columns=drop_col,inplace=True)
+    for col in df.columns:
+        try:
+            high = df[col].describe()['75%'] + 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
+            low = df[col].describe()['25%'] - 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
+            df[col] = df[col].map(lambda x: np.nan if (x >= high) | (x <= low) else x)
+            df[col] = df[col].fillna(method='ffill')
+            df[col] = df[col].fillna(method='bfill')
+        except:
+            pass
+    return df
 
+file_dir = './浙江各地市行业电量数据'
+city1 = os.listdir(file_dir)[0]
+df_city = pd.read_excel(os.path.join(file_dir, city1))
+df_city = normal(df_city)
+df_city = df_city.drop(columns='地市')
+df_city[df_city.columns[1:]] /= 10000
+df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
+df_city.stat_date = pd.to_datetime(df_city.stat_date)
+print(df_city.describe())
+
+list_1000 = []
+list_100 = []
+list_10 = []
+list_1 = []
+for i in df_city.columns[1:]:
+    if df_city[i].describe()['mean']>=1000:
+        list_1000.append(i)
+    if df_city[i].describe()['mean'] < 1000 and df_city[i].describe()['mean']  >= 100:
+        list_100.append(i)
+    if df_city[i].describe()['mean'] < 100 and df_city[i].describe()['mean']  >= 10:
+        list_10.append(i)
+    else:
+        list_1.append(i)
+print('list_1:',list_1)
+print('list_10:',list_10)
+print('list_100:',list_100)
+print('list_1000:',list_1000)

浙江行业电量/行业电量_输出为3.py

@@ -34,15 +34,18 @@ class LSTM(nn.Module):
 
 
 def normal(df):
+    drop_col = [x for x in df.columns if len(df[df[x]==0])/len(df) >= 0.5]
+    df.drop(columns=drop_col,inplace=True)
     for col in df.columns:
         try:
             high = df[col].describe()['75%'] + 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
             low = df[col].describe()['25%'] - 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
             df[col] = df[col].map(lambda x: np.nan if (x >= high) | (x <= low) else x)
             df[col] = df[col].fillna(method='ffill')
+            df[col] = df[col].fillna(method='bfill')
         except:
             pass
-
+    return df
 
 def create_data(df_industry, industry):
     dataset_x = []
@@ -83,10 +86,13 @@ df_city[df_city.columns[1:]] /= 10000
 df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
 df_city.stat_date = pd.to_datetime(df_city.stat_date)
 
+
+
 industry = '全社会用电总计'
 df_industry = df_city[['stat_date', industry]]
 dataset_x, dataset_y = create_data(df_industry, industry)
 
+
 for industry in df_city.columns[2:]:
     df_level = df_city[['stat_date', industry]]
     x, y = create_data(df_level, industry)
@@ -95,6 +101,7 @@ for industry in df_city.columns[2:]:
 
 for excel in os.listdir(file_dir)[1:]:
     df_city = pd.read_excel(os.path.join(file_dir, excel)).drop(columns='地市')
+    df_city = normal(df_city)
     df_city[df_city.columns[1:]] /= 10000
     df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
     df_city.stat_date = pd.to_datetime(df_city.stat_date)
@@ -104,6 +111,7 @@ for excel in os.listdir(file_dir)[1:]:
         dataset_x = np.concatenate([dataset_x, x])
         dataset_y = np.concatenate([dataset_y, y])
 
+
 print(dataset_x.shape, dataset_y.shape)
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
@@ -114,7 +122,7 @@ dataset_x = (dataset_x - min_value) / (max_value - min_value)
 dataset_y = (dataset_y - min_value) / (max_value - min_value)
 
 print(max_value, min_value)
-print(np.max(dataset_x), np.min(dataset_x), np.max(dataset_y), np.min(dataset_y))
+
 
 # 划分训练集和测试集
 train_size = int(len(dataset_x) * 0.8)