|
|
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
|
|
|
import datetime
|
|
|
import math
|
|
|
from sklearn.preprocessing import LabelEncoder
|
|
|
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
|
|
|
elif str(x)[5:7] in ['01', '02', '03', '06', '09', '11', '12']:
|
|
|
return 1
|
|
|
elif str(x)[5:7] in['04', '05', '10']:
|
|
|
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[(nd<high)&(nd>low)].index
|
|
|
|
|
|
# df = pd.read_excel(r'C:\Users\鸽子\Desktop\杭州19年至今日电量及气象数据.xlsx',sheet_name=0)
|
|
|
# df_elec = pd.read_excel(r'C:\Users\鸽子\Desktop\杭州19年至今日电量及气象数据.xlsx',sheet_name=1)
|
|
|
# df_elec.columns = df_elec.columns.map(lambda x:x.strip())
|
|
|
# df_elec['售电量'] = df_elec['售电量']/10000
|
|
|
# df.columns = df.columns.map(lambda x:x.strip())
|
|
|
# df = df[['dtdate','tem_max','tem_min']]
|
|
|
# # print(df.head())
|
|
|
# # print(df_elec.head())
|
|
|
#
|
|
|
# merge_df = pd.merge(df_elec,df,left_on='pt_date',right_on='dtdate')[['pt_date','tem_max','tem_min','售电量']]
|
|
|
# merge_df.set_index('pt_date',inplace=True)
|
|
|
# merge_df.index = pd.to_datetime(merge_df.index,format='%Y%m%d')
|
|
|
#
|
|
|
#
|
|
|
# merge_df['month'] = merge_df.index.strftime('%Y-%m-%d').str[5:7]
|
|
|
# merge_df['month'] = merge_df['month'].astype('int')
|
|
|
# merge_df.to_csv('杭州入模数据.csv',encoding='gbk')
|
|
|
data = pd.read_csv(r'杭州入模数据.csv',encoding='gbk')
|
|
|
|
|
|
data.drop_duplicates(subset='pt_date',inplace=True)
|
|
|
|
|
|
data.set_index('pt_date',inplace=True)
|
|
|
data.index = pd.to_datetime(data.index)
|
|
|
|
|
|
print(data.loc['2023-07'])
|
|
|
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)
|
|
|
|
|
|
data['24ST']=data.index
|
|
|
data['24ST']=data['24ST'].astype('string').map(jq_dict)
|
|
|
data['24ST'].fillna(method='ffill',inplace=True)
|
|
|
data['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()
|
|
|
data['24ST'] = le.fit_transform(data['24ST'])
|
|
|
data = data.loc[normal(data['售电量'])]
|
|
|
|
|
|
data['season'] = data.index.map(season)
|
|
|
print(data['售电量'].describe())
|
|
|
print(data)
|
|
|
# list2 = []
|
|
|
# list0 = []
|
|
|
# list1 = []
|
|
|
# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
|
|
|
# month_index = df.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
|
|
|
# if df.loc[month_index]['售电量'].mean() >= df['售电量'].describe()['75%']:
|
|
|
# list2.append(i)
|
|
|
# elif df.loc[month_index]['售电量'].mean() <= df['售电量'].describe()['25%']:
|
|
|
# list0.append(i)
|
|
|
# else:
|
|
|
# list1.append(i)
|
|
|
# print(list0,list1,list2)
|
|
|
|
|
|
|
|
|
|
|
|
# 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]
|
|
|
# plt.plot(range(len(data['售电量']['2021':'2022'])),data['售电量']['2021':'2022'])
|
|
|
# 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['2023-9']
|
|
|
df_train = data.loc['2019-1':'2023-8']
|
|
|
print(len(df_train),len(df_eval))
|
|
|
plt.plot(range(len(data.loc['2019-1':'2023-9'])),data.loc['2019-1':'2023-9'])
|
|
|
plt.show()
|
|
|
# df_train = df[500:850]
|
|
|
print(len(df_eval),len(df_train),len(data))
|
|
|
|
|
|
print(data.corr(method='pearson')['售电量'])
|
|
|
|
|
|
df_train = df_train[['tem_max','tem_min','24ST','售电量','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','season','24ST']]
|
|
|
X_eval = df_eval[['tem_max','tem_min','season','24ST']]
|
|
|
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=0.2,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)
|
|
|
|