xgboost 序列数据实战

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_percentage_error
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import PredefinedSplit
from sklearn.preprocessing import MinMaxScaler
df = pd.read_csv('C.test_data201803.csv')
df.time = pd.to_datetime(df.time)

df['KWH'].hist()
df['date'] = df.time.dt.date
plt.plot(df.groupby(['date']).agg({
   'KWH':'sum'}))
df['hour'] = df.time.dt.hour
plt.plot(df.groupby(['hour']).agg({
   'KWH':'sum'}))
df['dow'] = df.time.dt.dayofweek
plt.plot(df.groupby(['dow']).agg({
   'KWH':'sum'}))
tempdf = df.groupby(['date']).agg({
   'KWH':'sum'})
tempdf.loc[tempdf['KWH']==0]

hourRollingMeandf = pd.DataFrame()
for hour in df['hour'].unique