python按时间坐标预测销量

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
import datetime

import warnings
warnings.filterwarnings("ignore")

import statsmodels.api as sm
from statsmodels.graphics.api import qqplot
from statsmodels.tsa.arima_model import ARIMA
from statsmodels.tsa.seasonal import seasonal_decompose
from statsmodels.tsa.stattools import adfuller as ADF

## 设置字符集,防止中文乱码
mpl.rcParams['font.sans-serif']=[u'simHei']
mpl.rcParams['axes.unicode_minus']=False


data=pd.read_excel("天猫销售数据.xlsx")
data.info()
#fx=lambda x: pd.datetime.strptime(x,"%Y/%m/%d")
#data["Date"]=data["Date"].apply(fx)
df=data.set_index("Date") #将Date设置为索引
df
df=pd.Series(df.Orders,index=df.index ) 

fig=plt.figure(figsize=(10,4))
ax=fig.add_subplot(111)
plt.plot(df)
ax.set(title="Orders of Date",
      ylabel="Orders",
      xlabel="Date")
plt.show()

## 做差分,检查平稳性
def diff(timeseries):
    time_diff1=timeseries.diff(1).fillna(0) #1阶差分
    time_diff2=time_diff1.diff(1).fillna(0) #2阶差分

    time_adf=ADF(timeseries)
    time_diff1_adf=ADF(time_diff1)
    time_diff2_adf=ADF(time_diff2)

    return [time_diff1_adf,time_diff2_adf]

diff(df)
#[(-3.683025128820224,
#  0.004358356299291195,
#  10,
#  138,
#  {'1%': -3.47864788917503,
#   '5%': -2.882721765644168,
#   '10%': -2.578065326612056},
#  1423.5325819802563),
# (-9.388939765399352,
#  6.641377737915045e-16,
#  9,
#  139,
#  {'1%': -3.4782936965183815,
#   '5%': -2.882567574015525,
#   '10%': -2.5779830117488745},
#  1434.1670882621088)]
# 
 
def autocorr(time_series,lags):
    fig=plt.figure(figsize=(12,8))
    ax1=fig.add_subplot(211)
    sm.graphics.tsa.plot_acf(time_series,lags=lags,ax=ax1)
    
    ax2=fig.add_subplot(212)
    sm.graphics.tsa.plot_pacf(time_series,lags=lags,ax=ax2)
    
    plt.show()

time_diff1=df.diff(1).fillna(0) 
autocorr(time_diff1,30)  

data_eva=sm.tsa.arma_order_select_ic(df,ic=["aic","bic"],trend="nc",max_ar=7,max_ma=7)
print("data_AIC",data_eva.aic_min_order)
print("data_BIC",data_eva.bic_min_order)
#
#data_AIC (7, 7)
#data_BIC (1, 1)
#data_AIC (1, 3)
#data_BIC (1, 1)


arma_77=sm.tsa.SARIMAX(df,order=(3,1,1)).fit()
print("arma_77",arma_77.aic,arma_77.bic,arma_77.hqic)

arma_71=sm.tsa.SARIMAX(df,order=(1,1,7)).fit()
print("arma_71",arma_71.aic,arma_71.bic,arma_71.hqic)

arma_11=sm.tsa.SARIMAX(df,order=(1,1,1)).fit()
print("arma_11",arma_11.aic,arma_11.bic,arma_11.hqic)

arma_35=sm.tsa.SARIMAX(df,order=(3,1,5)).fit()
print("arma_35",arma_35.aic,arma_35.bic,arma_35.hqic)


arma_77.plot_diagnostics(figsize=(12,8))

 # D-W检验
 # DW趋近2,P=0,不存在自相关性
print(sm.stats.durbin_watson(arma_77.resid.values))

resid=arma_77.resid
fig=plt.figure(figsize=(16,12))
ax1=fig.add_subplot(211)
sm.graphics.tsa.plot_acf(resid,lags=15,ax=ax1)  #自相关系数

ax2=fig.add_subplot(212)
sm.graphics.tsa.plot_pacf(resid,lags=15,ax=ax2)  #偏相关系数
acf,q,p=sm.tsa.acf(resid.values.squeeze(),nlags=20,qstat=True)
data=np.c_[range(1,21),acf[1:],q,p]
table=pd.DataFrame(data,columns=["lag","AC","Q","P-value"])
print(table.set_index("lag"))



pre=arma_77.predict("2020-07-01","2020-07-23",dynamic=True)
#绘制预测曲线图
fig,ax=plt.subplots(figsize=(12,8))
ax=df.ix["2020-04-05":].plot(ax=ax)
fig=arma_77.predict("2020-07-01","2020-07-23",dynamic=True,ax=ax,plot_insample=False).plot(style="r-.")
plt.title("未来10天的销售额预测",fontsize=20)
plt.show()
  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值