7种方式做时间序列预测

导入数据：

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
 
df = pd.read_csv(r'XXX',engine="python")
df.head()

检查图片：

import pandas as pd
import matplotlib.pyplot as plt
 
# Subsetting the dataset
# Index 11856 marks the end of year 2013
df = pd.read_csv(r'XXX',engine="python", nrows=11856)
 
# Creating train and test set
# Index 10392 marks the end of October 2013
train = df[0:10392]
test = df[10392:]
 
# Aggregating the dataset at daily level
df['Timestamp'] = pd.to_datetime(df['Datetime'], format='%d-%m-%Y %H:%M')
df.index = df['Timestamp']
df = df.resample('D').mean() #按天采样，计算均值
 
train['Timestamp'] = pd.to_datetime(train['Datetime'], format='%d-%m-%Y %H:%M')
train.index = train['Timestamp']
train = train.resample('D').mean() #
 
test['Timestamp'] = pd.to_datetime(test['Datetime'], format='%d-%m-%Y %H:%M')
test.index = test['Timestamp']
test = test.resample('D').mean()
 
#Plotting data
train.Count.plot(figsize=(15,8), title= 'Daily Ridership', fontsize=14)
test.Count.plot(figsize=(15,8), title= 'Daily Ridership', fontsize=14)
plt.show()

朴素法：

# 朴素法
dd = np.asarray(train['Count'])
y_hat = test.copy()
y_hat['naive'] = dd[len(dd) - 1]
plt.figure(figsize=(12, 8))
plt.plot(train.index, train['Count'], label='Train')
plt.plot(test.index, test['Count'], label='Test')
plt.plot(y_hat.index, y_hat['naive'], label='Naive Forecast')
plt.legend(loc='best')
plt.title("Naive Forecast")
plt.show()

简单平均法：

y_hat_avg = test.copy()
y_hat_avg['avg_forecast'] = train['Count'].mean()
plt.figure(figsize=(12,8))
plt.plot(train['Count'], label='Train')
plt.plot(test['Count'], label='Test')
plt.plot(y_hat_avg['avg_forecast'], label='Average Forecast')
plt.legend(loc='best')
plt.show()

移动平均法：

#移动平均法
y_hat_avg = test.copy()
y_hat_avg['moving_avg_forecast'] = train['Count'].rolling(60).mean().iloc[-1]
plt.figure(figsize=(16,8))
plt.plot(train['Count'], label='Train')
plt.plot(test['Count'], label='Test')
plt.plot(y_hat_avg['moving_avg_forecast'], label='Moving Average Forecast')
plt.legend(loc='best')
plt.show()

简单指数法

from statsmodels.tsa.api import SimpleExpSmoothing
 
y_hat_avg = test.copy()
fit = SimpleExpSmoothing(np.asarray(train['Count'])).fit(smoothing_level=0.6, optimized=False)
y_hat_avg['SES'] = fit.forecast(len(test))
plt.figure(figsize=(16, 8))
plt.plot(train['Count'], label='Train')
plt.plot(test['Count'], label='Test')
plt.plot(y_hat_avg['SES'], label='SES')
plt.legend(loc='best')
plt.show()

Holt-winter法：

from statsmodels.tsa.api import Holt
 
y_hat_avg = test.copy()
 
fit = Holt(np.asarray(train['Count'])).fit(smoothing_level=0.3, smoothing_slope=0.1)
y_hat_avg['Holt_linear'] = fit.forecast(len(test))
 
plt.figure(figsize=(16, 8))
plt.plot(train['Count'], label='Train')
plt.plot(test['Count'], label='Test')
plt.plot(y_hat_avg['Holt_linear'], label='Holt_linear')
plt.legend(loc='best')
plt.show()

来源：CSDN

作者：Moongodap

链接：https://blog.csdn.net/Moongodap/article/details/104857833

标签

test

时间序列