arma_demo

# 用ARMA进行时间序列预测
import pandas as pd
import matplotlib.pyplot as plt
import statsmodels.api as sm
from statsmodels.tsa.arima_model import ARMA
from statsmodels.graphics.api import qqplot

# 创建数据
data = [3821, 4236, 3758, 6783, 4664, 2589, 2538, 3542, 4626, 5886, 6233, 4199, 3561, 2335, 5636, 3524, 
4327, 6064, 3912, 1356, 4305, 4379, 4592, 4233, 4281, 1613, 1233, 4514, 3431, 2159, 2322, 4239, 4733, 
2268, 5397, 5821, 6115, 6631, 6474, 4134, 2728, 5753, 7130, 7860, 6991, 7499, 5301, 2808, 6755, 6658, 
6944, 6372, 8380, 7366, 6352, 8333, 8281, 11548, 10823, 13642, 9973, 6723, 13416, 12205, 13942, 9590, 
11693, 9276, 6519, 6863, 8237, 10122, 8646, 9749, 5346, 4836, 9806, 7502, 9387, 11078, 9832, 6886, 4285, 
8351, 9725, 11844, 12387, 10666, 7072, 6429]
data=pd.Series(data)
data_index = sm.tsa.datetools.dates_from_range('1901','1990')
#print(data_index)

# 绘制数据图
data.index = pd.Index(data_index)
data.plot(figsize=(12,8))
plt.show()
# 创建ARMA模型# 创建ARMA模型
arma = ARMA(data,(7,0)).fit()
print('AIC: %0.4lf' %arma.aic)
# 模型预测
predict_y = arma.predict('1990', '2000')
# 预测结果绘制
fig, ax = plt.subplots(figsize=(12, 8))
ax = data.ix['1901':].plot(ax=ax)
predict_y.plot(ax=ax)
plt.show()

stock_arima

# -*- coding: utf-8 -*-
# 沪市指数走势预测，使用时间序列ARMA
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.arima_model import ARIMA
import statsmodels.api as sm
import warnings
from itertools import product
from datetime import datetime, timedelta
import calendar

warnings.filterwarnings('ignore')
plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
# 数据加载
df = pd.read_csv('./shanghai_index_1990_12_19_to_2020_03_12.csv')
df = df[['Timestamp', 'Price']]

# 将时间作为df的索引
df.Timestamp = pd.to_datetime(df.Timestamp)
df.index = df.Timestamp
# 数据探索
print(df.head())
# 按照月，季度，年来统计
df_month = df.resample('M').mean()
df_Q = df.resample('Q-DEC').mean()
df_year = df.resample('A-DEC').mean()
print(df_month)

# 设置参数范围
ps = range(0, 5)
qs = range(0, 5)
ds = range(1, 2)
parameters = product(ps, ds, qs)
parameters_list = list(parameters)
# 寻找最优ARMA模型参数，即best_aic最小
results = []
best_aic = float("inf") # 正无穷
for param in parameters_list:
    try:
        #model = ARIMA(df_month.Price,order=(param[0], param[1], param[2])).fit()
        # SARIMAX 包含季节趋势因素的ARIMA模型
        model = sm.tsa.statespace.SARIMAX(df_month.Price,
                                order=(param[0], param[1], param[2]),
                                #seasonal_order=(4, 1, 2, 12),
                                enforce_stationarity=False,
                                enforce_invertibility=False).fit()

    except ValueError:
        print('参数错误:', param)
        continue
    aic = model.aic
    if aic < best_aic:
        best_model = model
        best_aic = aic
        best_param = param
    results.append([param, model.aic])
# 输出最优模型
print('最优模型: ', best_model.summary())

# 设置future_month，需要预测的时间date_list
df_month2 = df_month[['Price']]
future_month = 3
last_month = pd.to_datetime(df_month2.index[len(df_month2)-1])
date_list = []
for i in range(future_month):
    # 计算下个月有多少天
    year = last_month.year
    month = last_month.month
    if month == 12:
        month = 1
        year = year+1
    else:
        month = month + 1
    next_month_days = calendar.monthrange(year, month)[1]
    #print(next_month_days)
    last_month = last_month + timedelta(days=next_month_days)
    date_list.append(last_month)
print('date_list=', date_list)

# 添加未来要预测的3个月
future = pd.DataFrame(index=date_list, columns= df_month.columns)
df_month2 = pd.concat([df_month2, future])

# get_prediction得到的是区间，使用predicted_mean
df_month2['forecast'] = best_model.get_prediction(start=0, end=len(df_month2)).predicted_mean

# 沪市指数预测结果显示
plt.figure(figsize=(30,7))
df_month2.Price.plot(label='实际指数')
df_month2.forecast.plot(color='r', ls='--', label='预测指数')
plt.legend()
plt.title('沪市指数（月）')
plt.xlabel('时间')
plt.ylabel('指数')
plt.show()

stock_prophet

# 使用Prophet预测manning未来365天的页面流量
# 从2007年12月10日开始
import pandas as pd
from fbprophet import Prophet
import matplotlib.pyplot as plt
%matplotlib inline

# 读入数据集
df = pd.read_csv('./shanghai_index_1990_12_19_to_2020_03_12.csv')
# 修改列名 Timestamp => ds, Price => y
df.rename(columns={'Timestamp':'ds', 'Price':'y'}, inplace=True)
print(df.head())

#print(df.tail())
# 拟合模型
model = Prophet()
model.fit(df)

# 构建待预测日期数据框，periods = 365 代表除历史数据的日期外再往后推 365 天
future = model.make_future_dataframe(periods=365)
#print(future.tail())

# 预测数据集
forecast = model.predict(future)
#print(forecast.columns)
print(forecast[['ds', 'yhat', 'yhat_lower', 'yhat_upper']].tail())

# 展示预测结果
model.plot(forecast)
plt.show()

# 预测的成分分析绘图，展示预测中的趋势、周效应和年度效应
model.plot_components(forecast)
print(forecast.columns)

stock_tsa

# 使用tsa对沪市指数进行分析：trend, seasonal, residual
import statsmodels.api as sm
import matplotlib.pyplot as plt
import pandas as pd

# 数据加载
data = pd.read_csv('shanghai_index_1990_12_19_to_2020_03_12.csv', usecols=['Timestamp', 'Price'])
print(data.head())

# 转换为pandas中的日期格式
data.Timestamp = pd.to_datetime(data.Timestamp)
data = data.set_index('Timestamp')
data['Price'] = data['Price'].apply(pd.to_numeric, errors='ignore')
# 进行线性插补缺漏值, 插入的空缺值，比如 1990-12-25日 本来应该有数值，但是为None
print(data.Price.shape)
# 插入的是Price字段
data.Price.interpolate(inplace=True)
print(data.head())

#  返回三个部分 trend（趋势），seasonal（季节性）和residual (残留)
# price = trend + seasonal + resid, 设置freq = 1年内的有效数据个数，平均值，freq=365
result = sm.tsa.seasonal_decompose(data.Price, freq=288)
#print(result)
result.plot()
plt.show()

stock_prophet.py

#!/usr/bin/env python
# coding: utf-8

# In[6]:


# 使用Prophet预测manning未来365天的页面流量
# 从2007年12月10日开始
import pandas as pd
from fbprophet import Prophet
import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')

# 读入数据集
df = pd.read_csv('./shanghai_index_1990_12_19_to_2020_03_12.csv')
# 修改列名 Timestamp => ds, Price => y
df.rename(columns={'Timestamp':'ds', 'Price':'y'}, inplace=True)
print(df.head())


# In[7]:


#print(df.tail())
# 拟合模型
model = Prophet()
model.fit(df)

# 构建待预测日期数据框，periods = 365 代表除历史数据的日期外再往后推 365 天
future = model.make_future_dataframe(periods=365)
#print(future.tail())

# 预测数据集
forecast = model.predict(future)
#print(forecast.columns)
print(forecast[['ds', 'yhat', 'yhat_lower', 'yhat_upper']].tail())

# 展示预测结果
model.plot(forecast)
plt.show()


# In[8]:


# 预测的成分分析绘图，展示预测中的趋势、周效应和年度效应
model.plot_components(forecast)
print(forecast.columns)