数据分析5之线性模型

1，线性预测

import numpy as np
import matplotlib.pyplot as plt
import datetime as dt
import matplotlib.dates as md


# 日期转换函数
def dmy2ymd(dmy):
    dmy = str(dmy, encoding='utf-8')
    time = dt.datetime.strptime(dmy, '%d-%m-%Y').date()
    t = time.strftime('%Y-%m-%d')
    return t


# 加载文件
dates, opening_prices, highest_prices, lowest_prices, closing_prices = \
    np.loadtxt('data/da_data/aapl.csv',
               delimiter=',',
               usecols=(1, 3, 4, 5, 6),
               dtype='M8[D], f8, f8, f8, f8',
               unpack=True,
               converters={1: dmy2ymd}              # 日期转换
               )
# print(dates)

plt.figure('aapl', facecolor='grey')
plt.title('aapl', fontsize=20)

plt.grid(linestyle=':')
plt.xlabel('date', fontsize=14)
plt.ylabel('closing_prices', fontsize=14)

ax = plt.gca()
# 刻度主定位器
ax.xaxis.set_major_locator(md.WeekdayLocator(byweekday=md.MO))
ax.xaxis.set_major_formatter(md.DateFormatter('%Y/%m/%d'))
# # 刻度次定位器
ax.xaxis.set_minor_locator(md.DayLocator())
plt.tick_params(labelsize=8)
dates = dates.astype(md.datetime.datetime)

plt.plot(dates, closing_prices, linewidth=2, linestyle='--', label='closing_price')
# 线性预测,三元
N = 3
pred = np.zeros(closing_prices.size-2*N)
for j in range(pred.size):
    A = np.zeros((N, N))
    for i in range(3):
        A[i:] = closing_prices[i+j: i+j+N]
    B = closing_prices[j+N: j+N*2]
    # 采用最小二乘求参
    x = np.linalg.lstsq(A, B)[0]
    # print(x)
    pred[j] = B.dot(x)
    # print(pred[j], closing_prices[5+j])
plt.plot(dates[2*N:], pred, 'o-', label='pred')
plt.gcf().autofmt_xdate()
plt.legend()
plt.show()

2.线性拟合

import numpy as np
import matplotlib.pyplot as plt
import datetime as dt
import matplotlib.dates as md


# 日期转换函数
def dmy2ymd(dmy):
    dmy = str(dmy, encoding='utf-8')
    time = dt.datetime.strptime(dmy, '%d-%m-%Y').date()
    t = time.strftime('%Y-%m-%d')
    return t


# 加载文件
dates, opening_prices, highest_prices, lowest_prices, closing_prices = \
    np.loadtxt('data/da_data/aapl.csv',
               delimiter=',',
               usecols=(1, 3, 4, 5, 6),