学习笔记_vnpy实战培训day02

这节课主要讲了numpy，pandas，tushare，talib，matlabplot用法，如果有基础的化不用听了

能看懂如下样例代码就行了

numpy

####numpy数据结构####
v = [0.5, 0.75, 1.0, 1.5, 2.0] 
m = [v, v, v]  # matrix of numbers
m

m[1]

m[1][0]

v1 = [0.5, 1.5]
v2 = [1, 2]
m = [v1, v2]
c = [m, m]  # cube of numbers
c

c[1][1][0]

v = [0.5, 0.75, 1.0, 1.5, 2.0]
m = [v, v, v]
m

v[0] = 'Python'
m

from copy import deepcopy
v = [0.5, 0.75, 1.0, 1.5, 2.0]
m = 3 * [deepcopy(v), ]
m

v[0] = 'Python'
m

import numpy as np

a = np.array([0, 0.5, 1.0, 1.5, 2.0])
type(a)

a[:2]
 
a.sum()
a.std()
a.cumsum()
a * 2
a ** 2
np.sqrt(a)

b = np.array([a, a * 2])
b
b[0]
b[0, 2]  # third element of first row

b.sum()
b.sum(axis=0)
b.sum(axis=1)

pandas

import numpy as np
import pandas as pd
from pandas import Series, DataFrame


df = pd.DataFrame([10,20,30,40],columns=['number'],index = ['a','b','c','d'])

df['floats'] = (1.5,2.5,3.5,4.5)


df.append(pd.DataFrame({'number':100,'floats':5.7},index=['z']))

df['squares'] = (1,4,9,16)

df[['number','squares']].mean()
df[['number','squares']].std()



a = np.random.standard_normal((9,4))

df = pd.DataFrame(a)
#print df

df.columns = [['No1','No2','No3','No4']]
#print df
#
#print df['No2'][3]


dates = pd.date_range('2015-1-1',periods = 9,freq = 'D')
#print dates
df.index = dates
print df

talib用法

#MA

import pandas as pd
import tushare as ts
import talib as ta

#从tushare获取数据
sh = ts.get_hist_data('sh')
sh = sh.sort_index()
#print sh['close']
#使用TALIB计算20日均线
ma = ta.MA(sh['close'].values,20)
sh.loc[:,'tama'] = ma

sh[['close','tama']].plot(figsize = (15,5),grid = True)

#bollinger

import numpy as np
import pandas as pd
import tushare as ts
import talib as ta

sh = ts.get_hist_data('sh')
sh = sh.sort_index()
close = sh[['close','volume']]

#函数用的price必须为narray
upper,middle,lower = ta.BBANDS(
                                sh['close'].values,
                                timeperiod=20,
                                nbdevup = 2,
                                nbdevdn = 2,
                                matype = 0
                               )

close.loc[:, 'upper'] = upper
close.loc[:,'middle']=middle
close.loc[:,'lower']=lower

close[['close','middle','upper','lower']].plot(figsize=(15,8),grid = True)

matplotlib

# -*- coding: utf-8 -*-

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import warnings; warnings.simplefilter('ignore')
# import seaborn as sns; sns.set()
get_ipython().magic(u'matplotlib inline')

####二维绘图####
##折线图
#一维数据集
np.random.seed(1000)
y = np.random.standard_normal(20)

x = range(len(y))
plt.plot(x, y)

plt.plot(y)

plt.plot(y.cumsum())

plt.plot(y.cumsum())
plt.grid(True)  # adds a grid
plt.axis('tight')


plt.plot(y.cumsum())
plt.grid(True)
plt.xlim(-1, 20)
plt.ylim(np.min(y.cumsum()) - 1,
         np.max(y.cumsum()) + 1)
         
         
plt.figure(figsize=(7, 4))
  # the figsize parameter defines the
  # size of the figure in (width, height)
plt.plot(y.cumsum(), 'b', lw=1.5)
plt.plot(y.cumsum(), 'ro')
plt.grid(True)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value')
plt.title('A Simple Plot')


#二维数据集
np.random.seed(2000)
y = np.random.standard_normal((20, 2)).cumsum(axis=0)

plt.figure(figsize=(7, 4))
plt.plot(y, lw=1.5)
  # plots two lines
plt.plot(y, 'ro')
  # plots two dotted lines
plt.grid(True)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value')
plt.title('A Simple Plot')



plt.figure(figsize=(7, 4))
plt.plot(y[:, 0], lw=1.5, label='1st')
plt.plot(y[:, 1], lw=1.5, label='2nd')
plt.plot(y, 'ro')
plt.grid(True)
plt.legend(loc=0)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value')
plt.title('A Simple Plot')

y[:, 0] = y[:, 0] * 100
plt.figure(figsize=(7, 4))
plt.plot(y[:, 0], lw=1.5, label='1st')
plt.plot(y[:, 1], lw=1.5, label='2nd')
plt.plot(y, 'ro')
plt.grid(True)
plt.legend(loc=0)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value')
plt.title('A Simple Plot')


fig, ax1 = plt.subplots()
plt.plot(y[:, 0], 'b', lw=1.5, label='1st')
plt.plot(y[:, 0], 'ro')
plt.grid(True)
plt.legend(loc=8)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value 1st')
plt.title('A Simple Plot')
ax2 = ax1.twinx()
plt.plot(y[:, 1], 'g', lw=1.5, label='2nd')
plt.plot(y[:, 1], 'ro')
plt.legend(loc=0)
plt.ylabel('value 2nd')

plt.figure(figsize=(7, 5))
plt.subplot(211)
plt.plot(y[:, 0], lw=1.5, label='1st')
plt.plot(y[:, 0], 'ro')
plt.grid(True)
plt.legend(loc=0)
plt.axis('tight')
plt.ylabel('value')
plt.title('A Simple Plot')
plt.subplot(212)
plt.plot(y[:, 1], 'g', lw=1.5, label='2nd')
plt.plot(y[:, 1], 'ro')
plt.grid(True)
plt.legend(loc=0)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value')



plt.figure(figsize=(9, 4))
plt.subplot(121)
plt.plot(y[:, 0], lw=1.5, label='1st')
plt.plot(y[:, 0], 'ro')
plt.grid(True)
plt.legend(loc=0)
plt.axis('tight')
plt.xlabel('index')
plt.ylabel('value')
plt.title('1st Data Set')
plt.subplot(122)
plt.bar(np.arange(len(y)), y[:, 1], width=0.5,
        color='g', label='2nd')
plt.grid(True)
plt.legend(loc=0)
plt.axis('tight')
plt.xlabel('index')
plt.title('2nd Data Set')

##散点图
y = np.random.standard_normal((1000, 2))

plt.figure(figsize=(7, 5))
plt.plot(y[:, 0], y[:, 1], 'ro')
plt.grid(True)
plt.xlabel('1st')
plt.ylabel('2nd')
plt.title('Scatter Plot')

plt.figure(figsize=(7, 5))
plt.scatter(y[:, 0], y[:, 1], marker='o')
plt.grid(True)
plt.xlabel('1st')
plt.ylabel('2nd')
plt.title('Scatter Plot')

c = np.random.randint(0, 10, len(y))

plt.figure(figsize=(7, 5))
plt.scatter(y[:, 0], y[:, 1], c=c, marker='o')
plt.colorbar()
plt.grid(True)
plt.xlabel('1st')
plt.ylabel('2nd')
plt.title('Scatter Plot')

##直方图
plt.figure(figsize=(7, 4))
plt.hist(y, label=['1st', '2nd'], bins=25)
plt.grid(True)
plt.legend(loc=0)
plt.xlabel('value')
plt.ylabel('frequency')
plt.title('Histogram')

plt.figure(figsize=(7, 4))
plt.hist(y, label=['1st', '2nd'], color=['b', 'g'],
            stacked=True, bins=20)
plt.grid(True)
plt.legend(loc=0)
plt.xlabel('value')
plt.ylabel('frequency')
plt.title('Histogram')

##箱线图
fig, ax = plt.subplots(figsize=(7, 4))
plt.boxplot(y)
plt.grid(True)
plt.setp(ax, xticklabels=['1st', '2nd'])
plt.xlabel('data set')
plt.ylabel('value')
plt.title('Boxplot')

#面积图
from matplotlib.patches import Polygon
def func(x):
    return 0.5 * np.exp(x) + 1

a, b = 0.5, 1.5  # integral limits
x = np.linspace(0, 2)
y = func(x)

fig, ax = plt.subplots(figsize=(7, 5))
plt.plot(x, y, 'b', linewidth=2)
plt.ylim(ymin=0)
Ix = np.linspace(a, b)
Iy = func(Ix)
verts = [(a, 0)] + list(zip(Ix, Iy)) + [(b, 0)]
poly = Polygon(verts, facecolor='0.7', edgecolor='0.5')
ax.add_patch(poly)

plt.text(0.5 * (a + b), 1, r"$\int_a^b f(x)\mathrm{d}x$",
         horizontalalignment='center', fontsize=20)

plt.figtext(0.9, 0.075, '$x$')
plt.figtext(0.075, 0.9, '$f(x)$')

ax.set_xticks((a, b))
ax.set_xticklabels(('$a$', '$b$'))
ax.set_yticks([func(a), func(b)])
ax.set_yticklabels(('$f(a)$', '$f(b)$'))
plt.grid(True)


##蜡烛图
import matplotlib.finance as mpf

start = (2014, 5, 1)
end = (2014, 6, 30)

quotes = mpf.quotes_historical_yahoo_ohlc('^GDAXI', start, end)
quotes[:2]

fig, ax = plt.subplots(figsize=(8, 5))
fig.subplots_adjust(bottom=0.2)
mpf.candlestick_ohlc(ax, quotes, width=0.6, colorup='b', colordown='r')
plt.grid(True)
ax.xaxis_date()
  # dates on the x axis
ax.autoscale_view()
plt.setp(plt.gca().get_xticklabels(), rotation=30)

fig, ax = plt.subplots(figsize=(8, 5))
mpf.plot_day_summary_ohlc(ax, quotes, colorup='b', colordown='r')
plt.grid(True)
ax.xaxis_date()
plt.title('DAX Index')
plt.ylabel('index level')
plt.setp(plt.gca().get_xticklabels(), rotation=30)


quotes = np.array(mpf.quotes_historical_yahoo_ochl('YHOO', start, end))

fig, (ax1, ax2) = plt.subplots(2, sharex=True, figsize=(8, 6))
mpf.candlestick_ohlc(ax1, quotes, width=0.6, colorup='b', colordown='r')
ax1.set_title('Yahoo Inc.')
ax1.set_ylabel('index level')
ax1.grid(True)
ax1.xaxis_date()
plt.bar(quotes[:, 0] - 0.25, quotes[:, 5], width=0.5)
ax2.set_ylabel('volume')
ax2.grid(True)
ax2.autoscale_view()
plt.setp(plt.gca().get_xticklabels(), rotation=30)


####3d绘图####

strike = np.linspace(50, 150, 24)
ttm = np.linspace(0.5, 2.5, 24)
strike, ttm = np.meshgrid(strike, ttm)

strike[:2]

iv = (strike - 100) ** 2 / (100 * strike) / ttm


from mpl_toolkits.mplot3d import Axes3D

fig = plt.figure(figsize=(9, 6))
ax = fig.gca(projection='3d')
surf = ax.plot_surface(strike, ttm, iv, rstride=2, cstride=2,
                       cmap=plt.cm.coolwarm, linewidth=0.5,
                       antialiased=True)
ax.set_xlabel('strike')
ax.set_ylabel('time-to-maturity')
ax.set_zlabel('implied volatility')


fig.colorbar(surf, shrink=0.5, aspect=5)
fig = plt.figure(figsize=(8, 5))
ax = fig.add_subplot(111, projection='3d')
ax.view_init(30, 60)
ax.scatter(strike, ttm, iv, zdir='z', s=25,
           c='b', marker='^')
ax.set_xlabel('strike')
ax.set_ylabel('time-to-maturity')
ax.set_zlabel('implied volatility')


#####figure与subplot
#figure对象
fig = plt.figure()

ax1 = fig.add_subplot(2, 2, 1)
ax2 = fig.add_subplot(2, 2, 2)
ax3 = fig.add_subplot(2, 2, 3)
plt.show()

from numpy.random import randn
plt.plot(randn(50).cumsum(), 'k--')
fig.show()

_ = ax1.hist(randn(100), bins=20, color='k', alpha=0.3)
ax2.scatter(np.arange(30), np.arange(30) + 3 * randn(30))
plt.close('all')

fig, axes = plt.subplots(2, 3)
axes

#调整subplot周围的间距
plt.subplots_adjust(left=None, bottom=None, right=None, top=None,
                wspace=None, hspace=None)

fig, axes = plt.subplots(2, 2, sharex=True, sharey=True)
for i in range(2):
    for j in range(2):
        axes[i, j].hist(randn(500), bins=50, color='k', alpha=0.5)
plt.subplots_adjust(wspace=0, hspace=0)



#####matplotlib基本设置
#颜色、标记和线型
plt.figure()

plt.plot(x,y,linestyle='--',color='g')

plt.plot(randn(30).cumsum(), 'ko--')

plt.plot(randn(30).cumsum(),color='k',linestyle='dashed',marker='o')

plt.close('all')

data = randn(30).cumsum()
plt.plot(data, 'k--', label='Default')
plt.plot(data, 'k-', drawstyle='steps-post', label='steps-post')
plt.legend(loc='best')

#设置标题、轴标签、刻度以及刻度标签
fig = plt.figure(); ax = fig.add_subplot(1, 1, 1)
ax.plot(randn(1000).cumsum())

ticks = ax.set_xticks([0, 250, 500, 750, 1000])
labels = ax.set_xticklabels(['one', 'two', 'three', 'four', 'five'],
                            rotation=30, fontsize='small')
ax.set_title('My first matplotlib plot')
ax.set_xlabel('Stages')

#添加图例
fig = plt.figure(); ax = fig.add_subplot(1, 1, 1)
ax.plot(randn(1000).cumsum(), 'k', label='one')
ax.plot(randn(1000).cumsum(), 'k--', label='two')
ax.plot(randn(1000).cumsum(), 'k.', label='three')

ax.legend(loc='best')

#注释以及在subplot上绘图
from datetime import datetime
import pandas as pd

fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)

data = pd.read_csv('d:/data/spx.csv', index_col=0, parse_dates=True)
spx = data['SPX']

spx.plot(ax=ax, style='k-')

crisis_data = [
    (datetime(2007, 10, 11), 'Peak of bull market'),
    (datetime(2008, 3, 12), 'Bear Stearns Fails'),
    (datetime(2008, 9, 15), 'Lehman Bankruptcy')
]

for date, label in crisis_data:
    ax.annotate(label, xy=(date, spx.asof(date) + 50),
                xytext=(date, spx.asof(date) + 200),
                arrowprops=dict(facecolor='black'),
                horizontalalignment='left', verticalalignment='top')

ax.set_xlim(['1/1/2007', '1/1/2011'])
ax.set_ylim([600, 1800])

ax.set_title('Important dates in 2008-2009 financial crisis')

fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)

rect = plt.Rectangle((0.2, 0.75), 0.4, 0.15, color='k', alpha=0.3)
circ = plt.Circle((0.7, 0.2), 0.15, color='b', alpha=0.3)
pgon = plt.Polygon([[0.15, 0.15], [0.35, 0.4], [0.2, 0.6]],
                   color='g', alpha=0.5)

ax.add_patch(rect)
ax.add_patch(circ)
ax.add_patch(pgon)


#图表的保存
fig

fig.savefig('figpath.svg')

fig.savefig('figpath.png', dpi=400, bbox_inches='tight')

from io import BytesIO
buffer = BytesIO()
plt.savefig(buffer)
plot_data = buffer.getvalue()


#matplotlib配置
plt.rc('figure', figsize=(10, 10))

font_options={'family':'monospace',
              'weight':'bold','size':'small'}

plt.rc('font',**font_options)