# -*- coding: utf-8 -*-
from __future__ import division
from numpy.random import randn
import numpy as np
import os
import matplotlib.pyplot as plt
np.random.seed(12345)
plt.rc('figure', figsize=(10, 6))
from pandas import Series, DataFrame
import pandas as pd
np.set_printoptions(precision=4)
get_ipython().magic(u'matplotlib inline')
get_ipython().magic(u'pwd')
#####matplotlib創(chuàng)建圖表
plt.plot([1,2,3,2,3,2,2,1])
plt.show()
plt.plot([4,3,2,1],[1,2,3,4])
plt.show()
#更多簡單的圖形
x = [1,2,3,4]
y = [5,4,3,2]
plt.figure()
plt.subplot(2,3,1)
plt.plot(x, y)
plt.subplot(232)
plt.bar(x, y)
plt.subplot(233)
plt.barh(x, y)
plt.subplot(234)
plt.bar(x, y)
y1 = [7,8,5,3]
plt.bar(x, y1, bottom=y, color = 'r')
plt.subplot(235)
plt.boxplot(x)
plt.subplot(236)
plt.scatter(x,y)
plt.show()
#####figure與subplot
#figure對象
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
#調(diào)整subplot周圍的間距
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基本設(shè)置
#顏色、標(biāo)記和線型
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')
#設(shè)置標(biāo)題诈胜、軸標(biāo)簽财饥、刻度以及刻度標(biāo)簽
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')
#添加圖例
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')
#注釋以及在subplot上繪圖
from datetime import datetime
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)
#圖表的保存
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)
#####pandas中的繪圖函數(shù)
#線圖
plt.close('all')
s = Series(np.random.randn(10).cumsum(), index=np.arange(0, 100, 10))
s.plot()
df = DataFrame(np.random.randn(10, 4).cumsum(0),
columns=['A', 'B', 'C', 'D'],
index=np.arange(0, 100, 10))
df.plot()
#柱形圖
fig, axes = plt.subplots(2, 1)
data = Series(np.random.rand(16), index=list('abcdefghijklmnop'))
data.plot(kind='bar', ax=axes[0], color='k', alpha=0.7)
data.plot(kind='barh', ax=axes[1], color='k', alpha=0.7)
df = DataFrame(np.random.rand(6, 4),
index=['one', 'two', 'three', 'four', 'five', 'six'],
columns=pd.Index(['A', 'B', 'C', 'D'], name='Genus'))
df
df.plot(kind='bar')
plt.figure()
df.plot(kind='barh', stacked=True, alpha=0.5)
tips = pd.read_csv('d:/data/tips.csv')
party_counts = pd.crosstab(tips.day, tips['size'])
party_counts
party_counts = party_counts.ix[:, 2:5]
party_pcts = party_counts.div(party_counts.sum(1).astype(float), axis=0)
party_pcts
party_pcts.plot(kind='bar', stacked=True)
#直方圖和密度圖
plt.figure()
tips['tip_pct'] = tips['tip'] / tips['total_bill']
tips['tip_pct'].hist(bins=50)
plt.figure()
tips['tip_pct'].plot(kind='kde')
plt.figure()
comp1 = np.random.normal(0, 1, size=200) ?# N(0, 1)
comp2 = np.random.normal(10, 2, size=200) ?# N(10, 4)
values = Series(np.concatenate([comp1, comp2]))
values.hist(bins=100, alpha=0.3, color='k', normed=True)
values.plot(kind='kde', style='k--')
#散點(diǎn)圖
macro = pd.read_csv('d:/data/macrodata.csv')
data = macro[['cpi', 'm1', 'tbilrate', 'unemp']]
trans_data = np.log(data).diff().dropna()
trans_data[-5:]
plt.figure()
plt.scatter(trans_data['m1'], trans_data['unemp'])
plt.title('Changes in log %s vs. log %s' % ('m1', 'unemp'))
pd.scatter_matrix(trans_data, diagonal='kde', color='k', alpha=0.3)
#####Matplotlib作圖
#誤差條形圖
x = np.arange(0, 10, 1)
y = np.log(x)
xe = 0.1 * np.abs(np.random.randn(len(y)))
plt.bar(x, y, yerr=xe, width=0.4, align='center', ecolor='r', color='cyan',
label='experiment #1');
plt.xlabel('# measurement')
plt.ylabel('Measured values')
plt.title('Measurements')
plt.legend(loc='upper left')
plt.show()
#餅圖
plt.figure(1, figsize=(8, 8))
ax = plt.axes([0.1, 0.1, 0.8, 0.8])
labels = 'Spring', 'Summer', 'Autumn', 'Winter'
values = [15, 16, 16, 28]
explode =[0.1, 0.1, 0.1, 0.1]
plt.pie(values, explode=explode, labels=labels,
autopct='%1.1f%%', startangle=67)
plt.title('Rainy days by season')
plt.show()
#等高線圖
import matplotlib as mpl
def process_signals(x, y):
return (1 - (x ** 2 + y ** 2)) * np.exp(-y ** 3 / 3)
x = np.arange(-1.5, 1.5, 0.1)
y = np.arange(-1.5, 1.5, 0.1)
X, Y = np.meshgrid(x, y)
Z = process_signals(X, Y)
N = np.arange(-1, 1.5, 0.3)
CS = plt.contour(Z, N, linewidths=2, cmap=mpl.cm.jet)
plt.clabel(CS, inline=True, fmt='%1.1f', fontsize=10)
plt.colorbar(CS)
plt.title('My function: $z=(1-x^2+y^2) e^{-(y^3)/3}$')
plt.show()
###3D圖像
#3d柱形圖
import matplotlib.dates as mdates
from mpl_toolkits.mplot3d import Axes3D
mpl.rcParams['font.size'] = 10
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
for z in [2011, 2012, 2013, 2014]:
xs = xrange(1,13)
ys = 1000 * np.random.rand(12)
color = plt.cm.Set2(random.choice(xrange(plt.cm.Set2.N)))
ax.bar(xs, ys, zs=z, zdir='y', color=color, alpha=0.8)
ax.xaxis.set_major_locator(mpl.ticker.FixedLocator(xs))
ax.yaxis.set_major_locator(mpl.ticker.FixedLocator(ys))
ax.set_xlabel('Month')
ax.set_ylabel('Year')
ax.set_zlabel('Sales Net [usd]')
plt.show()
#3d直方圖
mpl.rcParams['font.size'] = 10
samples = 25
x = np.random.normal(5, 1, samples)
y = np.random.normal(3, .5, samples)
fig = plt.figure()
ax = fig.add_subplot(211, projection='3d')
hist, xedges, yedges = np.histogram2d(x, y, bins=10)
elements = (len(xedges) - 1) * (len(yedges) - 1)
xpos, ypos = np.meshgrid(xedges[:-1]+.25, yedges[:-1]+.25)
xpos = xpos.flatten()
ypos = ypos.flatten()
zpos = np.zeros(elements)
dx = .1 * np.ones_like(zpos)
dy = dx.copy()
dz = hist.flatten()
ax.bar3d(xpos, ypos, zpos, dx, dy, dz, color='b', alpha=0.4)
ax.set_xlabel('X Axis')
ax.set_ylabel('Y Axis')
ax.set_zlabel('Z Axis')
ax2 = fig.add_subplot(212)
ax2.scatter(x, y)
ax2.set_xlabel('X Axis')
ax2.set_ylabel('Y Axis')
plt.show()
