绘图和可视化

import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

# 图片和子图

fig = plt.figure()

ax1 = fig.add_subplot(2,2,1)

ax2 = fig.add_subplot(2,2,2)

ax3 = fig.add_subplot(2,2,3)

# bins 条状图数目

plt.show()

# 设置边界

fig,axes = plt.subplots(2,2,sharex=True,sharey=True)

for i in range(2):

for j in range(2):

plt.subplots_adjust(wspace=0,hspace=0)

plt.show()

# from numpy.random import randn

# k 颜色 ，o 圆点 -- 虚线

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

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

plt.show()

plt.plot(data,'k--',label='Default')

plt.plot(data,'k-',drawstyle='steps-post',label='steps-post')

plt.legend(loc='best')

plt.show()

fig = plt.figure()

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

ticks =ax.set_xticks([0,250,500,750,1000])

labels = ax.set_xticklabels(['one','two','three','four','five'],rotation = 5 ,fontsize='small')

ax.set_xlabel('Stages')

ax.set_title('My First matplotlib plot')

plt.show()

from numpy.random import randn

fig = plt.figure()

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

ax.plot(randn(1000).cumsum(),'k',label = 'one')

ax.plot(randn(1000).cumsum(),'r--',label = 'two')

ax.plot(randn(1000).cumsum(),'b.',label='three')

ax.legend(loc='best')

plt.show()

# 注释与子视图加工

from datetime import datetime

fig = plt.figure()

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

data = pd.read_csv('examples/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 stearan fails'),

(datetime(2008,9,15),'lehman bankruptcy')]

for date , label in crisis_data:

ax.annotate(label,xy = (date,spx.asof(date)+75),xytext = (date,spx.asof(date)+225),arrowprops=dict(facecolor='black',headwidth =4,width =2,headlength=4),horizontalalignment='left',verticalalignment='top')

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

ax.set_ylim([600,1800])

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

plt.show()

fig = plt.figure()

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

rect = plt.Rectangle((0.2,0.74),0.4,0.15,color='k',alpha = 0.3)

ax.add_patch(rect)

circ = plt.Circle((0.7,0.2),0.15,color='b',alpha=0.3)

ax.add_patch(circ)

pgon = plt.Polygon([[0.15,0.15],[0.35,0.4],[0.2,0.6]])

ax.add_patch(pgon)

plt.show()

# 使用pandas和seaborn绘图

s.plot()

plt.show()

df.plot()

plt.show()

# 柱状图

fig ,axes = plt.subplots(2,1)

plt.show()

# print(df)

plt.show()

tips = pd.read_csv('examples/tips.csv')

party_counts = pd.crosstab(tips['day'],tips['size'])

print(party_counts)

party_counts=party_counts.loc[:,2:5]

print(party_counts)

party_pcts = party_counts.div(party_counts.sum(1),axis=0)

print(party_pcts)

# 每一行的综合的集合

#print(party_counts.sum(1))

plt.show()

import seaborn as sns

tips['tip_pct'] = tips['tip'] /(tips['total_bill'] - tips['tip'])

# print(tips.head())

# sns.barplot(x='tip_pct',y='day',hue='time',data=tips,orient='h')

sns.set(style='whitegrid')

# 直方图

# tips['tip_pct'].plot.hist(bins=50)

# 密度图

# tips['tip_pct'].plot.density()

# # plt.show()

values = pd.Series(np.concatenate([comp1,comp2]))

print(values)

sns.distplot(values,bins=100,color='k')

plt.show()