Python可视化库-Matplotlib

官方教程

折线图绘制

import pandas as pd
unrate = pd.read_csv('unrate.csv')
unrate['DATE']=pd.to_datetime(unrate['DATE'])  #to_datetime()转换成标准日期格式1948-01-01

import matplotlib.pyplot as plt
plt.plot()  #空白图
plt.show()

first_twelve=unrate[0:12]
plt.plot(first_twelve['DATE'],first_twelve['VALUE'])  #折线图
plt.show()

plt.xticks(rotation=45) #指定x轴刻度旋转角度
plt.xlabel('Month')  
plt.ylabel('unemployment Rate')
plt.title('Monthly Unemployment Trends,1948')
plt.show()

子图操作

import matplotlib.pyplot as plt
#fig=plt.figure(figsize=(6,3))  #得到6*3的画图区域
fig=plt.figure()  #得到画图区域
ax1=fig.add_subplot(4,3,1)  #4*3子图的第一个模块，按行排序
ax2=fig.add_subplot(4,3,2)
plt.show()

ax1.plot(np.random.randint(1,5,5),np.arange(5))  #在子图上画图

绘制多折线图

#取月份
#unrate['MONTH']=unrate['DATE'].dt.month

fig=plt.figure(figsize=(10,6))
colors=['red','blue','green','orange','black']
for i in range(5):
  start_index=i*12
  end_index=(i+1)*12
  subset=unrate[start_index:end_index]
  label=str(1948+i)  #指定label
  plt.plot(subset['MONTH'],subset['VALUE'],c=colors[i],label=label)
plt.legend(loc='best')  #
plt.show()

plt.legend(loc=‘best’)

Location String	Location Code
‘best’	0
‘upper right’	1
‘upper left’	2
‘lower left’	3
‘lower right’	4
‘right’	5
‘center left’	6
‘center right’	7
‘lower center’	8
‘upper center’	9
‘center’	10

条形图与散点图

import matplotlib.pyplot as plt
import pandas as pd
from numpy import arange
reviews=pd.read_csv('fandango_scores.csv')
cols=['RT_user_norm','Metacritic_user_form','IMDB_norm','Fandango_Ratingvalue','Fandango_stars']
norm_reviews=reviews[cols]

bar_heights=norm_reviews.ix[0,cols].values
bar_positions=arange(5)+0.75
fig,ax=plt.subplots()  #fig不用
ax.bar(bar_positions,bar_heights,0.3)  #柱形的宽为0.3
ax.set_ylabel('Rating source')
ax.set_xlabel('Average Rating')
ax.set_title('Average User Rating For Avengers(2015)')
plt.show()
#num_cols=['RT_user_norm','Metacritic_user_form','IMDB_norm','Fandango_Ratingvalue','Fandango_stars']
#bar_widths=norm_reviews.ix[0,cols].values
#bar_positions=arange(5)+0.75
#tick_positions=range(1,6)
#ax.barh(bar_positions,bar_widths,0.5)  #ax.barh()横着画
#ax.set_yticks(tick_positions)
#ax.set_yticklabels(num_cols)  #刻度标签
#plt.show()

散点图

fig控制图，ax具体画图

fig,ax=plt.subplots()
ax.scatter(norm_reviews['Fandango_Ratingvalue'],norm_reviews['RT_user_norm'])  #ax.scatter()散点图
plt.show()

子图

fig=plt.figure(figsize=(5,10))
ax1=fig.add_subplot(2,1,1)
ax2=fig.add_subplot(2,1,2)
ax1.scatter(norm_reviews['Fandango_Ratingvalue'],norm_reviews['RT_user_norm'])
ax2.scatter(norm_reviews['Fandango_Ratingvalue'],norm_reviews['RT_user_norm'])
plt.show()

柱形图与盒图

柱形图

fig,ax=plt.subplots()
ax.hist(norm_reviews['Fandango_Ratingvalue'])
#ax.hist(norm_reviews['Fandango_Ratingvalue'],bins=20)
#ax.hist(norm_reviews['Fandango_Ratingvalue'],range=(4,5),bins=20)
plt.show()

ax.set_ylim(0,50) 指定y的区间0-50

盒图

• 盒图指提取出数据某列特征四分之一，二分之一，四分之三处的值

fig,ax=plt.subplots()
ax.boxplot(norm_reviews['RT_user_norm'])
ax.set_xticklabels(['Rotten Tomatoes'])
ax.set_ylim(0,5)
plt.show()

num_cols=('RT_user_norm','Metacritic_user_form','IMDB_norm','Fandango_Ratingvalue')
fig,ax=plt.subplots()
ax.boxplot(norm_reviews[num_cols].values)
ax.set_xticklabels(num_cols,rotation=90)
ax.set_ylim(0,5)
plt.show()

细节设置

去掉图形的框

for key,spine in ax.spines.items():
    spine.setvisible(False)

选择是否要刻度线

ax.tick_params(bottom='off',top='off',left='off',right='off')

折线图线的粗细

ax.plot(subset['MONTH'],subset['VALUE'],c=colors[i],label=label,linewidth=10)  #linewidth指定线的粗细

在图上添加text

ax.text(2005,87,'Men')  #在x=2005,y=87位置添加Men