笔记Day03-1 图的绘制 matplotlib

折线图

import pandas as pd
import  matplotlib.pyplot as plt
unrate=pd.read_csv("E:/唐宇迪数据集/unrate.csv")
unrate['DATE']=pd.to_datetime(unrate['DATE'])
first_twelve=unrate[0:12]
plt.plot(first_twelve['DATE'],first_twelve['VALUE'])
plt.show()
           

import pandas as pd
import  matplotlib.pyplot as plt
unrate=pd.read_csv("E:/唐宇迪数据集/unrate.csv")
unrate['DATE']=pd.to_datetime(unrate['DATE'])
first_twelve=unrate[0:12]
plt.plot(first_twelve['DATE'],first_twelve['VALUE'])
plt.xticks(rotation=45)
plt.show()
           

import pandas as pd
import  matplotlib.pyplot as plt
unrate=pd.read_csv("E:/唐宇迪数据集/unrate.csv")
unrate['DATE']=pd.to_datetime(unrate['DATE'])
first_twelve=unrate[0:12]
plt.plot(first_twelve['DATE'],first_twelve['VALUE'])
plt.xticks(rotation=90)
plt.xlabel('Month')
plt.ylabel('Unemployment Rate')
plt.title('Monthly Unemployment Trends,1948')
plt.show()
           

子图

import matplotlib.pyplot as plt
fig=plt.figure()#指定画图区域
ax1=fig.add_subplot(2,2,1)
ax2=fig.add_subplot(2,2,2)
ax3=fig.add_subplot(2,2,4)
plt.show()
           

import  matplotlib.pyplot as plt
import numpy as np
fig=plt.figure(figsize=(10,5))#figsize 指定长度 和宽度
ax1=fig.add_subplot(2,1,1)
ax2=fig.add_subplot(2,1,2)
ax1.plot(np.random.randint(1,5,5),np.arange(5))
ax2.plot(np.arange(10)*3,np.arange(10))
plt.show()
           

#在同一个图中画出两条折线
import pandas as pd
import matplotlib.pyplot as plt
unrate=pd.read_csv("E:/唐宇迪数据集/unrate.csv")
unrate["DATE"]=pd.to_datetime(unrate['DATE'])
unrate['MONTH']=unrate['DATE'].dt.month
plt.plot(unrate[0:12]['MONTH'],unrate[0:12]['VALUE'],c='red')
plt.plot(unrate[12:24]['MONTH'],unrate[12:24]['VALUE'],c="blue")
plt.show()
           

import matplotlib.pyplot as plt
import pandas as pd
unrate=pd.read_csv("E:/唐宇迪数据集/unrate.csv")
unrate['DATE']=pd.to_datetime(unrate['DATE'])
unrate['MONTH']=unrate['DATE'].dt.month
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)
    plt.plot(subset['MONTH'],subset['VALUE'],c=colors[i],label=label)
plt.legend(loc='best')
#print(help(plt.legend))
plt.show()
           

import matplotlib.pyplot as plt
import pandas as pd
unrate=pd.read_csv("E:/唐宇迪数据集/unrate.csv")
unrate['DATE']=pd.to_datetime(unrate['DATE'])
unrate['MONTH']=unrate['DATE'].dt.month
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)
    plt.plot(subset['MONTH'],subset['VALUE'],c=colors[i],label=label)
plt.legend(loc='best')
plt.xlabel('MONTH,Integer')
plt.ylabel('Unemployment Rate,Percent')
plt.title('Monthly Unemployment Trends,1948-1952')
#print(help(plt.legend))
           

条形图（柱状图）

import pandas as pd
reviews = pd.read_csv('E:/唐宇迪数据集/fandango.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_reviews = reviews[cols][:1]

import matplotlib.pyplot as plt
from numpy import arange
#The Axes.bar() method has 2 required parameters, left and height. 
#We use the left parameter to specify the x coordinates of the left sides of the bar. 
#We use the height parameter to specify the height of each bar
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']

bar_heights = norm_reviews[num_cols].values[0]#这里一定要是一维的
print (bar_heights)
bar_positions = arange(5) + 0.75
tick_position=range(1,6)
print (bar_positions)
fig, ax = plt.subplots()
ax.bar(bar_positions, bar_heights, 0.5)
ax.set_xticks(tick_position)
ax.set_xticklabels(num_cols,rotation=6)
ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
plt.show()
           

import pandas as pd
import  matplotlib.pyplot as plt
from  numpy import  arange
review=pd.read_csv('E:/唐宇迪数据集/fandango.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_review=review[cols][:1]
norm_col=['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_width=norm_review[norm_col].values[0]
print(bar_width)
bar_positon=arange(5)+0.75
tick_poition=range(1,6)
fig,ax=plt.subplots()
ax.barh(bar_positon,bar_width,0.3)
ax.set_yticks(tick_poition)
ax.set_yticklabels(norm_col)
ax.set_xlabel('Score')
ax.set_ylabel('company')
plt.show()
           

散点图

import pandas as pd
import  matplotlib.pyplot as plt
review=pd.read_csv('E:/唐宇迪数据集/fandango.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_review=review[cols]
fig,ax=plt.subplots()
ax.scatter(norm_review['RT_user_norm'],norm_review['Metacritic_user_nom'])
ax.set_xlabel('RT_user_norm')
ax.set_ylabel('Metacritic_user_nom')
plt.show()
           

import pandas as pd
import  matplotlib.pyplot as plt
review=pd.read_csv('E:/唐宇迪数据集/fandango.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_review=review[cols]
fig=plt.figure(figsize=(5,10))
ax1=fig.add_subplot(2,1,1)
ax2=fig.add_subplot(2,1,2)
ax1.scatter(norm_review['RT_user_norm'],norm_review['Metacritic_user_nom'])
ax1.set_xlabel('RT_user_norm')
ax1.set_ylabel('Metacritic_user_nom')
ax2.scatter(norm_review['Metacritic_user_nom'],norm_review['RT_user_norm'])
ax2.set_xlabel('Metacritic_user_nom')
ax2.set_ylabel('RT_user_norm')
plt.show()
           

柱状图盒图

import pandas as pd
import  matplotlib.pyplot as plt
review=pd.read_csv('E:/唐宇迪数据集/fandango.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_review=review[cols]
fandango_distribution=norm_review['Fandango_Ratingvalue'].value_counts()
fandango_distribution=fandango_distribution.sort_index()

imdb_distribution=norm_review['IMDB_norm'].value_counts().sort_index()
print(imdb_distribution)
           

fig,ax=plt.subplots()
ax.hist(norm_review['Fandango_Ratingvalue'],edgecolor='black')#自动划分区间
ax.hist(norm_review['Fandango_Ratingvalue'],bins=20,edgecolor='black')#range(4,5)可以设置区间

plt.show()
           

fig,ax=plt.subplots()
ax.boxplot(norm_review['RT_user_norm'])
ax.set_xticklabels(['RottenTomatoes'])
ax.set_ylim(0,5)
plt.show()#图中表示在获取的数据中 1/4 1/2 3/4 分别在什么位置
           

num_col=['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
           

fig,ax=plt.subplots()
ax.boxplot(review[num_col].values)
ax.set_xticklabels(num_col,rotation=45)
ax.set_ylim(0,5)
plt.show()
           

细节设置

ax.tick_params(bottom="off",top="off",left="off",right="off")可以设置出数据不带多出的横线

自定义颜色 rgb示例

cb_dark_blue=(0/255,107/255,154/255)