matplotlib快速入门

1. 折线图

1.1 绘制一条折线

import pandas as pd
import matplotlib.pyplot as plt
unrate = pd.read_csv("unrate1.csv")
unrate["DATA"] = pd.to_datetime(unrate["DATA"])
# 获取2014年的数据
data_2014 = unrate[6:18]
print(len(data_2014))
# X 轴为时间，y轴为失业率
plt.plot(data_2014["DATA"],data_2014["UNEMPLOYMENTRATE"])
plt.xticks(rotation=90)
plt.xlabel("Month")
plt.ylabel("Unemployment Rate")
plt.title("Monthly Unemployment Trends 2014")
plt.show()

图形如下：

1.2绘制两条折线的方法：

import pandas as pd
import matplotlib.pyplot as plt
unrate = pd.read_csv("unrate1.csv")
unrate["DATA"] = pd.to_datetime(unrate["DATA"])
# 获取月份，并添加到unrate中
unrate["MONTH"] = unrate["DATA"].dt.month
# 设置图形的大小
plt.figure(figsize=[9,3])
# 绘制第一条折线
plt.plot(unrate[0:12]["MONTH"],unrate[0:12]["UNEMPLOYMENTRATE"],c="red")
# 绘制第二条折线
plt.plot(unrate[12:24]["MONTH"],unrate[12:24]["UNEMPLOYMENTRATE"],c="blue")
plt.show()

图形：

1.3 绘制多条曲线

import pandas as pd
import matplotlib.pyplot as plt
unrate = pd.read_csv("unrate1.csv")
unrate["DATA"] = pd.to_datetime(unrate["DATA"])
# 获取月份，并添加到unrate中
unrate["MONTH"] = unrate["DATA"].dt.month
# 设置图形的大小
plt.figure(figsize=[9,3])

colors =["red","green","blue","orange"]
for i in range(4):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]
    label=str(2002+i)
    # 设置标签的值
    plt.plot(subset["MONTH"],subset["UNEMPLOYMENTRATE"],c=colors[i],label=label)
# 设置标签的位置
plt.legend(loc="best")
plt.xlabel('Month. Integer')
plt.ylabel("Unemployment Rate")
plt.title("Monthly Unemployment Trends 2002-2005")
plt.show()

1.4 绘制子图

import pandas as pd
import matplotlib.pyplot as plt
# 获取绘制区域
fig = plt.figure()
# 绘制 2*2 中的第一个图形
ax1 = fig.add_subplot(2,2,1)
ax3 = fig.add_subplot(2,2,3)
ax4 = fig.add_subplot(2,2,4)

添加数据：

import numpy as np
from matplotlib.ticker import  MultipleLocator
import matplotlib.pyplot as plt
# 获取绘制区域
fig = plt.figure(figsize=[12,12])
# 绘制 2*2 中的第一个图形
ax1 = fig.add_subplot(2,2,1)
ax3 = fig.add_subplot(2,2,3)
ax4 = fig.add_subplot(2,2,4)
# 第一个图形的数据
ax1.plot(np.random.randint(1,50,15),np.arange(15))
# 设置刻度的间隔
ax1.xaxis.set_major_locator(MultipleLocator(5))
# 第3个图形的数据
ax3.plot(np.arange(10)*3,np.arange(10))
# 第4个图形的数据
ax4.plot(np.arange(-5,5,0.1),np.sin(np.arange(-5,5,0.1)))
ax4.xaxis.set_major_locator(MultipleLocator(1))
plt.show()

图形：

2. 条形图

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

reviews = pd.read_csv("fandango_score_comparison.csv")

# 评分指标列
num_cols =["RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
norm_reviews = reviews[num_cols]
# 获取第-行的数据
bar_heights = norm_reviews.loc[0, num_cols].values
# 条形图的位置
bar_pos = arange(5)+0.75
# 这句可以省略.直接用plt.bar即可
fig,ax = plt.subplots()
# 参数1： 条形图位置；参数2：条形图高度，参数3：条形图宽度
ax.bar(bar_pos,bar_heights,0.3)

# 设置标签的位置
ax.set_xticks(range(1,6))
# 设置标签的内容
ax.set_xticklabels(num_cols, rotation=45)
ax.set_xlabel("Rating Source")
ax.set_ylabel("Average Rating")
ax.set_title("Average User Rating For Avengers: Age of Ultron (2015)")
plt.show()
print(help(plt.xticks))

3.散点图

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

reviews = pd.read_csv("fandango_score_comparison.csv")

# 评分指标列
num_cols =["RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
norm_reviews = reviews[num_cols]
fig,ax =plt.subplots()
ax.scatter(norm_reviews["Fandango_Ratingvalue"],norm_reviews["RT_user_norm"])
ax.set_xlabel("Fandango")
ax.set_ylabel("Rotten Tomatoes")
plt.show()

4. 直方图

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

reviews = pd.read_csv("fandango_score_comparison.csv")

# 评分指标列
num_cols =["RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
norm_reviews = reviews[num_cols]
fig,ax = plt.subplots()
# range(3,5)表示x轴的范围是3~5。bings表示直方图将3-5的区间分成多少分。
ax.hist(norm_reviews["Fandango_Ratingvalue"],range=(3,5),bins=15)
plt.show()

5. 盒图

盒图(boxplot)。它对于显示数据的离散的分布情况效果不错。

盒图是在1977年由美国的统计学家约翰·图基(John Tukey)发明的。它由五个数值点组成：最小值(min)，下四分位数(Q1)，中位数(median)，上四分位数(Q3)，最大值(max)。也可以往盒图里面加入平均值(mean)。如上图。下四分位数、中位数、上四分位数组成一个“带有隔间的盒子”。上四分位数到最大值之间建立一条延伸线，这个延伸线成为“胡须(whisker)”。

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

reviews = pd.read_csv("fandango_score_comparison.csv")

num_cols =["RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
norm_reviews = reviews[num_cols]
fig,ax = plt.subplots()

ax.boxplot(norm_reviews["RT_user_norm"])
# 设置y轴的范围
ax.set_ylim(0,5)
plt.show()

一个图中可以显示多个盒图：

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

reviews = pd.read_csv("fandango_score_comparison.csv")

num_cols =["RT_user_norm","Metacritic_user_nom","IMDB_no rm","Fandango_Ratingvalue","Fandango_Stars"]
norm_reviews = reviews[num_cols]
fig,ax = plt.subplots()

# norm_reviews所有列都显示为盒图
ax.boxplot(norm_reviews.values)
ax.set_xticklabels(num_cols,rotation=90)
ax.set_ylim(0,5)
plt.show()

6. 细节设置

import pandas as pd
import matplotlib.pyplot as plt

women_degrees =pd.read_csv("percent-bachelors-degrees-women-usa.csv");
major_cats =["Biology","Computer Science","Engineering","Math and Statistics"]

cb_dark_blue = (0/255,107/255,104/255)
cb_orange = (255/255,128/255,14/255)

fig = plt.figure(figsize=(18,3))

for sp in range(0,4):
    ax = fig.add_subplot(1,4,sp+1)
    ax.plot(women_degrees["Year"],women_degrees[major_cats[sp]],c=cb_dark_blue,label="Women",linewidth=3)
    ax.plot(women_degrees["Year"],100-women_degrees[major_cats[sp]],c=cb_orange,label="Men",linewidth=3)
    ax.set_xlim(1968,2011)
    ax.set_ylim(0,100)
    ax.set_title(major_cats[sp])
   # ax.text(2010,60,"woman")#在指定坐标上加注释
    # 去除边框上的短线
    plt.tick_params(bottom=False,top=False,left=False,right=False)
    for key,spine in ax.spines.items():
        spine.set_visible(False) # 去除边框
    
plt.legend(loc="upper right")
plt.show()