四、 Python数据可视化库-Matplotlib
本节内容：
- 折线图绘制
- 子图操作
- 条形图与散点图
- 柱形图与盒图
- 细节设置
1、折线图绘制
import pandas as pd unrate = pd.read_csv('unrate.csv') print(unrate.head(5)) unrate['DATE'] = pd.to_datetime(unrate['DATE'])#通过.to_datetime这个日期函数对'DATE'进行一个标准格式的显示 print(unrate.head(5)) ### DATE VALUE 0 1948-01-01 3.4 1 1948-02-01 3.8 2 1948-03-01 4.0 3 1948-04-01 3.9 4 1948-05-01 3.5 DATE VALUE 0 1948-01-01 3.4 1 1948-02-01 3.8 2 1948-03-01 4.0 3 1948-04-01 3.9 4 1948-05-01 3.5 ###
import pandas as pd unrate = pd.read_csv('unrate.csv') unrate['DATE'] = pd.to_datetime(unrate['DATE'])#通过.to_datetime这个日期函数对'DATE'进行一个标准格式的显示 print(unrate.head(12)) import matplotlib.pyplot as plt #导入绘图库matplotlib.pyplot，起个别名为plt #%matplotlib inline #Using the different pyplot functions, we can create, customize, and display a plot. For example, we can use 2 functions to : plt.plot() #绘图 plt.show() #显示
###
###
first_twelve = unrate[0:5] plt.plot(first_twelve['DATE'], first_twelve['VALUE']) #第一参数为横坐标的值，第二个参数为纵坐标的值 plt.show() ###
###
#While the y-axis looks fine, the x-axis tick labels are too close together and are unreadable #We can rotate the x-axis tick labels by 90 degrees so they don't overlap #We can specify degrees of rotation using a float or integer value. plt.plot(first_twelve['DATE'], first_twelve['VALUE']) plt.xticks(rotation=45) #坐标值太长，对横坐标进行45°旋转 #print help(plt.xticks) plt.show() ###
###
#xlabel(): accepts a string value, which gets set as the x-axis label.接受一个字符串值，该值被设置为x轴标签。 #ylabel(): accepts a string value, which is set as the y-axis label.接受一个字符串值，该值被设置为y轴标签。 #title(): accepts a string value, which is set as the plot title.接受一个字符串值，该值被设置为plot标题。 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() ###
###
2、子图操作
#add_subplot(first,second,index) first means number of Row,second means number of Column. #add_subplot(first,second,index) first表示行数，second表示列数。 import matplotlib.pyplot as plt fig = plt.figure() #指定绘图区间（绘图域） ax1 = fig.add_subplot(2,2,1) #前两个参数表示2*2的矩阵形式，最后一个参数表示在2*2的矩阵的第一个位置 ax2 = fig.add_subplot(2,2,2) ax2 = fig.add_subplot(2,2,4) plt.show() ###
###
import numpy as np fig = plt.figure() fig = plt.figure(figsize=(10, 3))#对绘图域指定大小，第一个参数是长，第二个参数是宽 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))#在子图上进行一些随机操作 ax2.plot(np.arange(10)*3, np.arange(10)) plt.show() ###
###
unrate['MONTH'] = unrate['DATE'].dt.month #把数据里面的月份取出来 fig = plt.figure(figsize=(6,3)) plt.plot(unrate[0:12]['MONTH'], unrate[0:12]['VALUE'], c='red') plt.plot(unrate[12:24]['MONTH'], unrate[12:24]['VALUE'], c='blue') #用c来指定折线的颜色 plt.show() ###
###
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]#[0:12]-red,[12:24]-blue,[24,36]-green... plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i]) plt.show() ###
###
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) #给折线定标签 plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i], label=label) plt.legend(loc='best') #把标签框放在右边，改变loc的值，会改变标签框的位置 #print(help(plt.legend) ) plt.show() ###
###
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) plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i], label=label) plt.legend(loc='upper left') plt.xlabel('Month, Integer') plt.ylabel('Unemployment Rate, Percent') plt.title('Monthly Unemployment Trends, 1948-1952') plt.show() ###
###
3、条形图与散点图
import matplotlib.pyplot as plt from numpy import arange #The Axes.bar() method has 2 required parameters, left and height. bar()方法有两个必需的参数，左边和高度。 #We use the left parameter to specify the x coordinates of the left sides of the bar. 我们使用左参数来指定条形图左侧的x坐标。 #We use the height parameter to specify the height of each bar。我们使用高度参数来指定每个栏的高度 num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars'] bar_heights = norm_reviews.ix[0, num_cols].values #柱的高度，.ix是一种索引的依据 #print(bar_heights) bar_positions = arange(5) + 0.75 #每个柱离零值的距离 #print(bar_positions) fig, ax = plt.subplots() ax.bar(bar_positions, bar_heights, 0.5) #bar型图是条形，0.5是条形的宽度 plt.show() ###
###
#By default, matplotlib sets the x-axis tick labels to the integer values the bars 默认情况下，matplotlib将x轴标记标签设置为条上的整数值 #spanned on the x-axis (from 0 to 6). We only need tick labels on the x-axis where the bars are positioned. 在x轴上(从0到6)，我们只需要在横轴上的横轴上标记条就可以了。 #We can use Axes.set_xticks() to change the positions of the ticks to [1, 2, 3, 4, 5]:我们可以使用ax .set_xticks()将蜱的位置改变为[1,2,3,4,5]: num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars'] bar_heights = norm_reviews.ix[0, num_cols].values bar_positions = arange(5) + 0.75 tick_positions = range(1,6) fig, ax = plt.subplots() ax.bar(bar_positions, bar_heights, 0.5) ax.set_xticks(tick_positions) ax.set_xticklabels(num_cols, rotation=45) ##x轴下标的名字和放置角度 ax.set_xlabel('Rating Source') ax.set_ylabel('Average Rating') ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)') plt.show() ###
###
import matplotlib.pyplot as plt from numpy import arange num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars'] bar_widths = norm_reviews.ix[0, num_cols].values bar_positions = arange(5) + 0.75 tick_positions = range(1,6) fig, ax = plt.subplots() ax.barh(bar_positions, bar_widths, 0.5)# #barh型图是横条形，0.5是条形的宽度 ax.set_yticks(tick_positions) ax.set_yticklabels(num_cols) ax.set_ylabel('Rating Source') ax.set_xlabel('Average Rating') ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)') plt.show() ###
###
#Let's look at a plot that can help us visualize many points. fig, ax = plt.subplots() ax.scatter(norm_reviews['Fandango_Ratingvalue'], norm_reviews['RT_user_norm']) #绘点图 ax.set_xlabel('Fandango') ax.set_ylabel('Rotten Tomatoes') plt.show() ###
###
#Switching Axes 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']) ax1.set_xlabel('Fandango') ax1.set_ylabel('Rotten Tomatoes') ax2.scatter(norm_reviews['RT_user_norm'], norm_reviews['Fandango_Ratingvalue']) ax2.set_xlabel('Rotten Tomatoes') ax2.set_ylabel('Fandango') plt.show() ###
###
4、柱形图与盒图
import pandas as pd import matplotlib.pyplot as plt reviews = pd.read_csv('fandango_scores.csv') cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue'] norm_reviews = reviews[cols] print(norm_reviews[:5])
###
FILM RT_user_norm Metacritic_user_nom \
0 Avengers: Age of Ultron (2015) 4.3 3.55
1 Cinderella (2015) 4.0 3.75
2 Ant-Man (2015) 4.5 4.05
3 Do You Believe? (2015) 4.2 2.35
4 Hot Tub Time Machine 2 (2015) 1.4 1.70
IMDB_norm Fandango_Ratingvalue
0 3.90 4.5
1 3.55 4.5
2 3.90 4.5
3 2.70 4.5
4 2.55 3.0
###
fandango_distribution = norm_reviews['Fandango_Ratingvalue'].value_counts() fandango_distribution = fandango_distribution.sort_index() #对上值进行排序 imdb_distribution = norm_reviews['IMDB_norm'].value_counts() imdb_distribution = imdb_distribution.sort_index() print(fandango_distribution) print(imdb_distribution)
fig, ax = plt.subplots() ax.hist(norm_reviews['Fandango_Ratingvalue']) #hist中没有指定bins，默认为10条 #ax.hist(norm_reviews['Fandango_Ratingvalue'],bins=20) #ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(4, 5),bins=20) #range是空值显示的区间 plt.show() ###
###
fig = plt.figure(figsize=(5,20)) ax1 = fig.add_subplot(4,1,1) ax2 = fig.add_subplot(4,1,2) ax3 = fig.add_subplot(4,1,3) ax4 = fig.add_subplot(4,1,4) ax1.hist(norm_reviews['Fandango_Ratingvalue'], bins=20, range=(0, 5)) ax1.set_title('Distribution of Fandango Ratings') ax1.set_ylim(0, 50) #.set_ylim用于指定y轴的数值区间 ax2.hist(norm_reviews['RT_user_norm'], 20, range=(0, 5)) ax2.set_title('Distribution of Rotten Tomatoes Ratings') ax2.set_ylim(0, 50) ax3.hist(norm_reviews['Metacritic_user_nom'], 20, range=(0, 5)) ax3.set_title('Distribution of Metacritic Ratings') ax3.set_ylim(0, 50) ax4.hist(norm_reviews['IMDB_norm'], 20, range=(0, 5)) ax4.set_title('Distribution of IMDB Ratings') ax4.set_ylim(0, 50) plt.show()
盒图：
fig, ax = plt.subplots() ax.boxplot(norm_reviews['RT_user_norm'])#画盒图 ax.set_xticklabels(['Rotten Tomatoes']) ax.set_ylim(0, 5) plt.show() ###
###
num_cols = ['RT_user_norm', 'Metacritic_user_nom', '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() ###
###
5、细节设置
#Color 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, 164/255) #加载一些特别的颜色进来（eg:深蓝） cb_orange = (255/255, 128/255, 14/255) fig = plt.figure(figsize=(12, 12)) for sp in range(0,4): ax = fig.add_subplot(2,2,sp+1) # The color for each line is assigned here. ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c=cb_dark_blue, label='Women') ax.plot(women_degrees['Year'], 100-women_degrees[major_cats[sp]], c=cb_orange, label='Men') for key,spine in ax.spines.items(): spine.set_visible(False) ax.set_xlim(1968, 2011) ax.set_ylim(0,100) ax.set_title(major_cats[sp]) ax.tick_params(bottom="off", top="off", left="off", right="off") plt.legend(loc='upper right') plt.show() ### ###
#Setting Line Width cb_dark_blue = (0/255, 107/255, 164/255) cb_orange = (255/255, 128/255, 14/255) fig = plt.figure(figsize=(12, 12)) for sp in range(0,4): ax = fig.add_subplot(2,2,sp+1) # Set the line width when specifying how each line should look. ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c=cb_dark_blue, label='Women', linewidth=10)#linewidth指定线条宽度 ax.plot(women_degrees['Year'], 100-women_degrees[major_cats[sp]], c=cb_orange, label='Men', linewidth=10) for key,spine in ax.spines.items(): spine.set_visible(False) ax.set_xlim(1968, 2011) ax.set_ylim(0,100) ax.set_title(major_cats[sp]) ax.tick_params(bottom="off", top="off", left="off", right="off") #对四条边的齿轮进行隐藏 plt.legend(loc='upper right') plt.show() ###
###
stem_cats = ['Engineering', 'Computer Science', 'Psychology', 'Biology', 'Physical Sciences', 'Math and Statistics'] fig = plt.figure(figsize=(18, 3)) for sp in range(0,6): ax = fig.add_subplot(1,6,sp+1) ax.plot(women_degrees['Year'], women_degrees[stem_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3) ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[sp]], c=cb_orange, label='Men', linewidth=3) for key,spine in ax.spines.items(): spine.set_visible(False) ax.set_xlim(1968, 2011) ax.set_ylim(0,100) ax.set_title(stem_cats[sp]) ax.tick_params(bottom="off", top="off", left="off", right="off") plt.legend(loc='upper right') plt.show() ###
###
fig = plt.figure(figsize=(18, 3)) for sp in range(0,6): ax = fig.add_subplot(1,6,sp+1) ax.plot(women_degrees['Year'], women_degrees[stem_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3) ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[sp]], c=cb_orange, label='Men', linewidth=3) for key,spine in ax.spines.items(): spine.set_visible(False) ax.set_xlim(1968, 2011) ax.set_ylim(0,100) ax.set_title(stem_cats[sp]) ax.tick_params(bottom="off", top="off", left="off", right="off") plt.legend(loc='upper right') plt.show() fig = plt.figure(figsize=(18, 3)) for sp in range(0,6): ax = fig.add_subplot(1,6,sp+1) ax.plot(women_degrees['Year'], women_degrees[stem_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3) ax.plot(women_degrees['Year'], 100-women_degrees[stem_cats[sp]], c=cb_orange, label='Men', linewidth=3) for key,spine in ax.spines.items(): spine.set_visible(False) ax.set_xlim(1968, 2011) ax.set_ylim(0,100) ax.set_title(stem_cats[sp]) ax.tick_params(bottom="off", top="off", left="off", right="off") if sp == 0: ax.text(2005, 87, 'Men') ax.text(2002, 8, 'Women') elif sp == 5: ax.text(2005, 62, 'Men') ax.text(2001, 35, 'Women') plt.show() ###
###
浙公网安备 33010602011771号