一、Matplotlib简介
Matplotlib is a comprehensive library for creating static, animated, and interactive visualizations in Python. Matplotlib makes easy things easy and hard things possible.
二、使用Matplotlib生成图像
1、线形图
# 折线图
import numpy as np
import matplotlib.pyplot as plt
x = np.random.random(10)
plt.plot(x)
plt.show()
# 直线图
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(1, 10, 10)
plt.plot(x)
plt.show()
# 曲线图
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(1, 10, 10)
plt.plot(x, x ** 2)
plt.show()
# 点状图
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(1, 10, 10)
plt.plot(x, x ** 2, 'bo')
plt.show()
# 红点状图
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(1, 10, 10)
plt.plot(x, x ** 2, 'r+')
plt.show()
# 包含多条曲线的图
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(1, 10, 10)
plt.plot(x, x * 2)
plt.plot(x, x / 2)
plt.plot(x, x ** 2)
# 也可以使用plt.plot(x, x * 2, x, x / 2, x, x ** 2)来绘制三条曲线（不推荐）
plt.show()
# 开启网格线绘制图形
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(-np.pi, np.pi, 0.01)
plt.plot(x, np.sin(x), x, np.cos(x))
plt.grid(True) # 开启网格线
plt.show()
2、图片样式及风格
网格线及子视图
# 创建子视图
import numpy as np
import matplotlib.pyplot as plt
plt.figure(figsize=[15, 7]) # 设置画布大小
axes = plt.subplot(1, 3, 1) # 创建一个子视图，1行3列1号
x = np.arange(-20, 20, 0.1)
axes.plot(x, np.sin(x))
axes2 = plt.subplot(1, 3, 2) # 创建第二个子视图
x2 = np.arange(-20, 20, 0.1)
axes2.plot(x, np.sin(x))
axes3 = plt.subplot(1, 3, 3) # 创建第三个子视图
axes3.plot(x, np.arcsin(x))
plt.show()
# 修改网格线样式
import numpy as np
import matplotlib.pyplot as plt
plt.figure(figsize=[15, 8])
axes = plt.subplot(1, 3, 1) # 创建一个子视图
x = np.arange(-20, 20, 0.1)
axes.grid(color='r', linestyle='--', linewidth=2) # 设置网格颜色、线形、线的宽度
axes.plot(x, np.sin(x))
axes2 = plt.subplot(1, 3, 2) # 创建第二个子视图
x2 = np.arange(-20, 20, 0.1)
axes2.grid(color='g', linestyle='--')
axes2.plot(x, np.sin(x))
axes3 = plt.subplot(1, 3, 3) # 创建第三个子视图
axes2.grid(color='blue', linestyle='--')
axes3.plot(x, np.arcsin(x))
plt.show()
坐标轴界限
# 设置坐标轴界限
import numpy as np
import matplotlib.pyplot as plt
x = np.random.random(10)
plt.axis([-5, 15, -5, 10]) # 设置坐标轴范围[xmin, xmax, ymin, ymax]
# xlim()和ylimit()与上面等效
# plt.xlim(-5, 15)
# plt.ylim(-5, 10)
# plt.axis('off') 关闭坐标轴
plt.plot(x)
plt.show()
# 画个圆
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(-5, 5, 100)
plt.plot(np.sin(x), np.cos(x))
plt.axis('equal')
plt.show()
坐标轴的标签
# 设置坐标轴的标题和标签
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import font_manager
x = np.arange(0, 10, 2)
y = x ** 2 + 5
plt.plot(x, y)
my_font = font_manager.FontProperties(family='SimSun', size=20) # family指定字体（系统内，SimSun宋体），fname可以使用ttf文件路径的字体
plt.title('坐标标签测试图', fontproperties=my_font) # 设置标题
plt.xlabel('x', size=20)
plt.ylabel('f(x)=x^2+5', size=20, rotation=10) # rotation为旋转角度
plt.show()
图例
# 图例
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(0, 10, 2)
plt.plot(x, x, label='x')
plt.plot(x, x * 2, label='2x')
plt.plot(x, x ** 2, label='x^2')
plt.legend() # 创建图例
plt.show()
Location String | Location Code |
|---|---|
'best' (Axes only) | 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 |
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(0, 10, 2)
plt.plot(x, x)
plt.plot(x, x * 2)
plt.plot(x, x ** 2)
plt.legend(['x', '2x', 'x^2'], loc='right') # 修改图例位置，参数参考上表
plt.show()
线条样式
import numpy as np
import matplotlib.pyplot as plt
x1 = np.random.randn(100)
x2 = np.random.randn(100)
x3 = np.random.randn(100)
plt.plot(x1.cumsum(), color='blue', linestyle='--', marker='o')
plt.plot(x2.cumsum(), color='green', linestyle='-', marker='>')
plt.plot(x3.cumsum(), color='black', linestyle=':', marker='D')
plt.legend(['x1', 'x2', 'x3'])
plt.savefig('./pic.jpg', dpi=150) # 保存图片，可使用facecolor自定义背景颜色
plt.show()
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(0, 10, 0.1)
axes = plt.subplot(facecolor='pink')
axes.plot(x, np.sin(x), color='green', # 线条颜色
alpha=0.3, # 0~1之间的透明度
ls='-', # 线形状，与linestyle等效
lw=10 # 线条宽度与linewidth等效
)
plt.show()
坐标轴刻度
# 坐标刻度样式
import numpy as np
import matplotlib.pyplot as plt
x = np.random.randn(100)
plt.plot(x.cumsum())
plt.xticks(np.linspace(1, 100, 7), list('ABCDEFG'), rotation=90)
plt.yticks(np.linspace(-10, 20, 3), ['min', 0, 'max'], fontsize=15)
plt.show()
3、函数图像绘制
# 获知sinx、cosx和sqrt(x)
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import rcParams
# 全局字体
config = {
"mathtext.fontset": 'stix',
"font.family": 'serif',
"font.serif": ['Times New Roman'], # 字体
"font.size": 22,
'axes.unicode_minus': False # 处理负号，即-号
}
rcParams.update(config)
# 设置画布按大小
plt.figure(figsize=(10, 6))
# 数据内容
x = np.arange(0, 10, 0.2)
y1 = np.sin(x)
y2 = np.cos(x)
y3 = np.sqrt(x)
# 绘制数据
plt.plot(x, y1, color='darkseagreen', lw=1, ls='-', marker='.', label='$y=sinx$')
plt.plot(x, y2, color='dodgerblue', lw=1, ls='-', marker='*', label='$y=cosx$')
plt.plot(x, y3, color='orchid', lw=1, ls='-', marker='3', label='$y=\sqrt{x}$')
# 限制横纵坐标范围
plt.xlim((0, 10.5))
plt.ylim((-1.5, 4))
# 添加子图来修改坐标轴位置
ax = plt.subplot(1, 1, 1)
ax.spines['right'].set_color('none')
ax.spines['top'].set_color('none')
ax.spines['bottom'].set_position(('data', 0))
ax.spines['left'].set_position(('data', 0))
x0 = 8
y0 = 2 * np.sqrt(2)
# 绘制2根2的点
plt.plot(x0, y0, marker='o', color='orchid')
# 添加箭头及文字
plt.annotate('$2\sqrt{2}$', xy=(x0, y0),
textcoords='offset points', xytext=(+10, -30), fontsize=16,
arrowprops=dict(arrowstyle='->', connectionstyle='arc3,rad=0'))
# 添加xy的范围文字
plt.annotate('$x\in[0.0,10.0]$\n$y\in[-1.0,4.0]$', xy=(3.8, 2), fontsize=16,
textcoords='offset points', xytext=(+10, -30))
# 开启网格线
plt.grid()
# 设置图例
plt.legend(numpoints=2, fontsize=14)
plt.title('the function figure of cos(), sin() and sqrt()')
# 修改x轴文字距离x轴的距离
plt.xlabel('the input value of x', labelpad=80)
# 修改y轴的旋转度数
plt.ylabel('y=f(x)', rotation=90)
plt.show()
4、其他图形样式
直方图
import numpy as np
import matplotlib.pyplot as plt
x = np.random.randint(0, 10, 10)
plt.hist(x, density=True, orientation='horizontal', color='red')
plt.show()
条形图
import numpy as np
import matplotlib.pyplot as plt
x = np.linspace(0, 5, 5)
y = np.random.randint(0, 20, size=5)
# plt.bar(x, y) 竖直方向
plt.barh(x, y)
plt.show()
饼图
import numpy as np
import matplotlib.pyplot as plt
p = np.array([0.4, 0.2, 0.15, 0.15, 0.1])
plt.pie(p, labels=['b', 'b', 'c', 'd', 'e'], autopct='%.2f%%')
plt.show()
散点图
import numpy as np
import matplotlib.pyplot as plt
x = np.random.randn(1000)
y = np.random.randn(1000)
plt.scatter(x, y, color='r', s=18)
plt.show()
箱型图
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
df = pd.DataFrame(np.random.rand(10, 5))
plt.boxplot(df)
plt.show()
小提琴图
import numpy as np
import matplotlib.pyplot as plt
plt.violinplot(dataset=np.random.normal(size=1000))
plt.show()
三、根据数据集绘制图像
1、2000年以前温室气体浓度
# 根据csv绘制图像
import os
import requests
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import font_manager
# 数据准备
isExist = os.path.exists('./greenhouse_gases.csv')
if not isExist:
url = 'https://vincentarelbundock.github.io/Rdatasets/csv/dslabs/greenhouse_gases.csv'
open('./greenhouse_gases.csv', 'wb').write(requests.get(url).content)
# 设置画布按大小
plt.figure(figsize=(15, 10))
# 设置字体
title_font = font_manager.FontProperties(family='SimHei', size=25) # SimHei黑体
label_font = font_manager.FontProperties(family='SimHei', size=15)
# 读取温室气体浓度数据
gas_data = pd.read_csv('./greenhouse_gases.csv')
# 数据根据气体分组
gas_group = gas_data.groupby(by='gas', sort=True)
gas_list = gas_data['gas'].unique()
for gas in gas_list:
gas_data_by_type = gas_group.get_group(gas)
# 年份和浓度数据
year_list = gas_data_by_type['year']
year_list = ['{}年'.format(y) for y in year_list]
concentration_list = gas_data_by_type['concentration']
# 绘制图像
line = np.linspace(1, len(concentration_list), len(concentration_list))
plt.plot(line, concentration_list, label=gas)
# 修改x轴坐标数值
plt.xticks(np.arange(1, 100, step=10), year_list[::int(len(year_list) / 10)], fontsize=15, fontproperties=label_font)
plt.yticks(fontsize=15, fontproperties=label_font)
# 开启网格线
plt.grid()
# 设置标题
plt.title('2000年以前温室气体浓度趋势图', fontproperties=title_font)
# 创建图例并绘制图像
plt.legend(fontsize=15)
plt.show()
2、2013年纽约起飞的所有航班准点率
数据含义描述
Flights data
Description
On-time data for all flights that departed NYC (i.e. JFK, LGA or EWR) in 2013.
Usage
flights
Format
Data frame with columns
year, month, day : Date of departure.
dep_time, arr_time : Actual departure and arrival times (format HHMM or HMM), local tz.
sched_dep_time, sched_arr_time : Scheduled departure and arrival times (format HHMM or HMM), local tz.
dep_delay, arr_delay : Departure and arrival delays, in minutes. Negative times represent early departures/arrivals.
carrier : Two letter carrier abbreviation. See airlines to get name.
flight : Flight number.
tailnum : Plane tail number. See planes for additional metadata.
origin, dest : Origin and destination. See airports for additional metadata.
air_time : Amount of time spent in the air, in minutes.
distance : Distance between airports, in miles.
hour, minute : Time of scheduled departure broken into hour and minutes.
time_hour : Scheduled date and hour of the flight as a POSIXct date. Along with origin, can be used to join flights data to weather data.
Source
RITA, Bureau of transportation statistics, https://www.transtats.bts.gov/DL_SelectFields.asp?Table_ID=236
数据内容查看
import pandas as pd
# 读取航班的准点率数据
flights_data = pd.read_csv('./flights.csv')
# 不省略数据列
pd.set_option('display.max_columns', None)
# 查看数据基本信息
print('top 5 data: \n', flights_data.head(5), end='\n' + '-' * 80 + '\n')
print('data info : \n', flights_data.info(), end='\n' + '-' * 80 + '\n')
print('data describe : \n', flights_data.describe())
''' 输出：
top 5 data:
Unnamed: 0 year month day dep_time sched_dep_time dep_delay
0 1 2013 1 1 517.0 515 2.0 \
1 2 2013 1 1 533.0 529 4.0
2 3 2013 1 1 542.0 540 2.0
3 4 2013 1 1 544.0 545 -1.0
4 5 2013 1 1 554.0 600 -6.0
arr_time sched_arr_time arr_delay carrier flight tailnum origin dest
0 830.0 819 11.0 UA 1545 N14228 EWR IAH \
1 850.0 830 20.0 UA 1714 N24211 LGA IAH
2 923.0 850 33.0 AA 1141 N619AA JFK MIA
3 1004.0 1022 -18.0 B6 725 N804JB JFK BQN
4 812.0 837 -25.0 DL 461 N668DN LGA ATL
air_time distance hour minute time_hour
0 227.0 1400 5 15 2013-01-01 05:00:00
1 227.0 1416 5 29 2013-01-01 05:00:00
2 160.0 1089 5 40 2013-01-01 05:00:00
3 183.0 1576 5 45 2013-01-01 05:00:00
4 116.0 762 6 0 2013-01-01 06:00:00
--------------------------------------------------------------------------------
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 336776 entries, 0 to 336775
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Unnamed: 0 336776 non-null int64
1 year 336776 non-null int64
2 month 336776 non-null int64
3 day 336776 non-null int64
4 dep_time 328521 non-null float64
5 sched_dep_time 336776 non-null int64
6 dep_delay 328521 non-null float64
7 arr_time 328063 non-null float64
8 sched_arr_time 336776 non-null int64
9 arr_delay 327346 non-null float64
10 carrier 336776 non-null object
11 flight 336776 non-null int64
12 tailnum 334264 non-null object
13 origin 336776 non-null object
14 dest 336776 non-null object
15 air_time 327346 non-null float64
16 distance 336776 non-null int64
17 hour 336776 non-null int64
18 minute 336776 non-null int64
19 time_hour 336776 non-null object
dtypes: float64(5), int64(10), object(5)
memory usage: 51.4+ MB
data info :
None
--------------------------------------------------------------------------------
data describe :
Unnamed: 0 year month day dep_time
count 336776.000000 336776.0 336776.000000 336776.000000 328521.000000 \
mean 168388.500000 2013.0 6.548510 15.710787 1349.109947
std 97219.001466 0.0 3.414457 8.768607 488.281791
min 1.000000 2013.0 1.000000 1.000000 1.000000
25% 84194.750000 2013.0 4.000000 8.000000 907.000000
50% 168388.500000 2013.0 7.000000 16.000000 1401.000000
75% 252582.250000 2013.0 10.000000 23.000000 1744.000000
max 336776.000000 2013.0 12.000000 31.000000 2400.000000
sched_dep_time dep_delay arr_time sched_arr_time
count 336776.000000 328521.000000 328063.000000 336776.000000 \
mean 1344.254840 12.639070 1502.054999 1536.380220
std 467.335756 40.210061 533.264132 497.457142
min 106.000000 -43.000000 1.000000 1.000000
25% 906.000000 -5.000000 1104.000000 1124.000000
50% 1359.000000 -2.000000 1535.000000 1556.000000
75% 1729.000000 11.000000 1940.000000 1945.000000
max 2359.000000 1301.000000 2400.000000 2359.000000
arr_delay flight air_time distance
count 327346.000000 336776.000000 327346.000000 336776.000000 \
mean 6.895377 1971.923620 150.686460 1039.912604
std 44.633292 1632.471938 93.688305 733.233033
min -86.000000 1.000000 20.000000 17.000000
25% -17.000000 553.000000 82.000000 502.000000
50% -5.000000 1496.000000 129.000000 872.000000
75% 14.000000 3465.000000 192.000000 1389.000000
max 1272.000000 8500.000000 695.000000 4983.000000
hour minute
count 336776.000000 336776.000000
mean 13.180247 26.230100
std 4.661316 19.300846
min 1.000000 0.000000
25% 9.000000 8.000000
50% 13.000000 29.000000
75% 17.000000 44.000000
max 23.000000 59.000000
'''机场航班数量（条形图）
adict.py：
# 不保证信息准确性
carrier_dict = {'UA': {'name_ch': '美国联合航空'}, 'AA': {'name_ch': '美国航空'}, 'B6': {'name_ch': '捷蓝航空'},
'DL': {'name_ch': '达美航空'}, 'EV': {'name_ch': '美国快捷航空'}, 'MQ': {'name_ch': '特使航空'},
'US': {'name_ch': '美孟航空'}, 'WN': {'name_ch': '美国西南航空'}, 'VX': {'name_ch': '维珍航空'},
'FL': {'name_ch': '法国航空'}, 'AS': {'name_ch': 'FLY LILI'}, '9E': {'name_ch': '奋进航空'},
'F9': {'name_ch': '边疆航空'}, 'HA': {'name_ch': '哈亚航空'}, 'YV': {'name_ch': '梅萨航空公司'},
'OO': {'name_ch': '天西航空'}}
airport_code = {'EWR': {'name_ch': '纽瓦克自由国际机场'}, 'LGA': {'name_ch': '拉瓜迪亚机场'},
'JFK': {'name_ch': '纽约肯尼迪机场'}, 'IAH': {'name_ch': '乔治布什国际机场'},
'MIA': {'name_ch': '迈阿密国际机场'}, 'BQN': {'name_ch': '拉斐尔-埃尔南德斯机场'},
'ATL': {'name_ch': '亚特兰大国际机场'}, 'ORD': {'name_ch': '奥黑尔国际机场'},
'FLL': {'name_ch': '劳德代尔机场'}, 'IAD': {'name_ch': '华盛顿杜勒斯国际机场'},
'MCO': {'name_ch': '奥兰多国际机场'}, 'PBI': {'name_ch': '西棕榈滩国际机场'},
'TPA': {'name_ch': '坦帕机场'}, 'LAX': {'name_ch': '洛杉矶机场'}, 'SFO': {'name_ch': '旧金山机场'},
'DFW': {'name_ch': '达拉斯-沃斯堡国际机场'}, 'BOS': {'name_ch': '洛干国际机场'},
'LAS': {'name_ch': '麦克卡兰国际机场'}, 'MSP': {'name_ch': '圣保罗国际机场'},
'DTW': {'name_ch': '维纳郡机场'}, 'RSW': {'name_ch': '西南佛罗里达地区机场'},
'SJU': {'name_ch': '路易斯姆诺兹马灵机场'}, 'PHX': {'name_ch': '凤凰城机场'},
'BWI': {'name_ch': '巴尔的摩华盛顿国际机场'}, 'CLT': {'name_ch': '夏洛特-道格拉斯国际机场'},
'BUF': {'name_ch': '布法罗尼亚加拉国际机场'}, 'DEN': {'name_ch': '丹佛国际机场'},
'SNA': {'name_ch': '约翰维纳机场'}, 'MSY': {'name_ch': '新奥尔良路易斯阿姆斯特朗国际机场'},
'SLC': {'name_ch': '盐湖城国际机场'}, 'XNA': {'name_ch': '阿肯色西北地区机场'},
'MKE': {'name_ch': '米切尔国际机场'}, 'SEA': {'name_ch': '西雅图塔克马国际机场'},
'ROC': {'name_ch': '罗切斯特机场'}, 'SYR': {'name_ch': '雪城汉考克国际机场'},
'SRQ': {'name_ch': '布雷登顿国际机场'}, 'RDU': {'name_ch': '罗利机场'},
'CMH': {'name_ch': '哥伦布国际机场'}, 'JAX': {'name_ch': '杰克逊威尔机场'},
'CHS': {'name_ch': '查尔斯顿国际机场'}, 'MEM': {'name_ch': '孟菲斯机场'},
'PIT': {'name_ch': '匹兹堡机场'}, 'SAN': {'name_ch': '圣迭戈国际机场'},
'DCA': {'name_ch': '罗纳德·里根华盛顿国家机场'}, 'CLE': {'name_ch': '霍普金斯国际机场'},
'STL': {'name_ch': '兰伯特圣路易斯国际机场'}, 'MYR': {'name_ch': '默特尔比奇国际机场'},
'JAC': {'name_ch': '杰克逊霍勒机场'}, 'MDW': {'name_ch': '米德威机场'},
'HNL': {'name_ch': '火奴鲁鲁国际机场'}, 'BNA': {'name_ch': '那什维尔国际机场'},
'AUS': {'name_ch': '奥斯汀机场'}, 'BTV': {'name_ch': '柏林顿机场'}, 'PHL': {'name_ch': '费城国际机场'},
'STT': {'name_ch': '圣托马斯机场'}, 'EGE': {'name_ch': '伊格尔郡机场'},
'AVL': {'name_ch': '阿什维尔地区机场'}, 'PWM': {'name_ch': '波特兰国际喷气机机场'},
'IND': {'name_ch': '印第安纳波利斯机场'}, 'SAV': {'name_ch': '希尔顿首脑机场'},
'CAK': {'name_ch': '阿克伦坎通地区机场'}, 'HOU': {'name_ch': '霍比机场'},
'LGB': {'name_ch': '长滩地方机场'}, 'DAY': {'name_ch': '詹姆斯考克斯代顿机场'},
'ALB': {'name_ch': '奥尔巴尼国际机场'}, 'BDL': {'name_ch': '布拉德利国际机场'},
'MHT': {'name_ch': '曼彻斯特地方机场'}, 'MSN': {'name_ch': '麦迪逊机场'},
'GSO': {'name_ch': '格林斯伯勒机场'}, 'CVG': {'name_ch': '辛辛那提国际机场'},
'BUR': {'name_ch': '伯班克机场'}, 'RIC': {'name_ch': '里士满国际机场'},
'GSP': {'name_ch': '格林威尔机场'}, 'GRR': {'name_ch': '肯特郡国际机场'},
'MCI': {'name_ch': '堪萨斯城国际机场'}, 'ORF': {'name_ch': '诺福克国际机场'},
'SAT': {'name_ch': '圣安东尼奥机场'}, 'SDF': {'name_ch': '路易斯威尔机场'},
'PDX': {'name_ch': '波特兰国际机场'}, 'SJC': {'name_ch': '圣何塞地方机场'},
'OMA': {'name_ch': '奥马哈机场'}, 'CRW': {'name_ch': '查尔斯顿耶格机场'},
'OAK': {'name_ch': '奥克兰大都会国际机场'}, 'SMF': {'name_ch': '萨克拉门托大都会机场'},
'TUL': {'name_ch': '塔尔萨国际机场'}, 'TYS': {'name_ch': '麦克吉提森机场'},
'OKC': {'name_ch': '维尔罗杰斯机场'}, 'PVD': {'name_ch': '西奥多·弗朗西斯·格林机场'},
'DSM': {'name_ch': '得梅因机场'}, 'PSE': {'name_ch': '梅塞德塔国际机场'},
'BHM': {'name_ch': '伯明翰-沙特尔斯沃思国际机场'}, 'CAE': {'name_ch': '哥伦比亚机场'},
'HDN': {'name_ch': '亚姆帕瓦雷机场'}, 'BZN': {'name_ch': '加拉丁机场'},
'MTJ': {'name_ch': '蒙特罗斯郡机场'}, 'EYW': {'name_ch': '基韦斯特国际机场'},
'PSP': {'name_ch': '帕姆斯普林斯地方机场'}, 'ACK': {'name_ch': '南塔克特纪念机场'},
'BGR': {'name_ch': '班戈国际机场'}, 'ABQ': {'name_ch': '阿尔伯克基国际机场'},
'ILM': {'name_ch': '威尔明顿国际机场'}, 'MVY': {'name_ch': '马撒葡萄园岛机场'},
'SBN': {'name_ch': '南本德地区机场'}, 'LEX': {'name_ch': '布鲁格拉斯机场'},
'CHO': {'name_ch': '夏洛茨维尔机场'}, 'TVC': {'name_ch': '特拉佛斯城机场'},
'ANC': {'name_ch': '安克雷奇国际机场'}}import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import rcParams
import adict
# 设置画布按大小
plt.figure(figsize=(15, 10))
# 全局字体
config = {
"mathtext.fontset": 'stix',
"font.family": 'serif',
"font.serif": ['KaiTi'], # 楷体
"font.size": 20,
'axes.unicode_minus': False # 处理负号，即-号
}
rcParams.update(config)
# 调整图形边距
plt.subplots_adjust(top=0.9, bottom=0.28)
# 读取航班的准点率数据
flights_data = pd.read_csv('./flights.csv')
flights_data.set_index('Unnamed: 0', inplace=True)
# 新增count列
flights_data.loc[:, 'count'] = pd.Series(np.ones(len(flights_data.index)))
# 过滤空数据（过滤行中包含NA的数据）
# 对行中某列/某几列的过滤
# flights_data = flights_data[flights_data.dep_time.notnull()]
flights_data = flights_data.dropna() # 行中任意包含NA的过滤
# 仅留下origin, dest, count三列
flights_data = flights_data.loc[:, ['origin', 'dest', 'count']]
# 根据origin进行分组
flights_group = flights_data.groupby('origin', sort=True)
origin_arr = flights_data['origin'].unique()
# 初始化count_dict
count_dict = {}
for i in origin_arr:
count_dict[i] = []
# 分别统计这些目的地的航班量
dest_arr = [des for des in adict.airport_code][3:13] # 筛选部分目的地
for ori in origin_arr:
group_by_ori = flights_group.get_group(ori)
group_by_ori = group_by_ori[group_by_ori['dest'].isin(dest_arr)]
group_by_ori = group_by_ori.groupby(['origin', 'dest'], sort=True)
count_by_ori = group_by_ori.count()
for des in dest_arr:
if (ori, des) in count_by_ori.index:
count_dict[ori].append(count_by_ori.loc[(ori, des)]['count'])
else:
count_dict[ori].append(0)
deviation = -0.25
for ori in origin_arr:
plt.bar(np.arange(len(dest_arr)) + deviation, np.array(count_dict[ori]), 0.25,
label=adict.airport_code[ori]['name_ch'])
deviation += 0.25
plt.xticks(np.arange(len(dest_arr)),
[adict.airport_code[des]['name_ch'] for des in dest_arr],
rotation=55, ha='right')
plt.title('2013年纽约三大机场飞往各机场的航班数量图', fontsize=25)
plt.legend()
plt.show()
各航司航班数量占比（饼图）
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import rcParams
import adict
# 设置画布按大小
plt.figure(figsize=(15, 10))
# 全局字体
config = {
"mathtext.fontset": 'stix',
"font.family": 'serif',
"font.serif": ['KaiTi'], # 楷体
"font.size": 30,
'axes.unicode_minus': False # 处理负号，即-号
}
rcParams.update(config)
# 调整图形边距
plt.subplots_adjust(left=0.1, right=0.9, top=0.9, bottom=0.02)
# 读取航班的准点率数据
flights_data = pd.read_csv('./flights.csv')
flights_data.set_index('Unnamed: 0', inplace=True)
# 新增count列
flights_data.loc[:, 'count'] = pd.Series(np.ones(len(flights_data.index)))
# 过滤空数据（过滤行中包含NA的数据）
flights_data = flights_data.dropna()
carrier_list = flights_data['carrier'].unique()
flights_group = flights_data.groupby('carrier', sort=False)
# 仅留下origin, dest, count三列
flights_data = flights_data.loc[:, ['carrier', 'count']]
# 数据整理
data_list = []
carrier_ch_list = [adict.carrier_dict.get(ca)['name_ch'] for ca in carrier_list]
for carrier in carrier_list:
flights_group_by_carrier = flights_group.get_group(carrier)
data_list.append(flights_group_by_carrier.count()['count'])
# 统一比例过小的数据为其他
other_sum = 0
data_list_new = []
carrier_ch_list_new = []
data_sum = np.array(data_list).sum()
for i in range(len(carrier_ch_list)):
if 100 * data_list[i] / data_sum >= 3:
data_list_new.append(data_list[i])
carrier_ch_list_new.append(carrier_ch_list[i])
else:
other_sum += data_list[i]
data_list_new.append(other_sum)
carrier_ch_list_new.append('其他航空')
# 绘制饼图
patches, l_text, p_text = plt.pie(np.array(data_list_new), labels=carrier_ch_list_new,
autopct='%.2f%%', explode=[0.05 for i in carrier_ch_list_new])
for t in p_text:
t.set_size(20) # 设置百分比字体大小
plt.title('2013年各航司从纽约起飞的航班数占比图', fontsize=35)
plt.show()