【Matplotlib】数据可视化实例分析

数据可视化实例分析

作者：白宁超

2017年7月19日09:09:07

1 折线图的制作

1.1 需求描述

使用matplotlib绘制一个简单的折线图，在对其进行定制，以实现信息更加丰富的数据可视化，绘制（1,2,3,4,5）的平方折线图。

1.2 源码

#coding=utf-8
import matplotlib as mpl
import matplotlib.pyplot as plt
import pylab
# 解决中文乱码问题
mpl.rcParams['font.sans-serif']=['SimHei']
mpl.rcParams['axes.unicode_minus']=False

# squares = [1,35,43,3,56,7]
input_values = [1,2,3,4,5]
squares = [1,4,9,16,25]
# 设置折线粗细
plt.plot(input_values,squares,linewidth=5)

# 设置标题和坐标轴
plt.title('平方数图',fontsize=24)
plt.xlabel('值',fontsize=14)
plt.ylabel('平方值',fontsize=14)

# 设置刻度大小
plt.tick_params(axis='both',labelsize=14)

plt.show()

1.3 生成结果

AKDT,Max TemperatureF,Mean TemperatureF,Min TemperatureF,Max Dew PointF,MeanDew PointF,Min DewpointF,Max Humidity, Mean Humidity, Min Humidity, Max Sea Level PressureIn, Mean Sea Level PressureIn, Min Sea Level PressureIn, Max VisibilityMiles, Mean VisibilityMiles, Min VisibilityMiles, Max Wind SpeedMPH, Mean Wind SpeedMPH, Max Gust SpeedMPH,PrecipitationIn, CloudCover, Events, WindDirDegrees
2014-7-1,64,56,50,53,51,48,96,83,58,30.19,30.00,29.79,10,10,10,7,4,,0.00,7,,337
2014-7-2,71,62,55,55,52,46,96,80,51,29.81,29.75,29.66,10,9,2,13,5,,0.14,7,Rain,327
2014-7-3,64,58,53,55,53,51,97,85,72,29.88,29.86,29.81,10,10,8,15,4,,0.01,6,,258
2014-7-4,59,56,52,52,51,50,96,88,75,29.91,29.89,29.87,10,9,2,9,2,,0.07,7,Rain,255
2014-7-5,69,59,50,52,50,46,96,72,49,29.88,29.82,29.79,10,10,10,13,5,,0.00,6,,110
2014-7-6,62,58,55,51,50,46,80,71,58,30.13,30.07,29.89,10,10,10,20,10,29,0.00,6,Rain,213
2014-7-7,61,57,55,56,53,51,96,87,75,30.10,30.07,30.05,10,9,4,16,4,25,0.14,8,Rain,211
2014-7-8,55,54,53,54,53,51,100,94,86,30.10,30.06,30.04,10,6,2,12,5,23,0.84,8,Rain,159
2014-7-9,57,55,53,56,54,52,100,96,83,30.24,30.18,30.11,10,7,2,9,5,,0.13,8,Rain,201
2014-7-10,61,56,53,53,52,51,100,90,75,30.23,30.17,30.03,10,8,2,8,3,,0.03,8,Rain,215
2014-7-11,57,56,54,56,54,51,100,94,84,30.02,30.00,29.98,10,5,2,12,5,,1.28,8,Rain,250
2014-7-12,59,56,55,58,56,55,100,97,93,30.18,30.06,29.99,10,6,2,15,7,26,0.32,8,Rain,275
2014-7-13,57,56,55,58,56,55,100,98,94,30.25,30.22,30.18,10,5,1,8,4,,0.29,8,Rain,291
2014-7-14,61,58,55,58,56,51,100,94,83,30.24,30.23,30.22,10,7,0,16,4,,0.01,8,Fog,307
2014-7-15,64,58,55,53,51,48,93,78,64,30.27,30.25,30.24,10,10,10,17,12,,0.00,6,,318
2014-7-16,61,56,52,51,49,47,89,76,64,30.27,30.23,30.16,10,10,10,15,6,,0.00,6,,294
2014-7-17,59,55,51,52,50,48,93,84,75,30.16,30.04,29.82,10,10,6,9,3,,0.11,7,Rain,232
2014-7-18,63,56,51,54,52,50,100,84,67,29.79,29.69,29.65,10,10,7,10,5,,0.05,6,Rain,299
2014-7-19,60,57,54,55,53,51,97,88,75,29.91,29.82,29.68,10,9,2,9,2,,0.00,8,,292
2014-7-20,57,55,52,54,52,50,94,89,77,29.92,29.87,29.78,10,8,2,13,4,,0.31,8,Rain,155
2014-7-21,69,60,52,53,51,50,97,77,52,29.99,29.88,29.78,10,10,10,13,4,,0.00,5,,297
2014-7-22,63,59,55,56,54,52,90,84,77,30.11,30.04,29.99,10,10,10,9,3,,0.00,6,Rain,240
2014-7-23,62,58,55,54,52,50,87,80,72,30.10,30.03,29.96,10,10,10,8,3,,0.00,7,,230
2014-7-24,59,57,54,54,52,51,94,84,78,29.95,29.91,29.89,10,9,3,17,4,28,0.06,8,Rain,207
2014-7-25,57,55,53,55,53,51,100,92,81,29.91,29.87,29.83,10,8,2,13,3,,0.53,8,Rain,141
2014-7-26,57,55,53,57,55,54,100,96,93,29.96,29.91,29.87,10,8,1,15,5,24,0.57,8,Rain,216
2014-7-27,61,58,55,55,54,53,100,92,78,30.10,30.05,29.97,10,9,2,13,5,,0.30,8,Rain,213
2014-7-28,59,56,53,57,54,51,97,94,90,30.06,30.00,29.96,10,8,2,9,3,,0.61,8,Rain,261
2014-7-29,61,56,51,54,52,49,96,89,75,30.13,30.02,29.95,10,9,3,14,4,,0.25,6,Rain,153
2014-7-30,61,57,54,55,53,52,97,88,78,30.31,30.23,30.14,10,10,8,8,4,,0.08,7,Rain,160
2014-7-31,66,58,50,55,52,49,100,86,65,30.31,30.29,30.26,10,9,3,10,4,,0.00,3,,217

View Code



highs_lows.py文件信息

import csv
from datetime import datetime
from matplotlib import pyplot as plt
import matplotlib as mpl

# 解决中文乱码问题
mpl.rcParams['font.sans-serif']=['SimHei']
mpl.rcParams['axes.unicode_minus']=False

# Get dates, high, and low temperatures from file.
filename = 'death_valley_2014.csv'
with open(filename) as f:
reader = csv.reader(f)
header_row = next(reader)
# print(header_row)

# for index,column_header in enumerate(header_row):
#     print(index,column_header)

dates, highs,lows = [],[], []
for row in reader:
try:
current_date = datetime.strptime(row[0], "%Y-%m-%d")
high = int(row[1])
low = int(row[3])
except ValueError: # 处理
print(current_date, 'missing data')
else:
dates.append(current_date)
highs.append(high)
lows.append(low)

# 汇制数据图形
fig = plt.figure(dpi=120,figsize=(10,6))
plt.plot(dates,highs,c='red',alpha=0.5)# alpha指定透明度
plt.plot(dates,lows,c='blue',alpha=0.5)
plt.fill_between(dates,highs,lows,facecolor='orange',alpha=0.1)#接收一个x值系列和y值系列，给图表区域着色

#设置图形格式
plt.title('2014年加利福尼亚死亡谷日气温最高最低图',fontsize=24)
plt.xlabel('日（D）',fontsize=16)
fig.autofmt_xdate() # 绘制斜体日期标签
plt.ylabel('温度（F）',fontsize=16)
plt.tick_params(axis='both',which='major',labelsize=16)
# plt.axis([0,31,54,72]) # 自定义数轴起始刻度
plt.savefig('highs_lows.png',bbox_inches='tight')

plt.show()

6.3 生成结果

7 制作世界人口地图：JSON格式

7.1 需求描述

下载json格式的人口数据，并使用json模块来处理。

7.2 源码

json数据population_data.json部分信息



countries.py

from pygal.maps.world import COUNTRIES

for country_code in sorted(COUNTRIES.keys()):
print(country_code, COUNTRIES[country_code])

countries_codes.py

from pygal.maps.world import COUNTRIES
def get_country_code(country_name):
"""Return the Pygal 2-digit country code for the given country."""
for code, name in COUNTRIES.items():
if name == country_name:
return code
# If the country wasn't found, return None.
return

print(get_country_code('Thailand'))
# print(get_country_code('Andorra'))

americas.py

import pygal

wm =pygal.maps.world.World()
wm.title = 'North, Central, and South America'

wm.add('North America', ['ca', 'mx', 'us'])
wm.add('Central America', ['bz', 'cr', 'gt', 'hn', 'ni', 'pa', 'sv'])
wm.add('South America', ['ar', 'bo', 'br', 'cl', 'co', 'ec', 'gf',
'gy', 'pe', 'py', 'sr', 'uy', 've'])
wm.add('Asia', ['cn', 'jp', 'th'])
wm.render_to_file('americas.svg')

world_population.py

#conding = utf-8
import json
from matplotlib import pyplot as plt
import matplotlib as mpl
from country_codes import get_country_code
import pygal
from pygal.style import RotateStyle
from pygal.style import LightColorizedStyle
# 解决中文乱码问题
mpl.rcParams['font.sans-serif']=['SimHei']
mpl.rcParams['axes.unicode_minus']=False

# 加载json数据
filename='population_data.json'
with open(filename) as f:
pop_data = json.load(f)
# print(pop_data[1])

# 创建一个包含人口的字典
cc_populations={}
# cc1_populations={}

# 打印每个国家2010年的人口数量
for pop_dict in pop_data:
if pop_dict['Year'] == '2010':
country_name = pop_dict['Country Name']
population = int(float(pop_dict['Value'])) # 字符串数值转化为整数
# print(country_name + ":" + str(population))
code = get_country_code(country_name)
if code:
cc_populations[code] = population
# elif pop_dict['Year'] == '2009':
#     country_name = pop_dict['Country Name']
#     population = int(float(pop_dict['Value'])) # 字符串数值转化为整数
#     # print(country_name + ":" + str(population))
#     code = get_country_code(country_name)
#     if code:
#         cc1_populations[code] = population

cc_pops_1,cc_pops_2,cc_pops_3={},{},{}
for cc,pop in cc_populations.items():
if pop <10000000:
cc_pops_1[cc]=pop
elif pop<1000000000:
cc_pops_2[cc]=pop
else:
cc_pops_3[cc]=pop

# print(len(cc_pops_1),len(cc_pops_2),len(cc_pops_3))

wm_style = RotateStyle('#336699',base_style=LightColorizedStyle)
wm =pygal.maps.world.World(style=wm_style)
wm.title = '2010年世界各国人口统计图'
wm.add('0-10m', cc_pops_1)
wm.add('10m-1bm',cc_pops_2)
wm.add('>1bm',cc_pops_3)
# wm.add('2009', cc1_populations)

wm.render_to_file('world_populations.svg')

7.3 生成结果

countries.py



world_population.py

8 Pygal可视化github仓库

8.1 需求描述

调用web API对GitHub数据仓库进行可视化展示:https://api.github.com/search/repositories?q=language:python&sort=stars

8.2 源码

python_repos.py

# coding=utf-8
import requests
import pygal
from pygal.style import LightColorizedStyle as LCS, LightenStyle as LS

# Make an API call, and store the response.
url = 'https://api.github.com/search/repositories?q=language:python&sort=stars'
r = requests.get(url)
print("Status code:", r.status_code) # 查看请求是否成功，200表示成功

response_dict = r.json()
# print(response_dict.keys())
print("Total repositories:", response_dict['total_count'])

# Explore information about the repositories.
repo_dicts = response_dict['items']
print("Repositories returned:",len(repo_dicts))

# 查看项目信息
# repo_dict =repo_dicts[0]
# print('\n\neach repository:')
# for repo_dict in repo_dicts:
#     print("\nName:",repo_dict['name'])
#     print("Owner:",repo_dict['owner']['login'])
#     print("Stars:",repo_dict['stargazers_count'])
#     print("Repository:",repo_dict['html_url'])
#     print("Description:",repo_dict['description'])
# 查看每个项目的键
# print('\nKeys:',len(repo_dict))
# for key in sorted(repo_dict.keys()):
#     print(key)

names, plot_dicts = [], []
for repo_dict in repo_dicts:
names.append(repo_dict['name'])
plot_dicts.append(repo_dict['stargazers_count'])

# 可视化
my_style = LS('#333366', base_style=LCS)

my_config = pygal.Config() # Pygal类Config实例化
my_config.x_label_rotation = 45 # x轴标签旋转45度
my_config.show_legend = False # show_legend隐藏图例
my_config.title_font_size = 24 # 设置图标标题主标签副标签的字体大小
my_config.label_font_size = 14
my_config.major_label_font_size = 18
my_config.truncate_label = 15 # 较长的项目名称缩短15字符
my_config.show_y_guides = False # 隐藏图表中的水平线
my_config.width = 1000 # 自定义图表的宽度

chart = pygal.Bar(my_config, style=my_style)
chart.title = 'Most-Starred Python Projects on GitHub'
chart.x_labels = names
chart.add('', plot_dicts)
chart.render_to_file('python_repos.svg')

8.3 生成结果

9 参考文献

1 matplotlib官网

2 天气数据官网

3 实验数据下载


4 google charts

5 Plotly

6 Jpgraph