百度Python小白逆袭大神7天训练营——day3 《青你2》选手数据分析

本文链接：https://blog.csdn.net/wtlll/article/details/105741726

《青春有你2》选手数据分析

任务描述

基于第二天实践使用Python来爬去百度百科中《青春有你2》所有参赛选手的信息，进行数据可视化分析。
在这里插入图片描述

import sys
sys.path.append('/home/aistudio/external-libraries')
# 下载中文字体
!wget https://mydueros.cdn.bcebos.com/font/simhei.ttf
# 将字体文件复制到matplotlib字体路径
!cp simhei.ttf /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/mpl-data/fonts/ttf/
# 一般只需要将字体文件复制到系统字体目录下即可，但是在aistudio上该路径没有写权限，所以此方法不能用
# !cp simhei.ttf /usr/share/fonts/

# 创建系统字体文件路径
!mkdir .fonts
# 复制文件到该路径
!cp simhei.ttf .fonts/
!rm -rf .cache/matplotlib

绘制选手区域分布柱状图

import matplotlib.pyplot as plt
import numpy as np 
import json
import matplotlib.font_manager as font_manager

#显示matplotlib生成的图形
%matplotlib inline

with open('data/data31557/20200422.json', 'r', encoding='UTF-8') as file:
         json_array = json.loads(file.read())

#绘制小姐姐区域分布柱状图,x轴为地区，y轴为该区域的小姐姐数量

zones = []
for star in json_array:
    zone = star['zone']
    zones.append(zone)
print(len(zones))
print(zones)


zone_list = []
count_list = []

for zone in zones:
    if zone not in zone_list:
        count = zones.count(zone)
        zone_list.append(zone)
        count_list.append(count)

print(zone_list)
print(count_list)

# 设置显示中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体

plt.figure(figsize=(20,15))

plt.bar(range(len(count_list)), count_list,color='r',tick_label=zone_list,facecolor='#9999ff',edgecolor='white')

# 这里是调节横坐标的倾斜度，rotation是度数，以及设置刻度字体大小
plt.xticks(rotation=45,fontsize=20)
plt.yticks(fontsize=20)
!mkdir ./work/result
plt.legend()
plt.title('''《青春有你2》参赛选手''',fontsize = 24)
plt.savefig('/home/aistudio/work/result/bar_result.jpg')
plt.show()

way2

import matplotlib.pyplot as plt
import numpy as np 
import json
import matplotlib.font_manager as font_manager
import pandas as pd

#显示matplotlib生成的图形
%matplotlib inline


df = pd.read_json('data/data31557/20200422.json')
#print(df)

grouped=df['name'].groupby(df['zone'])
s = grouped.count()

zone_list = s.index
count_list = s.values


# 设置显示中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体

plt.figure(figsize=(20,15))

plt.bar(range(len(count_list)), count_list,color='r',tick_label=zone_list,facecolor='#9999ff',edgecolor='white')

# 这里是调节横坐标的倾斜度，rotation是度数，以及设置刻度字体大小
plt.xticks(rotation=45,fontsize=20)
plt.yticks(fontsize=20)
!mkdir ./work/result
plt.legend()
plt.title('''《青春有你2》参赛选手''',fontsize = 24)
plt.savefig('/home/aistudio/work/result/bar_result02.jpg')
plt.show()

请在下面完成作业，对选手体重分布进行可视化，绘制饼状图

import matplotlib.pyplot as plt
import numpy as np 
import json
import matplotlib.font_manager as font_manager

#显示matplotlib生成的图形
%matplotlib inline

with open('data/data31557/20200422.json', 'r', encoding='UTF-8') as file:
         json_array = json.loads(file.read())

#绘制小姐姐区域分布柱状图,x轴为地区，y轴为该区域的小姐姐数量

weight_list= []
for star in json_array:
    weight = star['weight'].strip('kg')
    weight_list.append(weight)
# print(len(weight_list))
# print(weight_list)


weight_label = ['<=45kg', '45~50kg', '50~55kg', '>55kg']
count_list = [0,0,0,0]

for weight in weight_list:
    weight=float(weight)
    if weight <= 45:
        count_list[0]=count_list[0]+1
        continue
    if weight>45 and weight<=50:
        count_list[1]=count_list[1]+1
        continue
    if weight > 50 and weight <= 55:
        count_list[2]=count_list[2]+1
        continue
    if weight>55:
        count_list[3]=count_list[3]+1
        continue



print(weight_label)
print(count_list)

# 设置显示中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体

plt.figure(figsize=(6,6))

# plt.pie(x=count_list ,labels=weight_label,autopct='%1.1f%%',shadow=False,startangle=150)
explode = (0, 0.1, 0, 0)
plt.pie(x=count_list ,explode=explode, labels=weight_label,autopct='%1.1f%%', shadow=False, startangle=90)


plt.axis('equal')
plt.legend()
plt.title('''《青春有你2》参赛选手''',fontsize = 24)
plt.savefig('/home/aistudio/work/result/pie_result.jpg')
plt.show()

方法2

import matplotlib.pyplot as plt
import numpy as np 
import json
import matplotlib.font_manager as font_manager

#显示matplotlib生成的图形
%matplotlib inline

df = pd.read_json('data/data31557/20200422.json')

weights = df['weight']
arrs = weights.values

for i in range(len(arrs)):
    arrs[i] = float(arrs[i] [0:-2])

bin = [0,45,50,55,100]
sel = pd.cut(arrs,bin)

#pandas的value_counts()函数可以对series里面的每个值进行计数并且排序
pd.value_counts(sel)

labels = '<= 45kg','45~50kg','50~55kg','>55kg'
sizes = pd.value_counts(sel)
explode = (0.1,0.1,0,0)

fig1,ax1 = plt.subplots()
ax1.pie(sizes,explode = explode, labels = labels, autopct = '%1.1f%%',shadow = True,startangle = 90)
ax1.axis('equal')
plt.legend(loc = "best")
plt.title('''《青春有你2》参赛选手''',fontsize = 24)
plt.savefig('/home/aistudio/work/result/pie_result.jpg')
plt.show()