【Python数据分析】可视化图表分析拉钩网招聘数据

前言

上次我们爬了拉钩网的数据，现在我们来分析下，看看哪些公司的招聘信息具体需求都是哪些，让我们用可视化图表展示

导入所需模块

import numpy as np
import pandas as pd
from pyecharts.charts import *
from pyecharts import options as opts
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
from pyecharts.globals import ThemeType

对于本篇文章有疑问的同学可以加【资料白嫖、解答交流群：1039649593】

清洗数据

导入数据

df = pd.read_csv('data.csv', encoding='UTF-8')
df.head()

查看整体性描述

df.info()

df.describe()

删除重复值

df.drop_duplicates(inplace = True)
df.duplicated().sum()

获取

df['地区'] = df['地区'].apply(lambda x:x.split('-')[0])
df['地区'].unique()

df['经验'].unique()

df['薪资'].unique()

df['m_max'] = df['薪资'].str.extract('(\d+)')#提取出最低薪资
df['m_min'] = df['薪资'].str.extract('(\d+)K')#提取出最高薪资
df['m_max'] = df['m_max'].apply('float64')#转换数据类型
df['m_min'] = df['m_min'].apply('float64')
df['平均薪资'] = (df['m_max']+df['m_min'])/2
df.head()

可视化

每个地区的招聘数量

dq = df.groupby('地区').count()['标题']
dq_index = dq.index.tolist()
dq_value = dq.values.tolist()

bar1 = (Bar(init_opts=opts.InitOpts(width='800px', height='400px',theme=ThemeType.MACARONS))
       .add_xaxis(dq_index)
       .add_yaxis('', dq_value,category_gap="50%")
       .set_global_opts(title_opts=opts.TitleOpts(title="每个地区的招聘数量"),
                       xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-50)),
                        visualmap_opts=opts.VisualMapOpts(max_=80),#彩色块
                        datazoom_opts=[opts.DataZoomOpts()]#拉动条形轴
                        )
      )
bar1.render_notebook()

经验学历需求图

pair_1 = [(i, int(j)) for i, j in zip(jingyan.index,jingyan.values)]
pie = (
    Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS,width='1000px',height='600px'))
    
    .add('', pair_1, radius=['40%', '70%'])
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%"))
    .set_global_opts(
        title_opts=opts.TitleOpts(
            title="经验学历需求图", 
            pos_left='center', 
            pos_top='center',
            title_textstyle_opts=opts.TextStyleOpts(
                color='black', 
                font_size=20, 
                font_weight='bold'
            ),
        )
    )
    
)
pie.render_notebook()

招聘公司所在领域

gongsi = df.groupby('经验').count()['标题']
pie1 = (
    Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS,width='1500px',height='600px'))
    .add(
        "",
        [list(z) for z in zip(gongsi.index.tolist(), gongsi.values.tolist())],
        radius=["20%", "80%"],
        center=["25%", "70%"],
        rosetype="radius",
        label_opts=opts.LabelOpts(is_show=False),
    ).set_global_opts(title_opts=opts.TitleOpts(title="招聘公司所在领域"))
)
pie1.render_notebook()