Is there anyone who can't analyze these data cases? A trick to teach you how to visualize recruitment data~

Hey, everyone, good duck ！ I'm a panda

I wonder if everyone has found their favorite job ？

This thing is similar to dating , Pay attention to a two-way rush ~

If you say too much, it's tears … Let's just look at the code ~

Code

what are you having? python I won't answer the related error report 、 Or source code information / Module installation / Women's clothing bosses are proficient in skills You can come here ：（https://jq.qq.com/?_wv=1027&k=2Q3YTfym） perhaps +V：python10010 Ask my assistant sister

import pandas as pd
from pyecharts.charts import *
from pyecharts import options as opts
import re
from pyecharts.globals import ThemeType
from pyecharts.commons.utils import JsCode
python Learning exchange group ：660193417###

、#  Reading data 
df = pd.read_csv(" Recruitment data .csv")
df.head()

df.info()

df[' Salary '].unique()
df['bottom']=df[' Salary '].str.extract('^(\d+).*')
df['top']=df[' Salary '].str.extract('^.*?-(\d+).*')
df['top'].fillna(df['bottom'],inplace=True)

df['commision_pct']=df[' Salary '].str.extract('^.*?·(\d{2}) pay ')
df['commision_pct'].fillna(12,inplace=True)
df['commision_pct']=df['commision_pct'].astype('float64')
df['commision_pct']=df['commision_pct']/12

df.dropna(inplace=True)

df['bottom'] = df['bottom'].astype('int64')
df['top'] = df['top'].astype('int64')
df[' Average salary '] = (df['bottom']+df['top'])/2*df['commision_pct']
df[' Average salary '] = df[' Average salary '].astype('int64')

df.head()

df[' Salary '] = df[' Salary '].apply(lambda x:re.sub('.* thousand / month ', '0.3-0.7 ten thousand / month ', x))
df[" Salary "].unique()

df['bottom'] = df[' Salary '].str.extract('^(.*?)-.*?')
df['top'] = df[' Salary '].str.extract('^.*?-(\d\.\d|\d)')
df.dropna(inplace=True)
df['bottom'] = df['bottom'].astype('float64')
df['top'] = df['top'].astype('float64')
df[' Average salary '] = (df['bottom']+df['top'])/2 * 10
df.head()

mean = df.groupby(' Education ')[' Average salary '].mean().sort_values()
x = mean.index.tolist()
y = mean.values.tolist()
c = (
    Bar()
    .add_xaxis(x)
    .add_yaxis(
        " Education ",
        y
    )
    .set_global_opts(title_opts=opts.TitleOpts(title=" Average salary for different degrees "),datazoom_opts=opts.DataZoomOpts())
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
)
c.render_notebook()

color_js = """new echarts.graphic.LinearGradient(0, 1, 0, 0,
    [{offset: 0, color: '#63e6be'}, {offset: 1, color: '#0b7285'}], false)"""

color_js1 = """new echarts.graphic.LinearGradient(0, 0, 0, 1, [{
                            offset: 0,
                            color: '#ed1941'
                        }, {
                            offset: 1,
                            color: '#009ad6'
                        }], false)"""

dq = df.groupby(' City ')[' Position '].count().to_frame(' Number ').sort_values(by=' Number ',ascending=False).reset_index()
x_data = dq[' City '].values.tolist()[:20]
y_data = dq[' Number '].values.tolist()[:20]
b1 = (
        Bar(init_opts=opts.InitOpts(theme=ThemeType.DARK,bg_color=JsCode(color_js1),width='1000px',height='600px'))
        .add_xaxis(x_data)
        .add_yaxis('',
                   y_data ,
                   category_gap="50%",
                   label_opts=opts.LabelOpts(
                        font_size=12,
                        color='yellow',
                        font_weight='bold', 
                        font_family='monospace',
                        position='insideTop',  
                        formatter = '{b}\n{c}'  
                    ),
                  )
        .set_series_opts(
            itemstyle_opts={
                "normal": {
                    "color": JsCode(color_js),
                    "barBorderRadius": [15, 15, 0, 0],
                    "shadowColor": "rgb(0, 160, 221)",
                }
            }
        )
        .set_global_opts(
            title_opts=opts.TitleOpts(title=' recruit   To hire   Count   The amount   front  20  Of   city   City   District   Domain ',
                                       title_textstyle_opts=opts.TextStyleOpts(color="yellow"),
                                       pos_top='7%',pos_left = 'center'
                                     ),
            legend_opts=opts.LegendOpts(is_show=False),
            xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
            yaxis_opts=opts.AxisOpts(name="",
                                     name_location='middle',
                                     name_gap=40,
                                     name_textstyle_opts=opts.TextStyleOpts(font_size=16)),
                         datazoom_opts=[opts.DataZoomOpts(range_start=1,range_end=50)]
                        )

    )
b1.render_notebook()
python Learning exchange group ：660193417###

boss = df[' Education '].value_counts()
x = boss.index.tolist()
y = boss.values.tolist()
data_pair = [list(z) for z in zip(x, y)]
c = (
    Pie(init_opts=opts.InitOpts(width="1000px", height="600px", bg_color="#2c343c"))
    .add(
        series_name=" Proportion of educational needs ",
        data_pair=data_pair,
        label_opts=opts.LabelOpts(is_show=False, position="center", color="rgba(255, 255, 255, 0.3)"),
    )
    .set_series_opts(
        tooltip_opts=opts.TooltipOpts(
            trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"
        ),
        label_opts=opts.LabelOpts(color="rgba(255, 255, 255, 0.3)"),
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(
            title=" Proportion of educational needs ",
            pos_left="center",
            pos_top="20",
            title_textstyle_opts=opts.TextStyleOpts(color="#fff"),
        ),
        legend_opts=opts.LegendOpts(is_show=False),
    )
    .set_colors(["#D53A35", "#334B5C", "#61A0A8", "#D48265", "#749F83"])
)
c.render_notebook()

boss = df[' Experience '].value_counts()
x = boss.index.tolist()
y = boss.values.tolist()
data_pair = [list(z) for z in zip(x, y)]
c = (
    Pie(init_opts=opts.InitOpts(width="1000px", height="600px", bg_color="#2c343c"))
    .add(
        series_name=" Proportion of experience demand ",
        data_pair=data_pair,
        label_opts=opts.LabelOpts(is_show=False, position="center", color="rgba(255, 255, 255, 0.3)"),
    )
    .set_series_opts(
        tooltip_opts=opts.TooltipOpts(
            trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"
        ),
        label_opts=opts.LabelOpts(color="rgba(255, 255, 255, 0.3)"),
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(
            title=" Proportion of experience demand ",
            pos_left="center",
            pos_top="20",
            title_textstyle_opts=opts.TextStyleOpts(color="#fff"),
        ),
        legend_opts=opts.LegendOpts(is_show=False),
    )
    .set_colors(["#D53A35", "#334B5C", "#61A0A8", "#D48265", "#749F83"])
)
c.render_notebook()

boss = df[' Company area '].value_counts()
x = boss.index.tolist()
y = boss.values.tolist()
data_pair = [list(z) for z in zip(x, y)]
c = (
    Pie(init_opts=opts.InitOpts(width="1000px", height="600px", bg_color="#2c343c"))
    .add(
        series_name=" The company's field accounts for ",
        data_pair=data_pair,
        label_opts=opts.LabelOpts(is_show=False, position="center", color="rgba(255, 255, 255, 0.3)"),
    )
    .set_series_opts(
        tooltip_opts=opts.TooltipOpts(
            trigger="item", formatter="{a} <br/>{b}: {c} ({d}%)"
        ),
        label_opts=opts.LabelOpts(color="rgba(255, 255, 255, 0.3)"),
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(
            title=" The company's field accounts for ",
            pos_left="center",
            pos_top="20",
            title_textstyle_opts=opts.TextStyleOpts(color="#fff"),
        ),
        legend_opts=opts.LegendOpts(is_show=False),
    )
    .set_colors(["#D53A35", "#334B5C", "#61A0A8", "#D48265", "#749F83"])
)
c.render_notebook()

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
boss = df[' Experience '].value_counts()
x = boss.index.tolist()
y = boss.values.tolist()
data_pair = [list(z) for z in zip(x, y)]

c = (
    Pie()
    .add("", data_pair)
    .set_colors(["blue", "green", "yellow", "red", "pink", "orange", "purple"])
    .set_global_opts(title_opts=opts.TitleOpts(title=" Proportion of experience requirements "))
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.render_notebook()

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker
boss = df[' Experience '].value_counts()
x = boss.index.tolist()
y = boss.values.tolist()
data_pair = [list(z) for z in zip(x, y)]

c = (
    Pie()
    .add(
        "",
        data_pair,
        radius=["40%", "55%"],
        label_opts=opts.LabelOpts(
            position="outside",
            formatter="{a|{a}}{abg|}\n{hr|}\n {b|{b}: }{c}  {per|{d}%}  ",
            background_color="#eee",
            border_color="#aaa",
            border_width=1,
            border_radius=4,
            rich={
                "a": {"color": "#999", "lineHeight": 22, "align": "center"},
                "abg": {
                    "backgroundColor": "#e3e3e3",
                    "width": "100%",
                    "align": "right",
                    "height": 22,
                    "borderRadius": [4, 4, 0, 0],
                },
                "hr": {
                    "borderColor": "#aaa",
                    "width": "100%",
                    "borderWidth": 0.5,
                    "height": 0,
                },
                "b": {"fontSize": 16, "lineHeight": 33},
                "per": {
                    "color": "#eee",
                    "backgroundColor": "#334455",
                    "padding": [2, 4],
                    "borderRadius": 2,
                },
            },
        ),
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="python Recruitment experience requirements "))
    
)
c.render_notebook()

gsly = df[' Company area '].value_counts()[:10]
x1 = gsly.index.tolist()
y1 = gsly.values.tolist()
c = (
    Bar()
    .add_xaxis(x1)
    .add_yaxis(
        " Company area ",
        y1
    )
    .set_global_opts(title_opts=opts.TitleOpts(title=" Company area "),datazoom_opts=opts.DataZoomOpts())
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
)
c.render_notebook()

gsgm = df[' The company size '].value_counts()[1:10]
x2 = gsgm.index.tolist()
y2 = gsgm.values.tolist()
c = (
    Bar()
    .add_xaxis(x2)
    .add_yaxis(
        " The company size ",
        y2
    )
    .set_global_opts(title_opts=opts.TitleOpts(title=" The company size "),datazoom_opts=opts.DataZoomOpts())
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
)
c.render_notebook()

import stylecloud
from PIL import Image
welfares = df[' welfare '].dropna(how='all').values.tolist()
welfares_list = []
for welfare in welfares:
    welfares_list += welfare.split(',')
pic_name = ' Welfare word cloud .png'
stylecloud.gen_stylecloud(
    text=' '.join(welfares_list),
    font_path='msyh.ttc',
    palette='cartocolors.qualitative.Bold_5',
    max_font_size=100,
    icon_name='fas fa-yen-sign',
    background_color='#212529',
    output_name=pic_name,
    )
Image.open(pic_name)

effect （ part ）

what are you having? python I won't answer the related error report 、 Or source code information / Module installation / Women's clothing bosses are proficient in skills You can come here ：（https://jq.qq.com/?_wv=1027&k=2Q3YTfym） perhaps +V：python10010 Ask my assistant sister

This is the end of the article , I hope you are learning to help ~

I'm a panda , See you in the next article (*◡‿◡)