数据显示拉勾网

import numpy as np
import pandas as pd
import os
import matplotlib.pyplot as plt
import matplotlib as mlt
import jieba
from pyecharts import Geo
from wordcloud import WordCloud
print(os.getcwd())
import os

from matplotlib.font_manager import FontProperties

指定字体

mlt.rcParams['font.sans-serif'] = ['SimHei']

mlt.rcParams['font.family']='sans-serif' #这个必须指定

设置绘图风格

plt.rcParams["axes.labelsize"] = 16.
plt.rcParams["xtick.labelsize"] = 14.
plt.rcParams["ytick.labelsize"] = 14.
plt.rcParams["legend.fontsize"] = 12.

plt.rcParams["figure.figsize"] = [15., 9.]

headers = ['positionName', 'workYear', 'education', 'jobNature', 'financeStage',

'city','salary','positionAdvantage','companyFullName'] #头部

# 读入数据并显示前几个

扫描二维码关注公众号，回复： 1372130 查看本文章

data = pd.read_csv("lagou.csv",names=headers,encoding="gbk") # 一定要指定encoding

data.dropna() # 去除None值

data.head()

# 画图横

data['workYear'].value_counts().plot(kind='barh')

# 竖

data['workYear'].value_counts().plot(kind='bar')

结巴分词

list(jieba.cut('python工程师')) # ['python','‘工程师’]

final = ''
stopwords = ['PYTHON','python','Python','工程师','（','）','/'] # 停止词
for n in range(data.shape[0]):

seg_list = list(jieba.cut(data['positionName'][n]))

for seg in seg_list:
if seg not in stopwords:
final = final + seg + ' '

# final 得到的词汇

# 指定可以显示中文的字体，否则不能显示中文
my_wordcloud = WordCloud(font_path = r'C:\Windows\Fonts\simkai.ttf',width=1000,height=600).generate(final)
plt.imshow(my_wordcloud) # 显示图片
plt.axis('off')

plt.rcParams["figure.figsize"] = [10., 10.] # 指定为圆和大小
data['workYear'].value_counts().plot(kind='pie',autopct='%1.2f%%',explode=np.linspace(0,0.2,6))

# explode 中6是块数必须一致 0.5 是程度可以自行测试

import re
# 提取数据框
data2 = list(map(lambda x:(data['city'][x],eval(re.split('k|K',data['salary'][x])[0])*1000),range(len(data))))
# 提取价格信息
data3 = pd.DataFrame(data2)
# 转化成Geo需要的格式

data4 = list(map(lambda x:(data3.groupby(0).mean()[1].index[x],data3.groupby(0).mean()[1].values[x]),range(len(data3.groupby(0)))))

# 地理位置展示
geo = Geo("全国Python工资布局", "制作人:挖掘机小王子", title_color="#fff", title_pos="left", width=1200, height=600,background_color='#404a59')
attr, value = geo.cast(data4)
geo.add("", attr, value, type="heatmap", is_visualmap=True, maptype='china', visual_range=[0, 300], visual_text_color='#fff')
# 中国地图Python工资，此分布是最低薪资
geo.render()

# 地理位置展示样式不同
geo = Geo("全国Python工资布局", "制作人:chase", title_color="#fff", title_pos="left", width=1200, height=600,background_color='#404a59')
attr, value = geo.cast(data4)
geo.add("", attr, value, type="effectScatter", is_visualmap=True, maptype='china', visual_range=[0, 300], visual_text_color='#fff')
# 中国地图Python工资，此分布是最低薪资
geo.render()

使用之前还要安装三个包

pip install echarts-countries-pypkg

pip install echarts-china-provinces-pypkg

pip install echarts-china-cities-pypkg 地图包

猜你喜欢