头歌实训答案:招聘数据分析

我不是卡夫卡

已于 2024-02-07 08:52:40 修改

阅读量1k

点赞数

分类专栏：头歌实训文章标签：数据分析 matplotlib python

于 2022-06-24 23:03:15 首次发布

本文链接：https://blog.csdn.net/qq_53776431/article/details/125453571

版权

头歌实训专栏收录该内容

7 篇文章 7 订阅

订阅专栏

import pymongo
from pymongo import MongoClient
class Lagou01Pipeline(object):
    def open_spider(self,spider):
        self.db = MongoClient('localhost',27017).lagou_db
        self.collection = self.db.lagou_collection
    def process_item(self, item, spider):
        self.collection.insert_one(dict(item))
        return item

#********** Begin **********#
#1.导入基础包
import numpy as np  
import pandas as pd  
import matplotlib.pyplot as plt  
import re  
#2.读取数据
path = r'step2/'  
filePath = path+r'positions.csv'  
display_column = ["salarylow","salaryhigh","company","positionname","index_id","position"]
df = pd.read_csv(filePath,encoding='gbk')  

#3.重新设置列的顺序
df = df.reindex(columns=display_column)  
#********** End **********#
d5 = df.head()
print(d5)  #显示前5行数据


#********** Begin **********#
#1.导入基础包
import numpy as np  
import pandas as pd  
import matplotlib  
 
matplotlib.use('Agg')  
import matplotlib.pyplot as plt  
import re  

# 防止中文乱码
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
matplotlib.rcParams['font.family']='sans-serif'

#2.导入文档数据
path = r'step3/'  
filePath = path+r'positions.csv'  
display_column = ['edu','index']  
df = pd.read_csv(filePath,encoding='gbk')  
df = df.reindex(columns=display_column)  
#3.分析数据
X = ['本科','大专','不限','硕士','博士']
Y = df['edu'].value_counts().tolist()
sum = df['edu'].value_counts().sum()
#4.画图
fig,ax = plt.subplots()    
ax.pie(Y/sum,autopct='%1.1f%%',labels=X)  
fig.set_size_inches(7,7)                 
#********** End **********#
plt.savefig(path+r'/yourimg/'+r'pie.png') #存储图片

#********** Begin **********#
#1.导入基础包
import numpy as np  
import pandas as pd  
import matplotlib.pyplot as plt  
import re  
#2.导入文档数据
path = r'step4/'  
filePath = path+r'positions.csv'  
display_column = ['salarylow']
df = pd.read_csv(filePath,encoding='gbk')  
df = df.reindex(columns=display_column)  
#3.分析数据
data = df['salarylow'].value_counts().sort_index()   
X = data.index
Y = data.tolist()    
#4.画图
x = np.arange(len(X)) + 1     
width = 0.5            
fig,ax = plt.subplots()  
ax.bar(x,Y,width,alpha = 1)  

for p in ax.patches:  
   ax.annotate(str(p.get_height()), xy=(p.get_x(), p.get_height()))  
#********** End **********#
plt.savefig(path+r'/yourimg/'+r'bar.png') #存储图片

#********** Begin **********#
#1.导入基础包
import numpy as np  
import pandas as pd  
import matplotlib  
matplotlib.use('Agg')  
import matplotlib.pyplot as plt  
import re  

# 防止中文乱码
matplotlib.rcParams['font.sans-serif'] = ['SimHei']
matplotlib.rcParams['font.family']='sans-serif'

#2.导入文档数据
path = r'step5/'  
filePath = path+r'positions.csv'  
display_column = ['salarylow','salaryhigh']
df = pd.read_csv(filePath,encoding='gbk')  
df = df.reindex(columns=display_column)  
#3.分析数据
datalow = df['salarylow'].value_counts().sort_index().values
datahigh = df['salaryhigh'].value_counts().sort_index().values
Xlow = np.arange(len(datalow)) + 1
Xhigh = np.arange(len(datahigh)) + 1
Ylow = datalow
Yhigh = datahigh

#4.画图
plt.title('薪资走势图')   
plt.plot(Xlow, Ylow, color='green', label='salarylow')  
plt.plot(Xhigh, Yhigh, color='red', label='salaryhigh')  
plt.legend() # 显示图例   
plt.xlabel('薪资')  
plt.ylabel('职位数')  
plt.show() 
#********** End **********#
plt.savefig(path+r'/yourimg/'+r'plot.png') #存储图片