首先十分感谢在博主(Radish_c-CSDN博客)的帮助下,完成了这个实验的1-3关,然后第4-5关就卡住了,然后搜了好久,这个实验4和5平台上只有博主 (Radish_c-CSDN博客)这个需要更改命令行的答案,博主的原文章在这里
Python应用-Scrapy爬虫之拉勾网招聘数据分析-CSDN博客
Python应用-Scrapy爬虫之拉勾网招聘数据分析(4,5关)_最低薪资柱状图csdn-CSDN博客
so,更新了一个可以直接通过的第4关、第5关的代码
第4关
#********** Begin **********#
#1.导入基础包
import numpy as np
import pandas as pd
import matplotlib
# Force matplotlib to not use any Xwindows backend.
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import re
#2.导入文档数据
path = r'step4/'
filePath = path+r'positions.csv'
df = pd.read_csv(filePath,encoding='gbk')
#3.分析数据
b1 = pd.DataFrame(df['salarylow'].value_counts())
b1.sort_index(inplace=True)
X = b1.index.tolist()
Y = list(b1.salarylow)
#4.画图
x = np.arange(len(X))+1
width = 0.5
fig,ax = plt.subplots()
ax.bar(x,Y,width)
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
第5关
#********** Begin **********#
#1.导入基础包
import numpy as np
import pandas as pd
import matplotlib
#强制matplotlib不使用任何Xwindows后端(X Window图形用户接口)
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'
df = pd.read_csv(filePath,encoding = 'gbk')
#3.分析数据
c = pd.DataFrame(df['salarylow'].value_counts())
c.sort_index(inplace=True)
X1 = c.index.tolist()
Y1 = list(c.salarylow)
d = pd.DataFrame(df['salaryhigh'].value_counts())
d.sort_index(inplace=True)
X2 = d.index.tolist()
Y2 = list(d.salaryhigh)
x1 = np.arange(len(X1))+1
x2 = np.arange(len(X2))+1
#4.画图
plt.title('薪资走势图') #给图设置标题
plt.plot(x1, Y1, color='g', label='salarylow')
plt.plot(x2, Y2, color='red', label='salaryhigh')
plt.legend() # 显示图例
plt.xlabel('薪资')
plt.ylabel('职位数')
#********** End **********#
plt.savefig(path+r'/yourimg/'+r'plot.png') #存储图片