什么你还不知道招聘信息，小唐来教你——最新2021取拉勾网招聘信息（二）

import pandas as pd
import re
import seaborn as sns
import matplotlib.pyplot as plt
from wordcloud import WordCloud
import cv2
#这里是为了让我们的中文可以显示出来
font = r'C:\Windows\Fonts\simfang.ttf'
plt.rcParams['font.sans-serif'] = ["SimHei"]
plt.rcParams["axes.unicode_minus"] = False

def ciyun():
    df = pd.read_excel('工程师.xls')#这个就是我们要分析的表
    for i in range(df.shape[0]):
        gz = df.loc[i, '工资']#选择工资那一列
        if re.search(r'.*k-.*k', gz):
            a = eval(re.search('(.*)k-(.*)k', gz).group(1)) * 1000
            b = eval(re.search('(.*)k-(.*)k', gz).group(2)) * 1000
            num = (a + b) / 2#求平均值
        try:
            df.loc[i, '工资'] = int(num)/1000
        except:
            print("跳过")
            df.loc[i, '工资'] =0
    visualization(df)#将我们洗好的数据传到我们下一个制作图表里面

def visualization(df):
    salarys=df['工资']
    for i in salarys:
        print(i)
    mean = round(salarys.mean(), 1)#求我们的平均值
    plt.figure(figsize=(8, 6), dpi=200)#确定下来我们的行列数
    sns.distplot(salarys, hist=True, kde=True, kde_kws={"color": "r", "linewidth": 1.5, 'linestyle': '-'})#画核密度图
    plt.axvline(mean, color='r', linestyle=":")#在中间值那里画一条红线
    plt.text(mean, 0.05, '平均月薪: %.1f千' % (mean), color='k', horizontalalignment='center', fontsize=15)#在红线中间输出中间值是多少
    plt.xlim(0, 35)
    plt.xlabel('月薪（单位：千）')
    plt.title('工程师行业的薪资分布')
    plt.show()
    a = df['需求']#这里可以更改，可以显示地区呀，需求呀的词云
    text = []
    n = 0
    #统计词频
    for i in a:
        text.append(i)
        n += 1
    text = ",".join(str(i) for i in text)
    mask = cv2.imread(r'D:\data\timg.jpg')#这个是我们的要他形成的一个形状，没有的话可以删掉这一行，记得后面的mask也要删掉喔
    wordcloud = WordCloud(font_path=font, background_color="white", mask=mask).generate(text)
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.show()

import pandas as pd
import re
import seaborn as sns
import matplotlib.pyplot as plt
from wordcloud import WordCloud
import cv2
font = r'C:\Windows\Fonts\simfang.ttf'
plt.rcParams['font.sans-serif'] = ["SimHei"]
plt.rcParams["axes.unicode_minus"] = False
def ciyun():
    df = pd.read_excel('工程师.xls')
    for i in range(df.shape[0]):
        gz = df.loc[i, '工资']
        if re.search(r'.*k-.*k', gz):
            a = eval(re.search('(.*)k-(.*)k', gz).group(1)) * 1000
            b = eval(re.search('(.*)k-(.*)k', gz).group(2)) * 1000
            num = (a + b) / 2
        try:
            df.loc[i, '工资'] = int(num)/1000
        except:
            print("跳过")
            df.loc[i, '工资'] =0
    visualization(df)
def visualization(df):
    salarys=df['工资']
    for i in salarys:
        print(i)
    mean = round(salarys.mean(), 1)
    plt.figure(figsize=(8, 6), dpi=200)
    sns.distplot(salarys, hist=True, kde=True, kde_kws={"color": "r", "linewidth": 1.5, 'linestyle': '-'})
    plt.axvline(mean, color='r', linestyle=":")
    plt.text(mean, 0.05, '平均月薪: %.1f千' % (mean), color='k', horizontalalignment='center', fontsize=15)
    plt.xlim(0, 35)
    plt.xlabel('月薪（单位：千）')
    plt.title('工程师行业的薪资分布')
    plt.show()
    a = df['需求']
    text = []
    n = 0
    for i in a:
        text.append(i)
        n += 1
    text = ",".join(str(i) for i in text)
    wordcloud = WordCloud(font_path=font, background_color="white").generate(text)
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.show()
ciyun()