-
-
-
不同岗位类型在不同城市下的平均薪资图(单位:K)北京地区各岗位数量图各大公司招聘岗位数top10
-
{% for item in ll %}
{{ item }}
{% endfor %}
django读取csv文件数据生成可视化系统
Django是一个高效、灵活的Python Web框架，它可以快速地构建Web应用程序。在本篇文章中，我们将介绍如何使用django读取csv文件生成数据可视化系统。
1.使用虚拟环境创建项目
pip install virtualenv
pip install virtualenvwrapper
2.安装django模块,可使用代码 pip install django 进行安装,也可以在Pycharm的Python解释器下”+”安装
pip install django3.创建项目,因为爬取的数据可能审核不通过,所以就不发了,读取的csv文件我们放到一个文件夹中
django-admin startproject bishe-master
4.创建app
cd bishe-master
python manage.py startapp User5..设置setting.py文件代码
INSTALLED_APPS = [
'simpleui',
'django.contrib.admin',
'django.contrib.auth',
'django.contrib.contenttypes',
'django.contrib.sessions',
'django.contrib.messages',
'django.contrib.staticfiles',
'user.apps.UserConfig',
'import_export',
]
MIDDLEWARE = [
'django.middleware.security.SecurityMiddleware',
'django.contrib.sessions.middleware.SessionMiddleware',
'django.middleware.common.CommonMiddleware',
# 'django.middleware.csrf.CsrfViewMiddleware',
'django.contrib.auth.middleware.AuthenticationMiddleware',
'django.contrib.messages.middleware.MessageMiddleware',
# 'django.middleware.clickjacking.XFrameOptionsMiddleware',
]
ROOT_URLCONF = 'testdjango.urls'
TEMPLATES = [
{
'BACKEND': 'django.template.backends.django.DjangoTemplates',
'DIRS': [os.path.join(BASE_DIR, 'templates')],
'APP_DIRS': True,
'OPTIONS': {
'context_processors': [
'django.template.context_processors.debug',
'django.template.context_processors.request',
'django.contrib.auth.context_processors.auth',
'django.contrib.messages.context_processors.messages',
],
},
},
]
WSGI_APPLICATION = 'testdjango.wsgi.application'
# Database
# https://docs.djangoproject.com/en/2.2/ref/settings/#databases
DATABASES = {
'default': {
'ENGINE': 'django.db.backends.mysql',
'NAME': 'test',
'HOST': '127.0.0.1',
'PORT': '3306',
'USER': 'bd',
'PASSWORD': '123456',
}
}
# Password validation
# https://docs.djangoproject.com/en/2.2/ref/settings/#auth-password-validators
AUTH_PASSWORD_VALIDATORS = [
# {
# 'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
# },
{
'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
},
]
# Internationalization
# https://docs.djangoproject.com/en/2.2/topics/i18n/
# 语言
# 时区
TIME_ZONE = 'Asia/Shanghai'
USE_I18N = True
USE_L10N = True
USE_TZ = True
# Static files (CSS, JavaScript, Images)
# https://docs.djangoproject.com/en/2.2/howto/static-files/
STATIC_URL = '/static/'
STATICFILES_DIRS = os.path.join(BASE_DIR, 'static'),
# SIMPLEUI_HOME_PAGE = '/echart/?type=index'
6.testdjango/urls.py配置,在这里定义了项目中所有可访问的 URL 地址和对应的视图函数
from django.contrib import admin
from django.urls import path,re_path
from user import views
from django.urls import include # 导入include
from django.views.generic import RedirectView
urlpatterns = [
path('admin/', admin.site.urls),
re_path(r'^$',views.zhuce),
path('ceshi2/', views.ceshi2),
path('test_pic',views.test_pic),
path('denglu/',views.denglu),
path('zhuce/', views.zhuce),
path('pie_bar_test', views.pie_bar_test),
path('job_demand',views.job_demand),
path('xinzi_bar', views.xinzi_bar),
path('xinzi_predict',views.xinzi_predict),
]
8.user/models.py配置,这里定义了四个Django模型：job、stu、comp和test。每个模型都有不同的字段，例如job模型有岗位名称、能力要求、地点、公司名、公司规模、公司薪资等字段。同时，每个模型都定义了Meta类，用于设置模型的元数据，例如verbose_name_plural字段用于设置模型在Admin后台显示的名称。
from django.db import models
# Create your models here.
class job(models.Model):
job_name = models.CharField('岗位名称', max_length=20, null=True)
work_demand = models.CharField('能力要求', max_length=80, null=True)
company_locale = models.CharField('地点', max_length=20, null=True)
company_name = models.CharField('公司名', max_length=100, null=True)
guimo = models.CharField('公司规模', max_length=20, null=True)
job_salary = models.CharField('公司薪资', max_length=20, null=True)
job_salary_fif = models.BooleanField('薪资是否不超过15K', choices=((True, '是'), (False, '否')), null=True)
demand = models.CharField('demand', max_length=20, null=True)
def __unicode__(self):
return self.job_name
class Meta:
verbose_name_plural = '招聘岗位信息表'
class stu(models.Model):
name = models.CharField(max_length=20, unique=True, verbose_name='姓名') # ,help_text='不要写小名'
gender = models.BooleanField('性别', choices=((True, '女'), (False, '男')))
age = models.IntegerField(default=18, verbose_name='年纪')
stuid = models.CharField(max_length=20, verbose_name='学号（登录账号）')
password = models.CharField('登录密码', max_length=20, null=True)
stuclass = models.CharField(max_length=20, verbose_name='班级')
academy = models.CharField(max_length=20, verbose_name='学院')
ability = models.TextField(blank=True, null=True, verbose_name='技能') # 可插入为空或设置default
def __str__(self):
return self.name
class Meta:
verbose_name_plural = '学生信息表'
class comp(models.Model):
name = models.CharField(max_length=20, verbose_name='公司名')
type = models.CharField(max_length=20, verbose_name='类型')
def __unicode__(self):
return self.name
class Meta:
verbose_name_plural = '公司信息表'
class test(models.Model):
uname = models.CharField(max_length=32)
upwd = models.CharField(max_length=64)
9.user/tests.py配置,在这里定义了两个资源类（StuResource和JobResource），用于将模型（Model）转换为CSV、JSON、XML等格式。这里使用了import_export库来实现这个功能。在这个库中，资源类（Resource）用于定义如何将模型转换为其他格式，Meta类用于指定模型、导入ID字段和排除字段等信息。具体来说，StuResource将模型stu转换为其他格式，JobResource将模型job转换为其他格式
from import_export import resources
from .models import *
class StuResource(resources.ModelResource):
class Meta:
model = stu
# import_id_fields = ['id','name','stuid','stuclass','academy', 'ability', 'age','gender']
# exclude = ['id'] #排除id
#上一行决定了update_or_create，可以避免重复导入
class JobResource(resources.ModelResource):
class Meta:
model = job10.user/views.py配置,在这里是处理用户输入的数据，将其存储在列表中，并且根据用户选择的职位类型，读取相应的数据文件。然后将城市、需求和公司规模等信息也加入到列表中，最后将这个列表作为参数传入到forest函数中进行预测,这里面是一个视图函数，用于生成总的岗位数量的饼图和柱状图。它首先读取一个CSV文件，并将其中的数据转换为DataFrame格式。然后，它从DataFrame中过滤出所有职位名称不为“其他职业”的数据，并统计每个职位名称出现的次数。接着，它将职位名称和出现次数分别存储在pie_data_index和pie_data中，并将它们组合成一个字典列表data。最后，它将这些数据传递给一个HTML模板，用于生成饼图和柱状图。
from django.shortcuts import render, redirect
import pandas as pd
from user.models import *
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
# 核心算法函数
def forest(list, df):
df['job_salary_range'] = df['job_salary_range'].astype(str).map({'0-10K': 0, '10-20K': 1, '20-30K': 2, '>30K': 3})
y = df['job_salary_range']
x = df.drop(labels=['job_salary_range', 'job_name', 'company_name'], axis=1) # 删除掉无关列
x = pd.get_dummies(x) # 独热编码
xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.2, random_state=5) # test_size是x，y测试集占总的20%
rfc = RandomForestClassifier(max_depth=None, min_samples_split=2,
random_state=0) # 实例化rfc = rfc.fit(xtrain, ytrain) #用训练集数据训练
rfc = rfc.fit(xtrain, ytrain)
# result = rfc.score(xtest, ytest) # 导入测试集，rfc的接口score计算的是模型准确率accuracy
res = rfc.predict(list)
return res
def xinzi_predict(request):
if request.method == 'GET':
return render(request, 'predict_xinzi.html')
else:
list1 = []
list_sum = []
java1 = request.POST.get('java1') # JAVA要求
spring1 = request.POST.get('spring1')
sql1 = request.POST.get('sql1')
python1 = request.POST.get('python1') # Python要求
linux1 = request.POST.get('linux1')
spider1 = request.POST.get('spider1')
html1 = request.POST.get('html1') # web要求
cssjs1 = request.POST.get('cssjs1')
vue1 = request.POST.get('vue1')
jiqi1 = request.POST.get('jiqi1') # 算法工程师要求
tuxiang1 = request.POST.get('tuxiang1')
C1 = request.POST.get('C1')
city = request.POST.get('city')
demand = request.POST.get('demand')
guimo = request.POST.get('guimo')
a = request.POST.get('job_name')
global df # 声明全局变量
if a == 'Java开发工程师':
list1.append(java1)
list1.append(spring1)
list1.append(sql1)
df = pd.read_csv('C:\\pythonProject\\pythonProject2\\bishe-master\\data_sum\\updata_java_ceshi222.csv',
encoding='gbk')
elif a == 'Python开发工程师':
list1.append(python1)
list1.append(linux1)
list1.append(spider1)
df = pd.read_csv('C:\\pythonProject\\pythonProject2\\bishe-master\\data_sum\\updata_python_ceshi.csv',
encoding='gbk')
elif a == 'web前端开发师':
list1.append(html1)
list1.append(cssjs1)
list1.append(vue1)
df = pd.read_csv('C:\\pythonProject\\pythonProject2\\bishe-master\\data_sum\\updata_web_ceshi.csv',
encoding='gbk')
elif a == '算法工程师':
list1.append(jiqi1)
list1.append(tuxiang1)
list1.append(C1)
df = pd.read_csv('C:\\pythonProject\\pythonProject2\bishe-master\\data_sum\\updata_suanfa_ceshi.csv',
encoding='gbk')
city = city.split(',')
list1.extend(city)
demand = demand.split(',')
list1.extend(demand)
guimo = guimo.split(',')
list1.extend(guimo)
list_sum.append(list1) # 得到双中括号包起来的列表，并且里面的元素都变成了算法可以直接调用的元素
res = forest(list_sum, df)
if res[0] == 0:
message = '预测薪资范围是每月5-10K'
elif res[0] == 1:
message = '预测薪资范围是每月10-20K'
elif res[0] == 2:
message = '预测薪资范围是每月20-30K'
else:
message = '预测薪资范围是每月在30k以上'
return render(request, 'predict_xinzi.html', {'message': message})
def ceshi2(request):
return render(request
, 'ceshi2.html',
{
'name': 'all',
'users': ['ab', 'qwe'],
'user_dict': {'k1': 'v1', 'k2': 'v2'},
'us': [
{'id': 1, 'name': 'xiaomm', 'email': '[email protected]'},
{'id': 2, 'name': 'xoapxaopx', 'email': '[email protected]'},
]
}
)
def job_demand(request):
return render(request, 'job_demand_pie_sum.html', )
def xinzi_bar(request):
return render(request, 'xinzi_bar_sum.html')
def denglu(request):
if request.method == "GET":
return render(request, 'zhuce.html')
else:
name = request.POST.get('username')
pwd = request.POST.get('password')
test = stu.objects.filter(stuid=name, password=pwd)
name = test.values('name')[0]['name'] # 通过学号和登录密码查询到学生的姓名
if test:
return render(request, 'zhuye.html', {'username': name})
else:
error_msg = '用户名或密码错误'
return render(request, 'zhuce.html', {"error_msg": error_msg})
def zhuce(request):
if request.method == "POST":
name = request.POST.get("uname")
stuid = request.POST.get("stuid")
if stu.objects.filter(stuid=stuid):
return render(request, 'zhuce.html', {"message": '该账号已存在，请重新注册！'})
aca = request.POST.get("aca")
clas = request.POST.get("class")
password = request.POST.get("password")
age = request.POST.get("age")
stu.objects.create(name=name, stuid=stuid, academy=aca, stuclass=clas, age=age, gender=1, password=password)
return render(request, 'zhuce.html', {"msg": '注册成功'})
else:
return render(request, "zhuce.html")
# 总的岗位数量的饼图和柱状图
def pie_bar_test(request):
df = pd.read_csv('C:\\pythonProject\\pythonProject2\\bishe-master\data_sum\\all.csv', encoding='gbk',
low_memory=False,
converters={'work_demand': str})
dd = df.loc[df['job_name'] != '其他职业']
pie_data_index = list(dd['job_name'].value_counts().index)
pie_data = list(dd['job_name'].value_counts())
data = []
for i in range(len(pie_data)):
dic = {}
dic['name'] = pie_data_index[i]
dic['value'] = pie_data[i]
data.append(dic)
return render(request, 'test.html', {"pie_data_index": pie_data_index,
"data": data,
"pie_data": pie_data,
})
# 辅助函数，用于主展示屏展示工作要求饼图
def abi_class(list):
newlist = []
for ele in list:
newlist += ele.split(',')
newlist = [x.strip() for x in newlist] # 这两行是为了使原df的工作要求单个呈现以逗号分割
res = dict()
for a in set(newlist):
res[a] = newlist.count(a)
ll = sorted(res.items(), key=lambda item: item[1], reverse=True) # 按从大到小排序每种技能的出现次数
ll = ll[0:6] # 取出list前6个值
return ll
def test_pic(request):
df = pd.read_csv('C:\\pythonProject\\pythonProject2\\bishe-master\\data_sum\\all.csv', encoding='gbk', low_memory=False,
converters={'work_demand': str})
# 取出每个城市及其岗位数
job = list(df['company_locale'].value_counts().index)
job1 = list(df['company_locale'].value_counts())
# 修改成元素为字典的list，以便地图绘制
data2 = []
for i in range(len(job)):
dic = {}
dic['name'] = job[i]
dic['value'] = job1[i]
data2.append(dic)
# 取出java技能各占比
a = df['work_demand'].str.split()
list1 = []
x = a.copy()
for i in range(len(x)):
if 'Java' in df['job_name'][i]:
list1 += x[i]
list1 = abi_class(list1)
abi_num = []
abi_name = []
for i in range(len(list1)):
if i < 6:
abi_num.append(list1[i][1])
abi_name.append(list1[i][0])
abi_snum = []
for i in range(len(abi_name)):
dict = {}
dict['value'] = abi_num[i]
dict['name'] = abi_name[i]
abi_snum.append(dict)
# 取出java、python和web在各地区薪资图
dff = df.loc[df['job_name'] == 'Java']
grouped2 = dff.groupby([df['job_name'], df['company_locale']])
a = grouped2['job_salary'].mean()
a = a.map(lambda x: int(x))
java_cities_price = a.values.tolist()
ddff = df.loc[df['job_name'] == 'Python']
grouped2 = ddff.groupby([df['job_name'], df['company_locale']])
a = grouped2['job_salary'].mean()
a = a.map(lambda x: int(x))
python_cities_price = a.values.tolist()
ddd = df.loc[df['job_name'] == 'web']
grouped2 = ddd.groupby([df['job_name'], df['company_locale']])
a = grouped2['job_salary'].mean()
a = a.map(lambda x: int(x))
web_cities_price = a.values.tolist()
dfdf = df.loc[df['job_name'] == '大数据']
grouped2 = dfdf.groupby([df['job_name'], df['company_locale']])
a = grouped2['job_salary'].mean()
a = a.map(lambda x: int(x))
hadoop_cities_price = a.values.tolist()
# 得到招聘岗位数排名前八的公司，返回元素为字符串的列表
a = list(df['company_name'].value_counts().index)
b = list(df['company_name'].value_counts())
ll = []
for i in range(0, 10):
c = str(i + 1) + ' ' + a[i] + ' ' + str(b[i]) + '个岗位'
ll.append(c)
# 取出不同岗位类型平均薪资
gp = df.groupby('demand')
a = gp['job_salary'].mean().sort_values(ascending=False)
job_price_index = a.index.tolist()
job_price = a.values.tolist()
for i in range(len(job_price)):
job_price[i] = int(job_price[i])
# job_price = np.trunc(job_price) #对list每个元素进行取整
return render(request, '../templates/index.html', {"job": job,
"job1": job1,
"data2": data2,
"job_price_index": job_price_index,
"job_price": job_price,
"abi_name": abi_name,
"abi_snum": abi_snum,
"java_cities_price": java_cities_price,
"python_cities_price": python_cities_price,
"web_cities_price": web_cities_price,
"hadoop_cities_price": hadoop_cities_price,
"ll": ll,
})
11.templates/index.html
index
页面加载中...
计算机行业就业情况大数据展示页面
12templates/ceshi2.html
Title
模板学习
{{ name }}
{{ users.0 }}
{{ users.1 }}
{{ k1 }}
{{ k2 }}
循环测试
{% for item in users %}
- {{ item }}
{% endfor %}
循环测试2
{% for item in us %}
{{ item.id }}
{{ item.name }}
{{ item.email }}
编辑 | 删除
{% endfor %}
{{ message }}
13 templates/job_demand_pie_sum.html
Awesome-pyecharts
14.templates/predict_xinzi.html
岗位薪资预测
15.templates/test.html
test
行业招聘岗位需求数据分析
16.templates/xinzi_bar_sum.html
Awesome-pyecharts
17.templates/zhuce.html
登录注册