def data_draw(csv_file):
page = Page(csv_file + ":按区域分析")
d = pd.read_csv(csv_file, engine='python', encoding='utf-8') # 读取CSV转为dataframe格式，并丢弃评论为空的的记录
position_info = d['positionName'].value_counts()
position_bar = pyecharts.Bar('职位信息柱状图')
position_bar.add('职位', position_info.index, position_info.values, is_stack=True, is_label_show=True)
position_bar.render(csv_file[:-4] + "_职位信息柱状图.html") # 取CSV文件名的前8位数
page.add_chart(position_bar)
salary_info = salary_count(csv_file)
salary_bar = pyecharts.Bar('月薪柱状图')
salary_bar.add('月薪', list(salary_info.keys()), list(salary_info.values()), is_stack=True, is_label_show=True)
salary_bar.render(csv_file[:-4] + "_月薪柱状图.html") # 取CSV文件名的前8位数
page.add_chart(salary_bar)
data = industryField_counts(csv_file)
industryField_pie = pyecharts.Pie("", "行业领域饼图", title_pos="right", width=1200, height=600)
industryField_pie.add("", list(data.keys()), list(data.values()), radius=[20, 50], label_text_color=None, is_label_show=True,
legend_orient='vertical', is_more_utils=True, legend_pos='left')
industryField_pie.render(csv_file[:-4] + "_行业领域饼图.html") # 取CSV文件名的前8位数
page.add_chart(industryField_pie)
companySize_info = d['companySize'].value_counts()
companySize_pie = pyecharts.Pie("", "公司规模饼图", title_pos="right", width=1200, height=600)
companySize_pie.add("", companySize_info._index, companySize_info.values, radius=[20, 50], label_text_color=None, is_label_show=True,
legend_orient='vertical', is_more_utils=True, legend_pos='left')
companySize_pie.render(csv_file[:-4] + "_公司规模饼图.html") # 取CSV文件名的前8位数
page.add_chart(companySize_pie)
financeStage_info = d['financeStage'].value_counts()
financeStage_pie = pyecharts.Pie("", "公司融资阶段饼图", title_pos="right", width=1200, height=600)
financeStage_pie.add("", financeStage_info._index, financeStage_info.values, radius=[20, 50], label_text_color=None, is_label_show=True,
legend_orient='vertical', is_more_utils=True, legend_pos='left')
financeStage_pie.render(csv_file[:-4] + "_公司融资阶段饼图.html") # 取CSV文件名的前8位数
page.add_chart(financeStage_pie)
workyear_info = d['workYear'].value_counts()
workyear_pie = pyecharts.Pie("", "职位工作经验饼图", title_pos="right", width=1200, height=600)
workyear_pie.add("", workyear_info._index, workyear_info.values, radius=[20, 50], label_text_color=None, is_label_show=True,
legend_orient='vertical', is_more_utils=True, legend_pos='left')
workyear_pie.render(csv_file[:-4] + "_职位工作经验饼图.html") # 取CSV文件名的前8位数
page.add_chart(workyear_pie)
education_info = d['education'].value_counts()
education_pie = pyecharts.Pie("", "职位学历要求饼图", title_pos="right", width=1200, height=600)
education_pie.add("", education_info._index, education_info.values, radius=[20, 50], label_text_color=None, is_label_show=True,
legend_orient='vertical', is_more_utils=True, legend_pos='left')
education_pie.render(csv_file + "_职位学历要求饼图.html") # 取CSV文件名的前8位数
page.add_chart(education_pie)
page.render(csv_file[:-4] + "_工作分析汇总.html")
def aboutMe(request):
gauge = pyecharts.Gauge('', background_color='#f5f5f5')
gauge.add('title',
'Percent',
80.66,
scale_range=[0, 100],
is_more_utils=True)
gauge.show_config()
result = gauge.render_embed()
data = [("海门", 9), ("鄂尔多斯", 10), ("招远", 12), ("舟山", 18), ("齐齐哈尔", 10),
("盐城", 15)]
geo = pyecharts.Geo("全国主要城市空气质量",
"data from pm2.5",
title_color="#000",
title_pos="center",
background_color='#f5f5f5')
attr, value = geo.cast(data)
geo.add("",
attr,
value,
type="effectScatter",
is_random=True,
effect_scale=5,
is_more_utils=True)
geo.show_config()
result1 = geo.render_embed()
attr = ["Jan", "Feb", "Mar", "Apr", "May", "Jun"]
v1 = [20, 33, 133, 124, 24, 313]
v2 = [2.6, 12, 31, 241, 324, 134]
bar = pyecharts.Bar('Bar Sample', background_color='#f5f5f5')
bar.add("A", attr, v1, mark_line=["average"], mark_point=["min", "max"])
bar.add("B",
attr,
v2,
mark_line=["average"],
mark_point=["min", "max"],
is_more_utils=True)
bar_result = bar.render_embed()
pie = pyecharts.Pie('', background_color="#f5f5f5")
pie.add("",
attr,
v1,
is_lable_show=True,
lable_text_color="#156ACF",
is_more_utils=True)
pie.show_config()
pie_result = pie.render_embed()
liquid = pyecharts.Liquid('', background_color="#000")
liquid.add("", [0.66, 0.5], ['diamond'], ['#294D99', '#156ACF'],
is_more_utils=True)
liquid.show_config()
liquid_result = liquid.render_embed()
return render_to_response(
'AboutMe.html', {
'result': result,
'result1': result1,
'bar_result': bar_result,
'pie_result': pie_result,
'liquid_result': liquid_result
})
def click2(self):
conn = pymysql.connect(host='localhost', user='******', password='******', port=3306, db='maoyan',charset='utf8mb4')
sql = "select * from films"
db = pd.read_sql(sql, conn)
t1 = threading.Thread(target=self.myshow)
year = int(self.comboBox.currentText())
month = int(self.comboBox_2.currentText())
t2 = threading.Thread(target=self.mytr,args = (year,month))
if month < 13:
db_ = db[(db.year == year) & (db.month == month)]
elif month > 123:
db_= db[(db.year == year)&(db.month>0)&(db.month<4)]
elif month == 456:
db_ = db[(db.year == year) & (db.month > 3) & (db.month < 7)]
elif month == 789:
db_ = db[(db.year == year) & (db.month > 6) & (db.month < 10)]
elif month == 101112:
db_ = db[(db.year == year) & (db.month > 9) & (db.month < 13)]
else:
db_ = db
x, y = visual(db_)
pie = pyecharts.Pie()
pie.add("", x, y, is_label_show=True, radius=[0, 50], center=[75, 50],legend_orient="vertical", legend_pos="right")
bar = pyecharts.Bar("", title_pos="left")
bar.add("", x, y, mark_line=["max", "average"], xaxis_interval=0,is_labal_show=True)
grid = pyecharts.Grid(width=1200)
grid.add(bar, grid_right='50%')
grid.add(pie, grid_left="50%")
grid.render(("db%d.html")%(year*100+month))
self.widget.load(QUrl('file:///db%d.html'%(year*100+month)))
t1.start()
t2.start()
def test_case_runhistory_report2():
REMOTE_HOST = "https://pyecharts.github.io/assets/js"
bar = pyecharts.Pie()
bar.add("Sports",
["Football", "Basketball", "Baseball", "Tennis", "Swimming"],
[23, 34, 45, 56, 67],
is_more_utils=True)
log.log().logger.info(request)
if request.method == 'GET':
log.log().logger.info('post')
info = request.values
log.log().logger.info('info : %s' % info)
id = viewutil.getInfoAttribute(info, 'id')
log.log().logger.info('id: %s' % id)
if len(test_case_manage.test_case_manage().show_test_cases(['id'],
[id], [],
2)) == 1:
return render_template("uitest/test_batch_result.html",
id=id,
type='test_case',
test_suite_id='',
myechart=bar.render_embed(),
host=REMOTE_HOST,
script_list=bar.get_js_dependencies())
else:
return render_template("uitest/test_cases.html")
else:
return render_template("uitest/test_cases.html")
def test_batch_detail_report():
REMOTE_HOST = "https://pyecharts.github.io/assets/js"
bar = pyecharts.Pie()
bar.width = 700
bar.height = 400
log.log().logger.info(request)
if request.method == 'GET':
log.log().logger.info('post')
info = request.values
log.log().logger.info('info : %s' % info)
id = viewutil.getInfoAttribute(info, 'test_suite_id')
log.log().logger.info('id: %s' % id)
statusList = test_batch_manage.test_batch_manage(
).show_test_batch_status(id)
nameList, valueList = bar.cast(statusList)
bar.add("results", ['失败', '待执行', '执行中', '成功'],
valueList[0:4],
is_more_utils=True,
is_area_show=True,
is_label_show=True,
legend_pos="50%")
return render_template("uitest/test_batch_detail_report.html",
id=id,
myechart=bar.render_embed(),
host=REMOTE_HOST,
script_list=bar.get_js_dependencies())
# return render_template("uitest/test_batch_report.html", id=id)
else:
return render_template('test_suite.html')
def create_Pie():
sun = 0
cloud = 0
lit_rain = 0
mit_rain = 0
sail = 0
shadom = 0
z_rain = 0
th_rain = 0
for i in types:
if i == '晴':
sun += 1
elif i == '多云':
cloud += 1
elif i == '小雨':
lit_rain += 1
elif i == '中雨':
mit_rain += 1
elif i == '阴':
shadom += 1
elif i == '阵雨':
z_rain += 1
elif i == '雷阵雨':
th_rain += 1
elif i == '扬沙':
sail += 1
pie = pyecharts.Pie("全国天气类型比例", '2018-4-16')
pie.add('', weather, [mit_rain, lit_rain, sail, sun, th_rain, cloud, shadom, z_rain], is_label_show=True, label_text_color=None, legend_orient='vertical', radius=[40, 50], center=[50, 50])
pie.add('', ['中雨', '小雨', '扬沙', '晴'], [lit_rain, mit_rain, sun, sail], radius=[10, 35], center=[50, 50], rosetype='area')
pie.render('Pie-weather.html')
def visual_pie_pye(data, path):
'''
use visual_pie_pye() to generate a html file
'''
data = OrderedDict(
sorted(data.items(), reverse=True, key=lambda x: x[1]['prop']))
labels = list(data.keys())[:10] + ['other']
sizes = [round(data[style]['prop'], 2) for style in labels[:-1]]
othersize = 1 - sum(sizes)
sizes.append(othersize)
#x:labels y:sizes
pie = pye.Pie("Proportions of Different Genres of Films",
title_pos='center',
width=1080,
height=640)
kwargs = dict(
radius=(40, 75),
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
legend_pos='left',
is_toolbox_show=False,
)
pie.add("", labels, sizes, **kwargs)
pie.render(path)
def get_pie():
pie = pyecharts.Pie()
style = pyecharts.Style()
pie_style = style.add(label_pos="center",
is_label_show=True,
label_text_color=None)
return pie, pie_style
def read_1688_all(cid, cat_name):
page = pyecharts.Page() # 实例化page类
bar = read_1688_index(cid, cat_name)
page.add(bar)
attr_list = mongo_client2.get_1688attr(cid)
# attrs = []
# for attr in attr_list:
# attrs.append(attr)
rows_by_type = defaultdict(list)
for attr in attr_list:
rows_by_type[attr['attr_type']].append(attr)
for attr_type in rows_by_type.items():
# print(attr_type[1]['attr_value'])
attr_value_index_group = []
attr_value_group = []
for attr in attr_type[1]:
attr_value_index_group.append(attr['attr_value_index'])
attr_value_group.append(attr['attr_value'])
# print(attr_type[0]+"\t"+attr['attr_value'])
# attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
# v1 = [11, 12, 13, 10, 10, 10]
pie = pyecharts.Pie(attr_type[0], title_pos='50%')
pie.add(attr_type[0],
attr_value_group,
attr_value_index_group,
radius=[40, 75],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
legend_pos='left')
page.add(pie)
# print(rows_by_type)
# pie
# attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
# v1 = [11, 12, 13, 10, 10, 10]
# pie = Pie("饼图-圆环图示例", title_pos='50%')
# pie.add("", attr, v1, radius=[40, 75], label_text_color=None,
# is_label_show=True, legend_orient='vertical', legend_pos='left')
# TODO 配置Grid类
# grid = Grid(height=720, width=1200) # 初始化，参数可传page_title,width,height
# grid.add(bar, grid_bottom="60%", grid_left="60%") # 添加要展示的图表，并设置显示位置
# # grid.add(line, grid_bottom="60%", grid_right="60%") # 添加要展示的图表，并设置显示位置
# grid.add(pie, grid_bottom="60%", grid_right="60%")
# grid.add(scatter, grid_top="60%", grid_left="60%") # 添加要展示的图表，并设置显示位置
# grid.add(es, grid_top="60%", grid_right="60%") # 添加要展示的图表，并设置显示位置
# grid.render("Grid_并行显示多张图表.html")
# return grid
return page
def pie_chart(x, y, title=None):
pie = pyecharts.Pie(width=700, height=450)
pie.add(title,
x,
y,
radius=[40, 75],
is_label_show=True,
legend_orient='vertical',
legend_pos='left',
label_text_color=None,
label_text_size=15)
return pie
def map_new_new(self, location, count, key):
pie = pyecharts.Pie('{}职业分布'.format(key),
width=1500,
height=800,
title_color='blue',
title_pos='bottom')
pie.add('{}'.format(key),
location,
count,
is_random=True,
is_label_show=True)
pie.render(r'E:\github\bingtu\%s.html' % key)
def democ(data):
es = pyecharts.Pie("")
sum = 0
for i in data.values():
sum += 1
print(sum)
flag = 1
for title in data.items():
if title[1] < 10: pass
es.add('', data.keys().data.values())
flag += 1
es.render()
es.render()
def gender_pie(title_name, gender_name, gender_num):
total_num = 0
for i in gender_num:
total_num += i
subtitle_name = '共有%d个好友' % (total_num)
pie = pyecharts.Pie(title=title_name, subtitle=subtitle_name)
pie.add('', gender_name, gender_num, is_label_show=True)
pie_file_name = './' + title_name + '.html'
try:
pie.render(path=pie_file_name)
print('%s已保存至%s' % (title_name, pie_file_name))
except Exception as e:
logging.debug(u'Error:%s' % e)
pass
def sex_distribution(sexData):
'''
性别饼图
:return: null
'''
number = []
number.append(sexData.count('0'))
number.append(sexData.count('1'))
number.append(sexData.count('2'))
attr = ['未知', '男', '女']
pie = pyecharts.Pie("性别图")
pie.add("", attr, number,is_label_show=True)
return pie
def draw_district_pic(csv_file):
page = Page(csv_file + ":城市区域职位分析")
d = pd.read_csv(csv_file, engine='python',
encoding='utf-8') # 读取CSV转为dataframe格式，并丢弃评论为空的的记录
district_info = d['district'].value_counts()
geo1 = Geo("",
"城市区域职位分布",
title_pos="center",
width=1200,
height=600,
background_color='#404a59',
title_color="#fff")
geo1.add("",
district_info.index,
district_info.values,
maptype="广州",
visual_range=[0, 300],
visual_text_color="#fff",
is_geo_effect_show=False,
is_piecewise=True,
visual_split_number=10,
symbol_size=15,
is_visualmap=True,
is_more_utils=True)
geo1.render(csv_file[:-4] + "_城市区域职位dotmap.html")
page.add_chart(geo1)
district_pie = pyecharts.Pie("",
"区域职位饼图",
title_pos="right",
width=1200,
height=600)
district_pie.add("",
district_info._index,
district_info.values,
radius=[20, 50],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
district_pie.render(csv_file[:-4] + "_区域职位饼图.html") # 取CSV文件名的前8位数
page.add_chart(district_pie)
page.render(csv_file + "_城市区域分析汇总.html")
def amount(self):
head_list = []
count_list = []
for collection_name in self.collections:
count = 0
for item in self.db[collection_name].find():
if 'commodity_name' not in item.keys():
continue
count += 1
if count != 0:
head_list.append(collection_name)
count_list.append(count)
pie = pyecharts.Pie('京东口红')
pie.add('数量', head_list, count_list, is_label_show=True)
pie.render('visualization/amount.html')
def color_distribution(self):
color_type_dict = {}
for collection_name in self.collections:
for item in self.db[collection_name].find():
if 'color_type' not in item.keys():
continue
color_type = item['color_type']
if color_type == '其它':
continue
if color_type in color_type_dict.keys():
color_type_dict[color_type] += 1
else:
color_type_dict[color_type] = 1
pie = pyecharts.Pie()
pie.add('色系分布', list(color_type_dict.keys()), list(color_type_dict.values()), is_label_show=True)
pie.render('visualization/color_distribution.html')
def mfRatio(self, chatroom=None): # 男女比例
male = female = othor = 0
lables = ['男', '女', '其他']
path = self.savedir + 'mfRatio.html'
if chatroom:
cmd = 'mfRatio %s' % chatroom
myLogging(self.cmdFile, self.nickName, infoType='cmd', other=cmd)
try:
chatroom == self.instance.search_chatrooms(
name=chatroom)[0]['NickName']
except Exception as reason:
self.instance.send('在您的通讯录中没有找到该群[%s]' % chatroom)
myLogging(self.errFile,
self.nickName,
infoType='err',
other=cmd,
info=reason)
return
memberList = self.getChatroomMembers(chatroom)['MemberList']
subtitle = self.nickName + ':' + chatroom
else:
cmd = 'mfRatio'
myLogging(self.cmdFile, self.nickName, infoType='cmd', other=cmd)
memberList = self.frdInfoList[1:]
subtitle = self.nickName
male = len([1 for each in memberList if each['Sex'] == 1])
female = len([2 for each in memberList if each['Sex'] == 2])
other = len([0 for each in memberList if each['Sex'] == 0])
values = [male, female, other]
pie = pyecharts.Pie('微信好友男女比例', subtitle)
pie.add('男女比例', lables, values, is_label_show=True)
pie.render(path)
self.instance.send('@fil@%s' % path)
os.remove(path)
myLogging(self.cmdFile,
self.nickName,
infoType='cmd',
status='success',
other=cmd)
def t10(pa):
pie = p.Pie("新兴与传统职业学历经验需求对比", width=700, height=400)
pie.add("传统学历需求", next(pa), next(pa), radius=[50, 55], center=[35, 53])
pie.add("新兴学历需求",
next(pa),
next(pa),
radius=[0, 45],
center=[35, 53],
rosetype='radius',
is_random=True)
pie.add("传统经验需求", next(pa), next(pa), radius=[50, 55], center=[70, 53])
pie.add("新兴经验需求",
next(pa),
next(pa),
radius=[0, 45],
center=[70, 53],
rosetype='radius',
legend_orient='vertical',
legend_pos='left',
legend_top='center',
is_random=True,
is_toolbox_show=False)
return pie
def friends_sex():
sex = []
with open('wechatfriends.txt', mode='r', encoding='utf-8') as f:
rows = f.readlines()
for i in rows:
# if (i.split(',')[2]) == '':
# pass
# print(i.split(','))
sex.append(i.split(',')[2])
labels = ['汉子', 'lady', '性别不明']
value = [sex.count('1'), sex.count('2'), sex.count('0')]
pie = pyecharts.Pie('好友性别比例',
'好友总人数：%d' % len(sex),
title_pos='center')
pie.add(
'',
labels,
value,
radius=[30, 75],
is_label_show=True,
legend_orient="vertical",
legend_pos="left",
)
pie.render('微信好友性别比例.html')
cat_sum[i['name']] = 0
for i in range(l):
cated = False
for j in dic:
flg = False
for k in j['keys']:
if accounts['CHECKING SUMMARY']['description'][i].lower().find(
k) != -1:
cat_sum[j['name']] += accounts['CHECKING SUMMARY']['amount'][i]
flg = True
cated = True
break
if flg is True:
break
if cated is False:
print(accounts['CHECKING SUMMARY']['description'][i])
cat_sum['other'] += accounts['CHECKING SUMMARY']['amount'][i]
cat_sum
# In[81]:
pie = pyecharts.Pie()
attr = []
v = []
for i in cat_sum:
attr.append(i)
v.append(round(cat_sum[i] * -1, 2))
pie.add('test', attr, v, is_legend_show=False, is_label_show=True)
# In[ ]:
attr,
[11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"],
)
line.add(
"最低气温",
attr,
[1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%",
)
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [11, 12, 13, 10, 10, 10]
pie = echarts.Pie("饼图示例", title_pos="55%")
pie.add(
"",
attr,
v1,
radius=[45, 65],
center=[65, 50],
legend_pos="80%",
legend_orient="vertical",
)
grid = echarts.Grid(width=1200)
grid.add(line, grid_right="55%")
grid.add(pie, grid_left="60%")
grid.render(path='tmp/grid.html')
#研究'年龄层次匹配','城市层级','消费档次','性别'四个字段的用户画像
#获取数据
a = ['年龄层次匹配', '城市层级', '消费档次', '性别']
attr = []
y = []
for i in a:
attri = df[i].value_counts().index.tolist()
yi = df[i].value_counts().values.tolist()
attr.append(attri)
y.append(yi)
#在一个页面显示4张饼图
pie = pe.Pie('某平台用户年龄层次、城市层级、消费档次、性别画像研究环形图',
title_pos='center',
height=600,
width=1000)
pie.add('年龄层次',
attr[0],
y[0],
radius=[25, 35],
center=[30, 30],
is_legend_show=False,
is_label_show=True)
pie.add('城市层级',
attr[1],
y[1],
radius=[25, 35],
center=[75, 30],
is_legend_show=False,
is_label_show=True)
def find(name):
user = "******"
password = "******"
db = pymysql.connect(host="localhost",
user=user,
password=password,
charset="utf8")
cursor = db.cursor()
cursor.execute('USE `ujn_a`;')
names = name + 's'
cursor.execute('DROP VIEW IF EXISTS {};'.format(names))
sql_1 = 'CREATE VIEW {} AS SELECT qcwy.xexperience,qcwy.education FROM qcwy WHERE title like "%{}%" '.format(
names, name)
cursor.execute(sql_1)
cursor.execute("select count(*) from " + names)
alls = cursor.fetchone()[0]
list1 = ['本科', '硕士', '博士']
list_edu = []
list_edu_sql = [
"select count(*) from {} where education = '{}';".format(names, i)
for i in list1
]
for i in list_edu_sql:
cursor.execute(i)
list_edu.append(cursor.fetchone()[0])
list2 = ['无工作经验', '1年经验', '2年经验', '3-4年经验', '5-7年经验', '8-9年经验', '10年以上经验']
list_exp = []
list_exp_sql = [
"select count(*) from {} where xexperience = '{}';".format(names, i)
for i in list2
]
for i in list_exp_sql:
cursor.execute(i)
list_exp.append(cursor.fetchone()[0])
p.configure(global_theme='macarons') # 设置主题
bing = p.Pie()
attr = list2
v1 = list_exp
bing.add("",
attr,
v1,
is_label_show=True,
is_toolbox_show=False,
legend_top='bottom')
bing.render('static/html/bing.html')
list4 = []
for i in range(3):
qiu = p.Liquid(title=list1[i],
title_pos='center',
title_text_size=30,
title_top='80%',
width=600,
height=400)
list3 = [round(list_edu[i] / alls, 2)]
list4.extend(list3)
qiu.add(list1[i],
list3,
is_liquid_animation=True,
is_toolbox_show=False,
liquid_color=['#21bbff', '#00b6ff', '#23c4ff', '#47c7ff'],
is_liquid_outline_show=False)
qiu.render('static/html/qiu{}.html'.format(i + 1))
# 返回
n = 1
e_all = 0
for i in list_exp[1:]:
e_all = e_all + i / alls / 21 * n
n = n + 1
n = 1
d_all = 0
for i in list_edu[1:]:
d_all = d_all + i / alls / 2 * n
n = n + 1
if e_all > d_all:
if e_all - d_all <= 0.06:
result = '考研和直接就业都很不错呢'
else:
result = '建议您毕业后直接就业哦'
else:
result = '建议您准备考研哦'
if name == '学习': name = '机器学习'
back = [name, result]
return back
return
def data_draw(csv_file):
page = Page(csv_file + ":按区域分析")
#读取csv转为dataframe格式
d = pd.read_csv(csv_file, engine='python', encoding='utf-8')
position_info = d['positionname'].value_counts()
#画职位信息柱状图
position_bar = pyecharts.Bar('职位信息柱状图')
position_bar.add('职位',
position_info.index,
position_info.values,
is_stack=True,
is_label_show=True)
position_bar.render(csv_file[:-4] + "_职位信息柱状图.html")
page.add_chart(position_bar)
salary_info = d['salary'].values
#画薪水信息柱状图
salary_bar = pyecharts.Bar('薪水信息柱状图')
dict = {
'2k-': 0,
'2k-5k': 0,
'5k-10k': 0,
'10k-15k': 0,
'15k-20k': 0,
'20k-30k': 0,
'30k+': 0
}
for salary in salary_info:
#正则表达式：^开始符，$结束符,[]:范围,\d:数字,{}位数
if re.match('^[0-1]k-*|.*-[0-1]k$', salary) != None:
dict['2k-'] += 1
if re.match('^[2-4]k-*|.*-[2-4]k$', salary) != None:
dict['2k-5k'] += 1
if re.match('^[5-9]k-*|.*-[5-9]k$', salary) != None:
dict['5k-10k'] += 1
if re.match('^1[0-4]k-*|.*-1[0-4]k$', salary) != None:
dict['10k-15k'] += 1
if re.match('^1[5-9]k-*|.*-1[5-9]k$', salary) != None:
dict['15k-20k'] += 1
if re.match('^2[0-9]k-*|.*-2[0-9]k$', salary) != None:
dict['20k-30k'] += 1
if re.match('^[3-9][0-9]k-*|.*-[3-9][0-9]k$|\d{3,}k-*|.*-\d{3,}k$',
salary) != None:
dict['30k+'] += 1
salary_bar.add('薪水',
list(dict.keys()),
list(dict.values()),
is_stack=True,
is_label_show=True)
salary_bar.render(csv_file[:-4] + '_薪水信息柱状图.html')
page.add_chart(salary_bar)
industryfield_info = d['industryfield'].values
#行业分布饼状图
industryfield_pie = pyecharts.Pie('行业分布饼状图', title_pos='right')
industryfields = []
for i in range(len(industryfield_info)):
try:
data = re.split('[,、 ]', industryfield_info[i]) #逗号，顿号，空格
except:
continue
for j in range(len(data)):
industryfields.append(data[j])
counts = Counter(industryfields) #字典类型
print(type(counts))
industryfield_pie.add('',
list(counts.keys()),
list(counts.values()),
radius=[15, 60],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
industryfield_pie.render(csv_file[:-4] + '_行业分布饼状图.html')
page.add_chart(industryfield_pie)
companysize_info = d['companysize'].value_counts()
#公司规模饼状图
companysize_pie = pyecharts.Pie('公司规模饼状图', title_pos='right')
companysize_pie.add('',
companysize_info.index,
companysize_info.values,
radius=[15, 60],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
companysize_pie.render(csv_file[:-4] + '_公司规模饼状图.html')
page.add_chart(companysize_pie)
#公司融资情况饼状图
financestage_info = d['financestage'].value_counts()
financestage_pie = pyecharts.Pie('公司融资信息饼状图', title_pos='right')
financestage_pie.add('',
financestage_info.index,
financestage_info.values,
radius=[15, 60],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
financestage_pie.render(csv_file[:-4] + '_公司融资信息饼状图.html')
page.add_chart(financestage_pie)
#工作经验饼状图
workyear_info = d['workyear'].value_counts()
workyear_pie = pyecharts.Pie('工作经验信息饼状图', title_pos='right')
workyear_pie.add('',
workyear_info.index,
workyear_info.values,
radius=[15, 60],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
workyear_pie.render(csv_file[:-4] + '_工作经验信息饼状图.html')
page.add_chart(workyear_pie)
#学历要去饼状图
education_info = d['education'].value_counts()
education_pie = pyecharts.Pie('学历要求信息饼状图', title_pos='right')
education_pie.add('',
education_info.index,
education_info.values,
radius=[15, 60],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
education_pie.render(csv_file[:-4] + '_学历要求信息饼状图.html')
page.add_chart(education_pie)
#工作地点饼状图
district_info = d['district'].value_counts()
district_pie = pyecharts.Pie('工作地点信息饼状图', title_pos='right')
district_pie.add('',
district_info.index,
district_info.values,
radius=[15, 60],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
district_pie.render(csv_file[:-4] + '_工作地点信息饼状图.html')
page.add_chart(district_pie)
#汇总
page.render(csv_file[:-4] + '.html')
def view():
"""
价格柱状图
"""
# Excel存储路径
excel_path = os.path.dirname(
os.path.realpath(__file__)) + '\\utils\\pdd.xlsx'
# 激活表格
wb = xlrd.open_workbook(filename=excel_path)
# sheet
sheet_name = wb.sheet_names()[0]
# sheet 内容
sheet_content = wb.sheet_by_name(sheet_name)
# 获取第五列所有价格
cols_price = sheet_content.col_values(4)[1:]
# 统计各价格区间的商品总量
price_zone = {
'less_than_1000': 0, # 非正常价格
'less_than_2000': 0, # 1000-2000
'less_than_3000': 0, # 2000-3000
'less_than_4000': 0, # 3000-4000
'greater_than_4000': 0, # 大于4000
}
for price in cols_price:
pirce_ = int(price)
if pirce_ > 4000:
price_zone['greater_than_4000'] += 1
elif pirce_ > 3000 and pirce_ <= 4000:
price_zone['less_than_4000'] += 1
elif pirce_ > 2000 and pirce_ <= 3000:
price_zone['less_than_3000'] += 1
elif pirce_ > 1000 and pirce_ <= 2000:
price_zone['less_than_2000'] += 1
else:
price_zone['less_than_1000'] += 1
data = []
labels = []
for k, v in price_zone.items():
data.append(v)
labels.append(k)
bar = pyecharts.Bar("各价格区间的商品数量", 'https://github.com/Northxw/')
bar.add('', labels, data, bar_category_gap="30%")
bar.render(path=os.path.dirname(os.path.realpath(__file__)) +
'\\view\\price.html')
# 获取第六列标签数据
cols_tags = sheet_content.col_values(6)[1:]
tags = {
'顺丰包邮': 0,
'极速退款': 0,
'退货包运费': 0,
'品牌馆': 0,
'全国联保': 0,
}
for tag in cols_tags:
if '顺丰包邮' in tag:
tags['顺丰包邮'] += 1
elif '极速退款' in tag:
tags['极速退款'] += 1
elif '退货包运费' in tag:
tags['退货包运费'] += 1
elif '品牌馆' in tag:
tags['品牌馆'] += 1
elif '全国联保' in tag:
tags['全国联保'] += 1
data = []
labels = []
for k, v in tags.items():
data.append(v)
labels.append(k)
pie = pyecharts.Pie("商家标签", 'https://github.com/Northxw/')
pie.add('', labels, data, is_label_show=True)
pie.render(path=os.path.dirname(os.path.realpath(__file__)) +
'\\view\\tags.html')
sports[s] = sports.get(s, 0) + 1
ts = u.teams.split()
for t in ts:
teams[t] = teams.get(t, 0) + 1
print(sports)
print(teams)
# In[36]:
from collections import Counter, OrderedDict
teams_most = OrderedDict(Counter(teams).most_common(40))
teams_most['其他'] = sum(teams.values()) - sum(teams_most.values())
print(teams_most)
pie = ec.Pie(width=1000)
pie.add('队伍', teams_most.keys(), teams_most.values(), is_legend_show=False, is_label_show=True)
pie
# In[37]:
s = sorted(sports.items(), key=lambda x: x[1], reverse=True)
s = OrderedDict(s)
pie = ec.Pie(width=1000)
pie.add('运动', s.keys(), s.values(), is_legend_show=False, is_label_show=True)
pie
# In[ ]:
# with open('../../data/top10.txt') as f:
# row = f.readlines()
# arr = [ss.strip('\n') for ss in row]
# for l in arr:
# txt = wordlist(l)
# wordWeight = tfidf(txt)
# s = sorted(wordWeight,key=lambda x:x[1],reverse=True)[:3]
# ll.append(s)
# print(ll)
ll = [[['stuff', 0.44233918732073285]], [['network', 0.30221302424344187]],
[['boys', 0.43515469193302975]], [['universe', 0.48004267235639847]],
[['world', 0.26678657924332194]], [['right', 0.35641846295458396]],
[['information', 0.27579849586805472]],
[['people', 0.43308190878605118]], [['brain', 0.34786262139146906]],
[['cancer', 0.52024972856630003]]]
pie = pyecharts.Pie('top10文章中的关键词')
x = []
y = []
for s in ll:
for l in s:
print(s)
x.append(l[0])
y.append(l[1])
pie.add('',
x,
y,
is_random=True,
legend_pos='right',
legend_orient='vertical',
radius=[20, 75],
rosetype='radius')
house = house.drop('house_info',axis=1) #删除House_info这一列
house.loc[house['location'].isna(),'location'] = house.loc[house['location'].isna()].house.apply(lambda x : x.split()[1]) #location公寓的有缺失位置进行处理
#可视化分析
#房屋户型分布数量前十柱形图
z = house.apartment.value_counts()[:10].sort_values()
bar = pyecharts.Bar("房屋户型分布前十","南京·NanJing")
bar.add(z,z.index,y_axis = list(z.values),is_convert= True,is_label_show =True,label_pos = 'inside',label_color = ["#996666"])
bar.render("南京租房房屋户型分析.html")
#各行政区房屋租赁数量分布及占比
part = house.part.value_counts().sort_values()
part_bar = pyecharts.Bar("各行政区房屋租赁数量分布及占比","南京·NanJing")
part_bar.add(part,part.index,part.values,is_label_show = True,label_color = ['#999999'],is_convert = True,label_pos = "inside")
pie_part = pyecharts.Pie(title_pos = "40%")
pie_part.add(part,part.index,part.values,is_label_show = True,legend_pos = '90%',legend_orient="vertical",center = [65,50])
grid = pyecharts.Grid(page_title="各行政区房屋租赁数量分布及占比",width=1200)
grid.add(part_bar,grid_right = "60%")
grid.add(pie_part,grid_left = "50%")
grid.render("南京租房数量分析.html")
#了解一下不同地区租房平均情况
single_price = round(house.loc[house.house_type == 'single'].money.groupby(house.loc[house.house_type == 'single']['part']).mean(),0)
all_price = round(house.loc[house.house_type == 'all'].money.groupby(house.loc[house.house_type == 'all']['part']).mean(),0)
line = pyecharts.Line("各行政区租房价格·¥","南京·NanJing")
line.add("整租",all_price.index,all_price.values,is_label_show = True)
line.add("合租",single_price.index,single_price.values,is_label_show = True)
line.render("南京租房房价分析.html")
'''******用户平台年龄以年为单位,用.dt.days获取了天数后除以365'''
df['用户平台年龄'] = df['用户平台年龄'].dt.days / 365
'''******用行为时间字段得出行为时刻'''
df['行为时刻'] = df['行为时间'].dt.hour
'''
获取需要用到的necklace的数据data
'''
data = df[df['产品类别'] == 'Necklace']
'''
第二步指标的量化及初判
'''
'''
行为类别
'''
'''全样本的行为类别'''
pie = pe.Pie('全样本的行为类别环形图', title_pos='center', height=500, width=600)
attr = df['行为类别'].value_counts().index.tolist()
d = df['行为类别'].value_counts().values.tolist()
pie.add('全样本的行为类别环形图',
attr,
d,
is_more_utils=True,
is_label_show=True,
is_legend_show=False,
radius=[40, 75])
pie.render('全样本的行为类别环形图.html')
order_all = df['行为类别'].value_counts()['Order'] / len(df['行为类别'])
print('最终实现了购买行为占所有关注用户的行为的%.2f%%' % (order_all * 100))
#所有有购买行为的用户(去重)/所有用户
order_cust_all = len(df[df['行为类别'] == 'Order']['客户编码'].value_counts()) / len(
df['客户编码'].value_counts())
