def test_mouse_click():
bar = Bar("我的第一个图表", "这里是副标题")
bar.add("服装", ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"],
[5, 20, 36, 10, 75, 90])
bar.on(events.MOUSE_CLICK, on_click)
assert "function on_click(" in bar._repr_html_()
from pyecharts import Bar
bar = Bar("我的第一个图表", "这里是副标题")
bar.add("服装", ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"],
[5, 20, 36, 10, -75, 90],
is_more_utils=True,
is_convert=True)
bar.render('./html/spread.html')
db='maoyan',
charset='utf8mb4')
cursor = conn.cursor()
sql = "select * from films"
db = pd.read_sql(sql, conn)
df = db.sort_values(by="people", ascending=False)
dom = df[['name', 'people']]
attr = np.array(dom['name'][0:10])
v1 = np.array(dom['people'][0:10])
attr = ["{}".format(i.replace('：无限战争', '')) for i in attr]
v1 = ["{}".format(float('%.2f' % (float(i) / 10000))) for i in v1]
bar = Bar("2018年电影人气TOP10(万人)",
title_pos='center',
title_top='18',
width=800,
height=400)
bar.add("",
attr,
v1,
is_convert=True,
xaxis_min=10,
yaxis_label_textsize=12,
is_yaxis_boundarygap=True,
yaxis_interval=0,
is_label_show=True,
is_legend_show=False,
label_pos='right',
is_yaxis_inverse=True,
is_splitline_show=False)
# -*- coding: utf-8 -*-
import pandas as pd
from pandas import DataFrame
from pyecharts import Bar, Grid, Page
# dataframe preparation
data = pd.read_excel('D:\Python\Test_Codes\\workload.XLSX',
sheet_name='Sheet2',
header=0)
df_raw = DataFrame(data)
# General settings of chart overview
bar1 = Bar(title='Number of Dialog Steps',
title_pos='left',
width=1000,
height=500,
renderer='canvas')
bar1.use_theme('essos')
bar1.add('Number of Dialog Steps',
df_raw['Task Type Name'],
df_raw['Number of Dialog Steps'],
is_stack=True,
mark_line=['average', 'max'],
mark_point=['max'],
mark_point_symbolsize=100,
is_label_show=True,
legend_selectedmode='single',
legend_pos=400,
from __future__ import unicode_literals
from pyecharts import Bar
from pyecharts.conf import PyEchartsConfig
from pyecharts.engine import EchartsEnvironment
from pyecharts.utils import write_utf8_html_file
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图数据堆叠示例")
bar.add("商家A", attr, v1, is_stack=True)
bar.add("商家B", attr, v2, is_stack=True)
config = PyEchartsConfig(echarts_template_dir='my_tpl',
jshost='https://cdn.bootcss.com/echarts/3.6.2')
env = EchartsEnvironment(pyecharts_config=config)
tpl = env.get_template(r'D:\python\tpl_demo.html')
html = tpl.render(bar=bar)
write_utf8_html_file('my_tpl_demo2.html', html)
shadow=False,
startangle=90)
plt.axis("equal")
plt.show()
#直方图
np.random.seed(0)
mu, sigma = 100, 20
a = np.random.normal(mu, sigma, size=100)
plt.hist(a, 10, normed=1, histtype="stepfilled", facecolor="b", alpha=0.75)
plt.show()
from pyecharts import Bar
bar = Bar("我的第一个图表")
bar.add("服装", ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"], [5, 20, 36, 10, 75, 90])
bar.print_echarts_options()
bar.render()
exit(0)
df1 = pd.DataFrame(np.arange(12.).reshape(3, 4), columns=list("abcd"))
df1.plot(kind="box", fontsize=12)
plt.show()
data1 = {"key": ["a", "a", "b", "b"], "name": [1, 2, 3, 4]}
frame1 = pd.DataFrame(data1)
seri = pd.Series([1, 1, 1, 1])
seri.name = "name2"
frame1[seri.name] = seri
# coding:utf-8
# 导入读取Excel的库
import xlrd
# 导入需要读取Excel表格的路径
data = xlrd.open_workbook(r'测试.xlsx')
table = data.sheets()[0]
y = ''
# 将列的值存入字符串
y = table.col_values(2) # 读取列的值
# 导入pyechats库
from pyecharts import Bar
import numpy as np
t = np.linspace(1, 1000000, len(y)) # 等间隔取值
bar = Bar("文章阅读量展示", "统计如下") # 主副标题
bar.add("博客文章阅读量折线图展示", t, y, is_more_utils=True) # 标题
bar.show_config() # 展示HTML源代码
bar.render(r"bokezhexiantu.html") # 保存到本地bokezhexiantu.html
# 过滤房价为0的无效数据
df = df[df.price > 0]
# # 去除重复行
# df = df.drop_duplicates()
print("row number is {0}".format(len(df.index)))
####################################################
# 最贵的小区排名
####################################################
df.sort_values("price", ascending=False, inplace=True)
num = 5
print(df.head(num))
city = df["city_ch"][0]
xqs = df["xiaoqu"][0:num]
prices = df["price"][0:num]
bar = Bar("{0}小区均价".format(city))
bar.add("小区均价前{0}名".format(num),
xqs,
prices,
is_stack=True,
is_label_show=True,
xaxis_interval=0,
xaxis_rotate=45)
bar.render(path="xiaoqu.html")
####################################################
# 区县均价排名
####################################################
district_df = df.groupby('district').mean()
district_df = district_df.round(0)
district_df.sort_values("price", ascending=False, inplace=True)
__author__ = 'zoulida'
#导入柱状图-Bar
from pyecharts import Bar
#设置行名
columns = [
"Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct",
"Nov", "Dec"
]
#设置数据
data1 = [2.0, 4.9, 7.0, 23.2, 25.6, 76.7, 135.6, 162.2, 32.6, 20.0, 6.4, 3.3]
data2 = [2.6, 5.9, 9.0, 26.4, 28.7, 70.7, 175.6, 182.2, 48.7, 18.8, 6.0, 2.3]
#设置柱状图的主标题与副标题
bar = Bar("柱状图", "一年的降水量与蒸发量")
#添加柱状图的数据及配置项
bar.add("降水量",
columns,
data1,
mark_line=["average"],
mark_point=["max", "min"])
bar.add("蒸发量",
columns,
data2,
mark_line=["average"],
mark_point=["max", "min"])
#生成本地文件（默认为.html文件）
bar.render()
import pandas as pd
import matplotlib.pyplot as plt
from pyecharts import Line, Bar
from pyecharts.engine import create_default_environment
'''评论数变化情况'''
df=pd.read_csv('Sina_Finance_Comments_All_20180811_Cleaned.csv',encoding='utf-8')
print(df.head())
# plt.plot(df.stamp,df.cmntcount)
# plt.show()
print('===================================================')
df_ymdcount=df.groupby('time_ymd')['cmntcount'].count()
print(df_ymdcount)
line1=Line('每日评论数变化情况')
line1.add('日期',df_ymdcount.index,df_ymdcount.values,is_label_show=True,line_type='dotted')
env=create_default_environment('html')
env.render_chart_to_file(line1, path='line1.html')
print('===================================================')
df_mdhcount=df.groupby('time_mdh')['cmntcount'].count()
print(df_mdhcount)
#折线图
line2=Line('每小时评论数')
line2.add('小时',df_mdhcount.index,df_mdhcount.values,is_label_show=True,line_type='dotted')
env.render_chart_to_file(line2,path='line2.html')
#柱状图
bar=Bar('每小时评论数')
bar.add('小时',df_mdhcount.index,df_mdhcount.values,is_label_show=True,line_type='dotted')
env.render_chart_to_file(bar,path='bar.html')
print(sfz)
sfzset = set(sfz)
# print(ageset)
for year in sfzset:
if year.isdigit():
# 判断count是不是字符即是否可被int
if int(year) > 1990 and int(year) < 2000:
# 判断count的值的区间
num.append(sfz.count(year))
age.append(str(year))
# print(year,sfz.count(year))
else:
pass
else:
pass
print(age)
print(num)
bar = Bar("年龄统计")
bar.add("年龄", age, num)
bar.show_config()
bar.render()
# if int(count)>1990 and int(count)<2000:
# print(count,age.count(count))
# else:
# pass
cursor.close()
# 关闭游标
conn.close()
# 关闭链接
# 使用饼图进行性别分析
#!/usr/bin/env python # -*- coding: utf-8 -*- # @Date : 2018-09-14 20:26:07 # @Author : cdl ([email protected]) # @Link : https://github.com/cdlwhm1217096231/python3_spider # @Version : $Id$ from pyecharts import Bar bar = Bar("图表1", "副标题") bar.use_theme('dark') # 使用主题 bar.add("服装", ["衬衫", "羊毛衫", "毛衣", "裤子", "高跟鞋", "袜子"], [5, 20, 36, 10, 75, 90], is_more_utils=True) bar.render(path='demo1.png')
def resource_report():
try:
form = MyForm.Form_resource_report()
days = tools.http_args(request, 'days')
date = datetime.datetime.now()
db_server = db_idc.idc_servers
if days:
days = int(days)
update_date = date - datetime.timedelta(days=days)
else:
days = 30
update_date = date - datetime.timedelta(days=30)
datazoom = True
if days == 30:
datazoom = False
Bars = {}
titles = {30: '近一个月', 90: '近三个月', 180: '近六个月', 360: '近一年内'}
db_third = db_idc.third_resource
db_project = db_op.project_list
vals = db_project.query.with_entities(
db_project.update_date, func.count(db_project.update_date)).filter(
and_(db_project.resource == 'tomcat',
db_project.update_date != '',
db_project.update_date >= update_date)).group_by(
db_project.update_date).all()
if vals:
attrs = [val[0] for val in vals]
datas = [val[-1] for val in vals]
tomcat_bar = Bar("tomcat(%s)" % titles[days],
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
tomcat_bar.add("",
attrs,
datas,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
xaxis_rotate=15,
is_datazoom_show=datazoom,
datazoom_type='both')
Bars['tomcat'] = tomcat_bar
vals = db_third.query.with_entities(
db_third.update_date, func.count(db_third.update_date)).filter(
and_(db_third.resource_type == 'redis',
db_third.update_date != '',
db_third.update_date >= update_date)).group_by(
db_third.update_date).all()
if vals:
attrs = [val[0] for val in vals]
datas = [val[-1] for val in vals]
redis_bar = Bar("redis(%s)" % titles[days],
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
redis_bar.add("",
attrs,
datas,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
xaxis_rotate=15,
is_datazoom_show=datazoom,
datazoom_type='both')
Bars['redis'] = redis_bar
vals = db_third.query.with_entities(
db_third.update_date, func.count(db_third.update_date)).filter(
and_(db_third.resource_type == 'redis',
db_third.update_date != '')).group_by(
db_third.update_date).all()
if vals:
attrs = [val[0] for val in vals]
datas = [val[-1] for val in vals]
mysql_bar = Bar("mysql(%s)" % titles[days],
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
mysql_bar.add("",
attrs,
datas,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
xaxis_rotate=15,
is_datazoom_show=datazoom,
datazoom_type='both')
Bars['mysql'] = mysql_bar
vals = db_third.query.with_entities(
db_third.update_date, func.count(db_third.update_date)).filter(
and_(db_third.resource_type == 'redis',
db_third.update_date != '')).group_by(
db_third.update_date).all()
if vals:
attrs = [val[0] for val in vals]
datas = [val[-1] for val in vals]
nginx_bar = Bar("nginx(%s)" % titles[days],
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
nginx_bar.add("",
attrs,
datas,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
xaxis_rotate=15,
is_datazoom_show=datazoom,
datazoom_type='both')
Bars['nginx'] = nginx_bar
try:
td = time.strftime("%Y-%m-%d", time.localtime())
std = datetime.datetime.now() - datetime.timedelta(days=180)
std = std.strftime("%Y-%m-%d")
if RC.exists('op_web_vm_vales_%s' % td) and RC.exists(
'op_web_py_vales_%s' % td):
vm_vals = eval(RC.get('op_web_vm_vales_%s' % td))
py_vals = eval(RC.get('op_web_py_vales_%s' % td))
else:
vm_vals = db_server.query.with_entities(
db_server.purch_date,
func.count(db_server.purch_date)).filter(
and_(db_server.host_type == 'vm',
db_server.purch_date > std)).group_by(
db_server.purch_date).all()
RC.set('op_web_vm_vales_%s' % td, vm_vals)
RC.expire('op_web_vm_vales_%s', 86400)
py_vals = db_server.query.with_entities(
db_server.purch_date,
func.count(db_server.purch_date)).filter(
and_(db_server.host_type == 'physical',
db_server.purch_date > std)).group_by(
db_server.purch_date).all()
RC.set('op_web_py_vales_%s' % td, py_vals)
RC.expire('op_web_py_vales_%s', 86400)
except Exception as e:
logging.error(e)
try:
server_bar = Bar("近6个月新增服务器数量",
title_pos='center',
title_text_size=12,
width='110%',
height='230px')
attrs = sorted(
set([val[0] for val in vm_vals if val] +
[val[0] for val in py_vals if val]))
vm_vals = {val[0]: val[1] for val in vm_vals}
py_vals = {val[0]: val[1] for val in py_vals}
for attr in attrs:
if attr not in vm_vals:
vm_vals[attr] = 0
if attr not in py_vals:
py_vals[attr] = 0
vm_vals = sorted(vm_vals.items(), key=lambda item: item[0])
vm_vals = [val[1] for val in vm_vals]
py_vals = sorted(py_vals.items(), key=lambda item: item[0])
py_vals = [val[1] for val in py_vals]
attrs = ['-'.join(val.split('-')[1:]) for val in attrs]
vm_counts = reduce(lambda x, y: x + y, vm_vals)
server_bar.add('虚拟机%s台' % vm_counts,
attrs,
vm_vals,
is_label_show=True,
is_toolbox_show=False,
xaxis_interval=0,
xaxis_rotate=25,
legend_pos='70%')
py_counts = reduce(lambda x, y: x + y, py_vals)
server_bar.add('物理机%s台' % py_counts,
attrs,
py_vals,
is_label_show=True,
is_toolbox_show=False,
xaxis_interval=0,
xaxis_rotate=25,
legend_pos='70%')
except Exception as e:
logging.error(e)
except Exception as e:
logging.error(e)
return redirect(url_for('error'))
return render_template('resource_report.html',
Bars=Bars,
form=form,
days=days,
server_bar=server_bar)
def server_used():
try:
try:
PIES = []
INFOS = []
ATTRS = []
if RC_CLUSTER.exists('op_zabbix_server_load_top'):
dict_load = eval(RC_CLUSTER.get('op_zabbix_server_load_top'))
bar_load = Bar("线上服务器cpu使用率TOP20",
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
attrs = [val[0] for val in dict_load]
vals = [int(val[1]) for val in dict_load]
ATTRS.extend(attrs)
bar_load.add("",
attrs,
vals,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
yaxis_formatter='%',
xaxis_rotate=15)
INFOS.append(bar_load)
if RC_CLUSTER.exists('op_zabbix_server_mem_top'):
dict_mem = eval(RC_CLUSTER.get('op_zabbix_server_mem_top'))
bar_mem = Bar("线上服务器内存使用率TOP20",
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
attrs = [val[0] for val in dict_mem]
vals = [int(val[1]) for val in dict_mem]
ATTRS.extend(attrs)
bar_mem.add("",
attrs,
vals,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
yaxis_formatter='%',
xaxis_rotate=15)
INFOS.append(bar_mem)
if RC_CLUSTER.exists('op_zabbix_server_openfile_top'):
dict_openfile = eval(
RC_CLUSTER.get('op_zabbix_server_openfile_top'))
bar_openfile = Bar("线上服务器openfile值TOP20",
width='110%',
height='100%',
title_pos='center',
title_text_size=14)
attrs = [val[0] for val in dict_openfile]
vals = [int(val[1]) for val in dict_openfile]
ATTRS.extend(attrs)
bar_openfile.add("",
attrs,
vals,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='right',
xaxis_interval=0,
is_random=True,
xaxis_rotate=15)
INFOS.append(bar_openfile)
except Exception as e:
logging.error(e)
try:
free_list = []
if RC_CLUSTER.exists('op_zabbix_free_servers'):
free_servers = eval(RC_CLUSTER.get('op_zabbix_free_servers'))
free_servers = [host for host in free_servers]
free_servers.sort()
# 导出服务器主机列表
tables = ['主机名']
search_key = 'search_results_%s' % g.token
export_values = [[host] for host in free_servers]
export_values.insert(0, tables)
RC.set(search_key, export_values)
host_count = len(free_servers)
# 服务器列表展示
free_list = [
free_servers[i * 5:(i + 1) * 5]
for i in range(len(free_servers) // 5)
]
except Exception as e:
logging.error(e)
if ATTRS:
db_project = db_op.project_list
db_third = db_idc.third_resource
db_server = db_idc.idc_servers
db_project_third = db_op.project_third
hosts = db_server.query.with_entities(db_server.ip).filter(
db_server.hostname.in_(tuple(set(ATTRS)))).all()
if hosts:
try:
# 应用服务占比
hosts = tuple([host[0] for host in hosts])
selfs = db_project.query.with_entities(
db_project.resource,
func.count(db_project.resource)).filter(
db_project.ip.in_(hosts)).group_by(
db_project.resource).all()
thirds = db_third.query.with_entities(
db_third.resource_type,
func.count(db_third.resource_type)).filter(
db_third.ip.in_(hosts)).group_by(
db_third.resource_type).all()
vals = selfs + thirds
if vals:
pie_app = Pie("TOP20应用服务占比",
width='100%',
height='100%',
title_pos='center',
title_text_size=14)
attrs = [val[0] for val in vals]
vals = [int(val[1]) for val in vals]
pie_app.add("",
attrs,
vals,
is_label_show=True,
is_toolbox_show=False,
is_legend_show=False,
xaxis_interval=0,
is_random=True)
PIES.append(pie_app)
# 线上项目占比
self_id = db_project.query.with_entities(
db_project.id).filter(db_project.ip.in_(hosts)).all()
third_id = db_third.query.with_entities(
db_third.id).filter(db_third.ip.in_(hosts)).all()
ids = self_id + third_id
ids = tuple([id[0] for id in ids])
vals = db_project_third.query.with_entities(
db_project_third.project,
func.count(db_project_third.project)).filter(
and_(db_project_third.project_id.in_(ids),
db_project_third.third_id.in_(ids))).group_by(
db_project_third.project).all()
if vals:
pie_project = Pie("TOP20线上项目占比",
width='100%',
height='100%',
title_pos='center',
title_text_size=14)
attrs = [val[0] for val in vals]
vals = [int(val[1]) for val in vals]
pie_project.add("",
attrs,
vals,
is_label_show=True,
is_toolbox_show=False,
legend_orient='vertical',
legend_pos='left',
xaxis_interval=0,
is_random=True)
PIES.append(pie_project)
except Exception as e:
logging.error(e)
except Exception as e:
logging.error(e)
return redirect(url_for('error'))
return render_template('server_used.html',
INFOS=INFOS,
PIES=PIES,
host_count=host_count,
free_list=free_list)
if __name__ == '__main__':
gender_htmlfile = './../../Resources/htmlfiles/article_comment_gender.html'
location_htmlfile = './../../Resources/htmlfiles/loaction.html'
business_htmlfile = './../../Resources/htmlfiles/business.html'
major_htmlfile = './../../Resources/htmlfiles/major.html'
comment_class_file = './../../Resources/htmlfiles/comment_class.html'
jsonfile1 = './../../Resources/jsonfiles/processed_zh_comment.json'
comment_txt = './../../Resources/CutWordPath/sentiment_comment.txt'
dict_comment = Read_file(jsonfile1)
attr = list(dict_comment.keys())
value = []
for key in attr:
value.append(len(dict_comment[key]))
bar = Bar('带评论的文章的类别分布')
bar.add('类别', attr, value, is_label_show=True, make_point=['average'])
bar.show_config()
bar.render(comment_class_file)
# 提取需要的信息
article_gender_list, article_place_list, article_business_list, article_major_list, articale_comment_list = extract_article_list(
dict_comment)
plt_Pie("社会话题的性别分布", article_gender_list, gender_htmlfile)
print("评论用户性别分布执行结束,%s文件生成" % gender_htmlfile)
plt_place(article_place_list, location_htmlfile)
print("评论用户位置分布执行结束,%s文件生成" % location_htmlfile)
plt_business("评论用户行业分布", article_business_list, business_htmlfile)
def kline_echarts(self, code=None):
def kline_formater(param):
return param.name + ':' + vars(param)
"""plot the market_data"""
if code is None:
path_name = '.' + os.sep + 'QA_' + self.type + \
'_codepackage_' + self.if_fq + '.html'
kline = Kline('CodePackage_' + self.if_fq + '_' + self.type,
width=1360,
height=700,
page_title='QUANTAXIS')
bar = Bar()
data_splits = self.splits()
for ds in data_splits:
data = []
axis = []
if ds.type[-3:] == 'day':
datetime = np.array(ds.date.map(str))
else:
datetime = np.array(ds.datetime.map(str))
ohlc = np.array(ds.data.loc[:,
['open', 'close', 'low', 'high']])
kline.add(ds.code[0],
datetime,
ohlc,
mark_point=["max", "min"],
is_datazoom_show=True,
datazoom_orient='horizontal')
return kline
else:
data = []
axis = []
ds = self.select_code(code)
data = []
#axis = []
if self.type[-3:] == 'day':
datetime = np.array(ds.date.map(str))
else:
datetime = np.array(ds.datetime.map(str))
ohlc = np.array(ds.data.loc[:, ['open', 'close', 'low', 'high']])
vol = np.array(ds.volume)
kline = Kline('{}__{}__{}'.format(code, self.if_fq, self.type),
width=1360,
height=700,
page_title='QUANTAXIS')
bar = Bar()
kline.add(
self.code,
datetime,
ohlc,
mark_point=["max", "min"],
# is_label_show=True,
is_datazoom_show=True,
is_xaxis_show=False,
# is_toolbox_show=True,
tooltip_formatter='{b}:{c}', # kline_formater,
# is_more_utils=True,
datazoom_orient='horizontal')
bar.add(self.code,
datetime,
vol,
is_datazoom_show=True,
datazoom_xaxis_index=[0, 1])
grid = Grid(width=1360, height=700, page_title='QUANTAXIS')
grid.add(bar, grid_top="80%")
grid.add(kline, grid_bottom="30%")
return grid
user='******',
password='******',
db='www_802k_cn',
charset='utf8')
sql = "select * from dd_chapter"
df = pd.read_sql(sql, con, index_col="id")
df
# In[13]:
x = df['mch'].index
# In[14]:
y = df['pernums'].values
# In[20]:
attr = ["{}条".format(i) for i in x]
# v1 = [random.randint(1, 30) for _ in range(30)]
bar = Bar("每条链接引入人数")
bar.add(
"",
attr,
y,
is_datazoom_show=True,
datazoom_type="inside",
datazoom_range=[10, 25],
)
bar.render('show_increase.html')
def draw_citys_pic(csv_file):
page = Page(csv_file + ":评论城市分析")
info = count_city(csv_file)
geo = Geo("",
"Ctipsy原创",
title_pos="center",
width=1200,
height=600,
background_color='#404a59',
title_color="#fff")
while True: # 二次筛选，和pyecharts支持的城市库进行匹配，如果报错则删除该城市对应的统计
try:
attr, val = geo.cast(info)
geo.add("",
attr,
val,
visual_range=[0, 300],
visual_text_color="#fff",
is_geo_effect_show=False,
is_piecewise=True,
visual_split_number=6,
symbol_size=15,
is_visualmap=True)
except ValueError as e:
e = str(e)
e = e.split("No coordinate is specified for ")[1] # 获取不支持的城市名称
info.pop(e)
else:
break
info = sorted(info.items(), key=lambda x: x[1], reverse=False) # list排序
# print(info)
info = dict(info) # list转dict
# print(info)
attr, val = [], []
for key in info:
attr.append(key)
val.append(info[key])
geo1 = Geo("",
"评论城市分布",
title_pos="center",
width=1200,
height=600,
background_color='#404a59',
title_color="#fff")
geo1.add("",
attr,
val,
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 + "_城市dotmap.html")
page.add_chart(geo1)
geo2 = Geo(
"",
"评论来源热力图",
title_pos="center",
width=1200,
height=600,
background_color='#404a59',
title_color="#fff",
)
geo2.add("",
attr,
val,
type="heatmap",
is_visualmap=True,
visual_range=[0, 50],
visual_text_color='#fff',
is_more_utils=True)
# geo2.render(csv_file+"_城市heatmap.html") # 取CSV文件名的前8位数
page.add_chart(geo2)
bar = Bar("", "评论来源排行", title_pos="center", width=1200, height=600)
bar.add("",
attr,
val,
is_visualmap=True,
visual_range=[0, 100],
visual_text_color='#fff',
mark_point=["average"],
mark_line=["average"],
is_more_utils=True,
is_label_show=True,
is_datazoom_show=True,
xaxis_rotate=45)
# bar.render(csv_file+"_城市评论bar.html") # 取CSV文件名的前8位数
page.add_chart(bar)
pie = Pie("", "评论来源饼图", title_pos="right", width=1200, height=600)
pie.add("",
attr,
val,
radius=[20, 50],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
# pie.render(csv_file + "_城市评论Pie.html") # 取CSV文件名的前8位数
page.add_chart(pie)
page.render(csv_file + "_城市评论分析汇总.html")
# ! /usr/bin/env python
# - * - coding:utf-8 - * -
# __author__ : KingWolf
# createtime : 2018/11/23 23:29
from pyecharts import Bar
#创建Bar柱形图对象
bar = Bar(title='狼胸_主标题', subtitle='kingwolf_副标题')
#使用主题
bar.use_theme('dark')
# 主要方法，用于添加图表的数据和设置各种配置项:第一个参数是name，放在图形的右上角展示，第二个参数是X轴参数，显示的是列表或者元祖，第三个参数是Y轴参数，显示的是列表或者元祖
bar.add("鞋袜", ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"], [5, 20, 36, 10, 75, 90])
#打印输出图表的所有配置项
# bar.print_echarts_options()
#默认将会在根目录下生成一个 render.html 的文件，支持 path 参数，设置文件保存位置，如 render(r"e:\my_first_chart.html")，文件用浏览器打开。
bar.render('render2.html')
def score_draw(csv_file):
page = Page(csv_file + ":评论等级分析")
score, date, val, score_list = [], [], [], []
result = {}
path = os.path.abspath(os.curdir)
csv_file = path + "\\" + csv_file + ".csv"
csv_file = csv_file.replace('\\', '\\\\')
d = pd.read_csv(csv_file, engine='python', encoding='utf-8')[[
'score', 'date'
]].dropna() # 读取CSV转为dataframe格式，并丢弃评论为空的记录
for indexs in d.index: # 一种遍历df行的方法（下面还有第二种，iterrows）
score_list.append(tuple(
d.loc[indexs].values[:])) # 目前只找到转换为tuple然后统计相同元素个数的方法
# print("有效评分总数量为：",len(score_list), " 条")
for i in set(list(score_list)):
result[i] = score_list.count(i) # dict类型 ('很差', '2018-04-28'): 55
info = []
for key in result:
score = key[0]
date = key[1]
val = result[key]
info.append([score, date, val])
info_new = DataFrame(info) # 将字典转换成为数据框
info_new.columns = ['score', 'date', 'votes']
info_new.sort_values('date',
inplace=True) # 按日期升序排列df，便于找最早date和最晚data，方便后面插值
# print("first df", info_new)
# 以下代码用于插入空缺的数据，每个日期的评分类型应该有5中，依次遍历判断是否存在，若不存在则往新的df中插入新数值
mark = 0
creat_df = pd.DataFrame(columns=['score', 'date',
'votes']) # 创建空的dataframe
for i in list(info_new['date']):
location = info_new[(info_new.date == i)
& (info_new.score == "力荐")].index.tolist()
if location == []:
creat_df.loc[mark] = ["力荐", i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == "推荐")].index.tolist()
if location == []:
creat_df.loc[mark] = ["推荐", i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == "还行")].index.tolist()
if location == []:
creat_df.loc[mark] = ["还行", i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == "较差")].index.tolist()
if location == []:
creat_df.loc[mark] = ["较差", i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == "很差")].index.tolist()
if location == []:
creat_df.loc[mark] = ["很差", i, 0]
mark += 1
info_new = info_new.append(creat_df.drop_duplicates(), ignore_index=True)
score_list = []
info_new.sort_values('date',
inplace=True) # 按日期升序排列df，便于找最早date和最晚data，方便后面插值
# print(info_new)
for index, row in info_new.iterrows(): # 第二种遍历df的方法
score_list.append([row['date'], row['votes'], row['score']])
tr = ThemeRiver()
tr.add(['力荐', '推荐', '还行', '较差', '很差'],
score_list,
is_label_show=True,
is_more_utils=True)
page.add_chart(tr)
attr, v1, v2, v3, v4, v5 = [], [], [], [], [], []
attr = list(sorted(set(info_new['date'])))
bar = Bar()
for i in attr:
v1.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == "力荐")]['votes']))
v2.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == "推荐")]['votes']))
v3.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == "还行")]['votes']))
v4.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == "较差")]['votes']))
v5.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == "很差")]['votes']))
bar.add("力荐", attr, v1, is_stack=True)
bar.add("推荐", attr, v2, is_stack=True)
bar.add("还行", attr, v3, is_stack=True)
bar.add("较差", attr, v4, is_stack=True)
bar.add("很差",
attr,
v5,
is_stack=True,
is_convert=True,
mark_line=["average"],
is_more_utils=True)
page.add_chart(bar)
line = Line()
line.add("力荐", attr, v1, is_stack=True)
line.add("推荐", attr, v2, is_stack=True)
line.add("还行", attr, v3, is_stack=True)
line.add("较差", attr, v4, is_stack=True)
line.add("很差",
attr,
v5,
is_stack=True,
is_convert=False,
mark_line=["average"],
is_more_utils=True)
page.add_chart(line)
page.render(csv_file[:-4] + "_日投票量分析汇总.html")
def plotFoodRanging(list_y1, list_y2, list_y3, list_y4, list_y5, list_y6,
list_y7, list_y8, list_y9, list_y10, list_y11, list_y12):
page = Page()
line1 = Line("上海饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line1.add("口味", list_y1[0], list_y1[1], mark_point=["max", "min"])
line1.add("环境", list_y1[0], list_y1[2], mark_point=["max", "min"])
line1.add("服务", list_y1[0], list_y1[3], mark_point=["max", "min"])
line1.add("综合", list_y1[0], list_y1[4], mark_point=["max", "min"])
bar1 = Bar("上海饭店评分统计", "数据来源于大众点评TOP100")
bar1.add("上海", list_y1[0][:10], list_y1[4][:10], mark_point=["max", "min"])
wordcloud1 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud1.add("",
list_y1[0][:20],
list_y1[4][:20],
word_size_range=[20, 100])
line2 = Line("北京饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line2.add("口味", list_y2[0], list_y2[1], mark_point=["max", "min"])
line2.add("环境", list_y2[0], list_y2[2], mark_point=["max", "min"])
line2.add("服务", list_y2[0], list_y2[3], mark_point=["max", "min"])
line2.add("综合", list_y2[0], list_y2[4], mark_point=["max", "min"])
bar2 = Bar("北京饭店评分统计", "数据来源于大众点评TOP100")
bar2.add("北京", list_y2[0][:10], list_y2[4][:10], mark_point=["max", "min"])
wordcloud2 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud2.add("",
list_y2[0][:20],
list_y2[4][:20],
word_size_range=[20, 100])
line3 = Line("广州饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line3.add("口味", list_y3[0], list_y3[1], mark_point=["max", "min"])
line3.add("环境", list_y3[0], list_y3[2], mark_point=["max", "min"])
line3.add("服务", list_y3[0], list_y3[3], mark_point=["max", "min"])
line3.add("综合", list_y3[0], list_y3[4], mark_point=["max", "min"])
bar3 = Bar("广州饭店评分统计", "数据来源于大众点评TOP100")
bar3.add("广州", list_y3[0][:10], list_y3[4][:10], mark_point=["max", "min"])
wordcloud3 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud3.add("",
list_y3[0][:20],
list_y3[4][:20],
word_size_range=[20, 100])
line4 = Line("深圳饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line4.add("口味", list_y4[0], list_y4[1], mark_point=["max", "min"])
line4.add("环境", list_y4[0], list_y4[2], mark_point=["max", "min"])
line4.add("服务", list_y4[0], list_y4[3], mark_point=["max", "min"])
line4.add("综合", list_y4[0], list_y4[4], mark_point=["max", "min"])
bar4 = Bar("深圳饭店评分统计", "数据来源于大众点评TOP100")
bar4.add("深圳", list_y4[0][:10], list_y4[4][:10], mark_point=["max", "min"])
wordcloud4 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud4.add("",
list_y4[0][:20],
list_y4[4][:20],
word_size_range=[20, 100])
line5 = Line("天津饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line5.add("口味", list_y5[0], list_y5[1], mark_point=["max", "min"])
line5.add("环境", list_y5[0], list_y5[2], mark_point=["max", "min"])
line5.add("服务", list_y5[0], list_y5[3], mark_point=["max", "min"])
bar5 = Bar("天津饭店评分统计", "数据来源于大众点评TOP100")
bar5.add("天津", list_y5[0][:10], list_y5[4][:10], mark_point=["max", "min"])
wordcloud5 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud5.add("",
list_y5[0][:20],
list_y5[4][:20],
word_size_range=[20, 100])
line6 = Line("杭州饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line6.add("口味", list_y6[0], list_y6[1], mark_point=["max", "min"])
line6.add("环境", list_y6[0], list_y6[2], mark_point=["max", "min"])
line6.add("服务", list_y6[0], list_y6[3], mark_point=["max", "min"])
line6.add("综合", list_y6[0], list_y6[4], mark_point=["max", "min"])
bar6 = Bar("杭州饭店评分统计", "数据来源于大众点评TOP100")
bar6.add("杭州", list_y6[0][:10], list_y6[4][:10], mark_point=["max", "min"])
wordcloud6 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud6.add("",
list_y6[0][:20],
list_y6[4][:20],
word_size_range=[20, 100])
line7 = Line("南京饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line7.add("口味", list_y7[0], list_y7[1], mark_point=["max", "min"])
line7.add("环境", list_y7[0], list_y7[2], mark_point=["max", "min"])
line7.add("服务", list_y7[0], list_y7[3], mark_point=["max", "min"])
line7.add("综合", list_y7[0], list_y7[4], mark_point=["max", "min"])
bar7 = Bar("南京饭店评分统计", "数据来源于大众点评TOP100")
bar7.add("南京", list_y7[0][:10], list_y7[4][:10], mark_point=["max", "min"])
wordcloud7 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud7.add("",
list_y7[0][:20],
list_y7[4][:20],
word_size_range=[20, 100])
line8 = Line("苏州饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line8.add("口味", list_y8[0], list_y8[1], mark_point=["max", "min"])
line8.add("环境", list_y8[0], list_y8[2], mark_point=["max", "min"])
line8.add("服务", list_y8[0], list_y8[3], mark_point=["max", "min"])
line8.add("综合", list_y8[0], list_y8[4], mark_point=["max", "min"])
bar8 = Bar("苏州饭店评分统计", "数据来源于大众点评TOP100")
bar8.add("苏州", list_y8[0][:10], list_y8[4][:10], mark_point=["max", "min"])
wordcloud8 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud8.add("",
list_y8[0][:20],
list_y8[4][:20],
word_size_range=[20, 100])
line9 = Line("成都饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line9.add("口味", list_y9[0], list_y9[1], mark_point=["max", "min"])
line9.add("环境", list_y9[0], list_y9[2], mark_point=["max", "min"])
line9.add("服务", list_y9[0], list_y9[3], mark_point=["max", "min"])
line9.add("综合", list_y9[0], list_y9[4], mark_point=["max", "min"])
bar9 = Bar("成都饭店评分统计", "数据来源于大众点评TOP100")
bar9.add("成都", list_y9[0][:10], list_y9[4][:10], mark_point=["max", "min"])
wordcloud9 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud9.add("",
list_y9[0][:20],
list_y9[4][:20],
word_size_range=[20, 100])
line10 = Line("武汉饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line10.add("口味", list_y10[0], list_y10[1], mark_point=["max", "min"])
line10.add("环境", list_y10[0], list_y10[2], mark_point=["max", "min"])
line10.add("服务", list_y10[0], list_y10[3], mark_point=["max", "min"])
line10.add("综合", list_y10[0], list_y10[4], mark_point=["max", "min"])
bar10 = Bar("武汉饭店评分统计", "数据来源于大众点评TOP100")
bar10.add("武汉",
list_y10[0][:10],
list_y10[4][:10],
mark_point=["max", "min"])
wordcloud10 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud10.add("",
list_y10[0][:20],
list_y10[4][:20],
word_size_range=[20, 100])
line11 = Line("重庆饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line11.add("口味", list_y11[0], list_y11[1], mark_point=["max", "min"])
line11.add("环境", list_y11[0], list_y11[2], mark_point=["max", "min"])
line11.add("服务", list_y11[0], list_y11[3], mark_point=["max", "min"])
line11.add("综合", list_y11[0], list_y11[4], mark_point=["max", "min"])
bar11 = Bar("重庆饭店评分统计", "数据来源于大众点评TOP100")
bar11.add("重庆",
list_y11[0][:10],
list_y11[4][:10],
mark_point=["max", "min"])
wordcloud11 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud11.add("",
list_y11[0][:20],
list_y11[4][:20],
word_size_range=[20, 100])
line12 = Line("西安饭店评分统计", "数据来源于大众点评TOP100", width=1200)
line12.add("口味", list_y12[0], list_y12[1], mark_point=["max", "min"])
line12.add("环境", list_y12[0], list_y12[2], mark_point=["max", "min"])
line12.add("服务", list_y12[0], list_y12[3], mark_point=["max", "min"])
line12.add("综合", list_y12[0], list_y12[4], mark_point=["max", "min"])
bar12 = Bar("西安饭店评分统计", "数据来源于大众点评TOP100")
bar12.add("西安",
list_y12[0][:10],
list_y12[4][:10],
mark_point=["max", "min"])
wordcloud12 = WordCloud(width=1000, height=620, background_color="#EECFA1")
wordcloud12.add("",
list_y12[0][:20],
list_y12[4][:20],
word_size_range=[20, 100])
page.add(line1)
page.add(wordcloud1)
page.add(bar1)
page.add(line2)
page.add(wordcloud2)
page.add(bar2)
page.add(line3)
page.add(wordcloud3)
page.add(bar3)
page.add(line4)
page.add(wordcloud4)
page.add(bar4)
page.add(line5)
page.add(wordcloud5)
page.add(bar5)
page.add(line6)
page.add(wordcloud6)
page.add(bar6)
page.add(line7)
page.add(wordcloud7)
page.add(bar7)
page.add(line8)
page.add(wordcloud8)
page.add(bar8)
page.add(line9)
page.add(wordcloud9)
page.add(bar9)
page.add(line10)
page.add(wordcloud10)
page.add(bar10)
page.add(line11)
page.add(wordcloud11)
page.add(bar11)
page.add(line12)
page.add(wordcloud12)
page.add(bar12)
data1 = pd.DataFrame(list_y1[4][:10], list_y1[0][:10], ["综合值"])
print(data1)
data2 = pd.DataFrame(list_y2[4][:10], list_y2[0][:10], ["综合值"])
print(data2)
data3 = pd.DataFrame(list_y3[4][:10], list_y3[0][:10], ["综合值"])
print(data3)
data4 = pd.DataFrame(list_y4[4][:10], list_y4[0][:10], ["综合值"])
print(data4)
data5 = pd.DataFrame(list_y5[4][:10], list_y5[0][:10], ["综合值"])
print(data5)
data6 = pd.DataFrame(list_y6[4][:10], list_y6[0][:10], ["综合值"])
print(data6)
data7 = pd.DataFrame(list_y7[4][:10], list_y7[0][:10], ["综合值"])
print(data7)
data8 = pd.DataFrame(list_y8[4][:10], list_y8[0][:10], ["综合值"])
print(data8)
data9 = pd.DataFrame(list_y9[4][:10], list_y9[0][:10], ["综合值"])
print(data9)
data10 = pd.DataFrame(list_y10[4][:10], list_y10[0][:10], ["综合值"])
print(data10)
data11 = pd.DataFrame(list_y11[4][:10], list_y11[0][:10], ["综合值"])
print(data11)
data12 = pd.DataFrame(list_y12[4][:10], list_y12[0][:10], ["综合值"])
print(data12)
page.render("全部.html")
import pandas as pd
from pyecharts import Bar
# 读取文件
df = pd.read_csv('douban.csv',
header=0,
names=["quote", "score", "info", "title", "people"])
# 清洗数据,获取电影年份,增加年份列
dom = []
for i in df['info']:
dom.append(i.split('/')[0].replace('(中国大陆)', '').strip())
df['year'] = dom
# 计数排序
place_message = df.groupby(['year'])
place_com = place_message['year'].agg(['count'])
place_com.reset_index(inplace=True)
place_com_last = place_com.sort_index()
dom1 = place_com_last.sort_values('year', ascending=True)
# 生成柱状图
v1 = dom1['year']
attr = dom1['count']
bar = Bar("豆瓣电影TOP250-电影上映年份分布",
title_pos='center',
title_top='18',
width=800,
height=400)
bar.add("", v1, attr, is_label_show=True, is_datazoom_show=True)
bar.render('豆瓣电影TOP250上映年份分布.html')
commodity_x, sales_y, price_avg, price_y = [], [], [], []
# 筛选出前3品牌所有信息
[
commodity_x.append(list(data[data['品牌'].isin([name[i]])]['名称'][:2]))
for i in range(3)
]
[
sales_y.append(list(data[data['品牌'].isin([name[j]])]['总评数'][:2]))
for j in range(3)
]
[price_y.append(data[data['品牌'].isin([name[j]])]['名称']) for j in range(3)]
x = list(chain(*commodity_x))
sales = list(chain(*sales_y))
name_index = ['2S', 'pro', 'AC4076', 'AC4076/18', 'F-PDF35C-G', 'F-PXF35C-S']
for h in name_index:
merchant = data[data['标题'].str.contains(h)]['价格']
price_avg.append(sum(merchant) / len(merchant))
bar = Bar(width=1200, height=600) #is_label_show=True 每根柱子显示值
bar.add('畅销型号销量',
x,
sales,
line_color='green',
is_label_show=True,
xaxis_rotate=30)
line = Line()
line.add("平均价格", x, price_avg)
overlap = Overlap()
overlap.add(bar)
overlap.add(line, yaxis_index=1, is_add_yaxis=True)
overlap.render('3.2畅销产品和平均价格.html')
from pyecharts import Bar
attr = ['衬衫', '羊毛衫', '雪纺衫', '裤子', '高跟鞋', '袜子']
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar('标记线和标记示例')
bar.add('商家A', attr, v1, mark_line=['min', 'max']) #标记点：商家A的平均值
bar.add('商家B', attr, v2, mark_line=['min', 'max']) #标记线：商家B最小/最大值
bar.render('./picture4.html')
import matplotlib.pyplot as plt
from pyecharts import Geo,Style,Line,Bar,Overlap,Map, Pie
if __name__ == '__main__':
conn = pymysql.connect(host="localhost",user="******",
password="******",database="maoyan",port=3306,charset="utf8")
cursor = conn.cursor()
sql1 = "alter table moviecomment add column count_city int(40);"
sql2 = """
update moviecomment as m1 inner join
(select city, count(*) as counting from moviecomment group by city) as m2
on m1.city = m2.city set m1.count_city = m2.counting;
"""
cursor.execute(sql1)
cursor.execute(sql2)
data = pd.read_sql("select * from moviecomment", conn) # 读取moviecomment中的数据
cursor.close()
conn.commit()
conn.close()
cityData = data.groupby(['city','ranking','count_city']) # 将数据先按城市分类，再按评分分类
citydata = cityData["id"].agg(["count"]) # 将分组后的数据的id进行叠加
citydata.reset_index(inplace=True) # 重置连续的index
citydata['praise_rate'] = None
citydata = citydata[~citydata['ranking'].isin([1.0, 2.0])]
citydata['praise_rate'] = citydata.apply(lambda x: x['count'] / x['count_city'], axis=1)
bar = Bar("各省好评率对比", width=1000,height=700)
bar.add("百分比",citydata['city'],citydata['praise_rate'], is_convert=True,is_stack=True,xaxis_rotate=30,
xaxis_interval=0,is_splitline_show=True,is_label_show=True)
bar.render("D:\python_code\sample\猫眼\province_ranking.html")
'大大的三个字', '这里一共是十个字的吧', '这里一共是十个字的吧（这里是七个字）', '其他', '十全十美的十个字啊',
'python仪表盘', '快乐三个字', '可乐续保三个字', '骑缝三个字', '里面好玩三个字', '信用卡三个字', '没空理我的',
'订单问问三个字', '紫金学习三个字', '袋鼠妈妈三个字', '楼面价微信交流群', '密码三个字', '看见了来看看了解是是是',
'大门口流量数据', '烤面筋解决三个字', '到读到蓝莓味'
]
# # 设置数据
data1 = [
841, 0, 136, 0, 3317, 784, 1, 19, 691, 131, 21, 6461, 123, 0, 692, 0, 0, 0,
0, 0, 0
]
data2 = [
13056, 16614, 701, 0, 5815, 4274, 256, 689, 13838, 21723, 0, 16073, 28297,
0, 279, 463, 25261, 60400, 0, 2493, 16
]
# # 设置柱状图的主标题与副标题
bar = Bar("这里是大标题", "这里上介绍文字", width=1200, height=600)
# # 添加柱状图的数据及配置项
def label_formatter(params):
return str(params.value) + "\t\t"
bar.add("外网",
columns,
data1,
bar_category_gap='10%',
label_formatter=label_formatter,
xaxis_label_textsize=6,
grid_bottom=500,
label_text_size=8,
#!/usr/bin/Python
# -*- coding: utf-8 -*-
# @Date : 2020-09-07
# Author : flying
from pyecharts import Bar
# 绘制多个条形图
x_movies_name = ["猩球崛起", "敦刻尔克", "蜘蛛侠", "战狼2"]
y_16 = [15746, 312, 4497, 319]
y_15 = [12357, 156, 2045, 168]
y_14 = [2358, 399, 2358, 362]
bar2 = Bar(title="某年内地电影票房前20的电影", subtitle="子标题")
bar2.add('14号',x_movies_name,y_14)
bar2.add('15号',x_movies_name,y_15)
bar2.add('16号',x_movies_name,y_16)
bar2.render()
for hotcomment in data['hotComments']:
item = {
'nickname':hotcomment['user']['nickname'],
'content':hotcomment['content'],
'likedCount':hotcomment['likedCount']
}
hotcomments.append(item)
#获取评论用户名,内容,以及对应的获赞数
content_list = [content['content'] for content in hotcomments]
nickname = [content['nickname'] for content in hotcomments]
liked_count = [content['likedCount'] for content in hotcomments]
from pyecharts import Bar
bar = Bar("热评中点赞数示例图")
bar.add( "点赞数",nickname, liked_count, is_stack=True,mark_line=["min", "max"],mark_point=["average"])
bar.render()
from wordcloud import WordCloud
import matplotlib.pyplot as plt
content_text = " ".join(content_list)
wordcloud = WordCloud(font_path=r"C:\simhei.ttf",max_words=200).generate(content_text)
plt.figure()
plt.imshow(wordcloud,interpolation='bilinear')
plt.axis('off')
plt.show()
def test_bar_marks():
bar = Bar("标记线和标记点示例")
bar.add("商家A", CLOTHES, clothes_v1, mark_point=["average"])
bar.add("商家B", CLOTHES, clothes_v2, mark_line=["min", "max"])
assert '"average"' in bar._repr_html_()
# 1. 柱状图
from pyecharts import Bar
bar = Bar("我的第一个图表", "Bar")
# 将3个关键字参数打包成1个数据类型为字典的变量kwargs。
kwargs = dict(name="柱状图",
x_axis=["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"],
y_axis=[5, 20, 6, 36, 10, 75])
# kwargs作为参数传入Bar对象的add方法中时，
# 需要使用**kwargs，这样可以使其自动解包，字典中的键值对会对应函数需要的参数。
bar.add(**kwargs)
# Bar对象的render方法会产生一个html文件，可以用浏览器打开该文件进行查看。
bar.render("bar01.html")
# 2. 直方图
# 在pyecharts中，直方图也是使用Bar对象画出。
# 与柱形图的不同之处是实例化Bar对象时多了1个参数bar_category_gap，
# 含义是每个柱子之间的间隔，如果设置为0，则画直方图。
bar = Bar("我的第二个图表", "Histogram")
kwargs = dict(name="直方图",
x_axis=["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"],
y_axis=[5, 20, 6, 36, 10, 75],
bar_category_gap=0)
bar.add(**kwargs)
bar.render('Histogram.html')
# 3. 堆叠柱状图
x = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
