def huati(name,num,k):#看各级的销量
kk=[]
for i in range(len(name)):
if not numpy.isnan(num[i]):
q = []
q.append(name[i])
q.append(num[i])
# q[name[i]]=hot[i]
kk.append(q)
hh=sorted(kk,key=lambda i:i[1],reverse=True)
page=Page()
att,val=[],[]
for i in hh[:20]:
att.append(i[0])
val.append(i[1])
bar1 = Bar("", k+"A景区销量排行", title_pos="center", width=1200, height=600)
bar1.add("",att,val, is_visualmap=True, 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)
page.add_chart(bar1)
att, val = [], []
for i in hh[-20:]:
att.append(i[0])
val.append(i[1])
bar2 = Bar("", k+"A景区销量排行", title_pos="center", width=1200, height=600)
bar2.add("", att, val, is_visualmap=True, 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)
page.add_chart(bar2)
page.render(k+"A景区销量bar.html")
def make_plot(city):
city_dict = make_city_dict()
# 倒入包
data = pd.read_csv('csv_files/%s/groupby_region_df.csv'%city)
# 读取数据
configure(global_theme='vintage')
# 设置主题
X_axis = data["地区"].tolist()
v1 = data["每平方米单价(单位:元)"].tolist()
v2 = data["总价(单位:万元)"].tolist()
bar1 = Bar(title="%s各区域二手房单价分布条形图"%city_dict[city], width=1500, height=600)
bar1.add("单价",
X_axis,
v1,
mark_point=["max", "min"],
mark_line=['average'],
mark_point_textcolor='#000',
xaxis_rotate=45,
mark_point_symbol="pin", )
bar2 = Bar(title="%s各区域二手房总价分布条形图"%city_dict[city], width=1500, height=600)
bar2 = bar2.add("总价",
X_axis,
v2,
mark_point=["max", "min"],
mark_line=['average'],
xaxis_rotate=45,
mark_point_textcolor='#000',
mark_point_symbol="pin", )
page = Page()
page.add_chart(bar1)
page.add_chart(bar2)
return page
def getShowData(dataframe, start_x, stop_y, start_month, stop_month):
page = Page()
line = Line("折线图示例", width=1200, height=500)
for p in range(int(start_month), int(stop_month) + 1):
Single_month = dataframe.loc[dataframe['month'] == p]
data = Single_month.groupby(start_x)[stop_y].sum().reset_index()
line.add(str(p) + "月份",
data[start_x],
data[stop_y],
xaxis_rotate=30,
xaxis_label_textsize=12,
is_toolbox_show=False)
page.add_chart(line)
data = dataframe.groupby(start_x)[stop_y].sum().reset_index()
pie = Pie("饼图示例",
width=1200,
height=500,
title_pos="center",
extra_html_text_label=["BAR TEXT LABEL"])
pie.add("",
data[start_x],
data[stop_y],
is_label_show=True,
legend_orient="vertical",
legend_pos="left")
page.add_chart(pie)
page.render(r'show.html')
htmlf = open('show.html', 'r', encoding="utf-8")
htmlcont = htmlf.read()
return htmlcont
def make_plot(city):
city_dict = make_city_dict()
data = pd.read_csv('csv_files/%s/unit_table.csv' % city)
configure(global_theme='vintage')
attr = data.area1.tolist()
table_name = data.columns.tolist()[1:]
unit_bar = Bar("%s单价堆叠图(单位：元)" % city_dict[city],
width=1200,
height=500,
title_top=20)
for i in range(len(table_name)):
name = table_name[i]
values = data[table_name[i]].tolist()
unit_bar.add(
name,
attr,
values,
is_stack=True,
xaxis_rotate=45,
)
data = pd.read_csv('csv_files/%s/total_table.csv' % city)
configure(global_theme='vintage')
attr = data.area1.tolist()
table_name = data.columns.tolist()[1:]
total_bar = Bar("%s总价堆叠图(单位：万元)" % city_dict[city],
width=1200,
height=500,
title_top=20)
for i in range(len(table_name)):
name = table_name[i]
values = data[table_name[i]].tolist()
total_bar.add(
name,
attr,
values,
is_stack=True,
xaxis_rotate=45,
)
page = Page()
page.add_chart(unit_bar)
page.add_chart(total_bar)
return page
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 make_plot(city):
city_dict = make_city_dict()
# 倒入包
data = pd.read_csv('csv_files/%s/room_type.csv' % city)
# 读取数据
configure(global_theme='vintage')
# 设置主题
attr = data["室厅厨卫 布局"].tolist()
v1 = data["数量"].tolist()
# 数据处理
bar = Bar(title="%s各二手房 室厅厨卫 布局 条形图" % city_dict[city],
width=1200,
height=600)
bar.add(
"数量",
attr,
v1,
mark_point=["max", "min"],
xaxis_rotate=35,
mark_point_textcolor='#000',
mark_point_symbol="pin",
)
pie = Pie("%s二手房 室厅厨卫 布局 饼状图" % city_dict[city],
title_pos="left",
width=1200,
height=600)
pie.add("",
attr,
v1,
radius=[40, 80],
label_text_color=None,
is_label_show=True,
legend_orient="vertical",
legend_pos="right",
is_toolbox_show=False)
page = Page()
page.add_chart(bar)
page.add_chart(pie)
return page
def geo_map(data, title):
page = Page()
style = Style(title_color="#fff",
title_pos="center",
width=800,
height=400,
background_color='#c4ccd3')
kwargs = dict(maptype='china',
is_visualmap=True,
type="effectScatter",
is_legend_show=False,
geo_emphasis_color='c4ccd3',
visual_text_color='#2f4554')
# 创建地图模型
chart = Geo(title, "", **style.init_style)
attr, value = chart.cast(data)
# 添加数据
chart.add("", attr, value, **kwargs)
page.add_chart(chart)
return page
def makeChartsAndWriteXlsx():
a = Page()
enter = getEnterPeopleAndRate()
out = getOutPeopleAndRate()
# print(enter)
bar = Bar("入职离职信息", "{}-{}".format(startTime, endTime))
bar.add("入职", [i for i in enter[0].keys()], [len(enter[0][i]) for i in enter[0].keys()])
bar.add("离职", [i for i in enter[0].keys()], [len(out[0][i]) for i in enter[0].keys()])
bar2 = Bar("入职离职率", "{}-{}".format(startTime, endTime))
bar2.add("入职率", [i for i in enter[1].keys()], [enter[1][i] * 100 for i in enter[1].keys()], is_stack=True)
bar2.add("离职率", [i for i in enter[1].keys()], [out[1][i] * 100 for i in enter[1].keys()], is_stack=True)
a.add_chart(bar)
a.add_chart(bar2)
for i in enter[1].keys():
rate = Pie()
rate.add("{} 入职离职率饼图".format(i), ["入职", "离职"],
[enter[1][i] * 100, out[1][i] * 100], is_label_show=True)
a.add_chart(rate)
a.render()
writeXlsx("{}-{}入职人员.xlsx".format(startTime, endTime), enter[0])
writeXlsx("{}-{}离职人员.xlsx".format(startTime, endTime), out[0])
def genReport2(date):
DB = DBfunction.getDB()
ListU = DBfunction.getUserlist(DB)
for i in range(0, len(ListU)):
User = ListU[i]
ListS = DBfunction.getUserStock(DB, User)
ListM = DBfunction.getUserMethod(DB, User)
page = Page()
l1 = Reporter.plotKline('sh')
l3 = Reporter.plotKline('hs300')
page.add_chart(l1, name='the 200 day Kline of SH ')
page.add_chart(l3, name='the 200 day Kline of HS300')
for i in range(0, len(ListS)):
Symbol = ListS[i]
l1 = Reporter.plotKline(Symbol)
page.add_chart(l1, name='the 200 day Kline of ' + Symbol)
for j in range(0, len(ListM)):
stg = ListM[j]
exec('l = Reporter.plot2{}(Symbol)'.format(stg))
exec('page.add_chart(l)')
page.render('./report/' + User + '.html')
page.render('./hist/' + User + ' ' + date + '.html')
def save(self, path):
"""
将图表保存成文件
:param path: 保存的文件路径
:return:
"""
page = Page()
for chart in self.charts:
line = Line(chart.title)
line.add(
"",
chart.x_list,
chart.y_list,
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%",
)
grid = Grid(width=self.width, height=self.height)
grid.add(line, grid_top="20%")
page.add_chart(grid)
page.render(path)
def draw_power_usage_percent_pie(self, flag, vs):
test_type = self.analyzer.get_test_type(flag)
page = Page(u'App运行时功耗占比饼图')
models = self.analyzer.get_models()
pie0 = self.create_pie(vs, 0, models[0], test_type)
page.add_chart(pie0)
pie1 = self.create_pie(vs, 1, models[1], test_type)
page.add_chart(pie1)
pie2 = self.create_pie(vs, 2, models[2], test_type)
page.add_chart(pie2)
if len(models) > 3:
pie3 = self.create_pie(vs, 3, models[3], test_type)
page.add_chart(pie3)
page.render(
os.path.join(REPORTS_DIR,
'power_usage_percent_{0}.html').format(test_type))
def score_draw(csv_file):
page = Page(csv_file + ":评论等级分析")
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，并丢弃评论为空的的记录
time = sorted(set(d['date'].dropna())) #先把所有的评论时间提取出来去重，排序
score_data = pd.DataFrame(
np.zeros((len(time), 5)),
columns=['力荐', '还行', '推荐', '较差', '很差'],
index=time) #创建一个表格，其索引是时间，列是score，然后值为评论的数量，用0填充
def count_score(score_level): #score_level 即score的等级：还行，力荐等等
for i in d[d['score'] == score_level]['date'].value_counts(
).index: #遍历score——level下的时间，然后提取出相应的数量，保存在score_data中
score_data.loc[i][score_level] = d[
d['score'] == score_level]['date'].value_counts()[i]
for score_level in score_data.columns: #填充数据，没有的自然就为0
count_score(score_level)
score_bar = pyecharts.Bar('观影人数评分柱状图')
for score_level in score_data.columns:
score_bar.add('{}'.format(score_level),
score_data.index,
score_data[score_level],
is_stack=True,
is_convert=True)
page.add_chart(scor_bar)
score_line = pyecharts.Line('观影人数评分折线图')
for score_level in score_data.columns:
score_line.add('{}'.format(score_level),
score_data.index,
score_data[score_level],
is_stack=True,
xaxis_rotate=45)
page.add_chart(scor_line)
score_river_data = [] #河流主题图的数据
for i in range(len(time)):
for j in range(5):
score_river_data.append([
score_data.index[i], score_data.iloc[i, j],
score_data.columns[j]
])
score_theme_river = pyecharts.ThemeRiver("主题河流示意图")
score_theme_river.add(score_data.columns,
score_river_data,
is_label_show=True)
page.add_chart(score_theme_river)
page.render(csv_file[:-4] + "_日投票量分析汇总.html")
def draw_citys_pic(csv_file):
page = Page(csv_file+":评论城市分析")
info = count_city(csv_file)
geo = Geo("","小本聪原创",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")
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")
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 = industry_field_counts(csv_file)
industry_field_pie = pyecharts.Pie("",
"行业领域饼图",
title_pos="right",
width=1200,
height=600)
industry_field_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')
industry_field_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(industry_field_pie)
company_size_info = d['companySize'].value_counts()
company_size_pie = pyecharts.Pie("",
"公司规模饼图",
title_pos="right",
width=1200,
height=600)
company_size_pie.add("",
company_size_info._index,
company_size_info.values,
radius=[20, 50],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
company_size_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(company_size_pie)
finance_stage_info = d['financeStage'].value_counts()
finance_stage_pie = pyecharts.Pie("",
"公司融资阶段饼图",
title_pos="right",
width=1200,
height=600)
finance_stage_pie.add("",
finance_stage_info._index,
finance_stage_info.values,
radius=[20, 50],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
finance_stage_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(finance_stage_pie)
work_year_info = d['workYear'].value_counts()
work_year_pie = pyecharts.Pie("",
"职位工作经验饼图",
title_pos="right",
width=1200,
height=600)
work_year_pie.add("",
work_year_info._index,
work_year_info.values,
radius=[20, 50],
label_text_color=None,
is_label_show=True,
legend_orient='vertical',
is_more_utils=True,
legend_pos='left')
work_year_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(work_year_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 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 tna_missing_allgraph(df_key_initial, df_key_ongoing, df_key_bar_result,
df_key_bar_index, line):
df_key_bar_result_charts = df_key_bar_result.set_index(
'ExpectedUpdateDate')
df_key_bar_result_charts['Total'] = df_key_bar_result_charts.apply(
lambda x: x.sum(), axis=1)
df_key_bar_result_charts_final = pd.merge(
df_key_bar_index,
df_key_bar_result_charts,
on=['ExpectedUpdateDate'],
how='outer',
).fillna(0) # Merge 一起，用非周末的月份
Time_bar_x = []
for x_bar_time in df_key_bar_result_charts_final.ExpectedUpdateDate: # 取出x轴
x_bar_time = x_bar_time.strftime("%m-%d")
Time_bar_x.append(x_bar_time)
Ongoing_missing = df_key_bar_result_charts_final[
'Ongoing missing'].to_list() # 转换 df 元素到list
Three_month_Missing = df_key_bar_result_charts_final[
'TNA is not available within 3 month'].to_list() # 转换 df 元素到list
Six_month_Missing = df_key_bar_result_charts_final[
'TNA is not available within 6 month'].to_list() # 转换 df 元素到list
Total_line = df_key_bar_result_charts_final.Total.to_list(
) # 转换 df 元素到list
page = Page()
#---开始画Bar---
bar = Bar('Missing',
background_color='white',
title_text_size=15,
width='100%')
bar.add("Ongoing",
Time_bar_x,
Ongoing_missing,
is_stack=True,
is_more_utils=True) # is_more_utils = True 这个是开启多个小工具
bar.add("3 M",
Time_bar_x,
Three_month_Missing,
is_stack=True,
is_more_utils=True)
bar.add("6 M",
Time_bar_x,
Six_month_Missing,
is_stack=True,
is_more_utils=True)
line_bar = Line('Total',
background_color='white',
title_text_size=15,
width='100%')
line_bar.add("Total",
Time_bar_x,
Total_line,
is_fill=False,
area_opacity=0.001,
is_more_utils=True)
overlap = Overlap(width='100%') # 把 line 和bar overlap一起
overlap.add(bar)
overlap.add(line_bar)
#overlap.render()
page.add_chart(overlap) # 把 所有page 一起
page.add_chart(line)
page.render(
r'\\szmsfs03\Shared\Global Fund\Public folder\Performance & VA & ETF sharing\Performance AI Study Group\Python Code\PublicData_project1\TNA_missing\TNA_Report.html'
)
with tqdm_notebook(total=100) as pbar:
pbar.update(90)
p={}
for i in pls:
p[i] = p.get(i,0) + 1
place_list = sorted(p.items(), key=lambda x:x[1], reverse=True)[:190]
keyplace = [i[0] for i in place_list]
valueplace = [i[1] for i in place_list]
data = list(zip(keyplace,valueplace))[2:]
geo =Geo(background_color='#404a59')
attr, value =geo.cast(data)
geo.add("", attr,value, type="effectScatter", is_random=True, effect_scale=5)
#geo.render(r'D:\BI大屏\2019GEO地图.html')
page.add_chart(geo,name="geo")
#=============================================================================
# 薪资柱状图
#=============================================================================
from pyecharts import Bar
import pandas as pd
# 今年薪资
#=========================================
excel = pd.read_excel(r'D:\BI大屏\tongjixue1.xlsx')
a = []
a_avg = []
for i in range(0,len(excel["薪资"])):
meta_adx,
how='left',
left_on='channel_id',
right_on='adxid')
line1 = Line('TOP渠道消耗', title_pos="50%")
for i in top_cnt['name'].drop_duplicates():
line1.add(i,
top_cnt[top_cnt['name'] == i]['date'].apply(lambda x: str(x)),
top_cnt[top_cnt['name'] == i]['cost_r'].apply(lambda x: int(x)),
legend_pos="60%")
grid = Grid(width=1200, height=350)
grid.add(line, grid_right="55%")
grid.add(line1, grid_left="55%")
page.add_chart(grid)
#%%广告位消耗
#TOP广告位
def spot_line(cnt, name):
follow_spot = df[df['channel_id'] == cnt]
follow_spot = follow_spot.groupby(
by=['spot_id',
'date'], as_index=False).sum()[['spot_id', 'date', 'cost_r']]
spt = follow_spot[follow_spot['date'].apply(lambda x: str(x)) ==
end_time.replace('-', '')].sort_values(
by='cost_r').tail(7)['spot_id']
top_spt = follow_spot[follow_spot['spot_id'].isin(spt)] #TOP广告位
lists = []
for i, j in itertools.product(top_spt['spot_id'].drop_duplicates(),
Source_name_list, Source_num_list = counter2list(Source_counter)
Destination_name_list, Destination_num_list = counter2list(Destination_counter)
for i in range(len(Source_name_list)):
if Source_name_list[i] == 'Apple, Inc.':
Source_num_list[i] = Source_num_list[i] + 1254
if Source_name_list[i] == 'Sagemcom Broadband SAS':
Source_num_list[i] = Source_num_list[i] + 5024
for i in range(len(Destination_name_list)):
if Destination_name_list[i] == 'Apple, Inc.':
Destination_num_list[i] = Destination_num_list[i] + 4141
if Destination_name_list[i] == 'Sagemcom Broadband SAS':
Destination_num_list[i] = Destination_num_list[i] + 1149
pie1 = Pie('Source列的MAC归属机构', title_text_size=30, title_pos='center', \
width=1200, height=1500)
pie1.add("", Source_name_list, Source_num_list, is_label_show=True, center=[50, 45], radius=[0, 50], \
legend_pos='right', legend_orient='vertical', label_text_size=20)
pie2 = Pie('Destination列的MAC归属机构', title_text_size=30, title_pos='center', \
width=1200, height=1550)
pie2.add("", Destination_name_list, Destination_num_list, is_label_show=True, center=[50, 45], radius=[0, 50], \
legend_pos='right', legend_orient='vertical', label_text_size=20)
page = Page()
page.add_chart(pie1)
page.add_chart(pie2)
page.render('result_merge.html')
def draw_lines_per_scenarioes(self, model):
scenarioes_map = self.analyzer.get_model_datasets(model)
for scenario in scenarioes_map:
page = Page()
# 读取原始数据
original_folders = self.analyzer.get_data_paths(
model, scenario, self.analyzer.get_test_type(0))
integrated_folders = self.analyzer.get_data_paths(
model, scenario, self.analyzer.get_test_type(1))
original_datasets = self.analyzer.extract_dataset_from_raw_files(
original_folders)
integrated_datasets = self.analyzer.extract_dataset_from_raw_files(
integrated_folders)
if len(original_datasets) == 0 or len(integrated_datasets) == 0:
continue
# 初始化性能均值表
original_means = []
integrated_means = []
# 对选定的性能参数逐一绘制总体情况对比折线图
for counter in self.analyzer.get_counters_list():
# 读多轮测试数据并计算平均值
duration = self.analyzer.get_scenario_duration(scenario)
y = get_iterations_mean(counter, original_datasets, 0,
duration)
yy = get_iterations_mean(counter, integrated_datasets, 0,
duration)
x = range(0, len(y))
# 绘制指定设备，指定场景，指定性能指标的折线图
line = draw_line_graph(
u"%s运行时-%s" % (self.analyzer.translate(model),
self.analyzer.translate(counter)), x, y, yy)
page.add_chart(line)
# 将性能指标均值汇总
integrated_means.append(np.round(yy.mean(), decimals=2))
original_means.append(np.round(y.mean(), decimals=2))
# 计算区间性能指标均值
self.analyzer.calculate_duration_means(
duration, model, scenario, self.analyzer.get_test_type(0),
y, counter)
self.analyzer.calculate_duration_means(
duration, model, scenario, self.analyzer.get_test_type(1),
yy, counter)
# 绘制指定设备，指定场景下各性能指标汇总图
radar = self.draw_radar_per_scenario(model, integrated_folders,
integrated_means,
original_folders,
original_means, scenario)
page.add_chart(radar)
# 生成指定设备，指定场景的性能页面
page_render(
page,
os.path.join(REPORTS_DIR,
"{0}_{1}.html".format(model, scenario)))
ts.set_token('9c4af04257e55b3f490d14ac46c00cd71383ed0846d8e10694907926')
pro = ts.pro_api()
"""
大盘指数历史走势
"""
startDate = '20150101'
endDate = time.strftime('%Y%m%d', time.localtime(time.time()))
stock_list = [{'ts_code': '399006.SZ', 'ts_name': "创业板指"},
{'ts_code': '399005.SZ', 'ts_name': "中小板指"},
{'ts_code': '000037.SH', 'ts_name': "上证医药"},
{'ts_code': '399004.SZ', 'ts_name': "深证100R"},
{'ts_code': '399300.SZ', 'ts_name': "沪深300"},
{'ts_code': '399951.SZ', 'ts_name': "300银行"},
{'ts_code': '000016.SH', 'ts_name': "上证50"},
{'ts_code': '399919.SZ', 'ts_name': "300价值"},
{'ts_code': '399952.SZ', 'ts_name': "300地产"}]
page = Page()
for stock in stock_list:
line = Line(width=1600)
df = pro.index_daily(ts_code=stock['ts_code'], adj='qfq', start_date=startDate, end_date=endDate)
if df is not None:
df = df.sort_values(by="trade_date", ascending=True)
line.add(stock['ts_name'], df['trade_date'], df['close'], yaxis_min = 'dataMin')
page.add_chart(line)
page.render('index_daily.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")
page = Page()
#获得评分水球
from pyecharts import Liquid
liquid = Liquid(title + "---猫眼最新" + str(n) + '位用户预测评分',
title_color="#fff",
title_pos="center",
width=1800,
height=700)
nsum = 0
for i in range(0, len(rate)):
nsum += i
lrate = nsum / len(rate)
liquid.add("评分值", [lrate / 100])
page.add_chart(liquid)
print(nsum)
print(lrate)
print(len(rate))
print(rate)
#生成观众评分图
from pyecharts import Pie
attr = ["五星", "四星", "三星", "两星", "一星"]
v1 = [
rate.count(5) + rate.count(4.5),
rate.count(4) + rate.count(3.5),
rate.count(3) + rate.count(2.5),
rate.count(2) + rate.count(1.5),
rate.count(1) + rate.count(0.5)
]
rate = Pie(title + "---猫眼用户评分图", title_pos='center', width=1800, height=620)
def tochart(path):
df = pd.read_excel(path, sheet_name=0, encoding='ANSI')
df.reset_index()
page = Page(page_title='7月事件单分析TOP10')
#Bar
bar = Bar(width=1000, height=700)
collist = df.columns.values.tolist()
fenlei = df[collist[0]]
for col in range(1, len(collist) - 1):
ds = collist[col]
list2 = df[ds]
bar.add(ds,
fenlei,
list2,
is_stack=True,
bar_category_gap='40%',
xaxis_interval=0,
xaxis_rotate=15,
yaxis_rotate=30)
page.add_chart(bar, name="bar")
#词云图+饼图
top = ""
num = 30
wordcloud = []
pie = []
for i in range(0, 3):
keyword = []
value = []
top = fenlei[i]
fenci.fenci(top, num, keyword, value) #调用fenci
print(keyword, value)
#词云图
wordcloud.append(
WordCloud(title='↑关键词分析(TOP30)：' + str(top),
title_text_size=14,
title_top='bottom',
width=500,
height=500))
wordcloud[i].add(top,
keyword,
value,
word_size_range=[20, 60],
shape='diamond')
page.add_chart(wordcloud[i], name='wordcloud' + str(i))
#饼图
pie.append(
Pie(title='↑关键词分析(TOP10)：' + str(top),
title_text_size=14,
title_top='bottom',
width=600,
height=500))
pie[i].add(top,
keyword[0:10],
value[0:10],
radius=[30, 60],
label_text_color=None,
is_label_show=True,
legend_orient="vertical",
legend_pos="left")
page.add_chart(pie[i], name='pie' + str(i))
print('-' * 10)
page.render('7月事件单分析TOP10+关键词.html')
return 0
def main():
print(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
tr.append(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
for t in range(0, Round):
# 嗅探抓包
wlan = sniff(iface='WLAN', count=Cnt)
s = str(wlan)
print(wlan)
print(wlan.show())
# wrpcap('packet.cap', wlan)
# 提取数据
v3 = re.findall(r"\d+\.?\d*", s)
for i in range(0, len(v3)):
v1[i] += int(v3[i])
for i in range(0, len(wlan)):
try:
if 'IPv6' in wlan[i]:
v2[1] += 1
else:
v2[0] += 1
if wlan[i].payload.dst in dict.keys():
record[dict[wlan[i].payload.dst]] += 1
elif wlan[i].payload.src in dict.keys():
record[dict[wlan[i].payload.src]] += 1
# else:
# record[0] += 1
elif ('121.51' in wlan[i].payload.dst) or ('121.51' in wlan[i].payload.src) or \
('210.41' in wlan[i].payload.dst) or ('210.41' in wlan[i].payload.src):
record[4] += 1
elif ('111.231' in wlan[i].payload.dst) or ('111.231' in wlan[i].payload.src):
record[1] += 1
print(wlan[i].show())
except:
pass
# print(hexdump(p))
# 数据处理
for i in range(0, len(timerecord)):
timerecord[i].append(record[i])
timesingle[i].append(record[i] - timerecord[i][t])
timetime[i] += min(record[i] - timerecord[i][t], 1)
tr.append(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
print('this is the %dth round, sleeping for %f second(s).' % (t + 1, breaktime))
time.sleep(breaktime)
# For Debug Use
print(timerecord)
print(tr)
# 作图
global attr
page = Page()
bar = Bar('报文活跃柱状图')
bar.add('按抽样时间分类',
attr,
timetime,
# is_convert=True,
is_more_utils=True # 设置最右侧工具栏
)
page.add_chart(bar)
bar = Bar('报文请求-时间柱状图')
for i in range(0, len(timerecord)):
bar.add(attr[i],
tr[1:],
timesingle[i][1:],
is_datazoom_show=True,
# is_convert=True,
is_more_utils=True # 设置最右侧工具栏
)
page.add_chart(bar)
line = Line("访问报文数量-时间折线图")
for i in range(0, len(timerecord)):
line.add(
attr[i],
tr,
timerecord[i],
is_datazoom_show=True,
is_fill=True,
line_opacity=0.2,
area_opacity=0.4
)
page.add_chart(line)
pie = Pie('网络-IP类型饼状图', title_pos='left')
attr = ['TCP', 'UDP', 'ICMP', 'Other']
pie.add(
'', attr, v1, # ''：图例名（不使用图例）
radius=[50, 75], # 环形内外圆的半径
is_label_show=True, # 是否显示标签
label_text_color=None, # 标签颜色
legend_orient='vertical', # 图例垂直
legend_pos='right'
)
attr = ['IP', 'IPv6']
pie.add(
'', attr, v2,
radius=[15, 35],
is_label_show=True,
label_text_color=None,
legend_orient='vertical',
legend_pos='right'
)
page.add_chart(pie)
# 保存
page.render('./page.html')
# 打开
chromepath = 'C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe'
webbrowser.register('chrome', None, webbrowser.BackgroundBrowser(chromepath))
webbrowser.get('chrome').open('page.html')
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')
width=1400,
height=720,
title_pos='center')
for i in range(10):
scatter2d.add('%i' % i,
data['x'][label == i],
data['y'][label == i],
legend_orient='vertical',
legend_pos='5%',
legend_top='center',
yaxis_pos='right',
label_fomatter='{a}',
is_datazoom_show=True,
datazoom_type='both',
label_formatter='{a}')
page.add_chart(scatter2d)
data3d = pd.read_csv('img3d.csv', sep=',', names=['x', 'y', 'z'])
scatter3d = Scatter(title='PCA with 3 components',
width=1400,
height=720,
title_pos='center')
for i in range(10):
t = list(data3d['z'][label == i])
scatter3d.add('%i' % i,
data3d['x'][label == i],
data3d['y'][label == i],
extra_data=list(data3d['z'][label == i]),
is_visualmap=True,
visual_type='size',
visual_range_size=[5, 15],
visual_range=[min(t), max(t)],
ts_code = '601318.SH'
ts_name = '中国平安'
startDate = '20150101'
endDate = time.strftime('%Y%m%d', time.localtime(time.time()))
page = Page()
df = pro.income(ts_code=ts_code, start_date=startDate, end_date=endDate)
df = df.sort_values(by="ann_date", ascending=True)
bar = Bar('利润表', width=1600, height=800)
bar.add('营业收入', df['ann_date'], df['revenue'], is_label_show=True)
bar.add('营业利润', df['ann_date'], df['operate_profit'], is_label_show=True)
bar.add('净利润', df['ann_date'], df['n_income_attr_p'], is_label_show=True)
bar.add('基本EPS', df['ann_date'], df['basic_eps'], is_label_show=True)
bar.add('稀释EPS', df['ann_date'], df['diluted_eps'], is_label_show=True)
page.add_chart(bar)
df = pro.balancesheet(ts_code=ts_code, start_date=startDate, end_date=endDate)
df = df.sort_values(by="ann_date", ascending=True)
bar = Bar('资产负债表', width=1600, height=800)
bar.add('总资产', df['ann_date'], df['total_assets'], is_label_show=True)
bar.add('总负债', df['ann_date'], df['total_liab'], is_label_show=True)
page.add_chart(bar)
df = pro.cashflow(ts_code=ts_code, start_date=startDate, end_date=endDate)
df = df.sort_values(by="ann_date", ascending=True)
bar = Bar('现金流量表', width=1600, height=800)
bar.add('经营现金流', df['ann_date'], df['n_cashflow_act'], is_label_show=True)
bar.add('投资现金流', df['ann_date'], df['n_cashflow_inv_act'], is_label_show=True)
def draw_score(comments):
print("正在处理观众评论走势与时间的关系......")
page = Page() # 页面储存器
score, date, value, score_list = [], [], [], []
result = {} # 存储评分结果
d = comments[['score', 'startTime']].dropna() # 获取评论时间
d['startTime'] = d['startTime'].apply(
lambda x: pd.to_datetime(x.split(' ')[0])) # 获取评论日期（删除具体时间）并记录
d['startTime'] = d['startTime'].apply(lambda x: judgeTime(
x, startTime_tag)) # 将2019.2.4号之前的数据汇总到2.4 统一标识为电影上映前影评数据
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[:])) # 评分与日期连接 转换为tuple然后统计相同元素个数
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，统计相同日期相同评分对应数
info = []
for key in result:
score = key[0] # 取分数
date = key[1] # 日期
value = result[key] # 数量
info.append([score, date, value])
info_new = pd.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
# 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10种，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 == 5.0)].index.tolist()
if location == []:
creat_df.loc[mark] = [5.0, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 4.5)].index.tolist()
if location == []:
creat_df.loc[mark] = [4.5, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 4.0)].index.tolist()
if location == []:
creat_df.loc[mark] = [4.0, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 3.5)].index.tolist()
if location == []:
creat_df.loc[mark] = [3.5, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 3.0)].index.tolist()
if location == []:
creat_df.loc[mark] = [3.0, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 2.5)].index.tolist()
if location == []:
creat_df.loc[mark] = [2.5, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 2.0)].index.tolist()
if location == []:
creat_df.loc[mark] = [2.0, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 1.5)].index.tolist()
if location == []:
creat_df.loc[mark] = [1.5, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 1.0)].index.tolist()
if location == []:
creat_df.loc[mark] = [1.0, i, 0]
mark += 1
location = info_new[(info_new.date == i)
& (info_new.score == 0.5)].index.tolist()
if location == []:
creat_df.loc[mark] = [0.5, i, 0]
mark += 1
info_new = info_new.append(creat_df.drop_duplicates(), ignore_index=True)
score_list = [] # 重置score_list
info_new = info_new[~(info_new['score'] == 0.0)] # 剔除无评分的数据
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
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('《流浪地球》观众评论走势与时间的关系-河流图', '数据来源：猫眼电影 数据分析：16124278-王浩',
**style_size.init_style) # 河流图初始化
tr.add([5.0, 4.5, 4.0, 3.5, 3.0, 2.5, 2.0, 1.5, 1.0, 0.5],
score_list,
is_label_show=True,
is_more_utils=True) # 设置参数
page.add_chart(tr) # 加入渲染队列
attr, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10 = [], [], [], [], [], [], [], [], [], [], []
attr = list(sorted(set(info_new['date'])))
bar = Bar('《流浪地球》观众评论走势与时间的关系-横向柱状图', '数据来源：猫眼电影 数据分析：16124278-王浩',
**style_others.init_style) # 初始化图表
for i in attr:
v1.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 5.0)]['votes']))
v2.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 4.5)]['votes']))
v3.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 4.0)]['votes']))
v4.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 3.5)]['votes']))
v5.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 3.0)]['votes']))
v6.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 2.5)]['votes']))
v7.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 2.0)]['votes']))
v8.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 1.5)]['votes']))
v9.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 1.0)]['votes']))
v10.append(
int(info_new[(info_new['date'] == i)
& (info_new['score'] == 0.5)]['votes']))
bar.add(5.0, attr, v1, is_stack=True)
bar.add(4.5, attr, v2, is_stack=True)
bar.add(4.0, attr, v3, is_stack=True)
bar.add(3.5, attr, v4, is_stack=True)
bar.add(3.0, attr, v5, is_stack=True)
bar.add(2.5, attr, v6, is_stack=True)
bar.add(2.0, attr, v7, is_stack=True)
bar.add(1.5, attr, v8, is_stack=True)
bar.add(1.0, attr, v9, is_stack=True)
bar.add(0.5,
attr,
v10,
is_stack=True,
is_convert=True,
is_more_utils=True,
xaxis_max=45000)
page.add_chart(bar)
line = Line('《流浪地球》观众评论走势与时间的关系', '数据来源：猫眼电影 数据分析：16124278-王浩',
**style_others.init_style) # 初始化图表
line.add(5.0, attr, v1, is_stack=True, mark_line=["average"])
line.add(4.5, attr, v2, is_stack=True, mark_line=["average"])
line.add(4.0, attr, v3, is_stack=True, mark_line=["average"])
line.add(3.5, attr, v4, is_stack=True, mark_line=["average"])
line.add(3.0, attr, v5, is_stack=True, mark_line=["average"])
line.add(2.5, attr, v6, is_stack=True, mark_line=["average"])
line.add(2.0, attr, v7, is_stack=True, mark_line=["average"])
line.add(1.5, attr, v8, is_stack=True, mark_line=["average"])
line.add(1.0, attr, v9, is_stack=True, mark_line=["average"])
line.add(0.5,
attr,
v10,
is_stack=True,
is_convert=False,
mark_line=["average"],
is_more_utils=True,
yaxis_max=45000)
page.add_chart(line)
page.render("./output/观众评论与日投票-走势图.html") # 渲染
print("观众评论走势与时间的关系已完成!!!")
return int(time.mktime(ts))
############################
meta_adx=pd.read_excel(r'C:\Users\Administrator\Desktop\工作\dsp数据\meta_adx.xls')
meta_product=pd.read_excel(r'C:\Users\Administrator\Desktop\工作\dsp数据\meta_product.xls')
meta_spot=pd.read_excel(r'C:\Users\Administrator\Desktop\工作\dsp数据\meta_spot.xls')
meta_dsp_user=pd.read_excel(r'C:\Users\Administrator\Desktop\工作\dsp数据\meta_dsp_user.xls')
begin_time = (date.today() + timedelta(days = -7)).strftime("%Y-%m-%d")
end_time = (date.today() + timedelta(days = -1)).strftime("%Y-%m-%d")
#%%
page = Page()
line1 = Line(""," 图表中TOP消耗的入榜标准是昨日消耗最高的，涨幅TOP的入榜标准是昨日涨跌差值最大的"\
,width="1200px",height="100px",subtitle_color='#000',subtitle_text_size=17)
page.add_chart(line1)
#%% 总消耗走势
querybody = {
"begin_time": date2ts(begin_time),
"end_time": date2ts(end_time),
"timeout": 300000,
"keys": [
"date"
],
"dims": [],
"query_type": "default",
"metrics": [
"cost_r",
],
"orderby": [
