def v_positions_history(self, end=yesterdaydash(), rendered=True):
"""
river chart visulization of positions ratio history
use text size to avoid legend overlap in some sense, eg. legend_text_size=8
"""
start = self.totcftable.iloc[0].date
times = pd.date_range(start, end)
tdata = []
for date in times:
sdata = sorted(
[(
date,
fob.briefdailyreport(date).get("currentvalue", 0),
fob.name,
) for fob in self.fundtradeobj],
key=lambda x: x[1],
reverse=True,
)
tdata.extend(sdata)
tr = ThemeRiver()
tr.add(
series_name=[foj.name for foj in self.fundtradeobj],
data=tdata,
label_opts=opts.LabelOpts(is_show=False),
singleaxis_opts=opts.SingleAxisOpts(type_="time",
pos_bottom="10%"),
)
if rendered:
return tr.render_notebook()
else:
return tr
def theme_river(open_file) -> ThemeRiver:
"""
根据定义好的格式，利用pyecharts绘制主题河流图
:param open_file:
:return:
"""
title_str = str(open_file).strip().split("/")[-1].split(".")[0]
title_str = "主题河流图<" + title_str + ">"
# 打开文件读取数据
theme_list = []
res_list = []
file_in = open(open_file, "r", encoding="utf-8")
for line in file_in.readlines():
line = line.strip().split(",")
res_list.append(line)
if line[-1] not in theme_list:
theme_list.append(line[-1])
c = (ThemeRiver(
init_opts=opts.InitOpts(width="1900px",
height="900px",
page_title=title_str,
theme=ThemeType.SHINE)).add(
theme_list,
res_list,
label_opts=opts.LabelOpts(is_show=False),
singleaxis_opts=opts.SingleAxisOpts(
type_="time",
pos_bottom="10%")).set_global_opts(
title_opts=opts.TitleOpts(
title=title_str)))
return c
def themeriver() -> ThemeRiver:
a = [1,10,100,110,130,130] #模拟确诊
b = [0,2,20,50,100,102] #模拟治愈
c = [0,1,10,15,18,18] #模拟死亡
x = [1,2,3,4,5,6] #模拟日期
confirm = [list(z) for z in zip(x,a)]
for i in confirm:
i.append('确诊')
heal = [list(z) for z in zip(x,b)]
for i in heal:
i.append('治愈')
dead = [list(z) for z in zip(x,c)]
for i in dead:
i.append('死亡')
data = confirm + heal + dead
#print(data)
c = (
ThemeRiver()
.add(
["DQ", "TY", "SS"],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"),
)
.set_global_opts(title_opts=opts.TitleOpts(title="ThemeRiver-基本示例"))
)
return c
def th_base():
c = (ThemeRiver().add(
["休息", "锻炼", "自学", "玩或看剧", "虚空时间", "思考或琐事"],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"),
).set_global_opts(title_opts=opts.TitleOpts(title="ThemeRiver")))
return c
def v_positions_history(self, end=yesterdaydash(), **vkwds):
'''
river chart visulization of positions ratio history
use text size to avoid legend overlap in some sense, eg. legend_text_size=8
'''
start = self.totcftable.iloc[0].date
times = pd.date_range(start, end)
tdata = []
for date in times:
sdata = sorted([(date, fob.briefdailyreport(date).get('currentvalue', 0), fob.aim.name)
for fob in self.fundtradeobj], key=lambda x: x[1], reverse=True)
tdata.extend(sdata)
tr = ThemeRiver()
tr.add([foj.aim.name for foj in self.fundtradeobj], tdata, is_datazoom_show=True,
is_label_show=False, legend_top="0%", legend_orient='horizontal', **vkwds)
return tr
def dbscore(movie_name):
#读取数据
with open(movie_name + '\\' + movie_name + 'dbscores.txt',
'r+',
encoding='utf-8') as m:
allthings = m.read().split(',')
del allthings[-1]
all_date = []
points_dic = {}
#按评价进行分类
for div in allthings:
point, date = div.split()
if date not in all_date:
points_dic[date] = {
'很差': 0,
'较差': 0,
'还行': 0,
'推荐': 0,
'力荐': 0
}
all_date.append(date)
if point == '很差':
points_dic[date]['很差'] += 1
elif point == '较差':
points_dic[date]['较差'] += 1
elif point == '还行':
points_dic[date]['还行'] += 1
elif point == '推荐':
points_dic[date]['推荐'] += 1
else:
points_dic[date]['力荐'] += 1
#处理数据
data = []
for month, grade in points_dic.items():
for hzc, num in grade.items():
counting = []
counting.append(month)
counting.append(num)
counting.append(hzc)
data.append(counting)
#出图
themeriver = (ThemeRiver(init_opts=opts.InitOpts(
theme=ThemeType.WESTEROS)).add(
['很差', '较差', '还行', '推荐', '力荐'],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time",
pos_bottom="10%"),
).set_global_opts(title_opts=opts.TitleOpts(title=movie_name +
" 豆瓣评价分布图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True),
datazoom_opts=[
opts.DataZoomOpts(is_show=True,
range_start=0,
range_end=100)
]))
themeriver.render(movie_name + '\\' + movie_name + 'dbScore.html')
def test_themeriver_basefake_writer(fake_writer):
data = [
["2015/11/08", 10, "DQ"],
["2015/11/20", 30, "TY"],
["2015/11/08", 21, "SS"],
["2015/11/14", 7, "QG"],
["2015/11/22", 4, "SY"],
["2015/11/20", 26, "DD"],
]
c = ThemeRiver().add(
["DQ", "TY", "SS", "QG", "SY", "DD"],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"),
)
c.render()
_, content = fake_writer.call_args[0]
eq_(c.theme, "white")
eq_(c.renderer, "canvas")
def draw_river_picture(series_name, data, to_file, svg_name):
"""
主题河流图
:param series_name: [str]
:param data: [[date, value, series_name]]
:param svg_name: svg文件
:param to_file: 结果文件
:return:
"""
bar = ThemeRiver(init_opts=opts.InitOpts(width="800px", height="600px", bg_color='white')) \
.add(
series_name=series_name,
data=data,
singleaxis_opts=opts.SingleAxisOpts(
pos_top="2%",
pos_bottom="10%",
pos_right="20%",
type_="time",
name_textstyle_opts=opts.TextStyleOpts(font_size=25),
axislabel_opts=opts.LabelOpts(font_size=25)
),
label_opts=opts.LabelOpts(is_show=False, position='bottom', distance='200px'),
) \
.set_global_opts(
tooltip_opts=opts.TooltipOpts(trigger="axis", axis_pointer_type="line"),
toolbox_opts=opts.ToolboxOpts(
feature=opts.ToolBoxFeatureOpts(
# data_zoom=opts.ToolBoxFeatureDataZoomOpts(is_show=False),
# brush=opts.ToolBoxFeatureBrushOpts(is_show=False),
)
),
legend_opts=opts.LegendOpts(type_="scroll",
pos_left="82%",
pos_top="18%",
orient="vertical",
backgroundColor='rgb(255, 255, 255)',
item_width=40,
item_height=20,
textstyle_opts=opts.TextStyleOpts(font_size=25)
)
)
make_snapshot(snapshot, bar.render(to_file), svg_name) # 生成svg图片
def draw_river_picture_right_legend(series_name,
data,
to_file,
svg_name,
pos_right,
width='800px'):
"""
主题河流图
:param width:
:param pos_right:
:param series_name: [str]
:param data: [[date, value, series_name]]
:param svg_name: svg文件
:param to_file: 结果文件
:return:
"""
bar = ThemeRiver(init_opts=opts.InitOpts(width="800px", height="600px", bg_color='white')) \
.add(
series_name=series_name,
data=data,
singleaxis_opts=opts.SingleAxisOpts(
pos_top="50",
pos_bottom="50",
type_="time",
name_textstyle_opts=opts.TextStyleOpts(font_size=20),
axislabel_opts=opts.LabelOpts(font_size=20)
),
label_opts=opts.LabelOpts(is_show=False),
) \
.set_global_opts(
tooltip_opts=opts.TooltipOpts(trigger="axis", axis_pointer_type="line"),
toolbox_opts=opts.ToolboxOpts(
feature=opts.ToolBoxFeatureOpts(
data_zoom=opts.ToolBoxFeatureDataZoomOpts(is_show=False),
# brush=opts.ToolBoxFeatureBrushOpts(is_show=False),
)
),
legend_opts=opts.LegendOpts(pos_right=pos_right,
pos_top="2%",
orient="vertical",
item_width=30,
item_height=14,
textstyle_opts=opts.TextStyleOpts(font_size=18)
),
)
grid = (Grid(init_opts=opts.InitOpts(
width=width, height="600px", bg_color='rgb(255, 255, 255)')).add(
bar,
grid_opts=opts.GridOpts(pos_right='10%'),
is_control_axis_index=True))
make_snapshot(snapshot, grid.render(to_file), svg_name) # 生成svg图片
def list_2theme_river(res_list, opts_title_name)->ThemeRiver:
"""
根据传入的list数据，利用pyecharts绘制主题河流图
:param res_list:
:param opts_title_name:
:return:
"""
c = (
ThemeRiver(init_opts=opts.InitOpts(width="1920px", height="1080px", page_title=opts_title_name, theme=ThemeType.SHINE))
.add(['A1课题', '重点滚动课题', 'A2课题', 'B类课题', '部软科学', '院软科学', '团队课题', '支撑类'],
res_list,
label_opts=opts.LabelOpts(is_show=False),
singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"))
.set_global_opts(title_opts=opts.TitleOpts(title=opts_title_name))
)
return c
def bar_base() -> Bar:
data = [
["2015/11/08", 10, "DQ"],
["2015/11/09", 15, "DQ"],
["2015/11/10", 35, "DQ"],
["2015/11/14", 7, "DQ"],
["2015/11/15", 2, "DQ"],
]
c = (ThemeRiver().add(
["DQ", "TY", "SS", "QG", "SY", "DD"],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"),
).set_global_opts(title_opts=opts.TitleOpts(
title="ThemeRiver-基本示例")).dump_options_with_quotes())
return c
def IMDBscore(movie_name):
#处理爬取的数据
with open(movie_name+'\\'+movie_name+'Dscores.txt','r+',encoding='utf-8') as m:
allthings = m.read().split(',')
del allthings[-1]
all_date=[]
points_dic={}
#按分数进行分类
for div in allthings:
point,date = div.split()
if date not in all_date:
points_dic[date]={'好评':0,'中评':0,'差评':0}
all_date.append(date)
if int(point) <= 3:
points_dic[date]['差评']+=1
elif int(point) >= 7:
points_dic[date]['好评']+=1
else:
points_dic[date]['中评']+=1
#整理便于出图
data = []
for month, grade in points_dic.items():
for hzc, num in grade.items():
counting = []
counting.append(month)
counting.append(num)
counting.append(hzc)
data.append(counting)
#出图
themeriver=(
ThemeRiver(init_opts=opts.InitOpts(theme=ThemeType.WESTEROS))
.add(
['好评','中评','差评'],data,singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"),
)
.set_global_opts(title_opts=opts.TitleOpts(title=movie_name+" IMDB评价分布主题河流图",subtitle=None)
,toolbox_opts=opts.ToolboxOpts(is_show=True),
datazoom_opts=[opts.DataZoomOpts(is_show=True,range_start=0,range_end=100)])
)
themeriver.render(movie_name+'\\'+movie_name+'IMDBScore.html')
def themeriver_example() -> ThemeRiver:
data = [
["2015/11/08", 10, "DQ"],
["2015/11/09", 15, "DQ"],
["2015/11/10", 35, "DQ"],
["2015/11/14", 7, "DQ"],
["2015/11/15", 2, "DQ"],
["2015/11/16", 17, "DQ"],
["2015/11/17", 33, "DQ"],
["2015/11/18", 40, "DQ"],
["2015/11/19", 32, "DQ"],
["2015/11/20", 26, "DQ"],
["2015/11/08", 35, "TY"],
["2015/11/09", 36, "TY"],
["2015/11/10", 37, "TY"],
["2015/11/11", 22, "TY"],
["2015/11/12", 24, "TY"],
["2015/11/13", 26, "TY"],
["2015/11/14", 34, "TY"],
["2015/11/15", 21, "TY"],
["2015/11/16", 18, "TY"],
["2015/11/17", 45, "TY"],
["2015/11/18", 32, "TY"],
["2015/11/19", 35, "TY"],
["2015/11/20", 30, "TY"],
["2015/11/08", 21, "SS"],
["2015/11/09", 25, "SS"],
["2015/11/10", 27, "SS"],
["2015/11/11", 23, "SS"],
["2015/11/12", 24, "SS"],
["2015/11/13", 21, "SS"],
["2015/11/14", 35, "SS"],
["2015/11/15", 39, "SS"],
["2015/11/16", 40, "SS"],
["2015/11/17", 36, "SS"],
["2015/11/18", 33, "SS"],
["2015/11/19", 43, "SS"],
["2015/11/20", 40, "SS"],
["2015/11/14", 7, "QG"],
["2015/11/15", 2, "QG"],
["2015/11/16", 17, "QG"],
["2015/11/17", 33, "QG"],
["2015/11/18", 40, "QG"],
["2015/11/19", 32, "QG"],
["2015/11/20", 26, "QG"],
["2015/11/21", 35, "QG"],
["2015/11/22", 40, "QG"],
["2015/11/23", 32, "QG"],
["2015/11/24", 26, "QG"],
["2015/11/25", 22, "QG"],
["2015/11/08", 10, "SY"],
["2015/11/09", 15, "SY"],
["2015/11/10", 35, "SY"],
["2015/11/11", 38, "SY"],
["2015/11/12", 22, "SY"],
["2015/11/13", 16, "SY"],
["2015/11/14", 7, "SY"],
["2015/11/15", 2, "SY"],
["2015/11/16", 17, "SY"],
["2015/11/17", 33, "SY"],
["2015/11/18", 40, "SY"],
["2015/11/19", 32, "SY"],
["2015/11/20", 26, "SY"],
["2015/11/21", 35, "SY"],
["2015/11/22", 4, "SY"],
["2015/11/23", 32, "SY"],
["2015/11/24", 26, "SY"],
["2015/11/25", 22, "SY"],
["2015/11/08", 10, "DD"],
["2015/11/09", 15, "DD"],
["2015/11/10", 35, "DD"],
["2015/11/11", 38, "DD"],
["2015/11/12", 22, "DD"],
["2015/11/13", 16, "DD"],
["2015/11/14", 7, "DD"],
["2015/11/15", 2, "DD"],
["2015/11/16", 17, "DD"],
["2015/11/17", 33, "DD"],
["2015/11/18", 4, "DD"],
["2015/11/19", 32, "DD"],
["2015/11/20", 26, "DD"],
]
c = (ThemeRiver().add(
["DQ", "TY", "SS", "QG", "SY", "DD"],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time", pos_bottom="10%"),
).set_global_opts(title_opts=opts.TitleOpts(title="ThemeRiver-基本示例")))
return c
["2015/11/20", 26, "DD"],
["2015/11/21", 35, "DD"],
["2015/11/22", 40, "DD"],
["2015/11/23", 32, "DD"],
["2015/11/24", 26, "DD"],
["2015/11/25", 22, "DD"],
["2015/11/26", 16, "DD"],
["2015/11/27", 22, "DD"],
["2015/11/28", 10, "DD"],
]
c = (ThemeRiver(init_opts=opts.InitOpts(width="1600px", height="800px")).add(
series_name=series_data,
data=data,
singleaxis_opts=opts.SingleAxisOpts(
pos_top="50",
pos_bottom="50",
type_="time",
)).set_global_opts(tooltip_opts=opts.TooltipOpts(
trigger="axis", axis_pointer_type="line")).render("theme_river.html"))
# Section4 词云图
from pyecharts.charts import WordCloud
data = [
("生活资源", "999"),
("供热管理", "888"),
("供气质量", "777"),
("生活用水管理", "688"),
("一次供水问题", "588"),
("交通运输", "516"),
def scoring_trend_analysis(self, flag):
choose = flag
with open(r'./用户影评相关数据/' + self.filmname + '用户影评相关信息.json',
'r',
encoding='UTF-8') as f:
t1 = json.load(f, strict=False)
if choose == '1':
self.textBrowser.append("开始生成" + self.filmname +
"的评论推荐度与日期分析柱状图......")
QApplication.processEvents()
if choose == '2':
self.textBrowser.append("开始生成" + self.filmname +
"的评论推荐度与日期分析折线图......")
QApplication.processEvents()
if choose == '3':
self.textBrowser.append("开始生成" + self.filmname +
"的评论推荐度与日期分析河状图......")
QApplication.processEvents()
# 取出里面的评分数据
score, date, val, command_date_list = [], [], [], []
result = {}
for each in t1:
command_date_list.append((each['用户推荐度'], each['用户评论时间']))
# 数出各个日期各个得分的数量
for i in set(list(command_date_list)):
result[i] = command_date_list.count(i) # dict类型
info = []
# 将计数好的数据重新打包
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']
# 按日期升序排列df
info_new.sort_values('date', inplace=True)
# 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)
command_date_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
for index, row in info_new.iterrows():
command_date_list.append([row['date'], row['votes'], row['score']])
attr, v1, v2, v3, v4, v5 = [], [], [], [], [], []
attr = list(sorted(set(info_new['date'])))
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']))
# 柱状图
if choose == '1':
c = (Bar(
init_opts=opts.InitOpts(width="665px", height="500px")
).add_xaxis(attr).add_yaxis("力荐", v1, stack="stack1").add_yaxis(
"推荐", v2,
stack="stack1").add_yaxis("还行", v3, stack="stack1").add_yaxis(
"较差", v4, stack="stack1").add_yaxis(
"很差", v5,
stack="stack1").reversal_axis().set_series_opts(
label_opts=opts.LabelOpts(
is_show=False)).set_global_opts(
tooltip_opts=opts.TooltipOpts(
is_show=True),
toolbox_opts=opts.ToolboxOpts(
is_show=True,
pos_right="30%",
),
title_opts=opts.TitleOpts(
title="用户评论推荐度柱状图"),
datazoom_opts=opts.DataZoomOpts(
type_="inside",
range_start=0,
range_end=100),
).render("./爬虫数据关联可视化/" + self.filmname +
"影评可视化数据/bar_reversal_axis.html"))
QApplication.processEvents()
self.comment_columnar_pic = (Bar(
init_opts=opts.InitOpts(width="665px", height="500px")
).add_xaxis(attr).add_yaxis("力荐", v1, stack="stack1").add_yaxis(
"推荐", v2,
stack="stack1").add_yaxis("还行", v3, stack="stack1").add_yaxis(
"较差", v4, stack="stack1").add_yaxis(
"很差", v5,
stack="stack1").reversal_axis().set_series_opts(
label_opts=opts.LabelOpts(
is_show=False)).set_global_opts(
tooltip_opts=opts.TooltipOpts(
is_show=True),
toolbox_opts=opts.ToolboxOpts(
is_show=True,
pos_right="30%",
),
title_opts=opts.TitleOpts(
title="用户评论推荐度柱状图"),
datazoom_opts=opts.DataZoomOpts(
type_="inside",
range_start=0,
range_end=100),
))
self.saveflag = '4'
self.textBrowser.append("开始生成" + self.filmname +
"的评论推荐度与日期分析柱状图完成！")
QApplication.processEvents()
self.show_scoring_trend_analysis_columnar()
QApplication.processEvents()
# 折线图
if choose == '2':
polyline = (Line(
init_opts=opts.InitOpts(width="665px", height="500px")
).add_xaxis(attr).add_yaxis("力荐", v1, stack="stack1").add_yaxis(
"推荐", v2,
stack="stack1").add_yaxis("还行", v3, stack="stack1").add_yaxis(
"较差", v4, stack="stack1").add_yaxis(
"很差", v5, stack="stack1").set_global_opts(
tooltip_opts=opts.TooltipOpts(is_show=True),
toolbox_opts=opts.ToolboxOpts(
is_show=True,
pos_right="30%",
),
title_opts=opts.TitleOpts(title="用户评论推荐度折线图"),
datazoom_opts=opts.DataZoomOpts(type_="inside",
range_start=0,
range_end=100),
).render("./爬虫数据关联可视化/" + self.filmname +
"影评可视化数据/line_markpoint.html"))
QApplication.processEvents()
self.comment_polyline_pic = (Line(
init_opts=opts.InitOpts(width="665px", height="500px")
).add_xaxis(attr).add_yaxis("力荐", v1, stack="stack1").add_yaxis(
"推荐", v2,
stack="stack1").add_yaxis("还行", v3, stack="stack1").add_yaxis(
"较差", v4, stack="stack1").add_yaxis(
"很差", v5, stack="stack1").set_global_opts(
tooltip_opts=opts.TooltipOpts(is_show=True),
toolbox_opts=opts.ToolboxOpts(
is_show=True,
pos_right="30%",
),
title_opts=opts.TitleOpts(title="用户评论推荐度折线图"),
datazoom_opts=opts.DataZoomOpts(type_="inside",
range_start=0,
range_end=100),
))
self.saveflag = '5'
self.textBrowser.append(self.filmname + "的评论推荐度与日期分析折线图完成！")
QApplication.processEvents()
self.show_scoring_trend_analysis_polyline()
QApplication.processEvents()
# 河流图
if choose == '3':
river = (ThemeRiver(
init_opts=opts.InitOpts(width="665px", height="500px")).add(
series_name=['力荐', '推荐', '还行', '较差', '很差'],
data=command_date_list,
singleaxis_opts=opts.SingleAxisOpts(pos_top="50",
pos_bottom="50",
type_="time"),
).set_global_opts(
tooltip_opts=opts.TooltipOpts(is_show=True,
trigger="axis",
axis_pointer_type="line"),
toolbox_opts=opts.ToolboxOpts(
is_show=True,
pos_right="30%",
),
title_opts=opts.TitleOpts(title="推荐度河流图"),
datazoom_opts=opts.DataZoomOpts(type_="inside",
range_start=0,
range_end=100),
).render("./爬虫数据关联可视化/" + self.filmname +
"影评可视化数据/theme_river.html"))
QApplication.processEvents()
self.comment_river_pic = (ThemeRiver(
init_opts=opts.InitOpts(width="665px", height="500px")).add(
series_name=['力荐', '推荐', '还行', '较差', '很差'],
data=command_date_list,
singleaxis_opts=opts.SingleAxisOpts(pos_top="50",
pos_bottom="50",
type_="time"),
).set_global_opts(
tooltip_opts=opts.TooltipOpts(is_show=True,
trigger="axis",
axis_pointer_type="line"),
toolbox_opts=opts.ToolboxOpts(
is_show=True,
pos_right="30%",
),
title_opts=opts.TitleOpts(title="推荐度河流图"),
datazoom_opts=opts.DataZoomOpts(type_="inside",
range_start=0,
range_end=100),
))
self.saveflag = '6'
self.textBrowser.append(self.filmname + "的评论推荐度与日期分析河状图完成！")
QApplication.processEvents()
self.show_scoring_trend_analysis_river()
QApplication.processEvents()
dim=7,
name="等级",
type_="category",
data=["优", "良", "轻度污染", "中度污染", "重度污染", "严重污染"],
),
]
parallel = Parallel()
# 添加坐标轴和数据
parallel.add_schema(schema=schema).add("", data)
parallel.render_notebook()
# %% [markdown]
# ### Radar -- 雷达图
radar = Radar()
radar.add_schema(schema=[
opts.RadarIndicatorItem(name=_k, max_=200) for _k in list("ABCDFG")
])
radar.add("Expectation", [Faker.values()]).add("Reality", [Faker.values()])
radar.render_notebook()
# %% [markdown]
# ### ThemeRiver -- 流量图
themeriver = ThemeRiver()
with open("data/themeriver.json") as j:
data = json.load(j)
cats = list(set([i[-1] for i in data]))
themeriver.add(cats, data, singleaxis_opts=opts.SingleAxisOpts(type_="time"))
themeriver.render_notebook()
# 曲風河流圖
data_river = []
for g in genres:
df_river = pd.DataFrame(df_year['year'].unique(),
columns=['year'],
index=df_year['year'].unique())
df_river['year'] = df_river['year'].apply(str)
df_river['count'] = df_year[df_year[g] == 1].groupby(by=['year'])[g].sum()
df_river['genre'] = np.full(len(df_river), g)
df_river['count'] = df_river['count'].fillna(0)
data_river.extend(df_river.values.tolist())
river = ThemeRiver(init_opts=opts.InitOpts(
width="2000px", height="600px", theme=ThemeType.LIGHT))
river.add(
series_name=genres,
data=data_river,
label_opts=opts.LabelOpts(font_size=10),
singleaxis_opts=opts.SingleAxisOpts(
pos_top="50",
pos_bottom="50",
type_="time",
),
)
river.set_global_opts(
tooltip_opts=opts.TooltipOpts(trigger="axis", axis_pointer_type="line"),
title_opts=opts.TitleOpts(title="1901-2020 曲風流變",
subtitle="1901-2020",
pos_bottom="85%",
["2015/11/09", 15, "DD"],
["2015/11/10", 35, "DD"],
["2015/11/11", 38, "DD"],
["2015/11/12", 22, "DD"],
["2015/11/13", 16, "DD"],
["2015/11/14", 7, "DD"],
["2015/11/15", 2, "DD"],
["2015/11/16", 17, "DD"],
["2015/11/17", 33, "DD"],
["2015/11/18", 4, "DD"],
["2015/11/19", 32, "DD"],
["2015/11/20", 26, "DD"],
["2015/11/21", 35, "DD"],
["2015/11/22", 40, "DD"],
["2015/11/23", 32, "DD"],
["2015/11/24", 26, "DD"],
["2015/11/25", 22, "DD"],
["2015/11/26", 16, "DD"],
["2015/11/27", 22, "DD"],
["2015/11/28", 10, "DD"],
]
(ThemeRiver().add(
series_name=x_data,
data=y_data,
singleaxis_opts=opts.SingleAxisOpts(pos_top="50",
pos_bottom="50",
type_="time"),
).set_global_opts(tooltip_opts=opts.TooltipOpts(
trigger="axis", axis_pointer_type="line")).render("theme_river.html"))
def get_themeriver(data, lengend, num_frames):
'''
data = [
["2015/11/08", 10, "DQ"],
["2015/11/09", 15, "DQ"],
["2015/11/10", 35, "DQ"],
["2015/11/14", 7, "DQ"],
["2015/11/15", 2, "DQ"],
["2015/11/16", 17, "DQ"],
["2015/11/17", 33, "DQ"],
["2015/11/18", 40, "DQ"],
["2015/11/19", 32, "DQ"],
["2015/11/20", 26, "DQ"],
["2015/11/08", 35, "TY"],
["2015/11/09", 36, "TY"],
["2015/11/10", 37, "TY"],
["2015/11/11", 22, "TY"],
["2015/11/12", 24, "TY"],
["2015/11/13", 26, "TY"],
["2015/11/14", 34, "TY"],
["2015/11/15", 21, "TY"],
["2015/11/16", 18, "TY"],
["2015/11/17", 45, "TY"],
["2015/11/18", 32, "TY"],
["2015/11/19", 35, "TY"],
["2015/11/20", 30, "TY"],
["2015/11/08", 21, "SS"],
["2015/11/09", 25, "SS"],
["2015/11/10", 27, "SS"],
["2015/11/11", 23, "SS"],
["2015/11/12", 24, "SS"],
["2015/11/13", 21, "SS"],
["2015/11/14", 35, "SS"],
["2015/11/15", 39, "SS"],
["2015/11/16", 40, "SS"],
["2015/11/17", 36, "SS"],
["2015/11/18", 33, "SS"],
["2015/11/19", 43, "SS"],
["2015/11/20", 40, "SS"],
["2015/11/14", 7, "QG"],
["2015/11/15", 2, "QG"],
["2015/11/16", 17, "QG"],
["2015/11/17", 33, "QG"],
["2015/11/18", 40, "QG"],
["2015/11/19", 32, "QG"],
["2015/11/20", 26, "QG"],
["2015/11/21", 35, "QG"],
["2015/11/22", 40, "QG"],
["2015/11/23", 32, "QG"],
["2015/11/24", 26, "QG"],
["2015/11/25", 22, "QG"],
["2015/11/08", 10, "SY"],
["2015/11/09", 15, "SY"],
["2015/11/10", 35, "SY"],
["2015/11/11", 38, "SY"],
["2015/11/12", 22, "SY"],
["2015/11/13", 16, "SY"],
["2015/11/14", 7, "SY"],
["2015/11/15", 2, "SY"],
["2015/11/16", 17, "SY"],
["2015/11/17", 33, "SY"],
["2015/11/18", 40, "SY"],
["2015/11/19", 32, "SY"],
["2015/11/20", 26, "SY"],
["2015/11/21", 35, "SY"],
["2015/11/22", 4, "SY"],
["2015/11/23", 32, "SY"],
["2015/11/24", 26, "SY"],
["2015/11/25", 22, "SY"],
["2015/11/08", 10, "DD"],
["2015/11/09", 15, "DD"],
["2015/11/10", 35, "DD"],
["2015/11/11", 38, "DD"],
["2015/11/12", 22, "DD"],
["2015/11/13", 16, "DD"],
["2015/11/14", 7, "DD"],
["2015/11/15", 2, "DD"],
["2015/11/16", 17, "DD"],
["2015/11/17", 33, "DD"],
["2015/11/18", 4, "DD"],
["2015/11/19", 32, "DD"],
["2015/11/20", 26, "DD"],
]
'''
themeriver = (
ThemeRiver().add(
#["DQ", "TY", "SS", "QG", "SY", "DD"],
lengend,
data,
singleaxis_opts=opts.SingleAxisOpts(
pos_bottom="50%", min_=1, max_=num_frames), #可以通过调整坐标轴来调整图的位置
label_opts=opts.LabelOpts(is_show=False),
tooltip_opts=opts.TooltipOpts(formatter="{a}") #不能用 不知道为什么
).set_global_opts(
title_opts=opts.TitleOpts(title="事件链河流图", subtitle="图例按突发性程度降序排序"),
#tooltip_opts=opts.TooltipOpts(is_show=True,trigger="item",formatter='{@[0]}'),#formatter目前没效果？？？
legend_opts=opts.LegendOpts(type_='scroll',
pos_left="5%",
orient='vertical',
pos_top="55%"))
#datazoom_opts=opts.DataZoomOpts())#图例设置
)
return themeriver
for idx in range(69):
date = dates[idx][5:]
for idy, term in enumerate(data[date][topic]):
if term[0] not in BLACK_LIST:
wc_data[idx][1].append(term)
with open("news_top_title.json", "r") as f:
top_titles = json.load(f)[topic]
with open("news_emotion_count.json", "r") as f:
news_ec = json.load(f)
emotions = ["负面", "中性", "正面"]
with open("cov_cnt.json", "r") as f:
cc_data = json.load(f)
theme_river = ThemeRiver(
init_opts=opts.InitOpts(width="1200px", height="600px"))
theme_river.add(
series_name=tr_series[topic],
data=tr_data[topic],
label_opts=opts.LabelOpts(is_show=False),
singleaxis_opts=opts.SingleAxisOpts(pos_top="50",
pos_bottom="50",
type_="time"),
)
theme_river.set_global_opts(tooltip_opts=opts.TooltipOpts(
trigger="axis", axis_pointer_type="line"),
legend_opts=opts.LegendOpts(pos_top="5%",
is_show=True))
wc_tl = Timeline(init_opts=opts.InitOpts(width="1200px", height="600px"))
idx = 0
def showing_pics(movie_name):
#生成页面
page = (Page(page_title=movie_name))
#豆瓣用户豆龄图
#读取用户数据
filename = movie_name + '\\' + movie_name + 'dby.txt'
with open(filename, 'r+', encoding='utf-8') as f:
year_1 = f.read()
years = year_1.split()
#进行分层分类
time = {
'0<x<=25': 0,
'25<x<=50': 0,
'50<x<=75': 0,
'75<x<=100': 0,
'100<x<=125': 0,
'x>125': 0
}
for x in years:
if int(x) < 25:
time['0<x<=25'] += 1
elif int(x) < 50:
time['25<x<=50'] += 1
elif int(x) < 75:
time['50<x<=75'] += 1
elif int(x) < 100:
time['75<x<=100'] += 1
elif int(x) < 125:
time['100<x<=125'] += 1
else:
time['x>125'] += 1
#整理数据
month_list1 = time.items()
#出图
dbmonth = (Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS)).add(
"", month_list1, radius=["40%", "75%"]).set_global_opts(
title_opts=opts.TitleOpts(title=movie_name + " 豆瓣用户“豆龄”分布图",
subtitle='单位:月'),
toolbox_opts=opts.ToolboxOpts(is_show=True),
legend_opts=opts.LegendOpts(orient="vertical",
pos_top="15%",
pos_left="2%"),
).set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}")))
#IMDB用户D龄图
#读取用户数据
filename = movie_name + '\\' + movie_name + 'Dy.txt'
with open(filename, 'r+', encoding='utf-8') as f:
year_1 = f.read()
years = year_1.split()
#进行分类分层
time = {
'0<x<=40': 0,
'40<x<=80': 0,
'80<x<=120': 0,
'120<x<=160': 0,
'160<x<=200': 0,
'x>200': 0
}
for x in years:
if int(x) < 40:
time['0<x<=40'] += 1
elif int(x) < 80:
time['40<x<=80'] += 1
elif int(x) < 120:
time['80<x<=120'] += 1
elif int(x) < 160:
time['120<x<=160'] += 1
elif int(x) < 200:
time['160<x<=200'] += 1
else:
time['x>200'] += 1
#整理
month_list2 = time.items()
#出图
Dmonth = (Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS)).add(
"", month_list2, radius=["40%", "75%"]).set_global_opts(
title_opts=opts.TitleOpts(title=movie_name + " IMDB“D龄”分布图",
subtitle='单位:月'),
toolbox_opts=opts.ToolboxOpts(is_show=True),
legend_opts=opts.LegendOpts(orient="vertical",
pos_top="15%",
pos_left="2%"),
).set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}")))
#英文词云图
#读取数据
filename = movie_name + '\\' + movie_name + 'Dreview.txt'
with open(filename, 'r+', encoding='utf-8') as f:
rev_1 = f.read()
#处理标点
for i in rev_1:
if i in string.punctuation:
rev_1 = rev_1.replace(i, " ")
#分词+统计
words = rev_1.split()
words_dic = Counter(words)
#删除一些高频词
file_del = 'ban.txt'
with open(file_del, 'r+', encoding='utf-8') as d:
del_1 = d.read()
Ban_list = del_1.split('\n')
#处理数据
words_list = []
for word, time in words_dic.items():
if word.lower() in Ban_list or time < 35:
continue
else:
a_word = (word.title(), time)
words_list.append(a_word)
#出图
Eng_wordcloud = (WordCloud(init_opts=opts.InitOpts(
theme=ThemeType.MACARONS)).add(
"", words_list, word_size_range=[20, 100],
shape="diamond").set_global_opts(
title_opts=opts.TitleOpts(title=movie_name + " WordCloud",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True)))
#中文词云图
#读取爬取的文本文件
filename = movie_name + '\\' + movie_name + 'dbreview.txt'
with open(filename, 'r+', encoding='utf-8') as f:
rev_2 = f.read()
#中文分词
cut_douban = " ".join(jieba.cut(rev_2, cut_all=False))
list_douban = cut_douban.split(' ')
copy_list = []
for word in list_douban:
copy_list.append(word)
#删除长度为1的文本
for word in copy_list:
if len(word) == 1:
list_douban.remove(word)
stop = []
review_dic = Counter(list_douban)
#利用文件删除一些意义不大的词
file_stop = '删除.txt'
with open(file_stop, 'r+', encoding='utf-8') as s:
stop_1 = s.read()
stop = stop_1.split('\n')
#整理
word_list = []
for words, times in review_dic.items():
if words in stop or times < 9:
continue
else:
b_word = (words, times)
word_list.append(b_word)
#出图
Chn_wordcloud = (WordCloud(init_opts=opts.InitOpts(
theme=ThemeType.MACARONS)).add(
"", word_list, word_size_range=[20, 100],
shape="diamond").set_global_opts(
title_opts=opts.TitleOpts(title=movie_name + " 中文词云图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True)))
#豆瓣用户评分图
#读取数据
with open(movie_name + '\\' + movie_name + 'dbscores.txt',
'r+',
encoding='utf-8') as m:
allthings = m.read().split(',')
del allthings[-1]
all_date = []
points_dic = {}
#按评价进行分类
for div in allthings:
point, date = div.split()
if date not in all_date:
points_dic[date] = {
'很差': 0,
'较差': 0,
'还行': 0,
'推荐': 0,
'力荐': 0
}
all_date.append(date)
if point == '很差':
points_dic[date]['很差'] += 1
elif point == '较差':
points_dic[date]['较差'] += 1
elif point == '还行':
points_dic[date]['还行'] += 1
elif point == '推荐':
points_dic[date]['推荐'] += 1
else:
points_dic[date]['力荐'] += 1
#处理数据
data = []
for month, grade in points_dic.items():
for hzc, num in grade.items():
counting = []
counting.append(month)
counting.append(num)
counting.append(hzc)
data.append(counting)
#出图
dbpoints = (ThemeRiver(init_opts=opts.InitOpts(
theme=ThemeType.MACARONS)).add(
['很差', '较差', '还行', '推荐', '力荐'],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time",
pos_bottom="10%"),
).set_global_opts(title_opts=opts.TitleOpts(title=movie_name +
" 豆瓣评价分布图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True),
datazoom_opts=[
opts.DataZoomOpts(is_show=True,
range_start=0,
range_end=100)
]))
#IMDB评分图
#处理爬取的数据
with open(movie_name + '\\' + movie_name + 'Dscores.txt',
'r+',
encoding='utf-8') as m:
allthings = m.read().split(',')
del allthings[-1]
all_date = []
points_dic = {}
#按分数进行分类
for div in allthings:
point, date = div.split()
if date not in all_date:
points_dic[date] = {'好评': 0, '中评': 0, '差评': 0}
all_date.append(date)
if int(point) <= 3:
points_dic[date]['差评'] += 1
elif int(point) >= 7:
points_dic[date]['好评'] += 1
else:
points_dic[date]['中评'] += 1
#整理便于出图
data = []
for month, grade in points_dic.items():
for hzc, num in grade.items():
counting = []
counting.append(month)
counting.append(num)
counting.append(hzc)
data.append(counting)
#出图
Dpoints = (ThemeRiver(init_opts=opts.InitOpts(
theme=ThemeType.MACARONS)).add(
['好评', '中评', '差评'],
data,
singleaxis_opts=opts.SingleAxisOpts(type_="time",
pos_bottom="10%"),
).set_global_opts(title_opts=opts.TitleOpts(title=movie_name +
" IMDB评价分布主题河流图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True),
datazoom_opts=[
opts.DataZoomOpts(is_show=True,
range_start=0,
range_end=100)
]))
#热点图
#读取城市数据
with open(movie_name + '\\' + movie_name + 'dbplaces.txt',
'r+',
encoding='utf-8-sig') as f:
heat_1 = f.read()
for i in heat_1:
if i in string.punctuation:
heat_1 = heat_1.replace(i, "")
heat = heat_1.split()
heat_dic = Counter(heat)
#处理一些热点图数据库中没有的城市（此txt还要不停壮大）
with open('no city.txt', 'r+', encoding='utf-8-sig') as e:
no_city = e.read()
no_city_list = no_city.split(' ')
#整理数据
heat_list = []
for place, times in heat_dic.items():
if place in no_city_list:
continue
c_word = (place, times)
heat_list.append(c_word)
#出图,反复产生图，来处理乱填地区的情况
try:
heat_map = (Geo(init_opts=opts.InitOpts(
theme=ThemeType.MACARONS)).add_schema(maptype="china").add(
"", heat_list).set_series_opts(label_opts=opts.LabelOpts(
is_show=False)).set_global_opts(
visualmap_opts=opts.VisualMapOpts(),
title_opts=opts.TitleOpts(title=movie_name +
" 豆瓣观影热点图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True)))
except:
a = heat_list.pop(-1)
#中文情感分析图
with open(movie_name + '\\' + movie_name + "dbreview.txt",
'r',
encoding='utf-8') as f:
#读取影评文件
text = f.read()
s = SnowNLP(text)
chn_senti = []
#进行情感分析并记录数据
for sent in s.sentences:
chn_senti.append(SnowNLP(sent).sentiments)
times = {
'0<=x<=0.25': 0,
'0.25<x<=0.5': 0,
'0.5<x<=0.75': 0,
'0.75<x<=1': 0
}
for x in chn_senti:
if x < 0 or x > 1:
continue
elif x <= 0.25:
times['0<=x<=0.25'] += 1
elif x <= 0.5:
times['0.25<x<=0.5'] += 1
elif x <= 0.75:
times['0.5<x<=0.75'] += 1
else:
times['0.75<x<=1'] += 1
scores_list = times.items()
#出图
ch_motion = (Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS)).add(
"", scores_list, radius=["40%", "75%"]).set_global_opts(
title_opts=opts.TitleOpts(title=movie_name + "豆瓣用户评论情感分析图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True),
legend_opts=opts.LegendOpts(orient="vertical",
pos_top="15%",
pos_left="2%"),
).set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}")))
#英文情感分析图
with open(movie_name + '\\' + movie_name + "Dreview.txt",
'r',
encoding='utf-8') as f:
#读取影评文件
text = f.read()
blob = TextBlob(text)
eng_senti = []
#进行情感分析并记录数据
for sent in blob.sentences:
eng_senti.append(sent.sentiment.polarity)
time = {'-1<=x<=-0.5': 0, '-0.5<x<=0': 0, '0<x<=0.5': 0, '0.5<x<=1': 0}
for x in eng_senti:
if x < -1 or x > 1:
continue
elif x <= -0.5:
time['-1<=x<=-0.5'] += 1
elif x <= 0:
time['-0.5<x<=0'] += 1
elif x <= 0.5:
time['0<x<=0.5'] += 1
else:
time['0.5<x<=1'] += 1
score_list = time.items()
#出图
en_motion = (Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS)).add(
"", score_list, radius=["40%", "75%"]).set_global_opts(
title_opts=opts.TitleOpts(title=movie_name + "IMDB用户评论情感分析图",
subtitle=None),
toolbox_opts=opts.ToolboxOpts(is_show=True),
legend_opts=opts.LegendOpts(orient="vertical",
pos_top="15%",
pos_left="2%"),
).set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}")))
#将图加入页面中
page.add(dbmonth, Dmonth)
page.add(Chn_wordcloud, Eng_wordcloud)
page.add(dbpoints, Dpoints)
page.add(ch_motion, en_motion)
try:
page.add(heat_map)
except:
pass
page.render(movie_name + '\\' + movie_name + '数据图.html')