影院复工数据分析

df_3['box_num'] = df_3.boxOfficeStr.str.extract(r'(\d+\.\d+)').astype('float') 
df_3['box_unit'] = df_3.boxOfficeStr.str.extract(r'([\u4e00-\u9fa5]+)').replace({'万': 10000, '亿': 100000000})
df_3['true_box'] = df_3['box_num'] * df_3['box_unit']
df_3['true_box'] = df_3['true_box'] / 10000 
df_3.drop(['box_num', 'box_unit'], axis=1, inplace=True)
df_3.head() 

x_data = open_trend['showDate'].astype('str').str[-4:-2] + '-' + df_3['showDate'].astype('str').str[-2:]
x_data = x_data.values.tolist()
y_data = open_trend.openCinemaCnt.values.tolist() 

line2 = Line(init_opts=opts.InitOpts(width='1350px', height='750px'))
line2.add_xaxis(x_data)
line2.add_yaxis('', y_data, 
                markpoint_opts=opts.MarkPointOpts(data=[opts.MarkPointItem(type_="min"),
                                                        opts.MarkPointItem(type_="max")]),
#                 areastyle_opts=opts.AreaStyleOpts(opacity=0.5, color="#C67570"),
               ) 
line2.set_global_opts(title_opts=opts.TitleOpts(title='全国影院复工趋势图'), 
                      xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate='30')),
                      yaxis_opts=opts.AxisOpts(name='', type_='value', 
                                               axislabel_opts=opts.LabelOpts(formatter="{value}"))
                     )
line2.set_series_opts(label_opts=opts.LabelOpts(is_show=False), 
                      linestyle_opts=opts.LineStyleOpts(width=3)
                     )
line2.render() 

'C:\\Users\\wzd\\Desktop\\CDA\\CDA_Python\\Python项目实作\\网络爬虫\\电影\\电影复工分析\\code\\render.html'

猫眼电影票房分析

复工以来不同影片累计票房排名 前十

df_4 = pd.read_csv('../data/猫眼20200720-0827.csv')
df_4.head() 

 # 计算单日票房
df_4['box_num'] = df_4.boxSplitUnit.str.extract(r'(\d+\.\d+)').astype('float') 
df_4['box_unit'] = df_4.boxSplitUnit.str.extract(r'([\u4e00-\u9fa5]+)').replace({'万': 10000, '亿': 100000000})
df_4['unit_box'] = df_4['box_num'] * df_4['box_unit']
df_4.drop(['box_num', 'box_unit'], axis=1, inplace=True)
df_4.head() 

 

df_sumbox = pd.DataFrame() 

for name in df_4.movieName.drop_duplicates():
    # 计算累加
    df_onemovie = df_4[df_4['movieName'] == name][['movieName', 'select_date', 'unit_box']]
    df_onemovie['cum_box'] = df_onemovie.unit_box.cumsum() 
    # 追加
    df_sumbox = df_sumbox.append(df_onemovie, ignore_index=True)
df_sumbox.head()  

# 复制一份
df_sumbox2 = df_sumbox.copy()

# 筛选日期
df_sumbox = df_sumbox[df_sumbox['select_date'] == '2020-08-27']
df_sumbox.head() 

df_sumbox.loc[:, '累计票房(万)'] = (df_sumbox['cum_box'].copy() / 10000)
df_sumbox.head() 

box_top10 = df_sumbox.sort_values('cum_box', ascending=False)
box_top10 = box_top10.head(10)
box_top10

x_data = box_top10.movieName.values.tolist()
y_data = box_top10['累计票房(万)'].values.tolist()

# 条形图
bar3 = Bar(init_opts=opts.InitOpts(width='1350px', height='750px')) 
bar3.add_xaxis(x_data)
bar3.add_yaxis('', y_data) 
bar3.set_global_opts(title_opts=opts.TitleOpts(title='复工以来影片累计票房排名Top10'),
                     xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
                     yaxis_opts=opts.AxisOpts(name='', type_='value', 
                                              axislabel_opts=opts.LabelOpts(formatter="{value}万")),
                     visualmap_opts=opts.VisualMapOpts(is_show=False, max_=143361.58)
                    ) 
bar3.render() 

'C:\\Users\\wzd\\Desktop\\CDA\\CDA_Python\\Python项目实作\\网络爬虫\\电影\\电影复工分析\\code\\render.html'

影院复工后累计票房动图

df_sumbox2['cum_box'] = df_sumbox2['cum_box']/10000
df_sumbox2.head()

df_dongtu = pd.pivot_table(data=df_sumbox2, values='cum_box', index='movieName', 
                           columns='select_date', aggfunc='sum')
df_dongtu = df_dongtu.reset_index()
df_dongtu

df_dongtu.to_excel('../data/复工动图数据.xlsx', index=False)

# import plotly as py 
# import plotly.graph_objs as go 
# import plotly.express as px 
# from plotly import tools

# # 条形图
# fig1 = px.bar(df_sumbox2, x='movieName', y='cum_box', color='movieName', text='cum_box',
#              title=' 影院复工后累计票房动图', 
#              animation_frame='select_date',
#              range_y=[0, 143361.58],
# #              orientation='v'
#              ) 
# fig1.update_layout(xaxis_title='影片', yaxis_title='累计票房（万）')
# py.offline.plot(fig1, filename=' 影院复工后累计票房动图.html') 

' 影院复工后累计票房动图.html'

px.bar_polar()

生成page

page = Page() 

page.add(bar1, map1, bar2, line2, line1, bar3, bar4)
page.render('电影复工数据分析.html') 

'C:\\Users\\wzd\\Desktop\\CDA\\CDA_Python\\Python项目实作\\网络爬虫\\电影\\电影复工分析\\code\\电影复工数据分析.html'