Python专区加入小组

138个成员 36个话题创建时间：2019-12-17

全国院线总票房破50亿！影院复工后，哪些电影最受欢迎？文章代码

发表于2020-08-31 3035次查看

影院复工数据分析

# 导入包
import numpy as np 
import pandas as pd 

from pyecharts.charts import Bar, Map, Line, Page
from pyecharts import options as opts 
from pyecharts.globals import SymbolType, WarningType
WarningType.ShowWarning = False

影院复工地图-淘票票

复工率Top5省份

df_1 = pd.read_csv('../data/淘票票复工率Top5省份0827.csv') 
df_1 = df_1.sort_values('openCinemaRate') 
df_1

	boxOffice	boxOfficeStr	cityId	cityName	openCinemaCnt	openCinemaCntStr	openCinemaIncrCnt	openCinemaIncrCntStr	openCinemaRate	openCinemaRateStr	scheduleCnt	scheduleCntStr	showDate	soldSeatCnt	soldSeatCntStr
4	59522139	59.5万	999929	青海省	41	41	0	0	0.953	95.3%	1000	1000	20200827	16906	1.69万
3	970996899	971.0万	999916	河南省	510	510	0	0	0.964	96.4%	15119	1.51万	20200827	289174	28.92万
2	540238952	540.2万	999914	江西省	334	334	-5	-5	0.965	96.5%	7198	7198	20200827	158912	15.89万
1	370686517	370.7万	999920	广西	258	258	1	1	0.985	98.5%	5581	5581	20200827	104000	10.40万
0	27058030	27.1万	999926	西藏	23	23	1	1	1.000	100.0%	409	409	20200827	6764	6764

# 产生数据
x_data = df_1['cityName'].values.tolist() 
y_data = [float(i.split('%')[0]) for i in df_1['openCinemaRateStr'].values.tolist()]

# 条形图
bar1 = Bar(init_opts=opts.InitOpts(width='1350px', height='750px')) 
bar1.add_xaxis(x_data)
bar1.add_yaxis('', y_data, category_gap='50%') 
bar1.set_global_opts(title_opts=opts.TitleOpts(title='全国复工率Top5省份（8-27）'))
bar1.set_series_opts(label_opts=opts.LabelOpts(is_show=True, position='right')) 
bar1.set_colors('#F6A061')
bar1.reversal_axis()
bar1.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'

全国影院复工地图

df_2 = pd.read_csv('../data/淘票票各省票房-0827.csv')

# 城市数据
df_2['cityName'] = df_2['cityName'].str.replace('市', '').str.replace('省', '')
df_2.head()

	boxOffice	boxOfficeStr	cityId	cityName	openCinemaCnt	openCinemaCntStr	openCinemaIncrCnt	openCinemaIncrCntStr	openCinemaRate	openCinemaRateStr	scheduleCnt	scheduleCntStr	showDate	soldSeatCnt	soldSeatCntStr
0	571133208	571.1万	99991	北京	206	206	3	3	0.866	86.6%	5729	5729	20200827	115052	11.51万
1	220772644	220.8万	99992	天津	90	90	0	0	0.833	83.3%	2636	2636	20200827	57467	5.75万
2	636961140	637.0万	99993	河北	384	384	-3	-3	0.901	90.1%	9807	9807	20200827	180247	18.02万
3	364804000	364.8万	99994	山西	264	264	-4	-4	0.917	91.7%	6163	6163	20200827	103178	10.32万
4	241007410	241.0万	99995	内蒙古	186	186	-7	-7	0.842	84.2%	4207	4207	20200827	68254	6.83万

open_num = df_2[['cityName', 'openCinemaCnt']]
open_num.head()

	cityName	openCinemaCnt
0	北京	206
1	天津	90
2	河北	384
3	山西	264
4	内蒙古	186

x_data = open_num.cityName.values.tolist()
y_data = open_num.openCinemaCnt.values.tolist() 

# 地图
map1 = Map(init_opts=opts.InitOpts(width='1350px', height='750px'))
map1.add("", [list(z) for z in zip(x_data, y_data)],
         maptype='china'
        ) 
map1.set_global_opts(title_opts=opts.TitleOpts(title='全国影院复工数地图（8-27）'),
                     visualmap_opts=opts.VisualMapOpts(max_=open_num.openCinemaCnt.max(), 
                                                       is_piecewise=True, 
#                                                        pieces=
                                                      ),
                    )
map1.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'

全国影院复工数Top10

num_top10 = open_num.sort_values('openCinemaCnt', ascending=False).head(10) 
num_top10

	cityName	openCinemaCnt
18	广东	1092
9	江苏	813
10	浙江	663
22	四川	564
14	山东	517
15	河南	510
17	湖南	405
2	河北	384
16	湖北	374
11	安徽	363

x_data = num_top10.cityName.values.tolist()
y_data = num_top10.openCinemaCnt.values.tolist()

# 条形图
bar2 = Bar(init_opts=opts.InitOpts(width='1350px', height='750px')) 
bar2.add_xaxis(x_data)
bar2.add_yaxis('', y_data) 
bar2.set_global_opts(title_opts=opts.TitleOpts(title='全国影院复工数Top10省份（8-27日）'),
#                      xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-15)),
                     visualmap_opts=opts.VisualMapOpts(is_show=False, max_=1092)
                    ) 
bar2.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'

	boxOffice	boxOfficeStr	cityId	cityName	openCinemaCnt	openCinemaCntStr	openCinemaIncrCnt	openCinemaIncrCntStr	openCinemaRate	openCinemaRateStr	scheduleCnt	scheduleCntStr	showDate	soldSeatCnt	soldSeatCntStr
0	422155895	422.2万	-5	全国	1397	1397	1009	1009	0.129	12.9%	12599	1.26万	20200720	164716	16.47万
1	537683369	537.7万	-5	全国	2040	2040	643	643	0.189	18.9%	23482	2.35万	20200721	215780	21.58万
2	644860406	644.9万	-5	全国	2567	2567	527	527	0.237	23.7%	35414	3.54万	20200722	274121	27.41万
3	662853406	662.9万	-5	全国	3152	3152	585	585	0.291	29.1%	46315	4.63万	20200723	309331	30.93万
4	2030300376	2030.3万	-5	全国	4670	4670	1518	1518	0.432	43.2%	83543	8.35万	20200724	757934	75.79万

df_3.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 39 entries, 0 to 38
Data columns (total 15 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   boxOffice             39 non-null     int64  
 1   boxOfficeStr          39 non-null     object 
 2   cityId                39 non-null     int64  
 3   cityName              39 non-null     object 
 4   openCinemaCnt         39 non-null     int64  
 5   openCinemaCntStr      39 non-null     int64  
 6   openCinemaIncrCnt     39 non-null     int64  
 7   openCinemaIncrCntStr  39 non-null     int64  
 8   openCinemaRate        39 non-null     float64
 9   openCinemaRateStr     39 non-null     object 
 10  scheduleCnt           39 non-null     int64  
 11  scheduleCntStr        39 non-null     object 
 12  showDate              39 non-null     int64  
 13  soldSeatCnt           39 non-null     int64  
 14  soldSeatCntStr        39 non-null     object 
dtypes: float64(1), int64(9), object(5)
memory usage: 4.7+ KB