# 基础
import numpy as np
import pandas as pd
from pandas import DataFrame, Series
from datetime import datetime
import json
import warnings
warnings.filterwarnings('ignore')# 忽略python运行过程中的警告
# 可视化
import matplotlib.pyplot as plt
import seaborn as sns
from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator # 导入词云包
%matplotlib inline
下面是moviedf数据集中部分字段的含义介绍:
id:
标识号
imdb id:IMDB标识号
popularity:
在Movie Database上的相对页面查看次数
budget:
预算(美元)
revenue:
收入(美元)
original_title:
电影名称
cast:
演员列表,按|分隔,最多5名演员
homepage:
电影首页的URL
director:
导演列表,按|分隔,最多5名导演
tagline:
电影的标语
keywords:
与电影相关的关键字,按|分隔,最多5个关键字
overview:
剧情摘要
runtime:
电影时长
genres:
风格列表,按|分隔,最多5种风格
production_companies:
制作公司列表,按|分隔,最多5家公司
release_date:
首次上映日期
vote_count:
评分次数
vote_average:
平均评分·release year:
发行年份
# 导入电影数据
credits_url = '/Users/bennyrhys/Desktop/数据分析可视化/homework/tmdb_5000_credits.csv'
movies_url = '/Users/bennyrhys/Desktop/数据分析可视化/homework/tmdb_5000_movies.csv'
credits = pd.read_csv(credits_url)
movies = pd.read_csv(movies_url)
credits.head()
movie_id | title | cast | crew | |
---|---|---|---|---|
0 | 19995 | Avatar | [{"cast_id": 242, "character": "Jake Sully", "... | [{"credit_id": "52fe48009251416c750aca23", "de... |
1 | 285 | Pirates of the Caribbean: At World's End | [{"cast_id": 4, "character": "Captain Jack Spa... | [{"credit_id": "52fe4232c3a36847f800b579", "de... |
2 | 206647 | Spectre | [{"cast_id": 1, "character": "James Bond", "cr... | [{"credit_id": "54805967c3a36829b5002c41", "de... |
3 | 49026 | The Dark Knight Rises | [{"cast_id": 2, "character": "Bruce Wayne / Ba... | [{"credit_id": "52fe4781c3a36847f81398c3", "de... |
4 | 49529 | John Carter | [{"cast_id": 5, "character": "John Carter", "c... | [{"credit_id": "52fe479ac3a36847f813eaa3", "de... |
movies.head()
budget | genres | homepage | id | keywords | original_language | original_title | overview | popularity | production_companies | production_countries | release_date | revenue | runtime | spoken_languages | status | tagline | title | vote_average | vote_count | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 237000000 | [{"id": 28, "name": "Action"}, {"id": 12, "nam... | http://www.avatarmovie.com/ | 19995 | [{"id": 1463, "name": "culture clash"}, {"id":... | en | Avatar | In the 22nd century, a paraplegic Marine is di... | 150.437577 | [{"name": "Ingenious Film Partners", "id": 289... | [{"iso_3166_1": "US", "name": "United States o... | 2009-12-10 | 2787965087 | 162.0 | [{"iso_639_1": "en", "name": "English"}, {"iso... | Released | Enter the World of Pandora. | Avatar | 7.2 | 11800 |
1 | 300000000 | [{"id": 12, "name": "Adventure"}, {"id": 14, "... | http://disney.go.com/disneypictures/pirates/ | 285 | [{"id": 270, "name": "ocean"}, {"id": 726, "na... | en | Pirates of the Caribbean: At World's End | Captain Barbossa, long believed to be dead, ha... | 139.082615 | [{"name": "Walt Disney Pictures", "id": 2}, {"... | [{"iso_3166_1": "US", "name": "United States o... | 2007-05-19 | 961000000 | 169.0 | [{"iso_639_1": "en", "name": "English"}] | Released | At the end of the world, the adventure begins. | Pirates of the Caribbean: At World's End | 6.9 | 4500 |
2 | 245000000 | [{"id": 28, "name": "Action"}, {"id": 12, "nam... | http://www.sonypictures.com/movies/spectre/ | 206647 | [{"id": 470, "name": "spy"}, {"id": 818, "name... | en | Spectre | A cryptic message from Bond’s past sends him o... | 107.376788 | [{"name": "Columbia Pictures", "id": 5}, {"nam... | [{"iso_3166_1": "GB", "name": "United Kingdom"... | 2015-10-26 | 880674609 | 148.0 | [{"iso_639_1": "fr", "name": "Fran\u00e7ais"},... | Released | A Plan No One Escapes | Spectre | 6.3 | 4466 |
3 | 250000000 | [{"id": 28, "name": "Action"}, {"id": 80, "nam... | http://www.thedarkknightrises.com/ | 49026 | [{"id": 849, "name": "dc comics"}, {"id": 853,... | en | The Dark Knight Rises | Following the death of District Attorney Harve... | 112.312950 | [{"name": "Legendary Pictures", "id": 923}, {"... | [{"iso_3166_1": "US", "name": "United States o... | 2012-07-16 | 1084939099 | 165.0 | [{"iso_639_1": "en", "name": "English"}] | Released | The Legend Ends | The Dark Knight Rises | 7.6 | 9106 |
4 | 260000000 | [{"id": 28, "name": "Action"}, {"id": 12, "nam... | http://movies.disney.com/john-carter | 49529 | [{"id": 818, "name": "based on novel"}, {"id":... | en | John Carter | John Carter is a war-weary, former military ca... | 43.926995 | [{"name": "Walt Disney Pictures", "id": 2}] | [{"iso_3166_1": "US", "name": "United States o... | 2012-03-07 | 284139100 | 132.0 | [{"iso_639_1": "en", "name": "English"}] | Released | Lost in our world, found in another. | John Carter | 6.1 | 2124 |
# 合并数据集
fulldf = pd.concat([credits,movies],axis=1)
fulldf.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4803 entries, 0 to 4802
Data columns (total 24 columns):
movie_id 4803 non-null int64
title 4803 non-null object
cast 4803 non-null object
crew 4803 non-null object
budget 4803 non-null int64
genres 4803 non-null object
homepage 1712 non-null object
id 4803 non-null int64
keywords 4803 non-null object
original_language 4803 non-null object
original_title 4803 non-null object
overview 4800 non-null object
popularity 4803 non-null float64
production_companies 4803 non-null object
production_countries 4803 non-null object
release_date 4802 non-null object
revenue 4803 non-null int64
runtime 4801 non-null float64
spoken_languages 4803 non-null object
status 4803 non-null object
tagline 3959 non-null object
title 4803 non-null object
vote_average 4803 non-null float64
vote_count 4803 non-null int64
dtypes: float64(3), int64(5), object(16)
memory usage: 900.7+ KB
# 由于数据集中包含的信息过多,其中部分数据并不是我们研究的重点,所以从中选取我们需要的数据:
moviesdf = fulldf[['original_title','crew','release_date','genres','keywords','production_companies',
'production_countries','revenue','budget','runtime','vote_average']]
moviesdf.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4803 entries, 0 to 4802
Data columns (total 11 columns):
original_title 4803 non-null object
crew 4803 non-null object
release_date 4802 non-null object
genres 4803 non-null object
keywords 4803 non-null object
production_companies 4803 non-null object
production_countries 4803 non-null object
revenue 4803 non-null int64
budget 4803 non-null int64
runtime 4801 non-null float64
vote_average 4803 non-null float64
dtypes: float64(2), int64(2), object(7)
memory usage: 412.9+ KB
# 由于后面的数据分析涉及到电影类型的利润计算,先求出每部电影的利润,并在数据集moviesdf中增加profit数据列:
moviesdf['profit'] = moviesdf['revenue'] - moviesdf['budget']
moviesdf.head()
original_title | crew | release_date | genres | keywords | production_companies | production_countries | revenue | budget | runtime | vote_average | profit | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | Avatar | [{"credit_id": "52fe48009251416c750aca23", "de... | 2009-12-10 | [{"id": 28, "name": "Action"}, {"id": 12, "nam... | [{"id": 1463, "name": "culture clash"}, {"id":... | [{"name": "Ingenious Film Partners", "id": 289... | [{"iso_3166_1": "US", "name": "United States o... | 2787965087 | 237000000 | 162.0 | 7.2 | 2550965087 |
1 | Pirates of the Caribbean: At World's End | [{"credit_id": "52fe4232c3a36847f800b579", "de... | 2007-05-19 | [{"id": 12, "name": "Adventure"}, {"id": 14, "... | [{"id": 270, "name": "ocean"}, {"id": 726, "na... | [{"name": "Walt Disney Pictures", "id": 2}, {"... | [{"iso_3166_1": "US", "name": "United States o... | 961000000 | 300000000 | 169.0 | 6.9 | 661000000 |
2 | Spectre | [{"credit_id": "54805967c3a36829b5002c41", "de... | 2015-10-26 | [{"id": 28, "name": "Action"}, {"id": 12, "nam... | [{"id": 470, "name": "spy"}, {"id": 818, "name... | [{"name": "Columbia Pictures", "id": 5}, {"nam... | [{"iso_3166_1": "GB", "name": "United Kingdom"... | 880674609 | 245000000 | 148.0 | 6.3 | 635674609 |
3 | The Dark Knight Rises | [{"credit_id": "52fe4781c3a36847f81398c3", "de... | 2012-07-16 | [{"id": 28, "name": "Action"}, {"id": 80, "nam... | [{"id": 849, "name": "dc comics"}, {"id": 853,... | [{"name": "Legendary Pictures", "id": 923}, {"... | [{"iso_3166_1": "US", "name": "United States o... | 1084939099 | 250000000 | 165.0 | 7.6 | 834939099 |
4 | John Carter | [{"credit_id": "52fe479ac3a36847f813eaa3", "de... | 2012-03-07 | [{"id": 28, "name": "Action"}, {"id": 12, "nam... | [{"id": 818, "name": "based on novel"}, {"id":... | [{"name": "Walt Disney Pictures", "id": 2}] | [{"iso_3166_1": "US", "name": "United States o... | 284139100 | 260000000 | 132.0 | 6.1 | 24139100 |
通过上面的数据集信息可以知道:整个数据集缺失的数据比较少 其中release_date(首次上映日期)缺失1个数据,runtime(电影时长)缺失2个数据,可以通过网上查询补齐这个数据。
填补release_date(首次上映日期)数据:
# 找出首次上映时间的缺失数据
release_date_null = moviesdf['release_date'].isnull()
moviesdf.loc[release_date_null]
original_title | crew | release_date | genres | keywords | production_companies | production_countries | revenue | budget | runtime | vote_average | profit | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
4553 | America Is Still the Place | [] | NaN | [] | [] | [] | [] | 0 | 0 | 0.0 | 0.0 | 0 |
# 填充日期
moviesdf['release_date'] = moviesdf['release_date'].fillna('2014-06-01')
# 修改日期格式
moviesdf['release_date'] = pd.to_datetime(moviesdf['release_date'], format='%Y-%m-%d')
moviesdf.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4803 entries, 0 to 4802
Data columns (total 12 columns):
original_title 4803 non-null object
crew 4803 non-null object
release_date 4803 non-null datetime64[ns]
genres 4803 non-null object
keywords 4803 non-null object
production_companies 4803 non-null object
production_countries 4803 non-null object
revenue 4803 non-null int64
budget 4803 non-null int64
runtime 4801 non-null float64
vote_average 4803 non-null float64
profit 4803 non-null int64
dtypes: datetime64[ns](1), float64(2), int64(3), object(6)
memory usage: 450.4+ KB
# 找出runtime(电影时长)缺失的数据:
runtime_date_null = moviesdf['runtime'].isnull()
moviesdf.loc[runtime_date_null]
original_title | crew | release_date | genres | keywords | production_companies | production_countries | revenue | budget | runtime | vote_average | profit | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
2656 | Chiamatemi Francesco - Il Papa della gente | [{"credit_id": "5660019ac3a36875f100252b", "de... | 2015-12-03 | [{"id": 18, "name": "Drama"}] | [{"id": 717, "name": "pope"}, {"id": 5565, "na... | [{"name": "Taodue Film", "id": 45724}] | [{"iso_3166_1": "IT", "name": "Italy"}] | 0 | 15000000 | NaN | 7.3 | -15000000 |
4140 | To Be Frank, Sinatra at 100 | [{"credit_id": "592b25e4c3a368783e065a2f", "de... | 2015-12-12 | [{"id": 99, "name": "Documentary"}] | [{"id": 6027, "name": "music"}, {"id": 225822,... | [{"name": "Eyeline Entertainment", "id": 60343}] | [{"iso_3166_1": "GB", "name": "United Kingdom"}] | 0 | 2 | NaN | 0.0 | -2 |
# 填充runtime缺失值
value1 = {'runtime':98.0}
value2 = {'runtime':81.0}
moviesdf.fillna(value=value1, limit=1, inplace=True)
moviesdf.fillna(value=value2, limit=1, inplace=True)
moviesdf.loc[runtime_date_null]
original_title | crew | release_date | genres | keywords | production_companies | production_countries | revenue | budget | runtime | vote_average | profit | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
2656 | Chiamatemi Francesco - Il Papa della gente | [{"credit_id": "5660019ac3a36875f100252b", "de... | 2015-12-03 | [{"id": 18, "name": "Drama"}] | [{"id": 717, "name": "pope"}, {"id": 5565, "na... | [{"name": "Taodue Film", "id": 45724}] | [{"iso_3166_1": "IT", "name": "Italy"}] | 0 | 15000000 | 98.0 | 7.3 | -15000000 |
4140 | To Be Frank, Sinatra at 100 | [{"credit_id": "592b25e4c3a368783e065a2f", "de... | 2015-12-12 | [{"id": 99, "name": "Documentary"}] | [{"id": 6027, "name": "music"}, {"id": 225822,... | [{"name": "Eyeline Entertainment", "id": 60343}] | [{"iso_3166_1": "GB", "name": "United Kingdom"}] | 0 | 2 | 81.0 | 0.0 | -2 |
# genres列数据处理:
# genres列格式化
moviesdf['genres'] = moviesdf['genres'].apply(json.loads)
# 自定义函数解码json数据
def decode(column):
z = []
for i in column:
z.append(i['name'])
return ' '.join(z)
moviesdf['genres'] = moviesdf['genres'].apply(decode)
moviesdf.head(2)
original_title | crew | release_date | genres | keywords | production_companies | production_countries | revenue | budget | runtime | vote_average | profit | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | Avatar | [{"credit_id": "52fe48009251416c750aca23", "de... | 2009-12-10 | Action Adventure Fantasy Science Fiction | [{"id": 1463, "name": "culture clash"}, {"id":... | [{"name": "Ingenious Film Partners", "id": 289... | [{"iso_3166_1": "US", "name": "United States o... | 2787965087 | 237000000 | 162.0 | 7.2 | 2550965087 |
1 | Pirates of the Caribbean: At World's End | [{"credit_id": "52fe4232c3a36847f800b579", "de... | 2007-05-19 | Adventure Fantasy Action | [{"id": 270, "name": "ocean"}, {"id": 726, "na... | [{"name": "Walt Disney Pictures", "id": 2}, {"... | [{"iso_3166_1": "US", "name": "United States o... | 961000000 | 300000000 | 169.0 | 6.9 | 661000000 |
# 建立genres列表,提取电影的类型
genres_list = set()
for i in moviesdf['genres'].str.split(' '):
genres_list = set().union(i, genres_list)
genres_list = list(genres_list)
genres_list
genres_list.remove('')
genres_list
['Animation',
'Foreign',
'Drama',
'War',
'Music',
'Western',
'History',
'Documentary',
'TV',
'Action',
'Family',
'Romance',
'Horror',
'Comedy',
'Mystery',
'Thriller',
'Fantasy',
'Crime',
'Movie',
'Fiction',
'Adventure',
'Science']
# release_date列数据处理:
# 保留日期中的年份
moviesdf['release_date'] = pd.to_datetime(moviesdf['release_date']).dt.year
columns = {'release_date':'year'}
moviesdf.rename(columns=columns, inplace=True)
moviesdf['year'].apply(int).head()
0 2009
1 2007
2 2015
3 2012
4 2012
Name: year, dtype: int64
# 1、建立包含年份与电影类型数量的关系数据框:
for genre in genres_list:
moviesdf[genre] = moviesdf['genres'].str.contains(genre).apply(lambda x:1 if x else 0)
genre_year = moviesdf.loc[:,genres_list]
genre_year.head()
Animation | Foreign | Drama | War | Music | Western | History | Documentary | TV | Action | ... | Horror | Comedy | Mystery | Thriller | Fantasy | Crime | Movie | Fiction | Adventure | Science | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | ... | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 |
1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | ... | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 0 |
2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | ... | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 0 |
3 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | ... | 0 | 0 | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 0 |
4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 |
5 rows × 22 columns
# 把年份作为索引标签
genre_year.index = moviesdf['year']
# 将数据集按年份分组并求和,得出每个年份,各电影类型的总数
genresdf = genre_year.groupby('year').sum()
# 查看数据集.tail默认查看后五行数据
genresdf.tail()
Animation | Foreign | Drama | War | Music | Western | History | Documentary | TV | Action | ... | Horror | Comedy | Mystery | Thriller | Fantasy | Crime | Movie | Fiction | Adventure | Science | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
year | |||||||||||||||||||||
2013 | 17 | 0 | 110 | 3 | 12 | 1 | 8 | 10 | 2 | 56 | ... | 25 | 71 | 5 | 53 | 21 | 37 | 2 | 27 | 36 | 27 |
2014 | 14 | 0 | 110 | 10 | 9 | 3 | 7 | 7 | 0 | 54 | ... | 21 | 62 | 15 | 66 | 16 | 27 | 0 | 26 | 37 | 26 |
2015 | 13 | 0 | 95 | 2 | 8 | 7 | 9 | 7 | 0 | 46 | ... | 33 | 52 | 20 | 67 | 10 | 26 | 0 | 28 | 35 | 28 |
2016 | 4 | 0 | 37 | 3 | 1 | 1 | 6 | 0 | 0 | 39 | ... | 20 | 26 | 6 | 27 | 13 | 10 | 0 | 11 | 23 | 11 |
2017 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
5 rows × 22 columns
# 汇总电影类型的数量
genresdfSum = genresdf.sum(axis=0).sort_values(ascending=False)
genresdfSum
Drama 2297
Comedy 1722
Thriller 1274
Action 1154
Romance 894
Adventure 790
Crime 696
Science 535
Fiction 535
Horror 519
Family 513
Fantasy 424
Mystery 348
Animation 234
History 197
Music 185
War 144
Documentary 110
Western 82
Foreign 34
TV 8
Movie 8
dtype: int64
# 2、数据可视化
# 绘制各种电影类型的数量柱状图
# 设置画板大小
fig=plt.figure(figsize=(12,8))
# 创建画纸,这里只使用1
ax1 = plt.subplot(111)
# 在画纸上绘图
# 电影类型的数量按降序排序
rects = genresdfSum.sort_values(ascending=True).plot(kind='barh', label='genres')
plt.title('1各种电影类型的数量统计图')
plt.xlabel('2电影数量(部)',fontsize=15)
plt.ylabel('3电影类型',fontsize = 15)
plt.show()
# 绘制各种电影类型占比的饼状图:
genres_pie = genresdfSum / genresdfSum.sum()
# 设置other类,当电影类型所占比例小于%1时,全部归到other类中
others = 0.01
genres_pie_otr = genres_pie[genres_pie >= others]
genres_pie_otr['Other'] = genres_pie[genres_pie < others].sum()
# 所占比例小于或等于%2时,对应的饼状图往外长高一截
explode = (genres_pie_otr <= 0.02) / 20 + 0.05
# 设置饼状图的参数
genres_pie_otr.plot(kind='pie', label='',startangle=50,shadow=False,
figsize=(10,10),autopct='%1.11f%%', explode=explode)
plt.title('a各种电影类型所占比例')
Text(0.5, 1.0, 'a各种电影类型所占比例')
分析结论:
从上面的结果可以看出,在所有的电影类型中,Drama(戏剧)类型电影最多,占所有电影类型的18.9%,其次为Comedy(喜剧),占所有电影类型的14.2%。
在所有电影类型中,电影数量排名前5的电影类型分别为:
Drama(戏剧)、Comedy(喜剧)、Thriller(惊悚)、Action(动作)、Romance(冒险)。
# 3、电影类型随时间变化的趋势分析:
plt.figure(figsize=(12,8))
plt.plot(genresdf, label=genresdf.columns)
plt.xticks(range(1910,2018,5))
plt.legend(genresdf)
plt.title('1电影类型随时间变化的趋势',fontsize=15)
plt.xlabel('2年份',fontsize=15)
plt.ylabel('3数量(部)',fontsize=15)
plt.grid(True)
plt.show()
分析结论:
从图中观察到,随着时间的推移,所有电影类型都呈现出增长趋势,尤其是1992年以后各个类型的电影均增长迅速,其中Drama(戏剧)和Comedy(喜剧)增长最快,目前仍是最热门的电影类型。
# 先求出各种电影类型的平均利润:
# 把电影类型作为索引
mean_genre_profit = DataFrame(index=genres_list)
# 求出每种电影类型的平均利润
newarray = []
for genre in genres_list:
newarray.append(moviesdf.groupby(genre,as_index=True)['profit'].mean())
newarray2 = []
for i in range(len(genres_list)):
newarray2.append(newarray[i][1])
mean_genre_profit['mean_profit'] = newarray2
mean_genre_profit.head()
mean_profit | |
---|---|
Animation | 1.592271e+08 |
Foreign | -2.934369e+05 |
Drama | 3.143791e+07 |
War | 4.887342e+07 |
Music | 3.254800e+07 |
# 电影类型平均利润数据可视化:
# 数据可视化
plt.figure(figsize=(12,8))
# 对于mean_profig列数据按值大小进行降序排序
mean_genre_profit.sort_values(by='mean_profit',ascending=True).plot(kind='barh')
plt.title('1各种电影类型的平均利润')
plt.xlabel('2平均利润(美元)')
plt.ylabel('3电影类型')
plt.grid(True)
plt.show()
<Figure size 864x576 with 0 Axes>
分析结论:
从图中观察到,拍摄Animation、Adventure、Fantasy这三类电影盈利最好,而拍摄Foreign、TV、Movie这三类电影会存在亏本的风险。
Universal Pictures(环球影业)和Paramount Pictures(派拉蒙影业)是美国两家电影巨头公司。
1、查看 Universal Pictures和Paramount Pictures两家影视公司电影发行的数量
先对production_companies列数据进行处理:
# production_companies列数据格式化
moviesdf['production_companies'] = moviesdf['production_companies'].apply(json.loads)
# 调用自定义函数decode处理production_companies列数据
moviesdf['production_companies'] = moviesdf['production_companies'].apply(decode)
moviesdf.head(2)
original_title | crew | year | genres | keywords | production_companies | production_countries | revenue | budget | runtime | ... | Horror | Comedy | Mystery | Thriller | Fantasy | Crime | Movie | Fiction | Adventure | Science | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | Avatar | [{"credit_id": "52fe48009251416c750aca23", "de... | 2009 | Action Adventure Fantasy Science Fiction | [{"id": 1463, "name": "culture clash"}, {"id":... | Ingenious Film Partners Twentieth Century Fox ... | [{"iso_3166_1": "US", "name": "United States o... | 2787965087 | 237000000 | 162.0 | ... | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 |
1 | Pirates of the Caribbean: At World's End | [{"credit_id": "52fe4232c3a36847f800b579", "de... | 2007 | Adventure Fantasy Action | [{"id": 270, "name": "ocean"}, {"id": 726, "na... | Walt Disney Pictures Jerry Bruckheimer Films S... | [{"iso_3166_1": "US", "name": "United States o... | 961000000 | 300000000 | 169.0 | ... | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 0 |
2 rows × 34 columns
# 查询production_companies数据列并统计Universal Pictures和Paramount Pictures的数据:
# 查询production_companies数据列中是否含有Universal Pictures,Paramount Pictures有则标记为1
moviesdf['Universal Pictures'] = moviesdf['production_companies'].str.contains('Universal Pictures').apply(lambda x:1 if x else 0)
moviesdf['Paramount Pictures'] = moviesdf['production_companies'].str.contains('Paramount Pictures').apply(lambda x:1 if x else 0)
# 统计Universal Pictures和Paramount Pictures的数据
a = moviesdf['Universal Pictures'].sum()
b = moviesdf['Paramount Pictures'].sum()
dict_company = {'Universal':a, 'Paramount':b}
company_vs = Series(dict_company)
company_vs
Universal 314
Paramount 285
dtype: int64
# 使用饼状图比较两家公司发行的电影占比:
company_vs.plot(kind='pie', label='', startangle=50, shadow=False, autopct='%1.1f%%')
plt.title('Universal Pictures和Paramount Pictures两家公司电影发行数量对比',fontsize=13)
Text(0.5, 1.0, 'Universal Pictures和Paramount Pictures两家公司电影发行数量对比')
# 2、分析Universal Pictures和Paramount Pictures两家影视公司电影发行的走势
# 抽取相关数据列进行处理:
companydf = moviesdf[['Universal Pictures','Paramount Pictures']]
companydf.index = moviesdf['year']
# 对Universal和Paramount公司的发行数量按年分组求和
companydf = companydf.groupby('year').sum()
companydf.tail()
Universal Pictures | Paramount Pictures | |
---|---|---|
year | ||
2013 | 9 | 8 |
2014 | 10 | 8 |
2015 | 13 | 7 |
2016 | 10 | 5 |
2017 | 0 | 0 |
# 两家影视公司电影发行的折线图:
plt.figure(figsize=(12,8))
plt.plot(companydf, label=companydf.columns)
plt.xticks(range(1910,2018,5))
plt.legend(companydf)
plt.title('Universal Pictures和Paramount Pictures公司电影的发行量时间走势', fontsize=15)
plt.xlabel('年份', fontsize = 15)
plt.ylabel('数量(部)',fontsize=15)
plt.grid(True)
plt.show()
分析结论:
从图中观察到,随着时间的推移,Universal Pictures和Paramount Pictures公司的电影发行量呈现出增长趋势,尤其是在1995年后增长迅速,其中Universal Pictures公司比Paramount Pictures公司发行的电影数量更多。
# 对keywords列数据处理:
# 格式化
moviesdf['keywords'] = moviesdf['keywords'].apply(json.loads)
# 调用自定义的函数decode处理keywords列数据
moviesdf['keywords'] = moviesdf['keywords'].apply(decode)
moviesdf['keywords'].tail()
4798 united states–mexico barrier legs arms paper k...
4799
4800 date love at first sight narration investigati...
4801
4802 obsession camcorder crush dream girl
Name: keywords, dtype: object
# 提取关键字
a = 'based on novel'
moviesdf['if_original'] = moviesdf['keywords'].str.contains(a).apply(lambda x: 'no original' if x else 'original')
moviesdf['if_original'].value_counts()
original 4606
no original 197
Name: if_original, dtype: int64
original_profit = moviesdf[['if_original','budget','revenue','profit']]
original_profit = original_profit.groupby(by='if_original').mean()
original_profit
budget | revenue | profit | |
---|---|---|---|
if_original | |||
no original | 4.532546e+07 | 1.438100e+08 | 9.848457e+07 |
original | 2.834872e+07 | 7.962815e+07 | 5.127943e+07 |
# 描绘柱状图,对改编电影与原创电影在预算、收入及利润三方面进行比较:
# 可视化柱状图
plt.figure(figsize=(12,8))
original_profit.plot(kind='bar')
plt.title('改编电影与原创电影在预算、收入和利润的比较')
plt.xlabel('改编电影与原创电影')
plt.ylabel('金额(美元)')
plt.show()
<Figure size 864x576 with 0 Axes>
分析结论:
从图上可以看出,改编电影的预算略高于原创电影,但改编电影的票房收入和利润远远高于原创电影, 这可能是改编电影拥有一定的影迷基础。
# 电影时长与电影票房的关系:
moviesdf.plot(kind='scatter', x='runtime', y='revenue', figsize=(8,6))
plt.title('电影时长与电影票房的关系',fontsize = 15)
plt.xlabel('电影时长(分钟)',fontsize=15)
plt.ylabel('电影票房(美元)',fontsize=15)
plt.grid(True)
plt.show()
# 电影时长与电影平均评分的关系:
moviesdf.plot(kind='scatter', x='runtime', y='vote_average', figsize=(8,6))
plt.title('电影时长与电影平均评分的关系',fontsize=15)
plt.xlabel('电影时长(分钟)',fontsize=15)
plt.ylabel('电影平均评分',fontsize=15)
plt.grid(True)
plt.show()
分析结论:
从图上可以看出,电影要想获得较高的票房及良好的口碑,电影的时长应保持在90~150分钟内。
# 先提取电影关键字:
# 利用电影关键字制作词云图
# 建立keywords_list列表
keywords_list = []
for i in moviesdf['keywords']:
keywords_list.append(i)
keywords_list = list(keywords_list)
keywords_list
# 把字符串列表链接成一个长字符串
lis = ''.join(keywords_list)
# 使用空格替换中间多余的字符串'\'s'
lis.replace('\'s', '')
'culture clash future space war space colony society space travel futuristic romance space alien tribe alien planet cgi marine soldier battle love affair anti war power relations mind and soul 3docean drug abuse exotic island east india trading company love of one life traitor shipwreck strong woman ship alliance calypso afterlife fighter pirate
# 通过词云包WordCloud生成词云图:
wc = WordCloud(background_color='black',
max_words=2000,
max_font_size=100,
random_state=12)
# 根据字符串生成词云
wc.generate(lis)
plt.figure(figsize=(16,8))
# 显示图片
plt.imshow(wc)
plt.axis('off')
plt.show()
分析结论:
通过对电影关键字的分析,电影中经常被提及的词语是女性(woman)、独立(independent),其次是谋杀(murder)、爱情(love)、警察(police)、暴力(violence),可见观众对女性和独立方面题材的电影最感兴趣,其次是是犯罪类和爱情类电影。