📘 2024 年热门动漫/Animation.ipynb

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')
anime_data = pd.read_csv("Top_Anime_data.csv")
anime_data.head()

	Score	Popularity	Rank	Members	Description	Synonyms	Japanese	English	Type	Episodes	...	Premiered	Broadcast	Producers	Licensors	Studios	Source	Genres	Demographic	Duration	Rating
0	9.38	284	1	710	During their decade-long quest to defeat the D...	Frieren at the Funeral	葬送のフリーレン	Frieren: Beyond Journey's End	TV	28	...	Fall 2023	Fridays at 23:00 (JST)	Aniplex, Dentsu, Shogakukan-Shueisha Productio...	None found, add some	Madhouse	Manga	AdventureAdventure, DramaDrama, FantasyFantasy	ShounenShounen	24 min. per ep.	PG-13 - Teens 13 or older
1	9.09	3	2	3	After a horrific alchemy experiment goes wrong...	Hagane no Renkinjutsushi: Fullmetal Alchemist,...	鋼の錬金術師 FULLMETAL ALCHEMIST	Fullmetal Alchemist: Brotherhood	TV	64	...	Spring 2009	Sundays at 17:00 (JST)	Aniplex, Square Enix, Mainichi Broadcasting Sy...	Funimation, Aniplex of America	Bones	Manga	ActionAction, AdventureAdventure, DramaDrama, ...	ShounenShounen	24 min. per ep.	R - 17+ (violence & profanity)
2	9.07	13	3	2	Eccentric scientist Rintarou Okabe has a never...	NaN	STEINS;GATE	Steins;Gate	TV	24	...	Spring 2011	Wednesdays at 02:05 (JST)	Frontier Works, Media Factory, Kadokawa Shoten...	Funimation	White Fox	Visual novel	DramaDrama, Sci-FiSci-Fi, SuspenseSuspense	NaN	24 min. per ep.	PG-13 - Teens 13 or older
3	9.06	342	4	630	Gintoki, Shinpachi, and Kagura return as the f...	Gintama' (2015)	銀魂°	Gintama Season 4	TV	51	...	Spring 2015	Wednesdays at 18:00 (JST)	TV Tokyo, Aniplex, Dentsu	Funimation, Crunchyroll	Bandai Namco Pictures	Manga	ActionAction, ComedyComedy, Sci-FiSci-Fi	ShounenShounen	24 min. per ep.	PG-13 - Teens 13 or older
4	9.05	21	5	2	Seeking to restore humanity's diminishing hope...	NaN	進撃の巨人 Season3 Part.2	Attack on Titan Season 3 Part 2	TV	10	...	Spring 2019	Mondays at 00:10 (JST)	Production I.G, Dentsu, Mainichi Broadcasting ...	Funimation	Wit Studio	Manga	ActionAction, DramaDrama, SuspenseSuspense	ShounenShounen	23 min. per ep.	R - 17+ (violence & profanity)

5 rows × 22 columns

anime_data.shape
anime_data.info()
anime_data.describe()
anime_data.describe(include='O').T

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 22 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   Score        1000 non-null   float64
 1   Popularity   1000 non-null   int64  
 2   Rank         1000 non-null   int64  
 3   Members      1000 non-null   int64  
 4   Description  1000 non-null   object 
 5   Synonyms     709 non-null    object 
 6   Japanese     999 non-null    object 
 7   English      859 non-null    object 
 8   Type         1000 non-null   object 
 9   Episodes     1000 non-null   object 
 10  Status       1000 non-null   object 
 11  Aired        1000 non-null   object 
 12  Premiered    569 non-null    object 
 13  Broadcast    569 non-null    object 
 14  Producers    1000 non-null   object 
 15  Licensors    1000 non-null   object 
 16  Studios      1000 non-null   object 
 17  Source       1000 non-null   object 
 18  Genres       771 non-null    object 
 19  Demographic  521 non-null    object 
 20  Duration     1000 non-null   object 
 21  Rating       1000 non-null   object 
dtypes: float64(1), int64(3), object(18)
memory usage: 172.0+ KB

	count	unique	top	freq
Description	1000	999	Following their success in the qualifying roun...	2
Synonyms	709	701	The Magician's Bride, Mahoyome	2
Japanese	999	953	僕のヒーローアカデミア	5
English	859	856	Time of Eve	2
Type	1000	6	TV	569
Episodes	1000	84	1	292
Status	1000	2	Finished Airing	978
Aired	1000	961	Oct 6, 2013 to Mar 30, 2014	3
Premiered	569	129	Fall 2022	15
Broadcast	569	184	Unknown	58
Producers	1000	641	None found, add some	111
Licensors	1000	90	None found, add some	369
Studios	1000	166	Madhouse	56
Source	1000	15	Manga	547
Genres	771	237	ActionAction, AdventureAdventure, FantasyFantasy	43
Demographic	521	5	ShounenShounen	321
Duration	1000	141	24 min. per ep.	259
Rating	1000	5	PG-13 - Teens 13 or older	651

数据可视化

# 分数分布
plt.figure(figsize=(10, 6))
sns.histplot(anime_data['Score'], bins=30, kde=True, color='skyblue')
plt.title('Distribution of Scores')
plt.xlabel('Score')
plt.ylabel('Frequency')
plt.show()

# 受欢迎程度分布
plt.figure(figsize=(10, 6))
sns.histplot(anime_data['Popularity'], bins=30, kde=True, color='orange')
plt.title('Popularity Distribution')
plt.xlabel('Popularity')
plt.ylabel('Frequency')
plt.show()

# 先处理 'Genres' 列
genres = anime_data['Genres'].str.split(',').explode().str.strip()

# 获取前15个最常见的genres，并重置索引
top_genres = genres.value_counts().head(15).reset_index()
top_genres.columns = ['Genre', 'Count']

# 使用 top_genres 的结果进行绘制
plt.figure(figsize=(12, 8))
sns.barplot(y='Genre', x='Count', data=top_genres, palette='muted')
plt.title('Top 15 Genres Distribution')
plt.xlabel('Count')
plt.ylabel('Genre')
plt.show()

# 分数与人气的散点图
plt.figure(figsize=(10, 6))
sns.scatterplot(x='Score', y='Popularity', data=anime_data, alpha=0.7)
plt.title('Score vs. Popularity')
plt.xlabel('Score')
plt.ylabel('Popularity')
plt.show()

# 排名前十的生产商
top_producers = anime_data['Producers'].str.split(',').explode().value_counts().head(10)
plt.figure(figsize=(10, 6))
sns.barplot(x=top_producers.values, y=top_producers.index, palette='husl')
plt.title('Top 10 Producers by Count')
plt.xlabel('Count')
plt.ylabel('Producer')
plt.show()

# 动漫人口分布
anime_data["Demographic"].value_counts().plot.pie(figsize=(10,5))
plt.title("Distribution of Anime Demographic", loc='center',
color='red', fontsize=10, fontweight='bold')
plt.show()
labels=['Teens 13 or older', 'violence & profanity', 'Mild Nudity', 'All Ages', 'Children']
colors=['Pink','Yellow','Orange','Blue','Red']
plt.pie(anime_data["Rating"].value_counts(), labels=labels, colors=colors)
plt.axis('equal')
plt.title("Rating", loc='center', color='Blue', fontsize='15')
plt.gca().add_artist(plt.Circle(xy=(0,0),radius=0.75, facecolor='white'))
plt.show()

# 分数类别与来源的标准化交叉拟合
bins = [7.8, 7.9, 8.1, 8.3,9.4]
labels = ['7.8 to 7.9', '7.9 to 8.1','8.1 to 8.3','8.3 to 9.4']
anime_data['Score_Category'] = pd.cut(anime_data['Score'], bins=bins, labels=labels, right=False)
normalised_df = (pd.crosstab(anime_data["Score_Category"],anime_data["Source"],normalize="index")*100).round(2)
normalised_df.plot(kind="bar",stacked=True)
plt.xlabel('Score Category')
plt.ylabel('Percentage')
plt.title('Normalized Crosstabulation of Score Category and Source')
plt.legend(title='Source', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()

# 收视人数与收视率的标准化交叉校正
bins = [1.0, 500.0, 1000.0]
labels = ['1 to 500', '500 to 1000']
anime_data['Members_category'] = pd.cut(anime_data['Members'], bins=bins, labels=labels, right=False)
(pd.crosstab(anime_data["Members_category"],anime_data["Rating"],normalize="index")*100).round(2).plot(kind="bar",stacked=True)
plt.title('Normalized Crosstabulation of Number of Viewers and Rating')
plt.legend(title='Rating', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()

# 5大制作公司
anime_data["Studios"].value_counts().head(5).plot(kind="pie",autopct='%1.1f%%')
plt.title("Top 5 Production Houses")
plt.ylabel('')
plt.show()

# 疯人院制作的顶级动画
anime_data[anime_data["Studios"] == "Madhouse"]["Rating"].value_counts().plot(kind="pie",autopct='%1.1f%%')
plt.title("Top Anime produced by Madhouse")
plt.show()