python大作业

数据分析大作业,这里做个简单的记录,数据集下载https://gitee.com/Arno_vc/python.git

#通用函数
import pandas as pd;
import re
import numpy as np
import matplotlib.pyplot as plt

#plt字体设置
plt.rcParams['font.sans-serif']=['SimHei'];
plt.rcParams['font.size'] = '16';

def drawBox(data,title):
    data.plot.box(title=title,figsize=(10,10));
    plt.grid(linestyle="--", alpha=0.3);
    plt.show();
    
def drawBar(data,title):
    data.plot.bar(stacked=True,title=title,figsize=(10,10));
    plt.show();

def drawPie(data,title):
    data.plot.pie(title=title,figsize=(10,10));
    plt.show();
    
def drawScatter(data,x,y):
    data.plot.scatter(x=x, y=y,figsize=(10,10))
    plt.show();

def drawLine(data,title):
    data.plot.line(title=title,figsize=(10,10));
    plt.show();
    
def count(data):
    return len(data);

#获得年份
def getYear(data):
    res = re.findall(r'[(](.*?)[)]',data);
    return res[len(res)-1];

综合实验 MovieLens 1M数据分析

1. 数据集说明：

   MovieLens 1M Dataset：该数据集采集了一组从20世纪90年末到21世纪初由MovieLens用户提供的电影怦分数据。这些数据中包括电影评分、电影数据（风格类型和年代）以及关于用户的人口统计学数据（年龄、邮编、性别和职业等）。

   来源：https://grouplens.org/datasets/movielens/

   3个数据文件:

   • 电影：movies.dat，列：movie_id, title, genres
   • 用户：users.dat，列：user_id, gender, age, occupation, zip
   • 评分：ratings.dat，列：user_id, movie_id, rating, timestamp

2. 概要统计

   电影数量：总数、按年代、风格统计

   用户数量：总数、按性别、年龄、职业统计

   评分条数：总数、按电影、性别、职业统计

3. 分析目标

   （1） 每部电影的得分情况分析

   （2） 每种风格电影的得分情况分析

   （3） 不同性别用户偏爱的电影分析

   （4） 不同年龄段用户偏爱的电影分析

   （5） 不同性别用户偏爱的电影，随着年代的变化情况分析

#电影数量：总数、按年代、风格统计
import pandas as pd;
import re
import numpy as np
import matplotlib.pyplot as plt

#plt字体设置
plt.rcParams['font.sans-serif']=['SimHei']

#sep:分隔符,names:列名
movies = pd.read_table("../大作业2020/大作业题目1/movielens/movies.dat",sep="::",names=["movie_id","title","genres"],engine='python');
movies["year"] = movies.agg({"title":getYear},axios=1);
movies.head(1000)

	movie_id	title	genres	year
0	1	Toy Story (1995)	Animation|Children's|Comedy	1995
1	2	Jumanji (1995)	Adventure|Children's|Fantasy	1995
2	3	Grumpier Old Men (1995)	Comedy|Romance	1995
3	4	Waiting to Exhale (1995)	Comedy|Drama	1995
4	5	Father of the Bride Part II (1995)	Comedy	1995
...	...	...	...	...
995	1008	Davy Crockett, King of the Wild Frontier (1955)	Western	1955
996	1009	Escape to Witch Mountain (1975)	Adventure|Children's|Fantasy	1975
997	1010	Love Bug, The (1969)	Children's|Comedy	1969
998	1011	Herbie Rides Again (1974)	Adventure|Children's|Comedy	1974
999	1012	Old Yeller (1957)	Children's|Drama	1957

1000 rows × 4 columns

检查是否有缺失值

print("是否有缺失值:");
movies[movies.isnull().values==True]

是否有缺失值:

	movie_id	title	genres	year

查看电影总数:共3883条

print("电影总数:{}
".format(len(movies)));

电影总数:3883

​

电影年份相关统计:分析:该涵盖了1919年到2000年的电影,总数共3883条,统计不同年代的电影发行数并按升序排列,如图可知,发行最少的年代是1921年,只有1部;最多的年代是1996年,多达345部,且平均每年电影发行数为48部.通过变化的折线图可以看出,自1919年起,电影发行数目一直在逐年缓慢攀升,并从90年代开始有了剧烈的增长,1996到达顶峰(结合上一张图),之后到2000急剧下降.同时根据该箱线图,可以看出超过一半的年份的电影发行数在50以下,只有10个年份的电影发行数超过100.由以上电影类别统计的柱形图可知,Film-Noir(黑色电影)风格的电影最少,在这近100年来仅44部;最多的是Drama(戏剧)和Comedy(喜剧)

print("年份统计:
");
ageCount = movies[["title","year"]].groupby(by="year").count().sort_values(by="year");
drawLine(ageCount.loc[:,"title"],"不同年份的电影发行统计折线图");
drawBox(ageCount.loc[:,"title"],"不同年份的电影发行数统计箱线图");
ageCount

年份统计:

	title
year
1919	3
1920	2
1921	1
1922	2
1923	3
...	...
1996	345
1997	315
1998	337
1999	283
2000	156

81 rows × 1 columns

电影类别统计:可以看出电影最多的是Drama类型的电影,有1606;最少的Film-Noir类型的电影,仅44部

genres=[];
for i in range(0,len(movies)):
    temp = movies.loc[i,"genres"];
    temp = temp.split("|");
    for j in range(0,len(temp)):
        genres.append([movies.loc[i,"movie_id"],temp[j]]);
        
genres = pd.DataFrame(genres,columns=["movie_id","genres"]);
genresCount = genres.groupby(by="genres").count().sort_values(by="movie_id");
#关于类别统计的箱线图
drawBox(genresCount.loc[:,["movie_id"]],"电影类别统计箱线图")
drawBar(genresCount,"电影类别统计柱形图");
print("电影类别统计
");
genresCount

​

电影类别统计

	movie_id
genres
Film-Noir	44
Fantasy	68
Western	68
Animation	105
Mystery	106
Musical	114
Documentary	127
War	143
Crime	211
Children's	251
Sci-Fi	276
Adventure	283
Horror	343
Romance	471
Thriller	492
Action	503
Comedy	1200
Drama	1603

导入用户数据,同时检查用户数据

#用户数量：总数、按性别、年龄、职业统计
import pandas as pd;
import re
import numpy as np

#sep:分隔符,names:列名,occupation:职业,zip:邮编
users = pd.read_table("../大作业2020/大作业题目1/movielens/users.dat",sep="::",names=["user_id","gender","age","occupation","zip"],engine='python');
users.head(1000);

检查是否有缺失值

print("是否有缺失值");
users[users.isnull().values==True]

是否有缺失值

	user_id	gender	age	occupation	zip

用户总数

print("用户总数:{}
".format(len(users)));

用户总数:6040

​

性别统计:用户总数多达6040人,其中有1709人的女性,4331人的男性.由对应的饼图可以看出,男性占比接近3/4.

genderCount = users.loc[:,["user_id","gender"]].groupby(by="gender").count();
print("性别统计");
drawPie(genderCount.loc[:,"user_id"],"用户分布");
genderCount

性别统计

	user_id
gender
F	1709
M	4331

观众年龄统计:由以上关于用户机器年龄分布的表图近似于正态分布,用户主要为25岁的**年轻人**,主要区间也聚集在15~35岁的青少年即成年人.

ageCount = users.loc[:,["user_id","age"]].groupby(by="age").count();
drawBar(ageCount.loc[:,"user_id"],"观众年龄统计条形图");
print("年龄统计");
ageCount

年龄统计

	user_id
age
1	222
18	1103
25	2096
35	1193
45	550
50	496
56	380

观众职业统计:由于无法得知具体的职业名称,这里无法做过多的评判.

occupationCount = users.loc[:,["user_id","occupation"]].groupby(by="occupation").count();
drawBar(occupationCount.loc[:,"user_id"],"观众职业分布图");
print("职业统计
{}
");
occupationCount

​

	user_id
occupation
0	711
1	528
2	267
3	173
4	759
5	112
6	236
7	679
8	17
9	92
10	195
11	129
12	388
13	142
14	302
15	144
16	241
17	502
18	70
19	72
20	281

评分统计

#评分条数：总数、按电影、性别、职业统计
import pandas as pd;
import re
import numpy as np

#sep:分隔符,names:列名,occupation:职业,zip:邮编
rating = pd.read_table("../大作业2020/大作业题目1/movielens/ratings.dat",sep="::",names=["user_id","movie_id","rating","timestamp"],engine='python');
movies = pd.read_table("../大作业2020/大作业题目1/movielens/movies.dat",sep="::",names=["movie_id","title","genres"],engine='python');
data = pd.merge(movies,rating,how="inner",on="movie_id");
users = pd.read_table("../大作业2020/大作业题目1/movielens/users.dat",sep="::",names=["user_id","gender","age","occupation","zip"],engine='python');
data = pd.merge(data,users,how="inner",on="user_id");
rating.head(1000)

	user_id	movie_id	rating	timestamp
0	1	1193	5	978300760
1	1	661	3	978302109
2	1	914	3	978301968
3	1	3408	4	978300275
4	1	2355	5	978824291
...	...	...	...	...
995	10	3704	2	978228364
996	10	1020	3	978228726
997	10	784	3	978230946
998	10	858	3	978224375
999	10	1022	5	979775689

1000 rows × 4 columns

评分总条数统计

print("用户总数:{}
".format(len(rating)));

用户总数:1000209

​

按电影统计评分:由以下相关的统计数据可知,总评条数为1000209条,评论最少的电影有多部,都为1条;评论最多的电影为American Beaty,有3428条.平均每部电影有900条,然而超过50%的电影甚至连500条都远远没有达到.

titleCount = data.loc[:,["movie_id","title"]].groupby(by="title").count().sort_values(by="movie_id");
print("按电影统计评分");
drawBox(titleCount.loc[:,"movie_id"],"电影评分条数统计");
titleCount.head(1000)

按电影统计评分

	movie_id
title
Another Man's Poison (1952)	1
Night Tide (1961)	1
Shadows (Cienie) (1988)	1
McCullochs, The (1975)	1
Anna (1996)	1
...	...
Cats Don't Dance (1997)	37
How I Won the War (1967)	37
Idiots, The (Idioterne) (1998)	37
Isn't She Great? (2000)	37
Boys of St. Vincent, The (1993)	37

1000 rows × 1 columns

职业统计:可以看出0号和4号职业的电影评论较多,8号职业的评论格外少

occupationCount = data.loc[:,["movie_id","occupation"]].groupby(by="occupation").count();
drawBar(occupationCount.loc[:,"movie_id"],"电影评分与职业统计");
print("按职业统计评分");
occupationCount

按职业统计评分

	movie_id
occupation
0	130499
1	85351
2	50068
3	31623
4	131032
5	21850
6	37205
7	105425
8	2706
9	11345
10	23290
11	20563
12	57214
13	13754
14	49109
15	22951
16	46021
17	72816
18	12086
19	14904
20	60397

电影评分与性别统计:这里,尽管男性用户整体占比没有超过3/4,但男性评论的条数占比超过了3/4,说明了看电影的男性中有不少也是很感性的.

genderCount = data.loc[:,["movie_id","gender"]].groupby(by="gender").count();
drawPie(genderCount.loc[:,"movie_id"],"电影评分与性别统计");
print("按性别统计评分");
genderCount

按性别统计评分

	movie_id
gender
F	246440
M	753769

1. 每部电影的得分情况分析:由对应的箱线图数据可知,超过50%的电影得分均在2.7~3.7区间内,只有极少数异常的电影评分低于或等于1.5.

#电影得分分析
titleCount = data.loc[:,["title","rating"]].groupby(by="title").mean().sort_values(by="rating");
drawBox(titleCount,"各电影评价得分箱线图");
print("各电影评价得分");
titleCount.head(1000)

各电影评价得分

	rating
title
Elstree Calling (1930)	1.000000
Get Over It (1996)	1.000000
Venice/Venice (1992)	1.000000
Windows (1980)	1.000000
Kestrel's Eye (Falkens 鰃a) (1998)	1.000000
...	...
Net, The (1995)	2.869947
End of Violence, The (1997)	2.870370
Renaissance Man (1994)	2.870968
Funeral, The (1996)	2.870968
Robert A. Heinlein's The Puppet Masters (1994)	2.871508

1000 rows × 1 columns

2. 每种风格电影的得分情况分析:由上图可知,即便不同电影的评价得分有较大的变化区间,不同类别电影之间的评分差距却显得较为平和,可以认为无论是哪一类电影,都是既有糟糕的作品,也有优秀的作品.其中,平均得分最高的是Film-Noir电影,高达4.7,最低的是Horror类型的电影

#分隔信息表:movie_id与genres不是一一对应的关系
import pandas  as pd

del data["genres"];  #如果没有删除则需要删除
genres = pd.merge(genres,data,how="inner",on="movie_id");
ratingCount = genres.loc[:,["genres","rating"]].groupby(by="genres").mean().sort_values(by="genres");
drawBar(ratingCount.loc[:,"rating"],"不同电影风格得分统计");
print("不同风格电影得分情况比较");
ratingCount

不同风格电影得分情况比较

	rating
genres
Action	3.491185
Adventure	3.477257
Animation	3.684868
Children's	3.422035
Comedy	3.522099
Crime	3.708679
Documentary	3.933123
Drama	3.766332
Fantasy	3.447371
Film-Noir	4.075188
Horror	3.215013
Musical	3.665519
Mystery	3.668102
Romance	3.607465
Sci-Fi	3.466521
Thriller	3.570466
War	3.893327
Western	3.637770

3. 不同性别用户偏爱的电影分析:这里分析了不同类型电影的男女观影人数比较,可以看出有人男性占据绝对的人数优势,在所有电影的观看人次上都超过了女性,其中差距自大的Action类型电影,最小的是Documentary类型电影,当然这在一定程度上也和该电影的总体观影人数较少有关.

#使用交叉表展示性别与电影评分的关系
crosstab = pd.crosstab(genres["genres"],genres["gender"],values=genres["rating"],aggfunc=count);
crosstab.loc[:,"dis"] = crosstab.loc[:,"F"] - crosstab.loc[:,"M"]
#绘制双柱形图
crosstab.plot(kind="bar",title="不同性别用户偏爱的电影类别分析",figsize=(10,10))
plt.show();
print("不同性别用户偏爱的电影类别分析");
crosstab

c:usersgclappdatalocalprogramspythonpython37-32libsite-packagesmatplotlibackendsackend_agg.py:238: RuntimeWarning: Glyph 8722 missing from current font.
  font.set_text(s, 0.0, flags=flags)
c:usersgclappdatalocalprogramspythonpython37-32libsite-packagesmatplotlibackendsackend_agg.py:201: RuntimeWarning: Glyph 8722 missing from current font.
  font.set_text(s, 0, flags=flags)

不同性别用户偏爱的电影类别分析

gender	F	M	dis
genres
Action	45650	211807	-166157
Adventure	27332	106621	-79289
Animation	12221	31072	-18851
Children's	21317	50869	-29552
Comedy	96271	260309	-164038
Crime	16442	63099	-46657
Documentary	1940	5970	-4030
Drama	98153	256376	-158223
Fantasy	8718	27583	-18865
Film-Noir	4202	14059	-9857
Horror	14635	61751	-47116
Musical	13505	28028	-14523
Mystery	9976	30202	-20226
Romance	50297	97226	-46929
Sci-Fi	27400	129894	-102494
Thriller	40308	149372	-109064
War	14093	54434	-40341
Western	3477	17206	-13729

4. 不同年龄段用户偏爱的电影分析:各个年龄段的用户都喜欢看Action,Comedy,Drama;年级为1的用户最喜欢看Comedy;25岁,35岁的青壮年用户对于Romance,Sci-Fi(科幻小说),THriller也有不错的偏好.到45岁后用户的电影观看数量多比较少

crosstab = pd.crosstab(genres["genres"],genres["age"],values=genres["rating"],aggfunc=count);
drawBar(crosstab,"不同年龄段用户偏爱的电影类别分析");
print("不同年龄段用户偏爱的电影分析");
crosstab

age	1	18	25	35	45	50	56
genres
Action	6578	50186	105678	50503	19357	17012	8143
Adventure	3998	26324	52633	26682	10738	9090	4488
Animation	2449	10269	16454	8117	2889	2032	1083
Children's	4337	16924	25743	14004	5400	3890	1888
Comedy	11162	69980	143210	69244	27890	23133	11961
Crime	1701	15373	33030	14895	6048	5520	2974
Documentary	130	1081	3489	1708	687	555	260
Drama	7483	58104	138695	71590	32141	29247	17269
Fantasy	1360	7875	14290	7006	2695	2127	948
Film-Noir	330	2280	6539	4175	1860	1870	1207
Horror	2211	15184	31235	15122	6192	4681	1761
Musical	1647	7555	14705	8746	3898	3093	1889
Mystery	920	6401	15160	8179	3851	3520	2147
Romance	3599	25656	58003	29330	13283	11373	6279
Sci-Fi	4178	29033	63156	32333	13040	10674	4880
Thriller	4824	35877	77429	36840	14933	13240	6537
War	1578	10874	24830	14514	6642	6314	3775
Western	335	2863	7053	4546	2133	2420	1333

5. 不同性别用户偏爱的电影，随着年代的变化情况分析:

#通用函数
import pandas as pd;
import re
import numpy as np
import matplotlib.pyplot as plt

#plt字体设置
plt.rcParams['font.sans-serif']=['SimHei'];
plt.rcParams['font.size'] = '16';

def drawBox(data,title):
    data.plot.box(title=title,figsize=(10,10));
    plt.grid(linestyle="--", alpha=0.3);
    plt.show();
    
def drawBar(data,title):
    data.plot.bar(stacked=True,title=title,figsize=(10,10));
    plt.show();

def drawPie(data,title):
    data.plot.pie(title=title,figsize=(10,10));
    plt.show();
    
def drawScatter(data,x,y):
    data.plot.scatter(x=x, y=y,figsize=(10,10))
    plt.show();

def drawLine(data,title):
    data.plot.line(title=title,figsize=(20,20));
    plt.show();
    
def count(data):
    return len(data);

#获得年份
def getYear(data):
    res = re.findall(r'[(](.*?)[)]',data);
    return res[len(res)-1];
        
#sep:分隔符,names:列名,occupation:职业,zip:邮编
rating = pd.read_table("../大作业2020/大作业题目1/movielens/ratings.dat",sep="::",names=["user_id","movie_id","rating","timestamp"],engine='python');
movies = pd.read_table("../大作业2020/大作业题目1/movielens/movies.dat",sep="::",names=["movie_id","title","genres"],engine='python');
movies["year"] = movies.agg({"title":getYear},axios=1);
data = pd.merge(movies,rating,how="inner",on="movie_id");
users = pd.read_table("../大作业2020/大作业题目1/movielens/users.dat",sep="::",names=["user_id","gender","age","occupation","zip"],engine='python');
data = pd.merge(data,users,how="inner",on="user_id");
rating

genres=[];
for i in range(0,len(movies)):
    temp = movies.loc[i,"genres"];
    temp = temp.split("|");
    for j in range(0,len(temp)):
        genres.append([movies.loc[i,"movie_id"],temp[j]]);
        
genres = pd.DataFrame(genres,columns=["movie_id","genres"]);
genresCount = genres.groupby(by="genres").count().sort_values(by="movie_id");

del data["genres"]
data = pd.merge(data,genres,how="inner",on="movie_id");
data.head(1000)

	movie_id	title	year	user_id	rating	timestamp	gender	age	occupation	zip	genres
0	1	Toy Story (1995)	1995	1	5	978824268	F	1	10	48067	Animation
1	1	Toy Story (1995)	1995	1	5	978824268	F	1	10	48067	Children's
2	1	Toy Story (1995)	1995	1	5	978824268	F	1	10	48067	Comedy
3	1	Toy Story (1995)	1995	6	4	978237008	F	50	9	55117	Animation
4	1	Toy Story (1995)	1995	6	4	978237008	F	50	9	55117	Children's
...	...	...	...	...	...	...	...	...	...	...	...
995	1	Toy Story (1995)	1995	973	4	975860648	F	25	1	80026	Comedy
996	1	Toy Story (1995)	1995	977	3	975106685	M	25	2	80110	Animation
997	1	Toy Story (1995)	1995	977	3	975106685	M	25	2	80110	Children's
998	1	Toy Story (1995)	1995	977	3	975106685	M	25	2	80110	Comedy
999	1	Toy Story (1995)	1995	979	4	988055769	M	1	10	48073	Animation

1000 rows × 11 columns

import pandas as pd;
import re
import numpy as np
import matplotlib.pyplot as plt

pivot_table = pd.pivot_table(data,index="genres",columns=["gender","year"],aggfunc=count);
#pivot_table[pivot_table.isnull().values==False]=0
pivot_table.fillna(value=0,inplace=True);
#使用transpose实现行列转换
drawLine(pivot_table[("age","M")].transpose(),"1919~2020年男性电影观看变化");
drawLine(pivot_table[("age","F")].transpose(),"1919~2020年女性电影观看变化");
pivot_table.head(1000)

	age										...	zip
gender	F										...	M
year	1919	1920	1921	1922	1923	1925	1926	1927	1928	1929	...	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000
genres
Action	2.0	0.0	11.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	5557.0	8286.0	10967.0	9739.0	13057.0	12812.0	16087.0	16399.0	12329.0	9797.0
Adventure	0.0	0.0	0.0	0.0	0.0	0.0	7.0	0.0	0.0	0.0	...	2094.0	1346.0	4810.0	4366.0	6120.0	7453.0	7446.0	4133.0	4986.0	1848.0
Animation	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	824.0	1280.0	984.0	964.0	2694.0	1965.0	851.0	3004.0	3354.0	2159.0
Children's	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	1029.0	1964.0	2208.0	2746.0	4539.0	2637.0	1924.0	3562.0	3231.0	1826.0
Comedy	24.0	4.0	0.0	0.0	1.0	76.0	1.0	33.0	3.0	0.0	...	4970.0	11283.0	12658.0	16739.0	14666.0	14462.0	15431.0	17832.0	26541.0	11129.0
Crime	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	...	248.0	5468.0	2075.0	3737.0	6011.0	4659.0	6912.0	6971.0	2364.0	1509.0
Documentary	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	148.0	33.0	260.0	1048.0	297.0	693.0	437.0	415.0	664.0	334.0
Drama	2.0	0.0	0.0	0.0	1.0	51.0	16.0	13.0	0.0	0.0	...	7834.0	9497.0	11740.0	13705.0	18379.0	15226.0	18115.0	16693.0	21320.0	9881.0
Fantasy	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	983.0	352.0	348.0	1816.0	888.0	1787.0	494.0	343.0	2039.0	110.0
Film-Noir	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	23.0	0.0	272.0	242.0	1787.0	932.0	0.0	0.0
Horror	0.0	0.0	0.0	51.0	0.0	0.0	0.0	0.0	0.0	0.0	...	309.0	2389.0	1495.0	1868.0	1809.0	2609.0	2646.0	2790.0	5189.0	1846.0
Musical	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	15.0	...	1201.0	1158.0	934.0	844.0	666.0	1277.0	742.0	660.0	324.0	147.0
Mystery	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	1120.0	713.0	980.0	475.0	975.0	1831.0	6457.0	3965.0	1200.0	445.0
Romance	0.0	0.0	0.0	0.0	0.0	0.0	0.0	12.0	0.0	0.0	...	2454.0	4957.0	5728.0	9492.0	7489.0	7146.0	6180.0	8539.0	5597.0	1382.0
Sci-Fi	0.0	0.0	0.0	0.0	0.0	0.0	65.0	0.0	0.0	0.0	...	4136.0	3479.0	4782.0	2849.0	5958.0	6270.0	10448.0	7026.0	8233.0	4608.0
Thriller	0.0	0.0	0.0	0.0	0.0	0.0	8.0	0.0	0.0	2.0	...	5227.0	5824.0	5594.0	6460.0	10813.0	12358.0	16133.0	14574.0	16534.0	7839.0
War	0.0	0.0	0.0	0.0	0.0	50.0	0.0	12.0	0.0	0.0	...	66.0	1696.0	2404.0	2531.0	3463.0	3478.0	2523.0	3348.0	1161.0	1021.0
Western	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	838.0	547.0	1808.0	538.0	238.0	0.0	20.0	735.0	0.0

18 rows × 1296 columns

temp = pivot_table[("age","M")].transpose();
temp.head(50)

genres	Action	Adventure	Animation	Children's	Comedy	Crime	Documentary	Drama	Fantasy	Film-Noir	Horror	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
year
1919	2.0	3.0	0.0	0.0	14.0	0.0	0.0	5.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1920	0.0	0.0	0.0	0.0	20.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1921	51.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1922	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	187.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1923	0.0	0.0	0.0	0.0	8.0	0.0	0.0	7.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1925	0.0	0.0	0.0	0.0	246.0	0.0	0.0	188.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	184.0	0.0
1926	0.0	7.0	0.0	0.0	9.0	1.0	0.0	23.0	0.0	0.0	0.0	0.0	0.0	0.0	323.0	13.0	0.0	0.0
1927	0.0	0.0	0.0	0.0	173.0	0.0	0.0	33.0	0.0	0.0	0.0	0.0	0.0	33.0	0.0	0.0	33.0	0.0
1928	0.0	0.0	0.0	0.0	24.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1929	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	17.0	0.0	0.0	0.0	9.0	0.0	0.0
1930	0.0	0.0	0.0	0.0	1.0	1.0	1.0	72.0	0.0	0.0	0.0	1.0	8.0	0.0	0.0	7.0	221.0	0.0
1931	0.0	0.0	0.0	0.0	216.0	248.0	0.0	198.0	0.0	248.0	527.0	0.0	0.0	198.0	0.0	248.0	0.0	22.0
1932	0.0	0.0	0.0	0.0	37.0	0.0	0.0	76.0	0.0	0.0	127.0	0.0	0.0	203.0	0.0	1.0	39.0	0.0
1933	649.0	649.0	0.0	0.0	474.0	0.0	0.0	3.0	0.0	0.0	822.0	1.0	0.0	0.0	188.0	0.0	473.0	0.0
1934	0.0	0.0	0.0	0.0	370.0	0.0	0.0	27.0	0.0	0.0	0.0	54.0	196.0	54.0	0.0	96.0	0.0	0.0
1935	0.0	176.0	0.0	0.0	133.0	0.0	0.0	0.0	0.0	0.0	172.0	133.0	0.0	133.0	0.0	195.0	0.0	0.0
1936	0.0	0.0	0.0	0.0	364.0	0.0	0.0	15.0	0.0	0.0	0.0	24.0	2.0	0.0	0.0	61.0	0.0	0.0
1937	0.0	0.0	512.0	512.0	109.0	8.0	0.0	315.0	0.0	0.0	0.0	621.0	0.0	107.0	0.0	8.0	124.0	0.0
1938	294.0	294.0	0.0	0.0	431.0	0.0	0.0	137.0	0.0	0.0	0.0	0.0	129.0	138.0	0.0	129.0	0.0	0.0
1939	0.0	1294.0	83.0	1320.0	131.0	9.0	0.0	2278.0	0.0	0.0	53.0	1211.0	0.0	801.0	0.0	0.0	715.0	0.0
1940	0.0	81.0	1150.0	1150.0	1137.0	0.0	0.0	432.0	0.0	0.0	37.0	802.0	0.0	678.0	9.0	283.0	0.0	34.0
1941	0.0	0.0	368.0	368.0	119.0	0.0	0.0	982.0	0.0	808.0	115.0	375.0	913.0	111.0	0.0	105.0	0.0	0.0
1942	93.0	0.0	395.0	395.0	462.0	0.0	0.0	1426.0	0.0	0.0	60.0	162.0	0.0	1164.0	0.0	71.0	1426.0	8.0
1943	0.0	83.0	12.0	12.0	21.0	0.0	0.0	81.0	0.0	162.0	105.0	0.0	9.0	0.0	0.0	237.0	85.0	20.0
1944	89.0	0.0	0.0	0.0	485.0	579.0	0.0	259.0	0.0	656.0	78.0	101.0	726.0	0.0	0.0	788.0	259.0	0.0
1945	0.0	0.0	94.0	94.0	56.0	0.0	0.0	234.0	0.0	0.0	82.0	150.0	132.0	196.0	0.0	132.0	26.0	0.0
1946	0.0	153.0	172.0	172.0	0.0	16.0	0.0	787.0	0.0	769.0	0.0	172.0	416.0	357.0	0.0	317.0	174.0	60.0
1947	0.0	9.0	27.0	27.0	58.0	25.0	0.0	426.0	0.0	118.0	0.0	27.0	0.0	98.0	0.0	0.0	0.0	43.0
1948	0.0	364.0	19.0	19.0	171.0	361.0	0.0	621.0	0.0	398.0	165.0	19.0	0.0	0.0	0.0	508.0	0.0	0.0
1949	0.0	111.0	0.0	114.0	0.0	1.0	0.0	217.0	0.0	0.0	0.0	136.0	377.0	1.0	0.0	377.0	0.0	0.0
1950	0.0	0.0	353.0	362.0	546.0	123.0	0.0	255.0	0.0	476.0	0.0	353.0	19.0	0.0	105.0	19.0	0.0	0.0
1951	853.0	853.0	338.0	338.0	0.0	0.0	0.0	915.0	0.0	347.0	0.0	534.0	0.0	1046.0	588.0	347.0	853.0	0.0
1952	4.0	65.0	0.0	0.0	219.0	1.0	0.0	94.0	0.0	0.0	0.0	454.0	0.0	613.0	60.0	0.0	0.0	340.0
1953	668.0	0.0	396.0	396.0	245.0	0.0	0.0	1074.0	396.0	15.0	0.0	434.0	0.0	462.0	585.0	50.0	1086.0	249.0
1954	784.0	479.0	0.0	478.0	201.0	404.0	0.0	956.0	478.0	0.0	182.0	169.0	1010.0	172.0	986.0	1250.0	240.0	0.0
1955	0.0	0.0	545.0	545.0	1154.0	0.0	0.0	1063.0	0.0	33.0	56.0	689.0	108.0	977.0	103.0	384.0	333.0	114.0
1956	0.0	235.0	0.0	0.0	217.0	112.0	0.0	269.0	0.0	183.0	556.0	217.0	0.0	0.0	1020.0	280.0	18.0	210.0
1957	0.0	0.0	0.0	210.0	257.0	0.0	1.0	2062.0	0.0	0.0	56.0	128.0	0.0	139.0	67.0	32.0	999.0	0.0
1958	319.0	318.0	0.0	0.0	289.0	405.0	0.0	554.0	214.0	405.0	1036.0	292.0	671.0	369.0	879.0	1076.0	369.0	53.0
1959	576.0	683.0	319.0	544.0	697.0	577.0	0.0	2047.0	107.0	0.0	286.0	319.0	150.0	0.0	133.0	983.0	100.0	0.0
1960	0.0	203.0	0.0	281.0	617.0	19.0	0.0	988.0	0.0	0.0	1472.0	30.0	0.0	0.0	177.0	1228.0	0.0	0.0
1961	453.0	146.0	378.0	909.0	544.0	0.0	0.0	1806.0	381.0	0.0	81.0	644.0	0.0	835.0	146.0	16.0	484.0	189.0
1962	1042.0	746.0	0.0	12.0	0.0	0.0	0.0	1306.0	0.0	859.0	157.0	53.0	0.0	0.0	158.0	1082.0	991.0	43.0
1963	670.0	917.0	207.0	320.0	721.0	0.0	0.0	721.0	0.0	0.0	889.0	0.0	185.0	185.0	1245.0	683.0	1740.0	211.0
1964	1236.0	0.0	0.0	657.0	1081.0	0.0	0.0	157.0	0.0	0.0	59.0	1466.0	0.0	336.0	0.0	221.0	0.0	477.0
1965	407.0	0.0	0.0	72.0	689.0	0.0	0.0	595.0	0.0	0.0	12.0	918.0	72.0	408.0	57.0	186.0	385.0	518.0
1966	723.0	292.0	0.0	0.0	30.0	0.0	120.0	601.0	0.0	0.0	0.0	0.0	190.0	83.0	292.0	42.0	0.0	749.0
1967	636.0	180.0	445.0	474.0	1703.0	515.0	0.0	2914.0	0.0	0.0	0.0	630.0	258.0	886.0	59.0	0.0	668.0	303.0
1968	973.0	317.0	428.0	187.0	840.0	289.0	0.0	1907.0	0.0	0.0	1112.0	912.0	1372.0	202.0	3254.0	2100.0	75.0	0.0
1969	1735.0	917.0	0.0	172.0	1512.0	11.0	0.0	1001.0	0.0	0.0	3.0	0.0	0.0	0.0	0.0	42.0	304.0	1858.0

temp = pivot_table[("age","F")].transpose();
temp.head(50)

genres	Action	Adventure	Animation	Children's	Comedy	Crime	Documentary	Drama	Fantasy	Film-Noir	Horror	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
year
1919	2.0	0.0	0.0	0.0	24.0	0.0	0.0	2.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1920	0.0	0.0	0.0	0.0	4.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1921	11.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1922	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	51.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1923	0.0	0.0	0.0	0.0	1.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1925	0.0	0.0	0.0	0.0	76.0	0.0	0.0	51.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	50.0	0.0
1926	0.0	7.0	0.0	0.0	1.0	1.0	0.0	16.0	0.0	0.0	0.0	0.0	0.0	0.0	65.0	8.0	0.0	0.0
1927	0.0	0.0	0.0	0.0	33.0	0.0	0.0	13.0	0.0	0.0	0.0	0.0	0.0	12.0	0.0	0.0	12.0	0.0
1928	0.0	0.0	0.0	0.0	3.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1929	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	15.0	0.0	0.0	0.0	2.0	0.0	0.0
1930	0.0	0.0	0.0	0.0	0.0	0.0	0.0	30.0	0.0	0.0	0.0	0.0	3.0	0.0	0.0	3.0	47.0	0.0
1931	0.0	0.0	0.0	0.0	76.0	60.0	0.0	73.0	0.0	60.0	117.0	0.0	0.0	73.0	0.0	60.0	0.0	7.0
1932	0.0	0.0	0.0	0.0	15.0	0.0	0.0	25.0	0.0	0.0	35.0	0.0	0.0	67.0	0.0	0.0	17.0	0.0
1933	124.0	124.0	0.0	0.0	121.0	0.0	0.0	2.0	0.0	0.0	166.0	0.0	0.0	0.0	44.0	0.0	121.0	0.0
1934	0.0	0.0	0.0	0.0	196.0	0.0	0.0	31.0	0.0	0.0	0.0	51.0	96.0	51.0	0.0	32.0	0.0	0.0
1935	0.0	49.0	0.0	0.0	118.0	0.0	0.0	0.0	0.0	0.0	44.0	118.0	0.0	118.0	0.0	58.0	0.0	0.0
1936	0.0	0.0	0.0	0.0	129.0	0.0	0.0	9.0	0.0	0.0	0.0	12.0	0.0	0.0	0.0	12.0	0.0	0.0
1937	0.0	0.0	251.0	251.0	91.0	2.0	0.0	131.0	0.0	0.0	0.0	342.0	0.0	91.0	0.0	2.0	41.0	0.0
1938	84.0	84.0	0.0	0.0	258.0	0.0	0.0	73.0	0.0	0.0	0.0	0.0	70.0	77.0	0.0	70.0	0.0	0.0
1939	0.0	541.0	34.0	592.0	85.0	2.0	0.0	1108.0	0.0	0.0	12.0	507.0	0.0	487.0	0.0	0.0	441.0	0.0
1940	0.0	24.0	488.0	488.0	608.0	0.0	0.0	167.0	0.0	0.0	8.0	338.0	0.0	525.0	3.0	196.0	0.0	12.0
1941	0.0	0.0	200.0	200.0	66.0	0.0	0.0	363.0	0.0	235.0	19.0	200.0	297.0	74.0	0.0	62.0	0.0	0.0
1942	8.0	0.0	194.0	194.0	239.0	0.0	0.0	587.0	0.0	0.0	9.0	113.0	0.0	505.0	0.0	18.0	587.0	5.0
1943	0.0	15.0	3.0	3.0	7.0	0.0	0.0	37.0	0.0	71.0	19.0	0.0	4.0	0.0	0.0	108.0	15.0	3.0
1944	12.0	0.0	0.0	0.0	250.0	264.0	0.0	55.0	0.0	299.0	20.0	88.0	425.0	0.0	0.0	394.0	55.0	0.0
1945	0.0	0.0	32.0	32.0	47.0	0.0	0.0	138.0	0.0	0.0	21.0	79.0	74.0	110.0	0.0	74.0	3.0	0.0
1946	0.0	68.0	69.0	69.0	0.0	4.0	0.0	297.0	0.0	324.0	0.0	69.0	125.0	187.0	0.0	171.0	62.0	12.0
1947	0.0	3.0	8.0	8.0	7.0	11.0	0.0	236.0	0.0	41.0	0.0	8.0	0.0	85.0	0.0	0.0	0.0	8.0
1948	0.0	89.0	5.0	5.0	41.0	129.0	0.0	212.0	0.0	137.0	41.0	5.0	0.0	0.0	0.0	173.0	0.0	0.0
1949	0.0	33.0	0.0	38.0	0.0	1.0	0.0	64.0	0.0	0.0	0.0	87.0	103.0	0.0	0.0	103.0	0.0	0.0
1950	0.0	0.0	224.0	224.0	291.0	28.0	0.0	157.0	0.0	145.0	0.0	224.0	7.0	0.0	12.0	7.0	0.0	0.0
1951	309.0	309.0	187.0	187.0	0.0	0.0	0.0	306.0	0.0	135.0	0.0	335.0	0.0	488.0	106.0	135.0	309.0	0.0
1952	0.0	15.0	0.0	0.0	80.0	0.0	0.0	43.0	0.0	0.0	0.0	297.0	0.0	364.0	13.0	0.0	0.0	63.0
1953	116.0	0.0	198.0	198.0	251.0	0.0	0.0	313.0	198.0	3.0	0.0	231.0	0.0	327.0	75.0	19.0	237.0	56.0
1954	145.0	97.0	0.0	97.0	201.0	127.0	0.0	246.0	97.0	0.0	41.0	102.0	419.0	193.0	180.0	459.0	40.0	0.0
1955	0.0	0.0	319.0	319.0	574.0	0.0	0.0	401.0	0.0	5.0	6.0	435.0	39.0	585.0	12.0	206.0	88.0	16.0
1956	0.0	53.0	0.0	0.0	52.0	18.0	0.0	141.0	0.0	45.0	143.0	155.0	0.0	0.0	221.0	124.0	1.0	35.0
1957	0.0	0.0	0.0	91.0	205.0	0.0	2.0	519.0	0.0	0.0	7.0	118.0	0.0	166.0	8.0	6.0	169.0	0.0
1958	83.0	71.0	0.0	0.0	223.0	109.0	0.0	336.0	44.0	109.0	229.0	226.0	234.0	201.0	188.0	343.0	131.0	11.0
1959	128.0	179.0	192.0	281.0	295.0	255.0	0.0	636.0	51.0	0.0	72.0	192.0	49.0	0.0	36.0	332.0	7.0	0.0
1960	0.0	73.0	0.0	145.0	292.0	6.0	0.0	358.0	0.0	0.0	459.0	19.0	0.0	0.0	42.0	364.0	0.0	0.0
1961	49.0	34.0	187.0	456.0	172.0	0.0	0.0	741.0	161.0	0.0	26.0	400.0	0.0	602.0	34.0	7.0	62.0	26.0
1962	161.0	172.0	0.0	6.0	0.0	0.0	0.0	488.0	0.0	267.0	31.0	69.0	0.0	0.0	34.0	374.0	192.0	7.0
1963	101.0	223.0	86.0	140.0	303.0	0.0	0.0	232.0	0.0	0.0	286.0	0.0	121.0	121.0	258.0	295.0	323.0	68.0
1964	183.0	0.0	0.0	354.0	513.0	0.0	0.0	95.0	0.0	0.0	19.0	850.0	0.0	300.0	0.0	62.0	0.0	45.0
1965	56.0	0.0	0.0	51.0	260.0	0.0	0.0	234.0	0.0	0.0	3.0	419.0	51.0	189.0	7.0	54.0	179.0	87.0
1966	99.0	56.0	0.0	0.0	19.0	0.0	29.0	257.0	0.0	0.0	0.0	0.0	56.0	57.0	56.0	16.0	0.0	101.0
1967	71.0	81.0	219.0	235.0	652.0	171.0	0.0	1038.0	0.0	0.0	0.0	309.0	90.0	375.0	10.0	0.0	76.0	20.0
1968	189.0	69.0	192.0	91.0	264.0	65.0	0.0	576.0	0.0	0.0	329.0	358.0	344.0	154.0	725.0	608.0	1.0	0.0
1969	358.0	153.0	0.0	70.0	404.0	2.0	0.0	298.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	10.0	17.0	376.0

* 对比图表和相关的统计数据,可以看出男女性观看电影的**第一波高潮**都是在1938年的Drama,最一开始使人误以为是戏剧,但这里通过对比具体的电影可以发现应该是指剧情片.将1939年的剧情类电影进行统计,可以进一步看出最受关注的是gone with the wind(飘)和Wizard of Oz, The(绿野仙踪)

tempData = data[(data["year"]=="1939")&(data["genres"]=="Drama")];
dramaCount = tempData.loc[:,["title","movie_id"]].groupby(by=["title"]).count();
dramaCount

	movie_id
title
Gone with the Wind (1939)	1156
Jamaica Inn (1939)	8
Little Princess, The (1939)	77
Mr. Smith Goes to Washington (1939)	383
Only Angels Have Wings (1939)	33
They Made Me a Criminal (1939)	11
Wizard of Oz, The (1939)	1718

* 80年代前期,Sci-Fi一度成为了最受欢迎的电影.但是到了中期,最受欢迎的电影类型是Comedy,对应的电影是Terminator, The(终结者) * 90年代中期,依然还是Drama类型的电影,最受欢迎的此类电影是Bravehear(勇敢的心) * 男性观影的最高峰是在1999年,对应的电影类型又成了Comedy,对应的电影是American Beauty(美国丽人)

temp = pivot_table[("age","M")].transpose();
temp.tail(20)

genres	Action	Adventure	Animation	Children's	Comedy	Crime	Documentary	Drama	Fantasy	Film-Noir	Horror	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
year
1981	6489.0	4396.0	835.0	558.0	2086.0	534.0	43.0	2973.0	1431.0	0.0	1435.0	97.0	172.0	1151.0	3059.0	1495.0	909.0	0.0
1982	3993.0	2635.0	293.0	2529.0	3118.0	285.0	42.0	4758.0	3072.0	1488.0	2292.0	776.0	0.0	456.0	6707.0	1550.0	323.0	0.0
1983	2944.0	2661.0	0.0	158.0	5111.0	0.0	138.0	3870.0	0.0	0.0	1489.0	0.0	0.0	2552.0	2661.0	737.0	2368.0	0.0
1984	5590.0	4834.0	0.0	752.0	8039.0	512.0	182.0	6486.0	2125.0	514.0	3385.0	868.0	443.0	2746.0	6614.0	2747.0	1352.0	0.0
1985	3033.0	3218.0	147.0	1216.0	9588.0	0.0	0.0	5084.0	1623.0	0.0	1317.0	0.0	775.0	3926.0	4736.0	1066.0	755.0	289.0
1986	7279.0	5710.0	571.0	1889.0	9993.0	739.0	0.0	7372.0	518.0	0.0	2681.0	674.0	930.0	2470.0	4456.0	3195.0	3219.0	470.0
1987	9240.0	3650.0	0.0	41.0	9542.0	3459.0	0.0	6717.0	30.0	352.0	1817.0	396.0	484.0	3121.0	4120.0	2568.0	2435.0	0.0
1988	4468.0	3713.0	1884.0	96.0	8866.0	1098.0	357.0	4010.0	2950.0	1381.0	1126.0	105.0	0.0	1210.0	1278.0	2433.0	483.0	484.0
1989	6877.0	5392.0	800.0	1618.0	9875.0	2435.0	642.0	8763.0	791.0	0.0	1608.0	661.0	0.0	2547.0	4105.0	2251.0	1212.0	0.0
1990	9797.0	3362.0	364.0	1186.0	6294.0	3882.0	93.0	7150.0	557.0	661.0	2353.0	0.0	533.0	3316.0	4819.0	8600.0	0.0	2342.0
1991	5557.0	2094.0	824.0	1029.0	4970.0	248.0	148.0	7834.0	983.0	0.0	309.0	1201.0	1120.0	2454.0	4136.0	5227.0	66.0	0.0
1992	8286.0	1346.0	1280.0	1964.0	11283.0	5468.0	33.0	9497.0	352.0	0.0	2389.0	1158.0	713.0	4957.0	3479.0	5824.0	1696.0	838.0
1993	10967.0	4810.0	984.0	2208.0	12658.0	2075.0	260.0	11740.0	348.0	23.0	1495.0	934.0	980.0	5728.0	4782.0	5594.0	2404.0	547.0
1994	9739.0	4366.0	964.0	2746.0	16739.0	3737.0	1048.0	13705.0	1816.0	0.0	1868.0	844.0	475.0	9492.0	2849.0	6460.0	2531.0	1808.0
1995	13057.0	6120.0	2694.0	4539.0	14666.0	6011.0	297.0	18379.0	888.0	272.0	1809.0	666.0	975.0	7489.0	5958.0	10813.0	3463.0	538.0
1996	12812.0	7453.0	1965.0	2637.0	14462.0	4659.0	693.0	15226.0	1787.0	242.0	2609.0	1277.0	1831.0	7146.0	6270.0	12358.0	3478.0	238.0
1997	16087.0	7446.0	851.0	1924.0	15431.0	6912.0	437.0	18115.0	494.0	1787.0	2646.0	742.0	6457.0	6180.0	10448.0	16133.0	2523.0	0.0
1998	16399.0	4133.0	3004.0	3562.0	17832.0	6971.0	415.0	16693.0	343.0	932.0	2790.0	660.0	3965.0	8539.0	7026.0	14574.0	3348.0	20.0
1999	12329.0	4986.0	3354.0	3231.0	26541.0	2364.0	664.0	21320.0	2039.0	0.0	5189.0	324.0	1200.0	5597.0	8233.0	16534.0	1161.0	735.0
2000	9797.0	1848.0	2159.0	1826.0	11129.0	1509.0	334.0	9881.0	110.0	0.0	1846.0	147.0	445.0	1382.0	4608.0	7839.0	1021.0	0.0

tempData = data[(data["year"]=="1995")&(data["genres"]=="Drama") & (data["gender"] == "M")];
dramaCount = tempData.loc[:,["title","movie_id"]].groupby(by=["title"]).count().sort_values(by="movie_id");
dramaCount

	movie_id
title
Diebinnen (1995)	1
To Have, or Not (1995)	1
Sleepover (1995)	1
Boy Called Hate, A (1995)	1
Billy's Holiday (1995)	1
...	...
Apollo 13 (1995)	923
Get Shorty (1995)	1070
Babe (1995)	1172
Twelve Monkeys (1995)	1233
Braveheart (1995)	1897

135 rows × 1 columns

• 与男性不同,80年代中期的终结者并没有吸引太多的女性用户,同期的Drama更为卖座
• 女性在2000年前的一个观影小高峰在1995,还是Drama类型的电影,最受关注的该类型电影是Bravehear(勇敢的心)和Babe(小猪宝贝)
• 女性电影观看的最高峰是在1999年,同样是Commedy类型的电影,最受关注的电影是

temp = pivot_table[("age","F")].transpose();
temp.tail(20)

genres	Action	Adventure	Animation	Children's	Comedy	Crime	Documentary	Drama	Fantasy	Film-Noir	Horror	Musical	Mystery	Romance	Sci-Fi	Thriller	War	Western
year
1981	1376.0	983.0	182.0	232.0	573.0	140.0	19.0	853.0	321.0	0.0	253.0	15.0	85.0	382.0	487.0	348.0	173.0	0.0
1982	621.0	453.0	84.0	819.0	1010.0	82.0	4.0	1653.0	877.0	312.0	446.0	348.0	0.0	238.0	1536.0	353.0	64.0	0.0
1983	789.0	733.0	0.0	55.0	1686.0	0.0	44.0	1486.0	0.0	0.0	327.0	0.0	0.0	822.0	733.0	164.0	697.0	0.0
1984	1254.0	1260.0	0.0	288.0	2468.0	67.0	57.0	1981.0	708.0	114.0	973.0	250.0	55.0	978.0	1296.0	565.0	289.0	0.0
1985	550.0	934.0	53.0	440.0	3187.0	0.0	0.0	2113.0	518.0	0.0	199.0	0.0	323.0	1801.0	1249.0	425.0	107.0	23.0
1986	1508.0	1485.0	195.0	567.0	3351.0	141.0	0.0	2783.0	212.0	0.0	684.0	267.0	275.0	1224.0	871.0	684.0	546.0	99.0
1987	1959.0	1019.0	0.0	22.0	3189.0	732.0	0.0	2007.0	22.0	96.0	294.0	291.0	149.0	1463.0	651.0	634.0	602.0	0.0
1988	864.0	941.0	511.0	48.0	2849.0	171.0	89.0	1785.0	948.0	418.0	223.0	25.0	0.0	611.0	210.0	561.0	47.0	78.0
1989	1548.0	1333.0	450.0	721.0	3416.0	611.0	183.0	3124.0	254.0	0.0	322.0	374.0	0.0	1329.0	987.0	482.0	326.0	0.0
1990	2076.0	878.0	149.0	439.0	2088.0	950.0	48.0	2542.0	154.0	224.0	562.0	0.0	134.0	1656.0	910.0	2156.0	0.0	626.0
1991	1366.0	448.0	437.0	483.0	1926.0	98.0	61.0	3298.0	307.0	0.0	53.0	539.0	441.0	1245.0	846.0	1584.0	25.0	0.0
1992	1693.0	425.0	566.0	847.0	4154.0	1339.0	12.0	3788.0	88.0	0.0	574.0	548.0	201.0	2461.0	712.0	1341.0	633.0	159.0
1993	2336.0	1187.0	322.0	870.0	4804.0	344.0	91.0	4896.0	125.0	9.0	273.0	345.0	404.0	2984.0	1017.0	1671.0	796.0	93.0
1994	2191.0	1138.0	420.0	1179.0	6433.0	1191.0	318.0	6098.0	715.0	0.0	507.0	357.0	222.0	4437.0	525.0	1922.0	979.0	512.0
1995	2685.0	1474.0	1061.0	2087.0	6578.0	1503.0	159.0	8011.0	323.0	107.0	333.0	316.0	282.0	4783.0	1177.0	2680.0	961.0	75.0
1996	2639.0	1908.0	710.0	1222.0	5680.0	1328.0	204.0	6962.0	499.0	48.0	605.0	656.0	550.0	4118.0	1247.0	3274.0	1005.0	18.0
1997	3613.0	1818.0	366.0	883.0	6021.0	2068.0	144.0	7172.0	206.0	576.0	652.0	420.0	1886.0	3095.0	2248.0	4418.0	556.0	0.0
1998	3705.0	1071.0	1122.0	1462.0	7079.0	1752.0	165.0	7037.0	89.0	167.0	623.0	221.0	1158.0	4748.0	1344.0	3297.0	776.0	6.0
1999	3039.0	1368.0	1136.0	1269.0	10328.0	602.0	221.0	8282.0	626.0	0.0	1411.0	129.0	535.0	3064.0	2074.0	4885.0	275.0	167.0
2000	2327.0	462.0	696.0	659.0	4386.0	411.0	88.0	3781.0	25.0	0.0	519.0	53.0	132.0	754.0	997.0	2247.0	288.0	0.0

tempData = data[(data["year"]=="1995")&(data["genres"]=="Drama") & (data["gender"] == "F")];
dramaCount = tempData.loc[:,["title","movie_id"]].groupby(by=["title"]).count().sort_values(by="movie_id");
dramaCount

	movie_id
title
Killer: A Journal of Murder (1995)	1
Confessional, The (Le Confessionnal) (1995)	1
Fall Time (1995)	1
Midaq Alley (Callej髇 de los milagros, El) (1995)	1
Neon Bible, The (1995)	1
...	...
Apollo 13 (1995)	328
American President, The (1995)	379
Sense and Sensibility (1995)	420
Braveheart (1995)	546
Babe (1995)	579

119 rows × 1 columns

综上:可以看出在电影历史上,男女生对电影到的品味有着较高的相似度——Comedy和Drama长期占据着票房的头把交椅,但是对于科幻电影,男生显然更为喜欢一点.