Pandas 学习笔记二

Pandas 学习笔记二 数据的读取与存储 csv格式

import pandas as pd
# 读取csv文件
data = pd.read_csv("stock_day.csv",usecols=['open','high','low','close'])
data.head()

	open	high	close	low
2018-02-27	23.53	25.88	24.16	23.53
2018-02-26	22.80	23.78	23.53	22.80
2018-02-23	22.88	23.37	22.82	22.71
2018-02-22	22.25	22.76	22.28	22.02
2018-02-14	21.49	21.99	21.92	21.48

data = pd.read_csv("stock_day2.csv", names=["open", "high", "close", "low", "volume", "price_change", "p_change", "ma5", "ma10", "ma20", "v_ma5", "v_ma10", "v_ma20", "turnover"])
data.head()

	open	high	close	low	volume	price_change	p_change	ma5	ma10	ma20	v_ma5	v_ma10	v_ma20	turnover
2018-02-27	23.53	25.88	24.16	23.53	95578.03	0.63	2.68	22.942	22.142	22.875	53782.64	46738.65	55576.11	2.39
2018-02-26	22.80	23.78	23.53	22.80	60985.11	0.69	3.02	22.406	21.955	22.942	40827.52	42736.34	56007.50	1.53
2018-02-23	22.88	23.37	22.82	22.71	52914.01	0.54	2.42	21.938	21.929	23.022	35119.58	41871.97	56372.85	1.32
2018-02-22	22.25	22.76	22.28	22.02	36105.01	0.36	1.64	21.446	21.909	23.137	35397.58	39904.78	60149.60	0.90
2018-02-14	21.49	21.99	21.92	21.48	23331.04	0.44	2.05	21.366	21.923	23.253	33590.21	42935.74	61716.11	0.58

# 写入csv文件
# data.to_csv("1.csv")
# 保存'open'列的数据
data[:10].to_csv("test.csv", columns=["open"])
pd.read_csv("test.csv")

	Unnamed: 0	open
0	2018-02-27	23.53
1	2018-02-26	22.80
2	2018-02-23	22.88
3	2018-02-22	22.25
4	2018-02-14	21.49
5	2018-02-13	21.40
6	2018-02-12	20.70
7	2018-02-09	21.20
8	2018-02-08	21.79
9	2018-02-07	22.69

data[:10].to_csv("test.csv", columns=["open"], index=False, mode="a", header=False)
pd.read_csv("test.csv")

	Unnamed: 0	open
0	2018-02-27	23.53
1	2018-02-26	22.80
2	2018-02-23	22.88
3	2018-02-22	22.25
4	2018-02-14	21.49
5	2018-02-13	21.40
6	2018-02-12	20.70
7	2018-02-09	21.20
8	2018-02-08	21.79
9	2018-02-07	22.69
10	23.53	NaN
11	22.8	NaN
12	22.88	NaN
13	22.25	NaN
14	21.49	NaN
15	21.4	NaN
16	20.7	NaN
17	21.2	NaN
18	21.79	NaN
19	22.69	NaN

hdf5格式

# 读取hdf5文件
dayClose = pd.read_hdf("day_close.h5")
dayClose.head()

	000001.SZ	000002.SZ	000004.SZ	000005.SZ	000006.SZ	000007.SZ	000008.SZ	000009.SZ	000010.SZ	000011.SZ	...	001965.SZ	603283.SH	002920.SZ	002921.SZ	300684.SZ	002922.SZ	300735.SZ	603329.SH	603655.SH	603080.SH
0	16.30	17.71	4.58	2.88	14.60	2.62	4.96	4.66	5.37	6.02	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	17.02	19.20	4.65	3.02	15.97	2.65	4.95	4.70	5.37	6.27	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	17.02	17.28	4.56	3.06	14.37	2.63	4.82	4.47	5.37	5.96	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	16.18	16.97	4.49	2.95	13.10	2.73	4.89	4.33	5.37	5.77	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	16.95	17.19	4.55	2.99	13.18	2.77	4.97	4.42	5.37	5.92	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

5 rows × 3562 columns

# 写入hdf5文件
dayClose.to_hdf("test.h5",key="close")
pd.read_hdf("test.h5",key="close").head()

	000001.SZ	000002.SZ	000004.SZ	000005.SZ	000006.SZ	000007.SZ	000008.SZ	000009.SZ	000010.SZ	000011.SZ	...	001965.SZ	603283.SH	002920.SZ	002921.SZ	300684.SZ	002922.SZ	300735.SZ	603329.SH	603655.SH	603080.SH
0	16.30	17.71	4.58	2.88	14.60	2.62	4.96	4.66	5.37	6.02	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	17.02	19.20	4.65	3.02	15.97	2.65	4.95	4.70	5.37	6.27	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	17.02	17.28	4.56	3.06	14.37	2.63	4.82	4.47	5.37	5.96	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	16.18	16.97	4.49	2.95	13.10	2.73	4.89	4.33	5.37	5.77	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	16.95	17.19	4.55	2.99	13.18	2.77	4.97	4.42	5.37	5.92	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

5 rows × 3562 columns

dayOpen = pd.read_hdf("day_open.h5")
dayOpen.to_hdf("test.h5",key="open")
pd.read_hdf("test.h5",key="open").head()

	000001.SZ	000002.SZ	000004.SZ	000005.SZ	000006.SZ	000007.SZ	000008.SZ	000009.SZ	000010.SZ	000011.SZ	...	001965.SZ	603283.SH	002920.SZ	002921.SZ	300684.SZ	002922.SZ	300735.SZ	603329.SH	603655.SH	603080.SH
0	15.50	16.15	4.26	2.73	13.99	2.52	4.76	4.45	5.37	5.79	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	16.50	17.94	4.53	2.91	14.78	2.61	4.99	4.69	5.37	6.03	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	17.00	18.80	4.63	3.04	16.08	2.65	4.96	4.73	5.37	6.26	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	16.95	16.59	4.52	3.02	13.20	2.63	4.81	4.35	5.37	5.74	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	16.20	16.96	4.50	2.95	13.17	2.80	4.88	4.34	5.37	5.80	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

5 rows × 3562 columns

JSON格式

# 读取JSON格式文件
sa = pd.read_json("Sarcasm_Headlines_Dataset.json", orient="records", lines=True)
sa.head()

	article_link	headline	is_sarcastic
0	https://www.huffingtonpost.com/entry/versace-b...	former versace store clerk sues over secret 'b...	0
1	https://www.huffingtonpost.com/entry/roseanne-...	the 'roseanne' revival catches up to our thorn...	0
2	https://local.theonion.com/mom-starting-to-fea...	mom starting to fear son's web series closest ...	1
3	https://politics.theonion.com/boehner-just-wan...	boehner just wants wife to listen, not come up...	1
4	https://www.huffingtonpost.com/entry/jk-rowlin...	j.k. rowling wishes snape happy birthday in th...	0

# 写入JSON格式文件
sa.to_json("test.json", orient="records", lines=True)
pd.read_json("test.json", orient="records", lines=True)

	article_link	headline	is_sarcastic
0	https://www.huffingtonpost.com/entry/versace-b...	former versace store clerk sues over secret 'b...	0
1	https://www.huffingtonpost.com/entry/roseanne-...	the 'roseanne' revival catches up to our thorn...	0
2	https://local.theonion.com/mom-starting-to-fea...	mom starting to fear son's web series closest ...	1
3	https://politics.theonion.com/boehner-just-wan...	boehner just wants wife to listen, not come up...	1
4	https://www.huffingtonpost.com/entry/jk-rowlin...	j.k. rowling wishes snape happy birthday in th...	0
...	...	...	...
26704	https://www.huffingtonpost.com/entry/american-...	american politics in moral free-fall	0
26705	https://www.huffingtonpost.com/entry/americas-...	america's best 20 hikes	0
26706	https://www.huffingtonpost.com/entry/reparatio...	reparations and obama	0
26707	https://www.huffingtonpost.com/entry/israeli-b...	israeli ban targeting boycott supporters raise...	0
26708	https://www.huffingtonpost.com/entry/gourmet-g...	gourmet gifts for the foodie 2014	0

26709 rows × 3 columns

Pandas高级处理 缺失值处理

movie = pd.read_csv("IMDB-Movie-Data.csv")
movie.head()

	Rank	Title	Genre	Description	Director	Actors	Year	Runtime (Minutes)	Rating	Votes	Revenue (Millions)	metascore
0	1	Guardians of the Galaxy	Action,Adventure,Sci-Fi	A group of intergalactic criminals are forced ...	James Gunn	Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...	2014	121	8.1	757074	333.13	76.0
1	2	Prometheus	Adventure,Mystery,Sci-Fi	Following clues to the origin of mankind, a te...	Ridley Scott	Noomi Rapace, Logan Marshall-Green, Michael Fa...	2012	124	7.0	485820	126.46	65.0
2	3	Split	Horror,Thriller	Three girls are kidnapped by a man with a diag...	M. Night Shyamalan	James McAvoy, Anya Taylor-Joy, Haley Lu Richar...	2016	117	7.3	157606	138.12	62.0
3	4	Sing	Animation,Comedy,Family	In a city of humanoid animals, a hustling thea...	Christophe Lourdelet	Matthew McConaughey,Reese Witherspoon, Seth Ma...	2016	108	7.2	60545	270.32	59.0
4	5	Suicide Squad	Action,Adventure,Fantasy	A secret government agency recruits some of th...	David Ayer	Will Smith, Jared Leto, Margot Robbie, Viola D...	2016	123	6.2	393727	325.02	40.0

import numpy as np
# 判断是否存在缺失值
# 如果缺失值不是nan而是其他符号则先替换为nan再进行判断处理
# data_new = data.replace(to_replace="?", value=np.nan)
np.any(pd.isnull(movie)) # 返回True说明有缺失值

True

np.all(pd.notnull(movie)) # 返回False说明有缺失值

False

pd.notnull(movie).all() # 找到有缺失值的字段

Rank                   True
Title                  True
Genre                  True
Description            True
Director               True
Actors                 True
Year                   True
Runtime (Minutes)      True
Rating                 True
Votes                  True
Revenue (Millions)    False
metascore             False
dtype: bool

# 删除有缺失值的样本
data1 = movie.dropna()
pd.notnull(data1).all()

Rank                  True
Title                 True
Genre                 True
Description           True
Director              True
Actors                True
Year                  True
Runtime (Minutes)     True
Rating                True
Votes                 True
Revenue (Millions)    True
metascore             True
dtype: bool

# 替换有缺失值的样本
movie["Revenue (Millions)"].fillna(movie["Revenue (Millions)"].mean(), inplace=True)
movie["metascore"].fillna(movie["metascore"].mean(), inplace=True)
pd.notnull(movie).all() # 缺失值已经处理完毕

Rank                  True
Title                 True
Genre                 True
Description           True
Director              True
Actors                True
Year                  True
Runtime (Minutes)     True
Rating                True
Votes                 True
Revenue (Millions)    True
metascore             True
dtype: bool

数据离散化

data = pd.read_csv("stock_day.csv")
p_change = data["p_change"]
# 自动分组
sr = pd.qcut(p_change,10)
sr.value_counts()

(-10.030999999999999, -4.836]    65
(-0.462, 0.26]                   65
(0.26, 0.94]                     65
(5.27, 10.03]                    65
(-4.836, -2.444]                 64
(-2.444, -1.352]                 64
(-1.352, -0.462]                 64
(1.738, 2.938]                   64
(2.938, 5.27]                    64
(0.94, 1.738]                    63
Name: p_change, dtype: int64

pd.get_dummies(sr, prefix="涨跌幅").head()

	涨跌幅_(-10.030999999999999, -4.836]	涨跌幅_(-4.836, -2.444]	涨跌幅_(-2.444, -1.352]	涨跌幅_(-1.352, -0.462]	涨跌幅_(-0.462, 0.26]	涨跌幅_(0.26, 0.94]	涨跌幅_(0.94, 1.738]	涨跌幅_(1.738, 2.938]	涨跌幅_(2.938, 5.27]	涨跌幅_(5.27, 10.03]
2018-02-27	0	0	0	0	0	0	0	1	0	0
2018-02-26	0	0	0	0	0	0	0	0	1	0
2018-02-23	0	0	0	0	0	0	0	1	0	0
2018-02-22	0	0	0	0	0	0	1	0	0	0
2018-02-14	0	0	0	0	0	0	0	1	0	0

# 自定义分组
bins = [-100, -7, -5, -3, 0, 3, 5, 7, 100]
sr = pd.cut(p_change, bins)
sr.value_counts()

(0, 3]        215
(-3, 0]       188
(3, 5]         57
(-5, -3]       51
(5, 7]         35
(7, 100]       35
(-100, -7]     34
(-7, -5]       28
Name: p_change, dtype: int64

data2 = pd.get_dummies(sr, prefix="rise")
data2.head()

	rise_(-100, -7]	rise_(-7, -5]	rise_(-5, -3]	rise_(-3, 0]	rise_(0, 3]	rise_(3, 5]	rise_(5, 7]	rise_(7, 100]
2018-02-27	0	0	0	0	1	0	0	0
2018-02-26	0	0	0	0	0	1	0	0
2018-02-23	0	0	0	0	1	0	0	0
2018-02-22	0	0	0	0	1	0	0	0
2018-02-14	0	0	0	0	1	0	0	0

合并

# 按方向拼接 pd.concat(data1,data2,axis = 0)
pd.concat([data, data2], axis=1).head()

	open	high	close	low	volume	price_change	p_change	ma5	ma10	ma20	...	v_ma20	turnover	rise_(-100, -7]	rise_(-7, -5]	rise_(-5, -3]	rise_(-3, 0]	rise_(0, 3]	rise_(3, 5]	rise_(5, 7]	rise_(7, 100]
2018-02-27	23.53	25.88	24.16	23.53	95578.03	0.63	2.68	22.942	22.142	22.875	...	55576.11	2.39	0	0	0	0	1	0	0	0
2018-02-26	22.80	23.78	23.53	22.80	60985.11	0.69	3.02	22.406	21.955	22.942	...	56007.50	1.53	0	0	0	0	0	1	0	0
2018-02-23	22.88	23.37	22.82	22.71	52914.01	0.54	2.42	21.938	21.929	23.022	...	56372.85	1.32	0	0	0	0	1	0	0	0
2018-02-22	22.25	22.76	22.28	22.02	36105.01	0.36	1.64	21.446	21.909	23.137	...	60149.60	0.90	0	0	0	0	1	0	0	0
2018-02-14	21.49	21.99	21.92	21.48	23331.04	0.44	2.05	21.366	21.923	23.253	...	61716.11	0.58	0	0	0	0	1	0	0	0

5 rows × 22 columns

pd.concat([data, data2], axis=0).head()

	open	high	close	low	volume	price_change	p_change	ma5	ma10	ma20	...	v_ma20	turnover	rise_(-100, -7]	rise_(-7, -5]	rise_(-5, -3]	rise_(-3, 0]	rise_(0, 3]	rise_(3, 5]	rise_(5, 7]	rise_(7, 100]
2018-02-27	23.53	25.88	24.16	23.53	95578.03	0.63	2.68	22.942	22.142	22.875	...	55576.11	2.39	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2018-02-26	22.80	23.78	23.53	22.80	60985.11	0.69	3.02	22.406	21.955	22.942	...	56007.50	1.53	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2018-02-23	22.88	23.37	22.82	22.71	52914.01	0.54	2.42	21.938	21.929	23.022	...	56372.85	1.32	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2018-02-22	22.25	22.76	22.28	22.02	36105.01	0.36	1.64	21.446	21.909	23.137	...	60149.60	0.90	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2018-02-14	21.49	21.99	21.92	21.48	23331.04	0.44	2.05	21.366	21.923	23.253	...	61716.11	0.58	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

5 rows × 22 columns

pd.concat([data, data2], axis=0).tail()

	open	high	close	low	volume	price_change	p_change	ma5	ma10	ma20	...	v_ma20	turnover	rise_(-100, -7]	rise_(-7, -5]	rise_(-5, -3]	rise_(-3, 0]	rise_(0, 3]	rise_(3, 5]	rise_(5, 7]	rise_(7, 100]
2015-03-06	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0
2015-03-05	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0
2015-03-04	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0
2015-03-03	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0
2015-03-02	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0

5 rows × 22 columns

left = pd.Dataframe({'key1': ['K0', 'K0', 'K1', 'K2'],
                        'key2': ['K0', 'K1', 'K0', 'K1'],
                        'A': ['A0', 'A1', 'A2', 'A3'],
                        'B': ['B0', 'B1', 'B2', 'B3']})

right = pd.Dataframe({'key1': ['K0', 'K1', 'K1', 'K2'],
                        'key2': ['K0', 'K0', 'K0', 'K0'],
                        'C': ['C0', 'C1', 'C2', 'C3'],
                        'D': ['D0', 'D1', 'D2', 'D3']})

left

	key1	key2	A	B
0	K0	K0	A0	B0
1	K0	K1	A1	B1
2	K1	K0	A2	B2
3	K2	K1	A3	B3

right

	key1	key2	C	D
0	K0	K0	C0	D0
1	K1	K0	C1	D1
2	K1	K0	C2	D2
3	K2	K0	C3	D3

pd.merge(left, right, how="inner", on=["key1", "key2"])

	key1	key2	A	B	C	D
0	K0	K0	A0	B0	C0	D0
1	K1	K0	A2	B2	C1	D1
2	K1	K0	A2	B2	C2	D2

pd.merge(left, right, how="left", on=["key1", "key2"])

	key1	key2	A	B	C	D
0	K0	K0	A0	B0	C0	D0
1	K0	K1	A1	B1	NaN	NaN
2	K1	K0	A2	B2	C1	D1
3	K1	K0	A2	B2	C2	D2
4	K2	K1	A3	B3	NaN	NaN

pd.merge(left, right, how="right", on=["key1", "key2"])

	key1	key2	A	B	C	D
0	K0	K0	A0	B0	C0	D0
1	K1	K0	A2	B2	C1	D1
2	K1	K0	A2	B2	C2	D2
3	K2	K0	NaN	NaN	C3	D3

pd.merge(left, right, how="outer", on=["key1", "key2"])

	key1	key2	A	B	C	D
0	K0	K0	A0	B0	C0	D0
1	K0	K1	A1	B1	NaN	NaN
2	K1	K0	A2	B2	C1	D1
3	K1	K0	A2	B2	C2	D2
4	K2	K1	A3	B3	NaN	NaN
5	K2	K0	NaN	NaN	C3	D3

# pd.crosstab(星期数据列, 涨跌幅数据列)
# 准备星期数据列
data.index

Index(['2018-02-27', '2018-02-26', '2018-02-23', '2018-02-22', '2018-02-14',
       '2018-02-13', '2018-02-12', '2018-02-09', '2018-02-08', '2018-02-07',
       ...
       '2015-03-13', '2015-03-12', '2015-03-11', '2015-03-10', '2015-03-09',
       '2015-03-06', '2015-03-05', '2015-03-04', '2015-03-03', '2015-03-02'],
      dtype='object', length=643)

# pandas日期类型
date = pd.to_datetime(data.index)

date

DatetimeIndex(['2018-02-27', '2018-02-26', '2018-02-23', '2018-02-22',
               '2018-02-14', '2018-02-13', '2018-02-12', '2018-02-09',
               '2018-02-08', '2018-02-07',
               ...
               '2015-03-13', '2015-03-12', '2015-03-11', '2015-03-10',
               '2015-03-09', '2015-03-06', '2015-03-05', '2015-03-04',
               '2015-03-03', '2015-03-02'],
              dtype='datetime64[ns]', length=643, freq=None)

data["week"] = date.weekday
date.weekday

Int64Index([1, 0, 4, 3, 2, 1, 0, 4, 3, 2,
            ...
            4, 3, 2, 1, 0, 4, 3, 2, 1, 0],
           dtype='int64', length=643)

data.head()

	open	high	close	low	volume	price_change	p_change	ma5	ma10	ma20	v_ma5	v_ma10	v_ma20	turnover	week
2018-02-27	23.53	25.88	24.16	23.53	95578.03	0.63	2.68	22.942	22.142	22.875	53782.64	46738.65	55576.11	2.39	1
2018-02-26	22.80	23.78	23.53	22.80	60985.11	0.69	3.02	22.406	21.955	22.942	40827.52	42736.34	56007.50	1.53	0
2018-02-23	22.88	23.37	22.82	22.71	52914.01	0.54	2.42	21.938	21.929	23.022	35119.58	41871.97	56372.85	1.32	4
2018-02-22	22.25	22.76	22.28	22.02	36105.01	0.36	1.64	21.446	21.909	23.137	35397.58	39904.78	60149.60	0.90	3
2018-02-14	21.49	21.99	21.92	21.48	23331.04	0.44	2.05	21.366	21.923	23.253	33590.21	42935.74	61716.11	0.58	2

# 准备涨跌幅数据列
data["pona"] = np.where(data["p_change"] > 0, 1, 0)
data.head()

	open	high	close	low	volume	price_change	p_change	ma5	ma10	ma20	v_ma5	v_ma10	v_ma20	turnover	week	pona
2018-02-27	23.53	25.88	24.16	23.53	95578.03	0.63	2.68	22.942	22.142	22.875	53782.64	46738.65	55576.11	2.39	1	1
2018-02-26	22.80	23.78	23.53	22.80	60985.11	0.69	3.02	22.406	21.955	22.942	40827.52	42736.34	56007.50	1.53	0	1
2018-02-23	22.88	23.37	22.82	22.71	52914.01	0.54	2.42	21.938	21.929	23.022	35119.58	41871.97	56372.85	1.32	4	1
2018-02-22	22.25	22.76	22.28	22.02	36105.01	0.36	1.64	21.446	21.909	23.137	35397.58	39904.78	60149.60	0.90	3	1
2018-02-14	21.49	21.99	21.92	21.48	23331.04	0.44	2.05	21.366	21.923	23.253	33590.21	42935.74	61716.11	0.58	2	1

交叉表和透视表

# 交叉表
dataTable = pd.crosstab(data["week"], data["pona"])
dataTable

pona	0	1
week
0	63	62
1	55	76
2	61	71
3	63	65
4	59	68

dataTable.sum(axis=1)

week
0    125
1    131
2    132
3    128
4    127
dtype: int64

dataTable.div(dataTable.sum(axis=1), axis=0).plot(kind="bar", stacked=True)

​

​

dataTable.div(dataTable.sum(axis=1), axis=0)

pona	0	1
week
0	0.504000	0.496000
1	0.419847	0.580153
2	0.462121	0.537879
3	0.492188	0.507812
4	0.464567	0.535433

# 透视表
data.pivot_table(["pona"], index=["week"])

	pona
week
0	0.496000
1	0.580153
2	0.537879
3	0.507812
4	0.535433

分组与聚合

col = pd.Dataframe({'color': ['white','red','green','red','green'], 'object': ['pen','pencil','pencil','ashtray','pen'],'price1':[5.56,4.20,1.30,0.56,2.75],'price2':[4.75,4.12,1.60,0.75,3.15]})
col

	color	object	price1	price2
0	white	pen	5.56	4.75
1	red	pencil	4.20	4.12
2	green	pencil	1.30	1.60
3	red	ashtray	0.56	0.75
4	green	pen	2.75	3.15

# 进行分组，对颜色分组，price1进行聚合
# 用dataframe的方法进行分组
col.groupby(by="color")["price1"].max()

color
green    2.75
red      4.20
white    5.56
Name: price1, dtype: float64

col["price1"].groupby(col["color"]).max()

color
green    2.75
red      4.20
white    5.56
Name: price1, dtype: float64

实战案例 电影数据分析练习

数据文件：IMDB-Movie-Data.csv
问题1：我们想知道这些电影数据中评分的平均分，导演的人数等信息，我们应该怎么获取？
问题2：对于这一组电影数据，如果我们想rating，runtime的分布情况，应该如何呈现数据？
问题3：对于这一组电影数据，如果我们希望统计电影分类(genre)的情况，应该如何处理数据？

# 1、准备数据
movie = pd.read_csv("IMDB-Movie-Data.csv")
movie

	Rank	Title	Genre	Description	Director	Actors	Year	Runtime (Minutes)	Rating	Votes	Revenue (Millions)	metascore
0	1	Guardians of the Galaxy	Action,Adventure,Sci-Fi	A group of intergalactic criminals are forced ...	James Gunn	Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...	2014	121	8.1	757074	333.13	76.0
1	2	Prometheus	Adventure,Mystery,Sci-Fi	Following clues to the origin of mankind, a te...	Ridley Scott	Noomi Rapace, Logan Marshall-Green, Michael Fa...	2012	124	7.0	485820	126.46	65.0
2	3	Split	Horror,Thriller	Three girls are kidnapped by a man with a diag...	M. Night Shyamalan	James McAvoy, Anya Taylor-Joy, Haley Lu Richar...	2016	117	7.3	157606	138.12	62.0
3	4	Sing	Animation,Comedy,Family	In a city of humanoid animals, a hustling thea...	Christophe Lourdelet	Matthew McConaughey,Reese Witherspoon, Seth Ma...	2016	108	7.2	60545	270.32	59.0
4	5	Suicide Squad	Action,Adventure,Fantasy	A secret government agency recruits some of th...	David Ayer	Will Smith, Jared Leto, Margot Robbie, Viola D...	2016	123	6.2	393727	325.02	40.0
...	...	...	...	...	...	...	...	...	...	...	...	...
995	996	Secret in Their Eyes	Crime,Drama,Mystery	A tight-knit team of rising investigators, alo...	Billy Ray	Chiwetel Ejiofor, Nicole Kidman, Julia Roberts...	2015	111	6.2	27585	NaN	45.0
996	997	Hostel: Part II	Horror	Three American college students studying abroa...	Eli Roth	Lauren German, Heather Matarazzo, Bijou Philli...	2007	94	5.5	73152	17.54	46.0
997	998	Step Up 2: The Streets	Drama,Music,Romance	Romantic sparks occur between two dance studen...	Jon M. Chu	Robert Hoffman, Briana Evigan, Cassie Ventura,...	2008	98	6.2	70699	58.01	50.0
998	999	Search Party	Adventure,Comedy	A pair of friends embark on a mission to reuni...	Scot Armstrong	Adam Pally, T.J. Miller, Thomas Middleditch,Sh...	2014	93	5.6	4881	NaN	22.0
999	1000	Nine Lives	Comedy,Family,Fantasy	A stuffy businessman finds himself trapped ins...	Barry Sonnenfeld	Kevin Spacey, Jennifer Garner, Robbie Amell,Ch...	2016	87	5.3	12435	19.64	11.0

1000 rows × 12 columns

# 问题1：我们想知道这些电影数据中评分的平均分，导演的人数等信息，我们应该怎么获取？
# 评分的平均分
movie["Rating"].mean()

6.723199999999999

# 导演的人数
np.unique(movie["Director"]).size

644

# 问题2：对于这一组电影数据，如果我们想rating，runtime的分布情况，应该如何呈现数据？
movie["Rating"].plot(kind="hist", figsize=(20, 8))

​

​

import matplotlib.pyplot as plt
# 1、创建画布
plt.figure(figsize=(20, 8), dpi=80)

# 2、绘制直方图
plt.hist(movie["Rating"], 20)

# 修改刻度
plt.xticks(np.linspace(movie["Rating"].min(), movie["Rating"].max(), 21))

# 添加网格
plt.grid(linestyle="--", alpha=0.5)

# 3、显示图像
plt.show()

​

​

# 问题3：对于这一组电影数据，如果我们希望统计电影分类(genre)的情况，应该如何处理数据？# 1、创建画布
# 先统计电影类别都有哪些
movie_genre = [i.split(",") for i in movie["Genre"]]
movie_genre

[['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Mystery', 'Sci-Fi'],
 ['Horror', 'Thriller'],
 ['Animation', 'Comedy', 'Family'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Comedy', 'Drama', 'Music'],
 ['Comedy'],
 ['Action', 'Adventure', 'Biography'],
 ['Adventure', 'Drama', 'Romance'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Comedy', 'Drama'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Thriller'],
 ['Biography', 'Drama'],
 ['Drama', 'Mystery', 'Sci-Fi'],
 ['Adventure', 'Drama', 'Thriller'],
 ['Drama'],
 ['Crime', 'Drama', 'Horror'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy'],
 ['Action', 'Adventure', 'Drama'],
 ['Horror', 'Thriller'],
 ['Comedy'],
 ['Action', 'Adventure', 'Drama'],
 ['Comedy'],
 ['Drama', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Comedy'],
 ['Action', 'Horror', 'Sci-Fi'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Drama', 'Sci-Fi'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Adventure', 'Western'],
 ['Comedy', 'Drama'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Drama'],
 ['Horror'],
 ['Biography', 'Drama', 'History'],
 ['Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama', 'Thriller'],
 ['Adventure', 'Drama', 'Fantasy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Comedy', 'Drama'],
 ['Action', 'Crime', 'Thriller'],
 ['Action', 'Crime', 'Drama'],
 ['Adventure', 'Drama', 'History'],
 ['Crime', 'Horror', 'Thriller'],
 ['Drama', 'Romance'],
 ['Comedy', 'Drama', 'Romance'],
 ['Biography', 'Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Crime', 'Drama', 'Mystery'],
 ['Drama', 'Romance', 'Thriller'],
 ['Drama', 'Mystery', 'Sci-Fi'],
 ['Action', 'Adventure', 'Comedy'],
 ['Drama', 'History', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama'],
 ['Action', 'Drama', 'Thriller'],
 ['Drama', 'History'],
 ['Action', 'Drama', 'Romance'],
 ['Drama', 'Fantasy'],
 ['Drama', 'Romance'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Sci-Fi'],
 ['Adventure', 'Drama', 'War'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Comedy', 'Fantasy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy', 'Drama'],
 ['Biography', 'Comedy', 'Crime'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action', 'Crime', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Crime', 'Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action', 'Crime', 'Drama'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama'],
 ['Comedy', 'Crime', 'Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Comedy', 'Crime'],
 ['Animation', 'Drama', 'Fantasy'],
 ['Horror', 'Mystery', 'Sci-Fi'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Biography', 'Crime', 'Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Adventure', 'Drama', 'Sci-Fi'],
 ['Crime', 'Mystery', 'Thriller'],
 ['Action', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Thriller'],
 ['Comedy'],
 ['Action', 'Adventure', 'Drama'],
 ['Drama'],
 ['Drama', 'Mystery', 'Sci-Fi'],
 ['Action', 'Horror', 'Thriller'],
 ['Biography', 'Drama', 'History'],
 ['Romance', 'Sci-Fi'],
 ['Action', 'Fantasy', 'War'],
 ['Adventure', 'Drama', 'Fantasy'],
 ['Comedy'],
 ['Horror', 'Thriller'],
 ['Action', 'Biography', 'Drama'],
 ['Drama', 'Horror', 'Mystery'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Adventure', 'Drama', 'Family'],
 ['Adventure', 'Mystery', 'Sci-Fi'],
 ['Adventure', 'Comedy', 'Romance'],
 ['Action'],
 ['Action', 'Thriller'],
 ['Adventure', 'Drama', 'Family'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Crime', 'Mystery'],
 ['Comedy', 'Family', 'Musical'],
 ['Adventure', 'Drama', 'Thriller'],
 ['Drama'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Drama', 'Horror', 'Thriller'],
 ['Drama', 'Music'],
 ['Action', 'Crime', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Drama', 'Romance'],
 ['Mystery', 'Thriller'],
 ['Mystery', 'Thriller', 'Western'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy', 'Family'],
 ['Biography', 'Comedy', 'Drama'],
 ['Drama'],
 ['Drama', 'Western'],
 ['Drama', 'Mystery', 'Romance'],
 ['Comedy', 'Drama'],
 ['Action', 'Drama', 'Mystery'],
 ['Comedy'],
 ['Action', 'Adventure', 'Crime'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Adventure', 'Sci-Fi', 'Thriller'],
 ['Drama'],
 ['Action', 'Crime', 'Drama'],
 ['Drama', 'Horror', 'Mystery'],
 ['Action', 'Horror', 'Sci-Fi'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Comedy', 'Fantasy'],
 ['Action', 'Comedy', 'Mystery'],
 ['Thriller', 'War'],
 ['Action', 'Comedy', 'Crime'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Crime'],
 ['Action', 'Adventure', 'Thriller'],
 ['Drama', 'Fantasy', 'Romance'],
 ['Action', 'Adventure', 'Comedy'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Drama', 'History'],
 ['Action', 'Adventure', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Animation', 'Adventure', 'Family'],
 ['Adventure', 'Horror'],
 ['Drama', 'Romance', 'Sci-Fi'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Family'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Comedy'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Action', 'Adventure', 'Comedy'],
 ['Comedy', 'Romance'],
 ['Horror', 'Mystery'],
 ['Drama', 'Family', 'Fantasy'],
 ['Sci-Fi'],
 ['Drama', 'Thriller'],
 ['Drama', 'Romance'],
 ['Drama', 'War'],
 ['Drama', 'Fantasy', 'Horror'],
 ['Crime', 'Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Romance'],
 ['Drama'],
 ['Crime', 'Drama', 'History'],
 ['Horror', 'Sci-Fi', 'Thriller'],
 ['Action', 'Drama', 'Sport'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Crime', 'Drama', 'Thriller'],
 ['Adventure', 'Biography', 'Drama'],
 ['Biography', 'Drama', 'Thriller'],
 ['Action', 'Comedy', 'Crime'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama', 'Fantasy', 'Horror'],
 ['Biography', 'Drama', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Mystery'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama', 'Horror'],
 ['Comedy', 'Drama', 'Romance'],
 ['Comedy', 'Romance'],
 ['Drama', 'Horror', 'Thriller'],
 ['Action', 'Adventure', 'Drama'],
 ['Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Drama', 'Mystery'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Comedy'],
 ['Drama', 'Horror'],
 ['Action', 'Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Horror', 'Mystery'],
 ['Crime', 'Drama', 'Mystery'],
 ['Comedy', 'Crime'],
 ['Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Family'],
 ['Horror', 'Sci-Fi', 'Thriller'],
 ['Drama', 'Fantasy', 'War'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Adventure', 'Thriller'],
 ['Action', 'Adventure', 'Drama'],
 ['Drama', 'Romance'],
 ['Biography', 'Drama', 'History'],
 ['Drama', 'Horror', 'Thriller'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Action', 'Adventure', 'Romance'],
 ['Action', 'Drama', 'War'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Drama', 'Musical', 'Romance'],
 ['Drama', 'Sci-Fi', 'Thriller'],
 ['Comedy', 'Drama'],
 ['Action', 'Comedy', 'Crime'],
 ['Biography', 'Comedy', 'Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Thriller'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Drama', 'Sci-Fi'],
 ['Horror'],
 ['Drama', 'Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Thriller'],
 ['Comedy', 'Drama'],
 ['Drama'],
 ['Action', 'Adventure', 'Comedy'],
 ['Drama', 'Horror', 'Thriller'],
 ['Comedy'],
 ['Drama', 'Sci-Fi'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Horror'],
 ['Action', 'Adventure', 'Thriller'],
 ['Adventure', 'Fantasy'],
 ['Action', 'Comedy', 'Crime'],
 ['Comedy', 'Drama', 'Music'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Mystery'],
 ['Action', 'Comedy', 'Crime'],
 ['Crime', 'Drama', 'History'],
 ['Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Crime', 'Mystery', 'Thriller'],
 ['Action', 'Adventure', 'Crime'],
 ['Thriller'],
 ['Biography', 'Drama', 'Romance'],
 ['Action', 'Adventure'],
 ['Action', 'Fantasy'],
 ['Action', 'Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Comedy', 'Crime'],
 ['Thriller'],
 ['Action', 'Drama', 'Horror'],
 ['Comedy', 'Music', 'Romance'],
 ['Comedy'],
 ['Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama', 'Romance'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Comedy', 'Drama'],
 ['Biography', 'Crime', 'Drama'],
 ['Drama', 'History'],
 ['Action', 'Crime', 'Thriller'],
 ['Action', 'Biography', 'Drama'],
 ['Horror'],
 ['Comedy', 'Romance'],
 ['Comedy', 'Romance'],
 ['Comedy', 'Crime', 'Drama'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Crime', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Biography', 'Drama', 'Sport'],
 ['Drama', 'Romance'],
 ['Drama', 'Horror'],
 ['Adventure', 'Fantasy'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Action', 'Drama', 'Sci-Fi'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Horror'],
 ['Comedy', 'Horror', 'Thriller'],
 ['Action', 'Crime', 'Thriller'],
 ['Crime', 'Drama', 'Music'],
 ['Drama'],
 ['Action', 'Crime', 'Thriller'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Biography', 'Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama', 'Horror', 'Sci-Fi'],
 ['Biography', 'Comedy', 'Drama'],
 ['Crime', 'Horror', 'Thriller'],
 ['Crime', 'Drama', 'Mystery'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Biography', 'Drama'],
 ['Biography', 'Drama'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Biography', 'Drama'],
 ['Drama', 'Fantasy', 'Horror'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Sport'],
 ['Drama', 'Romance'],
 ['Comedy', 'Romance'],
 ['Action', 'Crime', 'Thriller'],
 ['Action', 'Crime', 'Drama'],
 ['Action', 'Drama', 'Thriller'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Action', 'Adventure'],
 ['Action', 'Adventure', 'Romance'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Crime', 'Drama'],
 ['Comedy', 'Horror'],
 ['Comedy', 'Fantasy', 'Romance'],
 ['Drama'],
 ['Drama'],
 ['Comedy', 'Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Adventure', 'Sci-Fi', 'Thriller'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Comedy', 'Drama'],
 ['Biography', 'Drama', 'Romance'],
 ['Comedy', 'Fantasy'],
 ['Comedy', 'Drama', 'Fantasy'],
 ['Comedy'],
 ['Horror', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Comedy', 'Horror'],
 ['Comedy', 'Mystery'],
 ['Drama'],
 ['Adventure', 'Drama', 'Fantasy'],
 ['Drama', 'Sport'],
 ['Action', 'Adventure'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Drama', 'Sci-Fi'],
 ['Action', 'Mystery', 'Sci-Fi'],
 ['Action', 'Crime', 'Drama'],
 ['Action', 'Crime', 'Fantasy'],
 ['Biography', 'Comedy', 'Drama'],
 ['Action', 'Crime', 'Thriller'],
 ['Biography', 'Crime', 'Drama'],
 ['Drama', 'Sport'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Action', 'Adventure', 'Thriller'],
 ['Comedy', 'Fantasy', 'Horror'],
 ['Drama', 'Sport'],
 ['Horror', 'Thriller'],
 ['Drama', 'History', 'Thriller'],
 ['Animation', 'Action', 'Adventure'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Comedy', 'Family'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Comedy'],
 ['Action', 'Crime', 'Drama'],
 ['Biography', 'Drama'],
 ['Comedy', 'Romance'],
 ['Comedy'],
 ['Drama', 'Fantasy', 'Romance'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy'],
 ['Comedy', 'Sci-Fi'],
 ['Comedy', 'Drama'],
 ['Animation', 'Action', 'Adventure'],
 ['Horror'],
 ['Action', 'Biography', 'Crime'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Drama', 'Romance'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Drama', 'History', 'Thriller'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Comedy'],
 ['Action', 'Thriller'],
 ['Comedy', 'Music'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Adventure', 'Crime'],
 ['Comedy', 'Drama', 'Horror'],
 ['Drama'],
 ['Drama', 'Mystery', 'Romance'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Drama'],
 ['Action', 'Drama', 'Thriller'],
 ['Drama'],
 ['Action', 'Horror', 'Romance'],
 ['Action', 'Drama', 'Fantasy'],
 ['Action', 'Crime', 'Drama'],
 ['Drama', 'Fantasy', 'Romance'],
 ['Action', 'Crime', 'Thriller'],
 ['Action', 'Mystery', 'Thriller'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Action', 'Horror', 'Sci-Fi'],
 ['Comedy', 'Drama'],
 ['Comedy'],
 ['Action', 'Adventure', 'Horror'],
 ['Action', 'Adventure', 'Thriller'],
 ['Action', 'Crime', 'Drama'],
 ['Comedy', 'Crime', 'Drama'],
 ['Drama', 'Romance'],
 ['Drama', 'Thriller'],
 ['Action', 'Comedy', 'Crime'],
 ['Comedy'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Drama', 'Romance'],
 ['Animation', 'Family', 'Fantasy'],
 ['Drama', 'Romance'],
 ['Thriller'],
 ['Adventure', 'Horror', 'Mystery'],
 ['Action', 'Sci-Fi'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Animation', 'Action', 'Adventure'],
 ['Drama', 'Horror'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy', 'Drama'],
 ['Action', 'Horror', 'Mystery'],
 ['Action', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Comedy', 'Crime'],
 ['Comedy', 'Romance'],
 ['Drama', 'Romance'],
 ['Crime', 'Drama', 'Thriller'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Biography', 'Drama'],
 ['Drama', 'Mystery', 'Sci-Fi'],
 ['Adventure', 'Comedy', 'Family'],
 ['Action', 'Adventure', 'Crime'],
 ['Action', 'Crime', 'Mystery'],
 ['Mystery', 'Thriller'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Action', 'Comedy', 'Crime'],
 ['Biography', 'Crime', 'Drama'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Biography', 'Drama', 'History'],
 ['Biography', 'Comedy', 'Drama'],
 ['Drama', 'Thriller'],
 ['Horror', 'Thriller'],
 ['Drama'],
 ['Drama', 'War'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Romance', 'Sci-Fi'],
 ['Action', 'Crime', 'Drama'],
 ['Comedy', 'Drama'],
 ['Animation', 'Action', 'Adventure'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Comedy', 'Drama', 'Family'],
 ['Drama', 'Romance', 'Thriller'],
 ['Comedy', 'Crime', 'Drama'],
 ['Animation', 'Comedy', 'Family'],
 ['Drama', 'Horror', 'Sci-Fi'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Horror', 'Sci-Fi'],
 ['Action', 'Crime', 'Sport'],
 ['Drama', 'Horror', 'Sci-Fi'],
 ['Drama', 'Horror', 'Sci-Fi'],
 ['Action', 'Adventure', 'Comedy'],
 ['Mystery', 'Sci-Fi', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Drama', 'Romance'],
 ['Crime', 'Drama', 'Thriller'],
 ['Comedy', 'Drama', 'Music'],
 ['Drama', 'Fantasy', 'Romance'],
 ['Crime', 'Drama', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Comedy', 'Romance'],
 ['Drama', 'Sci-Fi', 'Thriller'],
 ['Drama', 'War'],
 ['Action', 'Crime', 'Drama'],
 ['Sci-Fi', 'Thriller'],
 ['Adventure', 'Drama', 'Horror'],
 ['Comedy', 'Drama', 'Music'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Crime', 'Drama'],
 ['Adventure', 'Fantasy'],
 ['Drama', 'Romance'],
 ['Biography', 'History', 'Thriller'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Drama', 'History'],
 ['Biography', 'Comedy', 'Drama'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Biography', 'Drama'],
 ['Action', 'Drama', 'Sci-Fi'],
 ['Adventure', 'Horror'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Mystery'],
 ['Comedy', 'Drama', 'Romance'],
 ['Horror', 'Thriller'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Biography', 'Drama'],
 ['Action', 'Crime', 'Drama'],
 ['Action', 'Crime', 'Mystery'],
 ['Action', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Thriller'],
 ['Crime', 'Drama'],
 ['Mystery', 'Thriller'],
 ['Mystery', 'Sci-Fi', 'Thriller'],
 ['Action', 'Mystery', 'Sci-Fi'],
 ['Drama', 'Romance'],
 ['Drama', 'Thriller'],
 ['Drama', 'Mystery', 'Sci-Fi'],
 ['Comedy', 'Drama'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Biography', 'Drama', 'Sport'],
 ['Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Biography', 'Drama', 'Romance'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama', 'Sci-Fi', 'Thriller'],
 ['Drama', 'Romance', 'Thriller'],
 ['Mystery', 'Thriller'],
 ['Mystery', 'Thriller'],
 ['Action', 'Drama', 'Fantasy'],
 ['Action', 'Adventure', 'Biography'],
 ['Adventure', 'Comedy', 'Sci-Fi'],
 ['Action', 'Adventure', 'Thriller'],
 ['Fantasy', 'Horror'],
 ['Horror', 'Mystery'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Adventure', 'Drama'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Comedy', 'Drama'],
 ['Comedy', 'Drama'],
 ['Crime', 'Drama', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Animation', 'Comedy', 'Family'],
 ['Comedy', 'Drama'],
 ['Comedy', 'Drama'],
 ['Biography', 'Drama', 'Sport'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Drama', 'History'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Mystery'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action'],
 ['Action', 'Adventure', 'Family'],
 ['Comedy', 'Romance'],
 ['Comedy', 'Drama', 'Romance'],
 ['Biography', 'Drama', 'Sport'],
 ['Action', 'Fantasy', 'Thriller'],
 ['Biography', 'Drama', 'Sport'],
 ['Action', 'Drama', 'Fantasy'],
 ['Adventure', 'Sci-Fi', 'Thriller'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Drama', 'Romance'],
 ['Crime', 'Drama', 'Mystery'],
 ['Comedy', 'Romance', 'Sport'],
 ['Comedy', 'Family'],
 ['Drama', 'Horror', 'Mystery'],
 ['Action', 'Drama', 'Sport'],
 ['Action', 'Adventure', 'Comedy'],
 ['Drama', 'Mystery', 'Sci-Fi'],
 ['Animation', 'Action', 'Comedy'],
 ['Action', 'Crime', 'Drama'],
 ['Action', 'Crime', 'Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Animation', 'Action', 'Adventure'],
 ['Crime', 'Drama'],
 ['Drama'],
 ['Drama'],
 ['Comedy', 'Crime'],
 ['Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama', 'Fantasy', 'Romance'],
 ['Comedy', 'Drama'],
 ['Drama', 'Fantasy', 'Thriller'],
 ['Biography', 'Crime', 'Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Crime', 'Drama'],
 ['Sci-Fi'],
 ['Action', 'Biography', 'Drama'],
 ['Action', 'Comedy', 'Romance'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Comedy', 'Crime', 'Drama'],
 ['Action', 'Fantasy', 'Horror'],
 ['Drama', 'Horror'],
 ['Horror'],
 ['Action', 'Thriller'],
 ['Action', 'Adventure', 'Mystery'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Comedy', 'Drama', 'Romance'],
 ['Crime', 'Drama', 'Mystery'],
 ['Adventure', 'Comedy', 'Family'],
 ['Comedy', 'Drama', 'Romance'],
 ['Comedy'],
 ['Comedy', 'Drama', 'Horror'],
 ['Drama', 'Horror', 'Thriller'],
 ['Animation', 'Adventure', 'Family'],
 ['Comedy', 'Romance'],
 ['Mystery', 'Romance', 'Sci-Fi'],
 ['Crime', 'Drama'],
 ['Drama', 'Horror', 'Mystery'],
 ['Comedy'],
 ['Biography', 'Drama'],
 ['Comedy', 'Drama', 'Thriller'],
 ['Comedy', 'Western'],
 ['Drama', 'History', 'War'],
 ['Drama', 'Horror', 'Sci-Fi'],
 ['Drama'],
 ['Comedy', 'Drama'],
 ['Fantasy', 'Horror', 'Thriller'],
 ['Drama', 'Romance'],
 ['Action', 'Comedy', 'Fantasy'],
 ['Drama', 'Horror', 'Musical'],
 ['Crime', 'Drama', 'Mystery'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Comedy', 'Music'],
 ['Drama'],
 ['Biography', 'Crime', 'Drama'],
 ['Drama'],
 ['Action', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Drama'],
 ['Action', 'Comedy', 'Crime'],
 ['Comedy', 'Drama', 'Romance'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action', 'Comedy', 'Crime'],
 ['Drama'],
 ['Drama', 'Romance'],
 ['Crime', 'Drama', 'Mystery'],
 ['Adventure', 'Comedy', 'Romance'],
 ['Comedy', 'Crime', 'Drama'],
 ['Adventure', 'Drama', 'Thriller'],
 ['Biography', 'Crime', 'Drama'],
 ['Crime', 'Drama', 'Thriller'],
 ['Drama', 'History', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Comedy'],
 ['Horror'],
 ['Action', 'Crime', 'Mystery'],
 ['Comedy', 'Romance'],
 ['Comedy'],
 ['Action', 'Drama', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Fantasy', 'Horror'],
 ['Drama', 'Romance'],
 ['Biography', 'Drama'],
 ['Biography', 'Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Action', 'Horror', 'Sci-Fi'],
 ['Drama', 'Romance'],
 ['Biography', 'Drama'],
 ['Action', 'Adventure', 'Drama'],
 ['Adventure', 'Drama', 'Fantasy'],
 ['Drama', 'Family'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Romance', 'Sci-Fi'],
 ['Action', 'Adventure', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Crime', 'Drama', 'Horror'],
 ['Comedy', 'Fantasy'],
 ['Action', 'Comedy', 'Crime'],
 ['Adventure', 'Drama', 'Romance'],
 ['Action', 'Crime', 'Drama'],
 ['Crime', 'Horror', 'Thriller'],
 ['Romance', 'Sci-Fi', 'Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Crime', 'Drama'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Animation', 'Fantasy'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Drama', 'Mystery', 'War'],
 ['Comedy', 'Romance'],
 ['Animation', 'Comedy', 'Family'],
 ['Comedy'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Action', 'Adventure', 'Drama'],
 ['Comedy'],
 ['Drama'],
 ['Adventure', 'Biography', 'Drama'],
 ['Comedy'],
 ['Horror', 'Thriller'],
 ['Action', 'Drama', 'Family'],
 ['Comedy', 'Fantasy', 'Horror'],
 ['Comedy', 'Romance'],
 ['Drama', 'Mystery', 'Romance'],
 ['Action', 'Adventure', 'Comedy'],
 ['Thriller'],
 ['Comedy'],
 ['Adventure', 'Comedy', 'Sci-Fi'],
 ['Comedy', 'Drama', 'Fantasy'],
 ['Mystery', 'Thriller'],
 ['Comedy', 'Drama'],
 ['Adventure', 'Drama', 'Family'],
 ['Horror', 'Thriller'],
 ['Action', 'Drama', 'Romance'],
 ['Drama', 'Romance'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Comedy'],
 ['Action', 'Biography', 'Drama'],
 ['Drama', 'Mystery', 'Romance'],
 ['Adventure', 'Drama', 'Western'],
 ['Drama', 'Music', 'Romance'],
 ['Comedy', 'Romance', 'Western'],
 ['Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Horror', 'Thriller'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Horror', 'Mystery'],
 ['Comedy', 'Crime', 'Drama'],
 ['Action', 'Comedy', 'Romance'],
 ['Biography', 'Drama', 'History'],
 ['Adventure', 'Drama'],
 ['Drama', 'Thriller'],
 ['Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Biography', 'Drama'],
 ['Drama', 'Music'],
 ['Comedy', 'Drama'],
 ['Drama', 'Thriller', 'War'],
 ['Action', 'Mystery', 'Thriller'],
 ['Horror', 'Sci-Fi', 'Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Sci-Fi'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama', 'Mystery', 'Romance'],
 ['Drama'],
 ['Action', 'Adventure', 'Thriller'],
 ['Action', 'Crime', 'Thriller'],
 ['Animation', 'Action', 'Adventure'],
 ['Drama', 'Fantasy', 'Mystery'],
 ['Drama', 'Sci-Fi'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Horror', 'Thriller'],
 ['Action', 'Thriller'],
 ['Comedy'],
 ['Biography', 'Drama'],
 ['Action', 'Mystery', 'Thriller'],
 ['Action', 'Mystery', 'Sci-Fi'],
 ['Crime', 'Drama', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Comedy', 'Drama', 'Romance'],
 ['Biography', 'Drama', 'Thriller'],
 ['Drama'],
 ['Action', 'Adventure', 'Family'],
 ['Animation', 'Comedy', 'Family'],
 ['Action', 'Crime', 'Drama'],
 ['Comedy'],
 ['Comedy', 'Crime', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Animation', 'Comedy', 'Drama'],
 ['Action', 'Crime', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Adventure', 'Biography', 'Drama'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Action', 'Comedy', 'Sci-Fi'],
 ['Comedy', 'Fantasy', 'Horror'],
 ['Comedy', 'Crime'],
 ['Animation', 'Action', 'Adventure'],
 ['Action', 'Drama', 'Thriller'],
 ['Fantasy', 'Horror'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Comedy', 'Drama', 'Romance'],
 ['Biography', 'Drama', 'Romance'],
 ['Action', 'Drama', 'History'],
 ['Action', 'Adventure', 'Comedy'],
 ['Horror', 'Thriller'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Crime', 'Drama', 'Mystery'],
 ['Adventure', 'Biography', 'Drama'],
 ['Horror', 'Mystery', 'Thriller'],
 ['Horror', 'Thriller'],
 ['Drama', 'Romance', 'War'],
 ['Adventure', 'Fantasy', 'Mystery'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Biography', 'Drama'],
 ['Drama', 'Thriller'],
 ['Horror', 'Thriller'],
 ['Drama', 'Horror', 'Thriller'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Horror', 'Thriller'],
 ['Comedy'],
 ['Drama', 'Sport'],
 ['Comedy', 'Family'],
 ['Drama', 'Romance'],
 ['Action', 'Adventure', 'Comedy'],
 ['Comedy'],
 ['Mystery', 'Romance', 'Thriller'],
 ['Crime', 'Drama'],
 ['Action', 'Comedy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Biography', 'Drama', 'Romance'],
 ['Comedy', 'Crime'],
 ['Drama', 'Thriller'],
 ['Drama'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Action', 'Thriller'],
 ['Drama', 'Thriller'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Thriller'],
 ['Biography', 'Drama', 'Sport'],
 ['Crime', 'Drama', 'Thriller'],
 ['Drama', 'Music'],
 ['Crime', 'Drama', 'Thriller'],
 ['Drama', 'Romance'],
 ['Animation', 'Action', 'Adventure'],
 ['Comedy', 'Drama'],
 ['Action', 'Adventure', 'Drama'],
 ['Biography', 'Crime', 'Drama'],
 ['Horror'],
 ['Biography', 'Drama', 'Mystery'],
 ['Drama', 'Romance'],
 ['Animation', 'Drama', 'Romance'],
 ['Comedy', 'Family'],
 ['Drama'],
 ['Mystery', 'Thriller'],
 ['Drama', 'Fantasy', 'Horror'],
 ['Drama', 'Romance'],
 ['Biography', 'Drama', 'History'],
 ['Comedy', 'Family'],
 ['Action', 'Adventure', 'Thriller'],
 ['Comedy', 'Drama'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Thriller'],
 ['Drama', 'Romance'],
 ['Comedy', 'Drama', 'Romance'],
 ['Drama', 'Horror', 'Sci-Fi'],
 ['Comedy', 'Horror', 'Romance'],
 ['Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Action', 'Adventure', 'Drama'],
 ['Biography', 'Comedy', 'Drama'],
 ['Drama', 'Mystery', 'Romance'],
 ['Animation', 'Adventure', 'Comedy'],
 ['Drama', 'Romance', 'Sci-Fi'],
 ['Drama'],
 ['Drama', 'Fantasy'],
 ['Drama', 'Romance'],
 ['Comedy', 'Horror', 'Thriller'],
 ['Comedy', 'Drama', 'Romance'],
 ['Crime', 'Drama'],
 ['Comedy', 'Romance'],
 ['Action', 'Drama', 'Family'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Thriller', 'War'],
 ['Action', 'Comedy', 'Horror'],
 ['Biography', 'Drama', 'Sport'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Comedy', 'Romance'],
 ['Comedy', 'Romance'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Adventure', 'Crime'],
 ['Comedy', 'Romance'],
 ['Animation', 'Action', 'Adventure'],
 ['Action', 'Crime', 'Sci-Fi'],
 ['Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Crime', 'Thriller'],
 ['Comedy', 'Horror', 'Sci-Fi'],
 ['Drama', 'Thriller'],
 ['Drama', 'Fantasy', 'Horror'],
 ['Thriller'],
 ['Adventure', 'Drama', 'Family'],
 ['Mystery', 'Sci-Fi', 'Thriller'],
 ['Biography', 'Crime', 'Drama'],
 ['Drama', 'Fantasy', 'Horror'],
 ['Action', 'Adventure', 'Thriller'],
 ['Crime', 'Drama', 'Horror'],
 ['Crime', 'Drama', 'Fantasy'],
 ['Adventure', 'Family', 'Fantasy'],
 ['Action', 'Adventure', 'Drama'],
 ['Action', 'Comedy', 'Horror'],
 ['Comedy', 'Drama', 'Family'],
 ['Action', 'Thriller'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure', 'Drama', 'Fantasy'],
 ['Drama'],
 ['Drama'],
 ['Comedy'],
 ['Drama'],
 ['Comedy', 'Drama', 'Music'],
 ['Drama', 'Fantasy', 'Music'],
 ['Drama'],
 ['Thriller'],
 ['Comedy', 'Horror'],
 ['Action', 'Comedy', 'Sport'],
 ['Horror'],
 ['Comedy', 'Drama'],
 ['Action', 'Drama', 'Thriller'],
 ['Drama', 'Romance'],
 ['Horror', 'Mystery'],
 ['Adventure', 'Drama', 'Fantasy'],
 ['Thriller'],
 ['Comedy', 'Romance'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Fantasy', 'Mystery', 'Thriller'],
 ['Biography', 'Drama'],
 ['Crime', 'Drama'],
 ['Action', 'Adventure', 'Sci-Fi'],
 ['Adventure'],
 ['Comedy', 'Drama'],
 ['Comedy', 'Drama'],
 ['Comedy', 'Drama', 'Romance'],
 ['Adventure', 'Comedy', 'Drama'],
 ['Action', 'Sci-Fi', 'Thriller'],
 ['Comedy', 'Romance'],
 ['Action', 'Fantasy', 'Horror'],
 ['Crime', 'Drama', 'Thriller'],
 ['Action', 'Drama', 'Thriller'],
 ['Crime', 'Drama', 'Mystery'],
 ['Crime', 'Drama', 'Mystery'],
 ['Drama', 'Sci-Fi', 'Thriller'],
 ['Biography', 'Drama', 'History'],
 ['Crime', 'Horror', 'Thriller'],
 ['Drama'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Adventure', 'Biography'],
 ['Adventure', 'Biography', 'Crime'],
 ['Action', 'Horror', 'Thriller'],
 ['Action', 'Adventure', 'Western'],
 ['Horror', 'Thriller'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Comedy', 'Drama', 'Musical'],
 ['Horror', 'Mystery'],
 ['Biography', 'Drama', 'Sport'],
 ['Comedy', 'Family', 'Romance'],
 ['Drama', 'Mystery', 'Thriller'],
 ['Comedy'],
 ['Drama'],
 ['Drama', 'Thriller'],
 ['Biography', 'Drama', 'Family'],
 ['Comedy', 'Drama', 'Family'],
 ['Drama', 'Fantasy', 'Musical'],
 ['Comedy'],
 ['Adventure', 'Family'],
 ['Adventure', 'Comedy', 'Fantasy'],
 ['Horror', 'Thriller'],
 ['Drama', 'Romance'],
 ['Horror'],
 ['Biography', 'Drama', 'History'],
 ['Action', 'Adventure', 'Fantasy'],
 ['Drama', 'Family', 'Music'],
 ['Comedy', 'Drama', 'Romance'],
 ['Action', 'Adventure', 'Horror'],
 ['Comedy'],
 ['Crime', 'Drama', 'Mystery'],
 ['Horror'],
 ['Drama', 'Music', 'Romance'],
 ['Adventure', 'Comedy'],
 ['Comedy', 'Family', 'Fantasy']]

genres = np.unique([j for i in movie_genre for j in i])
genres

array(['Action', 'Adventure', 'Animation', 'Biography', 'Comedy', 'Crime',
       'Drama', 'Family', 'Fantasy', 'History', 'Horror', 'Music',
       'Musical', 'Mystery', 'Romance', 'Sci-Fi', 'Sport', 'Thriller',
       'War', 'Western'], dtype=' 
# 每个类别有几部电影
count = pd.Dataframe(np.zeros(shape=[1000,20],dtype="int32"),columns=genres)
count.head()
 
Action
Adventure
Animation
Biography
Comedy
Crime
Drama
Family
Fantasy
History
Horror
Music
Musical
Mystery
Romance
Sci-Fi
Sport
Thriller
War
Western
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
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
2
0
0
0
0
0
0
0
0
0
0
0
0
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
4
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
 
# 计数填表
for i in range(1000):
    count.loc[i, movie_genre[i]] = 1
count
 
Action
Adventure
Animation
Biography
Comedy
Crime
Drama
Family
Fantasy
History
Horror
Music
Musical
Mystery
Romance
Sci-Fi
Sport
Thriller
War
Western
0
1
1
0
0
0
0
0
0
0
0
0
0
0
0
0
1
0
0
0
0
1
0
1
0
0
0
0
0
0
0
0
0
0
0
1
0
1
0
0
0
0
2
0
0
0
0
0
0
0
0
0
0
1
0
0
0
0
0
0
1
0
0
3
0
0
1
0
1
0
0
1
0
0
0
0
0
0
0
0
0
0
0
0
4
1
1
0
0
0
0
0
0
1
0
0
0
0
0
0
0
0
0
0
0
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
995
0
0
0
0
0
1
1
0
0
0
0
0
0
1
0
0
0
0
0
0
996
0
0
0
0
0
0
0
0
0
0
1
0
0
0
0
0
0
0
0
0
997
0
0
0
0
0
0
1
0
0
0
0
1
0
0
1
0
0
0
0
0
998
0
1
0
0
1
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
999
0
0
0
0
1
0
0
1
1
0
0
0
0
0
0
0
0
0
0
0
 
1000 rows × 20 columns
 
count.sum(axis=0).sort_values(ascending=False).plot(kind="pie",figsize=(10,10),fontsize=20)
 
 
​
 
 ​
 
count.sum(axis=0).sort_values(ascending=False).plot(kind="bar",figsize=(20,9),fontsize=40,colormap="cool")
 
 
​
 
 ​