DataWhale之task01-探索性数据分析(EDA)

import numpy as np
import pandas as pd

df = pd.read_csv("train_chinese.csv")
df.head()

	乘客ID	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	船票信息	票价	客舱	登船港口
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S

df_01 = pd.DataFrame(data=np.arange(8).reshape((2,4)), index=[2,1], columns=['d','a','b','c'])
df_01

	d	a	b	c
2	0	1	2	3
1	4	5	6	7

索引排序

df_01.sort_index()

	d	a	b	c
1	4	5	6	7
2	0	1	2	3

df_01.sort_index(axis=1)

	a	b	c	d
2	1	2	3	0
1	5	6	7	4

df_01.sort_index(axis=1,ascending=False)

	d	c	b	a
2	0	3	2	1
1	4	7	6	5

列排序

df_01.sort_values(by=['b','c'], ascending=False)

	d	a	b	c
1	4	5	6	7
2	0	1	2	3

#按票价和年龄进行降序
df.sort_values(by=['票价','年龄'], ascending=False).head(20)

	乘客ID	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	船票信息	票价	客舱	登船港口
679	680	1	1	Cardeza, Mr. Thomas Drake Martinez	male	36.0	0	1	PC 17755	512.3292	B51 B53 B55	C
258	259	1	1	Ward, Miss. Anna	female	35.0	0	0	PC 17755	512.3292	NaN	C
737	738	1	1	Lesurer, Mr. Gustave J	male	35.0	0	0	PC 17755	512.3292	B101	C
438	439	0	1	Fortune, Mr. Mark	male	64.0	1	4	19950	263.0000	C23 C25 C27	S
341	342	1	1	Fortune, Miss. Alice Elizabeth	female	24.0	3	2	19950	263.0000	C23 C25 C27	S
88	89	1	1	Fortune, Miss. Mabel Helen	female	23.0	3	2	19950	263.0000	C23 C25 C27	S
27	28	0	1	Fortune, Mr. Charles Alexander	male	19.0	3	2	19950	263.0000	C23 C25 C27	S
742	743	1	1	Ryerson, Miss. Susan Parker "Suzette"	female	21.0	2	2	PC 17608	262.3750	B57 B59 B63 B66	C
311	312	1	1	Ryerson, Miss. Emily Borie	female	18.0	2	2	PC 17608	262.3750	B57 B59 B63 B66	C
299	300	1	1	Baxter, Mrs. James (Helene DeLaudeniere Chaput)	female	50.0	0	1	PC 17558	247.5208	B58 B60	C
118	119	0	1	Baxter, Mr. Quigg Edmond	male	24.0	0	1	PC 17558	247.5208	B58 B60	C
380	381	1	1	Bidois, Miss. Rosalie	female	42.0	0	0	PC 17757	227.5250	NaN	C
716	717	1	1	Endres, Miss. Caroline Louise	female	38.0	0	0	PC 17757	227.5250	C45	C
700	701	1	1	Astor, Mrs. John Jacob (Madeleine Talmadge Force)	female	18.0	1	0	PC 17757	227.5250	C62 C64	C
557	558	0	1	Robbins, Mr. Victor	male	NaN	0	0	PC 17757	227.5250	NaN	C
527	528	0	1	Farthing, Mr. John	male	NaN	0	0	PC 17483	221.7792	C95	S
377	378	0	1	Widener, Mr. Harry Elkins	male	27.0	0	2	113503	211.5000	C82	C
779	780	1	1	Robert, Mrs. Edward Scott (Elisabeth Walton Mc...	female	43.0	0	1	24160	211.3375	B3	S
730	731	1	1	Allen, Miss. Elisabeth Walton	female	29.0	0	0	24160	211.3375	B5	S
689	690	1	1	Madill, Miss. Georgette Alexandra	female	15.0	0	1	24160	211.3375	B5	S

#按年龄进行降序
df.sort_values(by='年龄',ascending=False).head(20)

	乘客ID	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	船票信息	票价	客舱	登船港口
630	631	1	1	Barkworth, Mr. Algernon Henry Wilson	male	80.0	0	0	27042	30.0000	A23	S
851	852	0	3	Svensson, Mr. Johan	male	74.0	0	0	347060	7.7750	NaN	S
493	494	0	1	Artagaveytia, Mr. Ramon	male	71.0	0	0	PC 17609	49.5042	NaN	C
96	97	0	1	Goldschmidt, Mr. George B	male	71.0	0	0	PC 17754	34.6542	A5	C
116	117	0	3	Connors, Mr. Patrick	male	70.5	0	0	370369	7.7500	NaN	Q
672	673	0	2	Mitchell, Mr. Henry Michael	male	70.0	0	0	C.A. 24580	10.5000	NaN	S
745	746	0	1	Crosby, Capt. Edward Gifford	male	70.0	1	1	WE/P 5735	71.0000	B22	S
33	34	0	2	Wheadon, Mr. Edward H	male	66.0	0	0	C.A. 24579	10.5000	NaN	S
54	55	0	1	Ostby, Mr. Engelhart Cornelius	male	65.0	0	1	113509	61.9792	B30	C
280	281	0	3	Duane, Mr. Frank	male	65.0	0	0	336439	7.7500	NaN	Q
456	457	0	1	Millet, Mr. Francis Davis	male	65.0	0	0	13509	26.5500	E38	S
438	439	0	1	Fortune, Mr. Mark	male	64.0	1	4	19950	263.0000	C23 C25 C27	S
545	546	0	1	Nicholson, Mr. Arthur Ernest	male	64.0	0	0	693	26.0000	NaN	S
275	276	1	1	Andrews, Miss. Kornelia Theodosia	female	63.0	1	0	13502	77.9583	D7	S
483	484	1	3	Turkula, Mrs. (Hedwig)	female	63.0	0	0	4134	9.5875	NaN	S
570	571	1	2	Harris, Mr. George	male	62.0	0	0	S.W./PP 752	10.5000	NaN	S
252	253	0	1	Stead, Mr. William Thomas	male	62.0	0	0	113514	26.5500	C87	S
829	830	1	1	Stone, Mrs. George Nelson (Martha Evelyn)	female	62.0	0	0	113572	80.0000	B28	NaN
555	556	0	1	Wright, Mr. George	male	62.0	0	0	113807	26.5500	NaN	S
625	626	0	1	Sutton, Mr. Frederick	male	61.0	0	0	36963	32.3208	D50	S

年龄大的前20人中只有5人存活

#两个DF相加
frame_a = pd.DataFrame(np.arange(9.).reshape(3,3),
                      index = ['one','two','three'],
                      columns = ['a','b','c'])
frame_b = pd.DataFrame(np.arange(12.).reshape(4,3),
                      index = ['first','one','two','second'],
                      columns = ['a','e','c'])
frame_a+frame_b

	a	b	c	e
first	NaN	NaN	NaN	NaN
one	3.0	NaN	7.0	NaN
second	NaN	NaN	NaN	NaN
three	NaN	NaN	NaN	NaN
two	9.0	NaN	13.0	NaN

df['家族人数'] = df['堂兄弟/妹个数'] + df['父母与小孩个数']
df.head()

	乘客ID	是否幸存	乘客等级(1/2/3等舱位)	乘客姓名	性别	年龄	堂兄弟/妹个数	父母与小孩个数	船票信息	票价	客舱	登船港口	家族人数
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S	1
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	1
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S	0
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S	1
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S	0

df['家族人数'].max()

10

df['家族人数'].value_counts()

0     537
1     161
2     102
3      29
5      22
4      15
6      12
10      7
7       6
Name: 家族人数, dtype: int64

#年龄分布
df['性别'].value_counts()

male      577
female    314
Name: 性别, dtype: int64

#基本统计信息
df.describe()

	乘客ID	是否幸存	乘客等级(1/2/3等舱位)	年龄	堂兄弟/妹个数	父母与小孩个数	票价	家族人数
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208	0.904602
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429	1.613459
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400	0.000000
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200	0.000000
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000	1.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200	10.000000

df['票价'].describe()

count    891.000000
mean      32.204208
std       49.693429
min        0.000000
25%        7.910400
50%       14.454200
75%       31.000000
max      512.329200
Name: 票价, dtype: float64

票价一共有891个数据,平均值为：32.20, 标准差为：49.69 说明票价波动较大
75%的人票价低于31, 票价最大约为：512

df['父母与小孩个数'].describe()

count    891.000000
mean       0.381594
std        0.806057
min        0.000000
25%        0.000000
50%        0.000000
75%        0.000000
max        6.000000
Name: 父母与小孩个数, dtype: float64