Unit1_Task01

import numpy as np
import pandas as pd

df = pd.read_csv('train.csv')
df.head(3)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
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

df = pd.read_csv(r'C:\Users\hp\hands-on-data-analysis-master\hands-on-data-analysis-master\第一单元项目集合\train - 副本.csv')#此处把csv文件变成不带BOM的UTF-8
df.head(3)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
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

chunker = pd.read_csv('train.csv', chunksize=1000)

df = pd.read_csv('train.csv', names=['乘客ID','是否幸存','仓位等级','姓名','性别','年龄','兄弟姐妹个数','父母子女个数','船票信息','票价','客舱','登船港口'],index_col='乘客ID',header=0)
df.head()

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

df.head(10)

	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
乘客ID
1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S
6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q
7	0	1	McCarthy, Mr. Timothy J	male	54.0	0	0	17463	51.8625	E46	S
8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.0750	NaN	S
9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.0	0	2	347742	11.1333	NaN	S
10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.0	1	0	237736	30.0708	NaN	C

df.tail(15)

	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
乘客ID
877	0	3	Gustafsson, Mr. Alfred Ossian	male	20.0	0	0	7534	9.8458	NaN	S
878	0	3	Petroff, Mr. Nedelio	male	19.0	0	0	349212	7.8958	NaN	S
879	0	3	Laleff, Mr. Kristo	male	NaN	0	0	349217	7.8958	NaN	S
880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56.0	0	1	11767	83.1583	C50	C
881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25.0	0	1	230433	26.0000	NaN	S
882	0	3	Markun, Mr. Johann	male	33.0	0	0	349257	7.8958	NaN	S
883	0	3	Dahlberg, Miss. Gerda Ulrika	female	22.0	0	0	7552	10.5167	NaN	S
884	0	2	Banfield, Mr. Frederick James	male	28.0	0	0	C.A./SOTON 34068	10.5000	NaN	S
885	0	3	Sutehall, Mr. Henry Jr	male	25.0	0	0	SOTON/OQ 392076	7.0500	NaN	S
886	0	3	Rice, Mrs. William (Margaret Norton)	female	39.0	0	5	382652	29.1250	NaN	Q
887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NaN	S
888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	NaN	1	2	W./C. 6607	23.4500	NaN	S
890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NaN	Q

df.isnull().head()

	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	船票信息	票价	客舱	登船港口
乘客ID
1	False	False	False	False	False	False	False	False	False	True	False
2	False	False	False	False	False	False	False	False	False	False	False
3	False	False	False	False	False	False	False	False	False	True	False
4	False	False	False	False	False	False	False	False	False	False	False
5	False	False	False	False	False	False	False	False	False	True	False

df.to_csv('train - 副本_chinese.csv')

#1.4

import numpy as np
import pandas as pd

data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002, 2003],'pop': [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}
example_2 = pd.DataFrame(data)
example_2

	state	year	pop
0	Ohio	2000	1.5
1	Ohio	2001	1.7
2	Ohio	2002	3.6
3	Nevada	2001	2.4
4	Nevada	2002	2.9
5	Nevada	2003	3.2

df = pd.read_csv(r'C:\Users\hp\hands-on-data-analysis-master\hands-on-data-analysis-master\第一单元项目集合\train - 副本.csv')
df.head(3)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
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

df.columns

Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

df['Cabin'].head(3)

0    NaN
1    C85
2    NaN
Name: Cabin, dtype: object

df.Cabin.head(3)

0    NaN
1    C85
2    NaN
Name: Cabin, dtype: object

test_1 = pd.read_csv('test_1.csv')
test_1.head(3)

	Unnamed: 0	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked	a
0	0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S	100
1	1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	100
2	2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S	100

# 删除多余的列
del test_1['a']
test_1.head(3)

	Unnamed: 0	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	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
2	2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S

df.drop(['PassengerId','Name','Age','Ticket'],axis=1).head(3)

	Survived	Pclass	Sex	SibSp	Parch	Fare	Cabin	Embarked
0	0	3	male	1	0	7.2500	NaN	S
1	1	1	female	1	0	71.2833	C85	C
2	1	3	female	0	0	7.9250	NaN	S

df.head(3) 

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
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

df[df["Age"]<10].head(3)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
7	8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.075	NaN	S
10	11	1	3	Sandstrom, Miss. Marguerite Rut	female	4.0	1	1	PP 9549	16.700	G6	S
16	17	0	3	Rice, Master. Eugene	male	2.0	4	1	382652	29.125	NaN	Q

midage = df[(df["Age"]>10)& (df["Age"]<50)]
midage.head(3)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
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

midage = midage.reset_index(drop=True)
midage.head(3)

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
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

midage.loc[[100],['Pclass','Sex']]

	Pclass	Sex
100	2	male

midage.loc[[100,105,108],['Pclass','Name','Sex']] 

	Pclass	Name	Sex
100	2	Byles, Rev. Thomas Roussel Davids	male
105	3	Cribb, Mr. John Hatfield	male
108	3	Calic, Mr. Jovo	male

midage.iloc[[100,105,108],[2,3,4]]

	Pclass	Name	Sex
100	2	Byles, Rev. Thomas Roussel Davids	male
105	3	Cribb, Mr. John Hatfield	male
108	3	Calic, Mr. Jovo	male

#1.6

text = pd.read_csv('train_chinese.csv')
text.head()

	乘客ID	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	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

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

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

frame.sort_values(by='c', ascending=True)

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

frame.sort_index()

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

frame.sort_index(axis=1)

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

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

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

frame.sort_values(by=['a', 'c'], ascending=False)

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

text.sort_values(by=['票价', '年龄'], ascending=False).head(3)

	乘客ID	是否幸存	仓位等级	姓名	性别	年龄	兄弟姐妹个数	父母子女个数	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

frame1_a = pd.DataFrame(np.arange(9.).reshape(3, 3),
                     columns=['A', 'B', 'C'],
                     index=['A', 'B', 'B'])
frame1_b = pd.DataFrame(np.arange(12.).reshape(4, 3),
                     columns=['a', 'e', 'c'],
                     index=['first', 'one', 'two', 'second'])
frame1_a

	A	B	C
A	0.0	1.0	2.0
B	3.0	4.0	5.0
B	6.0	7.0	8.0

frame1_b

	a	e	c
first	0.0	1.0	2.0
one	3.0	4.0	5.0
two	6.0	7.0	8.0
second	9.0	10.0	11.0

frame1_a + frame1_b#表格a我小小的修改了一下

	A	B	C	a	c	e
A	NaN	NaN	NaN	NaN	NaN	NaN
B	NaN	NaN	NaN	NaN	NaN	NaN
B	NaN	NaN	NaN	NaN	NaN	NaN
first	NaN	NaN	NaN	NaN	NaN	NaN
one	NaN	NaN	NaN	NaN	NaN	NaN
second	NaN	NaN	NaN	NaN	NaN	NaN
two	NaN	NaN	NaN	NaN	NaN	NaN

max(text['兄弟姐妹个数'] + text['父母子女个数'])

10

frame2 = pd.DataFrame([[1.4, np.nan], 
                       [7.1, -4.5],
                       [np.nan, np.nan], 
                       [0.75, -1.3]
                      ], index=['a', 'b', 'c', 'd'], columns=['one', 'two'])
frame2

	one	two
a	1.40	NaN
b	7.10	-4.5
c	NaN	NaN
d	0.75	-1.3

frame2.describe()

	one	two
count	3.000000	2.000000
mean	3.083333	-2.900000
std	3.493685	2.262742
min	0.750000	-4.500000
25%	1.075000	-3.700000
50%	1.400000	-2.900000
75%	4.250000	-2.100000
max	7.100000	-1.300000

text['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

text['父母子女个数'].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: 父母子女个数, dtype: float64

#还在摸索基础知识，这次课程对新手来说确实不太友好，我在pd.read_csv格式里研究了很久，还好群里老哥解释原因，还把csv文件变成不带BOM的UTF-8原因讲解了一下，这里可以说是设计课程的小彩蛋吧，花了不少心思。我对于新事物学习效率很低，希望能跟上大部队，不要掉队。第一次做过于粗糙。