In [2]:
import numpy as np
import pandas as pd
from sklearn import preprocessing
In [3]:
df = pd.read_csv("train.csv")
df.loc[df["Sex"] == 'female',"Sex"] = 0
df.loc[df["Sex"] == 'male',"Sex"] = 1
print(len(df))
df = df.fillna(value="Not available")
df = df.drop("Cabin")
df = df.drop("")
df_train = df[0:600]
df_cross_validate = df[601:]
df_train
df_test = pd.read_csv("test.csv")
891
Out[3]:
PassengerId
Survived
Pclass
Name
Sex
Age
SibSp
Parch
Ticket
Fare
Cabin
Embarked
0
1
0
3
Braund, Mr. Owen Harris
1
22
1
0
A/5 21171
7.2500
Not available
S
1
2
1
1
Cumings, Mrs. John Bradley (Florence Briggs Th...
0
38
1
0
PC 17599
71.2833
C85
C
2
3
1
3
Heikkinen, Miss. Laina
0
26
0
0
STON/O2. 3101282
7.9250
Not available
S
3
4
1
1
Futrelle, Mrs. Jacques Heath (Lily May Peel)
0
35
1
0
113803
53.1000
C123
S
4
5
0
3
Allen, Mr. William Henry
1
35
0
0
373450
8.0500
Not available
S
5
6
0
3
Moran, Mr. James
1
Not available
0
0
330877
8.4583
Not available
Q
6
7
0
1
McCarthy, Mr. Timothy J
1
54
0
0
17463
51.8625
E46
S
7
8
0
3
Palsson, Master. Gosta Leonard
1
2
3
1
349909
21.0750
Not available
S
8
9
1
3
Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)
0
27
0
2
347742
11.1333
Not available
S
9
10
1
2
Nasser, Mrs. Nicholas (Adele Achem)
0
14
1
0
237736
30.0708
Not available
C
10
11
1
3
Sandstrom, Miss. Marguerite Rut
0
4
1
1
PP 9549
16.7000
G6
S
11
12
1
1
Bonnell, Miss. Elizabeth
0
58
0
0
113783
26.5500
C103
S
12
13
0
3
Saundercock, Mr. William Henry
1
20
0
0
A/5. 2151
8.0500
Not available
S
13
14
0
3
Andersson, Mr. Anders Johan
1
39
1
5
347082
31.2750
Not available
S
14
15
0
3
Vestrom, Miss. Hulda Amanda Adolfina
0
14
0
0
350406
7.8542
Not available
S
15
16
1
2
Hewlett, Mrs. (Mary D Kingcome)
0
55
0
0
248706
16.0000
Not available
S
16
17
0
3
Rice, Master. Eugene
1
2
4
1
382652
29.1250
Not available
Q
17
18
1
2
Williams, Mr. Charles Eugene
1
Not available
0
0
244373
13.0000
Not available
S
18
19
0
3
Vander Planke, Mrs. Julius (Emelia Maria Vande...
0
31
1
0
345763
18.0000
Not available
S
19
20
1
3
Masselmani, Mrs. Fatima
0
Not available
0
0
2649
7.2250
Not available
C
20
21
0
2
Fynney, Mr. Joseph J
1
35
0
0
239865
26.0000
Not available
S
21
22
1
2
Beesley, Mr. Lawrence
1
34
0
0
248698
13.0000
D56
S
22
23
1
3
McGowan, Miss. Anna "Annie"
0
15
0
0
330923
8.0292
Not available
Q
23
24
1
1
Sloper, Mr. William Thompson
1
28
0
0
113788
35.5000
A6
S
24
25
0
3
Palsson, Miss. Torborg Danira
0
8
3
1
349909
21.0750
Not available
S
25
26
1
3
Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...
0
38
1
5
347077
31.3875
Not available
S
26
27
0
3
Emir, Mr. Farred Chehab
1
Not available
0
0
2631
7.2250
Not available
C
27
28
0
1
Fortune, Mr. Charles Alexander
1
19
3
2
19950
263.0000
C23 C25 C27
S
28
29
1
3
O'Dwyer, Miss. Ellen "Nellie"
0
Not available
0
0
330959
7.8792
Not available
Q
29
30
0
3
Todoroff, Mr. Lalio
1
Not available
0
0
349216
7.8958
Not available
S
...
...
...
...
...
...
...
...
...
...
...
...
...
570
571
1
2
Harris, Mr. George
1
62
0
0
S.W./PP 752
10.5000
Not available
S
571
572
1
1
Appleton, Mrs. Edward Dale (Charlotte Lamson)
0
53
2
0
11769
51.4792
C101
S
572
573
1
1
Flynn, Mr. John Irwin ("Irving")
1
36
0
0
PC 17474
26.3875
E25
S
573
574
1
3
Kelly, Miss. Mary
0
Not available
0
0
14312
7.7500
Not available
Q
574
575
0
3
Rush, Mr. Alfred George John
1
16
0
0
A/4. 20589
8.0500
Not available
S
575
576
0
3
Patchett, Mr. George
1
19
0
0
358585
14.5000
Not available
S
576
577
1
2
Garside, Miss. Ethel
0
34
0
0
243880
13.0000
Not available
S
577
578
1
1
Silvey, Mrs. William Baird (Alice Munger)
0
39
1
0
13507
55.9000
E44
S
578
579
0
3
Caram, Mrs. Joseph (Maria Elias)
0
Not available
1
0
2689
14.4583
Not available
C
579
580
1
3
Jussila, Mr. Eiriik
1
32
0
0
STON/O 2. 3101286
7.9250
Not available
S
580
581
1
2
Christy, Miss. Julie Rachel
0
25
1
1
237789
30.0000
Not available
S
581
582
1
1
Thayer, Mrs. John Borland (Marian Longstreth M...
0
39
1
1
17421
110.8833
C68
C
582
583
0
2
Downton, Mr. William James
1
54
0
0
28403
26.0000
Not available
S
583
584
0
1
Ross, Mr. John Hugo
1
36
0
0
13049
40.1250
A10
C
584
585
0
3
Paulner, Mr. Uscher
1
Not available
0
0
3411
8.7125
Not available
C
585
586
1
1
Taussig, Miss. Ruth
0
18
0
2
110413
79.6500
E68
S
586
587
0
2
Jarvis, Mr. John Denzil
1
47
0
0
237565
15.0000
Not available
S
587
588
1
1
Frolicher-Stehli, Mr. Maxmillian
1
60
1
1
13567
79.2000
B41
C
588
589
0
3
Gilinski, Mr. Eliezer
1
22
0
0
14973
8.0500
Not available
S
589
590
0
3
Murdlin, Mr. Joseph
1
Not available
0
0
A./5. 3235
8.0500
Not available
S
590
591
0
3
Rintamaki, Mr. Matti
1
35
0
0
STON/O 2. 3101273
7.1250
Not available
S
591
592
1
1
Stephenson, Mrs. Walter Bertram (Martha Eustis)
0
52
1
0
36947
78.2667
D20
C
592
593
0
3
Elsbury, Mr. William James
1
47
0
0
A/5 3902
7.2500
Not available
S
593
594
0
3
Bourke, Miss. Mary
0
Not available
0
2
364848
7.7500
Not available
Q
594
595
0
2
Chapman, Mr. John Henry
1
37
1
0
SC/AH 29037
26.0000
Not available
S
595
596
0
3
Van Impe, Mr. Jean Baptiste
1
36
1
1
345773
24.1500
Not available
S
596
597
1
2
Leitch, Miss. Jessie Wills
0
Not available
0
0
248727
33.0000
Not available
S
597
598
0
3
Johnson, Mr. Alfred
1
49
0
0
LINE
0.0000
Not available
S
598
599
0
3
Boulos, Mr. Hanna
1
Not available
0
0
2664
7.2250
Not available
C
599
600
1
1
Duff Gordon, Sir. Cosmo Edmund ("Mr Morgan")
1
49
1
0
PC 17485
56.9292
A20
C
600 rows × 12 columns
In [4]:
Features = ["PassengerId","Survived","Pclass","Sex","Age","Fare","Embarked"]
Passanger_data = df["PassengerId"]
Survived_data = df["Survived"]
Pclass_data = df["Pclass"]
Sex_data = df["Sex"]
Age_data = df["Age"]
Fare_data = df["Fare"]
Embarked_data = df["Embarked"]
In [1]:
feautre_list = ["PassengerId","Survived","Sex","Age","Fare"]
Content source: vbsteja/code
Similar notebooks: