uczenie_maszynowe_zadania/cw_4/.ipynb_checkpoints/main-checkpoint.ipynb

import numpy as np
import pandas as pd
from sklearn.impute import SimpleImputer
from sklearn.feature_extraction.text import TfidfVectorizer

data = pd.read_csv('titanic.tsv',sep='\t')
data.head()

	Survived	PassengerId	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	0	530	2	Hocking\t Mr. Richard George	male	23.0	2	1	29104	11.5000	NaN	S
1	0	466	3	Goncalves\t Mr. Manuel Estanslas	male	38.0	0	0	SOTON/O.Q. 3101306	7.0500	NaN	S
2	0	753	3	Vande Velde\t Mr. Johannes Joseph	male	33.0	0	0	345780	9.5000	NaN	S
3	0	855	2	Carter\t Mrs. Ernest Courtenay (Lilian Hughes)	female	44.0	1	0	244252	26.0000	NaN	S
4	0	333	1	Graham\t Mr. George Edward	male	38.0	0	1	PC 17582	153.4625	C91	S

data['Sex'] = data['Sex'].apply(lambda x: 1 if x=='male' else 0)
data['Name_to_num'] = data['Name'].apply(
    lambda x: 1 if 'Mr.' in x else 0
)
del data['Name']
data.head()

	Survived	PassengerId	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked	Name_to_num
0	0	530	2	1	23.0	2	1	29104	11.5000	NaN	S	1
1	0	466	3	1	38.0	0	0	SOTON/O.Q. 3101306	7.0500	NaN	S	1
2	0	753	3	1	33.0	0	0	345780	9.5000	NaN	S	1
3	0	855	2	0	44.0	1	0	244252	26.0000	NaN	S	0
4	0	333	1	1	38.0	0	1	PC 17582	153.4625	C91	S	1

data['Cabin'] = data['Cabin'].replace(np.nan,'Undefined')


vectorizer = TfidfVectorizer()
vectorizer.fit(data['Cabin'])
vector = vectorizer.transform(data['Cabin']).toarray()
vector_sum = []
for v in vector:
    vector_sum.append(v.sum())
data['Cabin']=vector_sum

data['Embarked'] = data['Embarked'].replace(np.nan,'Undefined')

data = pd.get_dummies(data,columns=['Embarked'])

imputer = SimpleImputer(missing_values=np.nan, strategy='median')
data[['Age']] = imputer.fit_transform(data[['Age']])
data['Age'].value_counts()

28.00    139
22.00     20
21.00     19
24.00     19
19.00     17
        ... 
61.00      1
70.50      1
0.75       1
10.00      1
46.00      1
Name: Age, Length: 82, dtype: int64

data['Ticket'] = data['Ticket'].replace(np.nan,'Undefined')

vectorizer = TfidfVectorizer()
vectorizer.fit(data['Ticket'])
vector = vectorizer.transform(data['Ticket']).toarray()
vector_sum = []
for v in vector:
    vector_sum.append(v.sum())
data['Ticket']=vector_sum

data.head()

	Survived	PassengerId	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Name_to_num	Embarked_C	Embarked_Q	Embarked_S	Embarked_Undefined
0	0	530	2	1	23.0	2	1	1.000000	11.5000	1.0	1	0	0	1	0
1	0	466	3	1	38.0	0	0	1.391284	7.0500	1.0	1	0	0	1	0
2	0	753	3	1	33.0	0	0	1.000000	9.5000	1.0	1	0	0	1	0
3	0	855	2	0	44.0	1	0	1.000000	26.0000	1.0	0	0	0	1	0
4	0	333	1	1	38.0	0	1	1.365721	153.4625	1.0	1	0	0	1	0