In [33]:

import numpy as np
import pandas as pd

from sklearn.model_selection import train_test_split, GridSearchCV

from sklearn.compose import ColumnTransformer

from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.linear_model import LogisticRegression

In [34]:
df = pd.read_csv('train.csv')

In [35]:
df.head()

Out[35]: PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket

Braund,
0 1 0 3 Mr. Owen male 22.0 1 0 A/5 21171
Harris

Cumings,
Mrs. John
Bradley
1 2 1 1 female 38.0 1 0 PC 17599
(Florence
Briggs
Th...

Heikkinen,
STON/O2.
2 3 1 3 Miss. female 26.0 0 0
3101282
Laina

Futrelle,
Mrs.
Jacques
3 4 1 1 female 35.0 1 0 113803
Heath
(Lily May
Peel)

Allen, Mr.
4 5 0 3 William male 35.0 0 0 373450
Henry

In [36]:
df.drop(columns=['PassengerId','Name','Ticket','Cabin'],inplace=True)

In [37]:
df.head()
Out[37]: Survived Pclass Sex Age SibSp Parch Fare Embarked

0 0 3 male 22.0 1 0 7.2500 S

1 1 1 female 38.0 1 0 71.2833 C

2 1 3 female 26.0 0 0 7.9250 S

3 1 1 female 35.0 1 0 53.1000 S

4 0 3 male 35.0 0 0 8.0500 S

In [38]:
X = df.drop(columns=['Survived'])
y = df['Survived']

In [39]:
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_stat

In [40]:
X_train.head()

Out[40]: Pclass Sex Age SibSp Parch Fare Embarked

30 1 male 40.0 0 0 27.7208 C

10 3 female 4.0 1 1 16.7000 S

873 3 male 47.0 0 0 9.0000 S

182 3 male 9.0 4 2 31.3875 S

876 3 male 20.0 0 0 9.8458 S

In [41]:
numerical_features = ['Age', 'Fare']
numerical_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='median')),
('scaler', StandardScaler())
])

categorical_features = ['Embarked', 'Sex']

categorical_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='most_frequent')),
('ohe',OneHotEncoder(handle_unknown='ignore'))
])

In [42]:
preprocessor = ColumnTransformer(
transformers=[
('num', numerical_transformer, numerical_features),
('cat', categorical_transformer, categorical_features)
]
)

In [43]:
clf = Pipeline(steps=[
('preprocessor', preprocessor),
 ('classifier', LogisticRegression())
])

In [21]:
from sklearn import set_config

set_config(display='diagram')
clf

Out[21]: Pipeline
Pipeline(steps=[('preprocessor',
ColumnTransformer(transformers=[('num',
Pipeline(steps=
[('imputer',

SimpleImputer(strategy='median')),

('scaler',

StandardScaler())]),
['Age', 'Far
e']),
('cat',
Pipeline(steps=
[('imputer',

SimpleImputer(strategy='most_frequent')),

('ohe',

OneHotEncoder(handle_unknown='ignore'))]),
['Embarked', 'S
ex'])])),
('classifier', LogisticRegression())])
preprocessor: ColumnTransformer
ColumnTransformer(transformers=[('num',
Pipeline(steps=[('imputer',
SimpleImputer(s
trategy='median')),
('scaler', Stand
ardScaler())]),
['Age', 'Fare']),
('cat',
Pipeline(steps=[('imputer',
SimpleImputer(s
trategy='most_frequent')),
('ohe',
OneHotEncoder(h
andle_unknown='ignore'))]),
['Embarked', 'Sex'])])
num
['Age', 'Fare']
SimpleImputer
 SimpleImputer(strategy='median')
StandardScaler
StandardScaler()
cat
['Embarked', 'Sex']
SimpleImputer
SimpleImputer(strategy='most_frequent')
OneHotEncoder
OneHotEncoder(handle_unknown='ignore')
LogisticRegression
LogisticRegression()

In [44]:
param_grid = {
'preprocessor__num__imputer__strategy': ['mean', 'median'],
'preprocessor__cat__imputer__strategy': ['most_frequent', 'constant'],
'classifier__C': [0.1, 1.0, 10, 100]
}

grid_search = GridSearchCV(clf, param_grid, cv=10)

In [45]:
grid_search.fit(X_train, y_train)

print(f"Best params:")
print(grid_search.best_params_)

Best params:
{'classifier__C': 1.0, 'preprocessor__cat__imputer__strategy': 'most_frequ
ent', 'preprocessor__num__imputer__strategy': 'mean'}

In [26]:
print(f"Internal CV score: {grid_search.best_score_:.3f}")

Internal CV score: 0.788

In [46]:
import pandas as pd

cv_results = pd.DataFrame(grid_search.cv_results_)
cv_results = cv_results.sort_values("mean_test_score", ascending=False)
cv_results[['param_classifier__C','param_preprocessor__cat__imputer__strategy'
Out[46]: param_classifier__C param_preprocessor__cat__imputer__strategy param_preprocess

4 1 most_frequent

5 1 most_frequent

6 1 constant

7 1 constant

8 10 most_frequent

9 10 most_frequent

10 10 constant

11 10 constant

12 100 most_frequent

13 100 most_frequent

14 100 constant

15 100 constant

0 0.1 most_frequent

1 0.1 most_frequent

2 0.1 constant

3 0.1 constant

In [ ]: