Kaggle Titanic by SVM

titanic.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

ds = pd.read_csv('train.csv')

# Ageの欠損値を Mr, Mrs, etc ごとの中央値で埋める
noage = ds[ ds['Age'].isna() ]
honorifics = ['Mr', 'Mrs', 'Ms', 'Miss', 'Master', 'Rev', 'Dr']
for h in honorifics:
    regexp = fr".*\b{h}\..*"
    tn1 = ds[ ds['Name'].str.match(regexp) ]
    median = tn1['Age'].median()
    #print(f"{h}: {len(tn1)}, {median}")
    hoe = noage[ noage['Name'].str.match(regexp) ]
    ds['Age'] = ds['Age'].fillna( hoe['Age'].fillna(median) )

# Sex カラムを One Hot Encode する（male カラムは除外）
ds['female'] = pd.get_dummies(ds['Sex'])['female'].values

# Sex, Age カラムのみ学習に使う
X = ds.loc[:, ['female', 'Age']]
# Survived カラム
y = ds.loc[:, ['Survived']]

# 標準化
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X = sc_X.fit_transform(X)

# 訓練データとテストデータを分割
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# Support Vector Machine
from sklearn.svm import SVC
svc = SVC()
svc.fit(X_train, y_train)

y_pred = svc.predict(X_test)

svc.score(X_test, y_test)
# 0.7988826815642458

from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))
#              precision    recall  f1-score   support
# 
#           0       0.84      0.84      0.84       110
#           1       0.74      0.74      0.74        69
# 
# avg / total       0.80      0.80      0.80       179