ML - 타이타닉 생존자 예측

import pandas as pd

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

titanic_url = 'titanic.xls'
titanic = pd.read_excel(titanic_url)
titanic.head()

컬럼의 의미

f, ax = plt.subplots(1,2,figsize = (12,5))
titanic['survived'].value_counts().plot.pie(ax=ax[0], autopct='%1.1f%%',shadow=True, explode=[0,0.05])
ax[0].set_title('Pie plot - Survived')
ax[0].set_ylabel('')

sns.countplot(x='survived',data=titanic, ax=ax[1])
ax[1].set_title('Count plot - Survived')

plt.show()

f, ax = plt.subplots(1,2,figsize = (12,5))

sns.countplot(x='sex',data=titanic,ax=ax[0])
ax[0].set_title('Count of passengers of sex')
ax[0].set_ylabel('')

sns.countplot(x='sex',data=titanic,hue='survived', ax=ax[1])
ax[1].set_title('Sex : survived')

plt.show()

pd.crosstab(titanic['pclass'],titanic['survived'],margins=True)

grid = sns.FacetGrid(titanic, row='pclass', col = 'sex', height = 4, aspect=2)
grid.map(plt.hist,'age', alpha=0.8,bins = 20)
grid.add_legend();

import plotly.express as px #마우스 가져가면 수치 나타내는 기능

fig = px.histogram(titanic, x='age')
fig.show()

grid = sns.FacetGrid(titanic, row='pclass', col = 'survived', height = 4, aspect=2)
grid.map(plt.hist,'age', alpha=0.5,bins = 20)
grid.add_legend();

# 구간별 정리
titanic['age_cut'] = pd.cut(titanic['age'], bins=[0,7,15,30,60,100], 
                        include_lowest=True,
                        labels=['baby','teen','young','adult','old'])
titanic.head()

plt.figure(figsize=(14,6))
plt.subplot(131) # 1행3열의 1번째
sns.barplot( x='pclass',y = 'survived',data = titanic)

plt.subplot(132) # 1행3열의 2번째
sns.barplot( x='age_cut',y = 'survived',data = titanic)
plt.subplot(133)
sns.barplot( x='sex',y = 'survived',data = titanic)
plt.show()

fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(14,6))

women = titanic[titanic['sex']=='female']
men = titanic[titanic['sex']=='male']

ax = sns.distplot(women[women['survived']==1]['age'], bins=20, label = 'survived', ax=axes[0], kde=False)
ax = sns.distplot(women[women['survived']==0]['age'], bins=40, label = 'not survived', ax=axes[0], kde=False)
ax.legend(); ax.set_title('Female')

ax = sns.distplot(men[men['survived']==1]['age'], bins=18, label = 'survived', ax=axes[1], kde=False)
ax = sns.distplot(men[men['survived']==0]['age'], bins=40, label = 'not survived', ax=axes[1], kde=False)
ax.legend(); ax.set_title('Male')

Text(0.5, 1.0, 'Male')

import re

title = []
for idx, dataset in titanic.iterrows():
    tmp = dataset['name']
    title.append(re.search('\,\s\w+(\s\w+)?\.',tmp).group()[2:-1])
titanic['title'] = title
titanic.head()

#성별별로 본 귀족
pd.crosstab(titanic['title'], titanic['sex'])

titanic['title'].unique()

array(['Miss', 'Master', 'Mr', 'Mrs', 'Col', 'Mme', 'Dr', 'Major', 'Capt',
       'Lady', 'Sir', 'Mlle', 'Dona', 'Jonkheer', 'the Countess', 'Don',
       'Rev', 'Ms'], dtype=object)

titanic['title'] = titanic['title'].replace('Mlle','Miss').replace('Ms','Miss').replace('Mme','Miss')
Rare_f = ['Dona','Lady','the Countess']
Rare_m = ['Capt','Col','Don','Major','Rev','Sir','Dr','Master','Jonkheer']

for each in Rare_f:
    titanic['title'] = titanic['title'].replace(each,'Rare_f')
for each in Rare_m:
    titanic['title'] = titanic['title'].replace(each,'Rare_m')

titanic['title'].unique()

array(['Miss', 'Rare_m', 'Mr', 'Mrs', 'Rare_f'], dtype=object)

titanic[['title','survived']].groupby(['title'],as_index=False).mean()

titanic['sex'].unique()

array(['female', 'male'], dtype=object)

import sklearn
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
titanic['gender'] = le.fit_transform(titanic['sex'])

titanic.head()

# 결측치 삭제
titanic = titanic[titanic['age'].notnull()]
titanic = titanic[titanic['fare'].notnull()]
titanic.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1045 entries, 0 to 1308
Data columns (total 17 columns):
 #   Column     Non-Null Count  Dtype   
---  ------     --------------  -----   
 0   pclass     1045 non-null   int64   
 1   survived   1045 non-null   int64   
 2   name       1045 non-null   object  
 3   sex        1045 non-null   object  
 4   age        1045 non-null   float64 
 5   sibsp      1045 non-null   int64   
 6   parch      1045 non-null   int64   
 7   ticket     1045 non-null   object  
 8   fare       1045 non-null   float64 
 9   cabin      272 non-null    object  
 10  embarked   1043 non-null   object  
 11  boat       417 non-null    object  
 12  body       119 non-null    float64 
 13  home.dest  685 non-null    object  
 14  age_cut    1045 non-null   category
 15  title      1045 non-null   object  
 16  gender     1045 non-null   int32   
dtypes: category(1), float64(3), int32(1), int64(4), object(8)
memory usage: 135.9+ KB

corr_matric = titanic.corr().round(1)
sns.heatmap(data=corr_matric,annot=True, cmap='bwr')

from sklearn.model_selection import train_test_split
X = titanic[['pclass','age','sibsp','parch','fare','gender']]
y = titanic['survived']

x_train,x_test,y_train,y_test = train_test_split(X,y, test_size = 0.8, random_state=13)

from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

dt = DecisionTreeClassifier(max_depth=4, random_state=13)
dt.fit(x_train,y_train)
pred = dt.predict(x_test)
print(accuracy_score(y_test,pred))

0.7655502392344498

# [['pclass','age','sibsp','parch','fare','gender']]
import numpy as np
dicaprio = np.array([[3,18,0,0,5,1]])
print('Decaprio: ',dt.predict_proba(dicaprio)[0,1])

Decaprio:  0.22950819672131148

winslet = np.array([[1,16,1,1,100,0]])
print('winslet: ',dt.predict_proba(winslet)[0,1])

winslet:  1.0