import pandas as pd
titanic_url = 'https://raw.githubusercontent.com/PinkWink/ML_tutorial/master/dataset/titanic.xls'
titanic = pd.read_excel(titanic_url)
f, ax = plt.subplots(1, 2, figsize=(18, 8))
titanic['survived'].value_counts().plot.pie(ax=ax[0], autopct='%1.1f%%', shadow=True, explode=[0, 0.05])
ax[0].set_title('Pie plot - servived')
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=(16, 8))
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 ')
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();
-> 3등실에는 남성이 많았다. (특히 20대 남성)
import plotly.express as px
fig = px.histogram(titanic, x='age')
fig.show()
-> 아이들 + 2~30대가 많았다.
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();
-> 선실 등급이 높으면 생존률이 높다.
titanic['age_cat'] = 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)
sns.barplot(x='pclass', y='survived', data=titanic)
plt.subplot(132)
sns.barplot(x='age_cat', y='survived', data=titanic)
plt.subplot(133)
sns.barplot(x='sex', y='survived', data=titanic)
plt.show()
-> 어리고 + 여성 + 1등실 일 수록 생존에 유리
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(14, 6))
women = titanic[titanic['sex']=='female']
men = titanic[titanic['sex']=='male']
ax = sns.displot(women[women['survived']==1]['age'], bins=20, label='survived', ax=axes[0], ked=False)
ax = sns.displot(women[women['survived']==0]['age'], bins=40, label='not survived', ax=axes[0])
ax.legend(); ax.set_title('Female')
ax = sns.displot(women[men['survived']==1]['age'], bins=18, label='survived', ax=axes[1], ked=False)
ax = sns.displot(women[men['survived']==0]['age'], bins=40, label='not survived', ax=axes[1])
ax.legend(); ax.set_title('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()
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')
titanic['title'] = titanic['title'].replace('Ms', 'Miss')
titanic['title'] = titanic['title'].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()
-> 생존률: 귀족 여성 > 평민 여성 > 귀족 남성 > 평민 남성
titanic.info()
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit(titanic['sex'])
titanic['gender'] = le.transform(titanic['sex'])
titanic.head()
titanic = titanic[titanic['age'].notnull()]
titanic = titanic[titanic['fare'].notnull()]
titanic.info()
titanic.columns
# Index(['pclass', 'survived', 'name', 'sex', 'age', 'sibsp', 'parch', 'ticket', 'fare', 'cabin', 'embarked', 'boat', 'body', 'home.dest', 'age_cat','title', 'gender'], dtype='object')
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=0.2, random_state=13)
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
dt = DecisionTreeClassifier(max_depth=2, random_state=13)
dt.fit(X_train, y_train)
pred = dt.predict(X_test)
print(accuracy_score(y_test, pred))
# 0.7559808612440191
import numpy as np
# ['pclass', 'age', 'sibsp', 'parch', 'fare', 'gender']
decaprio = np.array([[3, 18, 0, 0, 5, 1]])
print('Decaprio: ', dt.predict_proba(decaprio)[0,1])
# Decaprio: 0.1507537688442211
winslet = np.array([[1, 16, 1, 1, 100, 0]])
print('Winslet: ', dt.predict_proba(winslet)[0,1])
# Winslet: 0.9326424870466321