匯入模組

import numpy as np
import pandas as pd
%matplotlib inline

匯入資料

train = pd.read_csv("./train.csv")
test = pd.read_csv("./test.csv")

檢視資料

train.head()

print("train data shape:",train.shape)
print("test data shape:",test.shape)

檢視資料空值

train.isnull().sum()

# 用年齡中位數填充表中未知年齡的資料
train.Age.fillna(train.Age.median(),inplace=True)
 

嘗試從性別角度進行生存率分析

train.Sex.value_counts()

# 生還者中，男女的人數
survived = train[train.Survived==1].Sex.value_counts()

# 未生還者中，男女的人數
dead = train[train.Survived==0].Sex.value_counts()

df = pd.DataFrame([survived,dead],index=["survived","dead"])

繪製柱狀圖

df.plot.bar()

繪製生存率百分比圖

df['p_survived'] = df.survived / (df.survived + df.dead)
df['p_dead'] = df.dead / (df.survived + df.dead)
 

df[['p_survived','p_dead']].plot.bar(stacked=True)

分析年齡對生存率影響

survived = train[train.Survived==1].Age
dead = train[train.Survived==0].Age
df = pd.DataFrame([survived,dead],index=["survived","dead"])
df = df.T
df.plot.hist(stacked=True)

繪製密度圖

# 密度圖
df.plot.kde(xlim=(0,80))