【小睿的ML之路】Pandas自定义函数（含泰坦尼克号数据分析案例实战）

import pandas as pd

titanic_survival = pd.read_csv("titanic_train.csv")

# 返回第一百行数据
def hundredth_row(column):
    hundredth_item = column.loc[99]
    return hundredth_item

row = titanic_survival.apply(hundredth_row) # 调用自定义的函数
print(row)

PassengerId 100
Survived 0
Pclass 2
Name Kantor, Mr. Sinai
Sex male
Age 34.0
SibSp 1
Parch 0
Ticket 244367
Fare 26.0
Cabin NaN
Embarked S
dtype: object

def null_count(column): # 计算每列缺失值的数量
    column_null = pd.isnull(column)
    null = column[column_null]
    return len(null)

column_null_count = titanic_survival.apply(null_count) # 调用自定义的函数
print(column_null_count)

PassengerId 0
Survived 0
Pclass 0
Name 0
Sex 0
Age 177
SibSp 0
Parch 0
Ticket 0
Fare 0
Cabin 687
Embarked 2
dtype: int64

def which_class(row): # 替换列的值
    pclass = row['Pclass']
    if pd.isnull(pclass):
        return 'Unknow'
    elif pclass == 1:
        return 'First Class'
    elif pclass == 2:
        return 'Second Class'
    elif pclass == 3:
        return 'Third Class'
    
classes = titanic_survival.apply(which_class, axis=1) # 调用自定义的函数
print(classes)

0 Third Class
1 First Class
2 Third Class
3 First Class
4 Third Class
...
886 Second Class
887 First Class
888 Third Class
889 First Class
890 Third Class
Length: 891, dtype: object

titanic_survival['pclass_labels'] = classes
pclass_group_survival = titanic_survival.pivot_table(index="pclass_labels",values="Survived") # 统计不同舱位获救人数比例
print(pclass_group_survival)

Survived
pclass_labels
First Class 0.629630
Second Class 0.472826
Third Class 0.242363

# 可以看出，头等舱的获救比例较高，三等舱的获救比例相对较低。这符合常识，因为头等舱往往提供更好的设施和服务，可能在遇到危险时更有利于获救。