pandas数据预处理

import numpy as np
import pandas as pd
a=pd.read_csv("titanic_train.csv")
a.head()

age=a["Age"]
#print(age.loc[0:10])
age_is_null=pd.isnull(age)#pandas.isnull()判断是不是缺失值
#print(age_is_null)
age_null_true=age[age_is_null]#将age里的缺失值都提出来
#print(age_null_true)
age_null_count=len(age_null_true)#确定缺失值的长度
#print(age_null_count)

good_ages=a["Age"][age_is_null==False]   #去掉Age中的缺失值
#print(good_ages)
mean_good_ages=sum(good_ages)/len(good_ages)#算出去掉缺失值的平均年龄
print(mean_good_ages)
>>>
29.6991176471

correct_mean_age=a["Age"].mean()#.mean()求平均值（无视缺失值） 
print(correct_mean_age)
>>>
29.69911764705882

passenger_pclasses=[1,2,3]    #船舱有三种
pclass_by_fare={}             #定义一个空的字典，用来存船舱的平均价格
for this_class in passenger_pclasses:
    x=a[a['Pclass']==this_class]   #将全部一等舱的数据数据提取出来（循环，完了还有二等，三等）
    y=x['Fare'].mean()             #求一等舱价格的平均值
    pclass_by_fare[this_class]=y   #将一等舱及平均票价放在空字典中
print(pclass_by_fare)    

>>>
{1: 84.15468749999992, 2: 20.66218315217391, 3: 13.675550101832997}

passenger_survived=a.pivot_table(index='Pclass',values='Survived',aggfunc=np.mean)#.pivot_table(index=以什么为基中，values=以什么为判断，aggfunc=判断函数)用于统计
print(passenger_survived)#每种舱平均获救
>>>
        Survived
Pclass          
1       0.629630
2       0.472826
3       0.242363


passenger_age=a.pivot_table(index='Pclass',values='Age')#aggfunc不定义，默认求均值
print(passenger_age)#每种舱平均年龄
>>>
              Age
Pclass           
1       38.233441
2       29.877630
3       25.140620


port_stats=a.pivot_table(index='Embarked',values=['Fare','Survived'],aggfunc=np.sum)
print(port_stats)#不同港口票价总和，生存人数总和
>>>
                Fare  Survived
Embarked                      
C         10072.2962        93
Q          1022.2543        30
S         17439.3988       217

new_a=a.dropna(axis=0,subset=["Age","Sex"])#.dropna（axis=0按列，subset=去掉"Age","Sex"缺失的样本）去掉缺失值
#print(new_a)
print(len(new_a))
len(a)
>>>
714
891
  

row_index_83_age=a.loc[83,"Age"]#读取第83个样本的"Age"的值
print(row_index_83_age)
>>>
28.0

new_a2=a.sort_values("Age",ascending=False)#以"Age"为准降序，ascending=Fale升序为假，所以是降序咯
print(new_a2[0:5])

a_reindex=a.reset_index(drop=True)#更新索引值
print(a_reindex[0:5])

# This function returns the hundredth item from a series
def hundredth_row(column):
    # Extract the hundredth item
    hundredth_item = column.loc[99]
    return hundredth_item

# Return the hundredth item from each column
hundredth_row = titanic_survival.apply(hundredth_row)
print (hundredth_row)

def not_null_count(column):
    column_null = pd.isnull(column)
    null = column[column_null]
    return len(null)

column_null_count = titanic_survival.apply(not_null_count)
print (column_null_count)