Python数据分析招式：pandas库提取清洗排序-1

要点：

• 数据的基本处理
• 数据的提取
• 数据的初步清洗
• 数据的排序

泰坦尼克数据集下载地址： 地址1（需要注册）： https://www.kaggle.com/c/titanic/data 地址2（百度网盘）： https://pan.baidu.com/s/1Vp0QmVLu43_Hb9jHR2FKXg 密码: rdfr

导入数据

# -*- coding: utf-8 -*-

# @File    : 泰坦尼克数据分析.py
# @Date    : 2018-06-03

import numpy as np
import pandas as pd

file = "data/train.csv"
df = pd.DataFrame(pd.read_csv(file))

1、数据的基本处理

#  形状
print(df.shape)
# (891, 12)

# 查看前3行
print(df.head(3))
"""
   PassengerId  Survived  Pclass    ...        Fare Cabin  Embarked
0            1         0       3    ...      7.2500   NaN         S
1            2         1       1    ...     71.2833   C85         C
2            3         1       3    ...      7.9250   NaN         S

[3 rows x 12 columns]
"""

# 查看后3行
print(df.tail(3))
"""
     PassengerId  Survived  Pclass    ...      Fare Cabin  Embarked
888          889         0       3    ...     23.45   NaN         S
889          890         1       1    ...     30.00  C148         C
890          891         0       3    ...      7.75   NaN         Q

[3 rows x 12 columns]
"""

# 信息
print(df.info())
"""

RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB
None
"""

# 整体描述
print(df.describe())
"""
      PassengerId    Survived     ...           Parch        Fare
count   891.000000  891.000000     ...      891.000000  891.000000
mean    446.000000    0.383838     ...        0.381594   32.204208
std     257.353842    0.486592     ...        0.806057   49.693429
min       1.000000    0.000000     ...        0.000000    0.000000
25%     223.500000    0.000000     ...        0.000000    7.910400
50%     446.000000    0.000000     ...        0.000000   14.454200
75%     668.500000    1.000000     ...        0.000000   31.000000
max     891.000000    1.000000     ...        6.000000  512.329200

[8 rows x 7 columns]
"""

# 查看数据集的空值
print(df.isnull().sum())
"""
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
"""

# 唯一值
print(df["Pclass"].unique())
# [3 1 2]

2、数据的提取

# 按照索引的值提取数据
print(df.loc[630])
"""
PassengerId                                     631
Survived                                          1
Pclass                                            1
Name           Barkworth, Mr. Algernon Henry Wilson
Sex                                            male
Age                                              80
SibSp                                             0
Parch                                             0
Ticket                                        27042
Fare                                             30
Cabin                                           A23
Embarked                                          S
Name: 630, dtype: object
"""

# 取部分行和列 第二三四行和前5列
print(df.iloc[2:5, :5])
"""
   PassengerId   ...       Sex
2            3   ...    female
3            4   ...    female
4            5   ...      male

[3 rows x 5 columns]
"""

# 照条件提取  仓位为小于2的，并且性别为女性的数据
print(df[(df["Pclass"]int
print(ret.dtypes) # int32

# 更改列的名字
ret = df.rename(columns={'Survived':'是否获救'})
print(ret.head(3))
"""
   PassengerId  是否获救 Pclass    ...        Fare Cabin  Embarked
0            1     0    三等舱    ...      7.2500   NaN         S
1            2     1    一等舱    ...     71.2833   C85         C
2            3     1    三等舱    ...      7.9250   NaN         S

[3 rows x 12 columns]
"""

# 去掉重复值
# #比如我们想知道登船的类别，去掉所有重复的数据
ret = df['Embarked'].drop_duplicates()
print(ret)
"""
0       S
1       C
5       Q
61    NaN
Name: Embarked, dtype: object
"""

# 数据的代替,替换
df['Sex']=df['Sex'].replace('male','男')
print(df["Sex"].head(3))
"""
0         男
1    female
2    female
Name: Sex, dtype: object
"""

4、数据的排序

# 按照年龄进行降序排列
print(df.sort_values(by=['Age'],ascending=False)["Age"].head(3))
"""
630    80.0
851    74.0
493    71.0
Name: Age, dtype: float64
"""
# 按照index来排序
print(df.sort_index(ascending=False).head(3))
"""
     PassengerId  Survived Pclass    ...      Fare Cabin  Embarked
890          891         0    三等舱    ...      7.75   NaN         Q
889          890         1    一等舱    ...     30.00  C148         C
888          889         0    三等舱    ...     23.45   NaN         S
"""

参考文章： 18招，小白必看的数据分析招式|精选上篇