Task2–数据分析

EDA目标

• EDA的价值在于熟悉数据集，了解数据集
• 了解数据集之后更好地进行特征工程，使预测的问题更加可靠
• 完成对于数据的探索性分析，并对于数据进行一些图表或者文字总结并打卡

2.1： 载入各种数据科学以及可视化库

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import missingno as msno # 缺失值可视化处理包
# 导入warnings包，利用过滤器来实现忽略警告语句
import warnings
warnings.filterwarnings('ignore')

2.2：载入数据

Train_data = pd.read_csv('/Users/admin/Desktop/used_car_train_20200313.csv', sep=' ')
Test_data = pd.read_csv('/Users/admin/Desktop/used_car_testA_20200313.csv', sep=' ')

# 简略检查数据
Train_data.head().append(Train_data.tail())

10 rows × 31 columns

Train_data.shape

(150000, 31)

Test_data.head().append(Test_data.tail())

10 rows × 30 columns

Test_data.shape

(50000, 30)

2.3：数据总览

Train_data.describe()

8 rows × 30 columns

Test_data.describe()

8 rows × 29 columns

Train_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150000 entries, 0 to 149999
Data columns (total 31 columns):
 #   Column             Non-Null Count   Dtype  
---  ------             --------------   -----  
 0   SaleID             150000 non-null  int64  
 1   name               150000 non-null  int64  
 2   regDate            150000 non-null  int64  
 3   model              149999 non-null  float64
 4   brand              150000 non-null  int64  
 5   bodyType           145494 non-null  float64
 6   fuelType           141320 non-null  float64
 7   gearbox            144019 non-null  float64
 8   power              150000 non-null  int64  
 9   kilometer          150000 non-null  float64
 10  notRepairedDamage  150000 non-null  object 
 11  regionCode         150000 non-null  int64  
 12  seller             150000 non-null  int64  
 13  offerType          150000 non-null  int64  
 14  creatDate          150000 non-null  int64  
 15  price              150000 non-null  int64  
 16  v_0                150000 non-null  float64
 17  v_1                150000 non-null  float64
 18  v_2                150000 non-null  float64
 19  v_3                150000 non-null  float64
 20  v_4                150000 non-null  float64
 21  v_5                150000 non-null  float64
 22  v_6                150000 non-null  float64
 23  v_7                150000 non-null  float64
 24  v_8                150000 non-null  float64
 25  v_9                150000 non-null  float64
 26  v_10               150000 non-null  float64
 27  v_11               150000 non-null  float64
 28  v_12               150000 non-null  float64
 29  v_13               150000 non-null  float64
 30  v_14               150000 non-null  float64
dtypes: float64(20), int64(10), object(1)
memory usage: 35.5+ MB

Test_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 50000 entries, 0 to 49999
Data columns (total 30 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   SaleID             50000 non-null  int64  
 1   name               50000 non-null  int64  
 2   regDate            50000 non-null  int64  
 3   model              50000 non-null  float64
 4   brand              50000 non-null  int64  
 5   bodyType           48587 non-null  float64
 6   fuelType           47107 non-null  float64
 7   gearbox            48090 non-null  float64
 8   power              50000 non-null  int64  
 9   kilometer          50000 non-null  float64
 10  notRepairedDamage  50000 non-null  object 
 11  regionCode         50000 non-null  int64  
 12  seller             50000 non-null  int64  
 13  offerType          50000 non-null  int64  
 14  creatDate          50000 non-null  int64  
 15  v_0                50000 non-null  float64
 16  v_1                50000 non-null  float64
 17  v_2                50000 non-null  float64
 18  v_3                50000 non-null  float64
 19  v_4                50000 non-null  float64
 20  v_5                50000 non-null  float64
 21  v_6                50000 non-null  float64
 22  v_7                50000 non-null  float64
 23  v_8                50000 non-null  float64
 24  v_9                50000 non-null  float64
 25  v_10               50000 non-null  float64
 26  v_11               50000 non-null  float64
 27  v_12               50000 non-null  float64
 28  v_13               50000 non-null  float64
 29  v_14               50000 non-null  float64
dtypes: float64(20), int64(9), object(1)
memory usage: 11.4+ MB

2.4：判断数据缺失和异常

2.4.1：缺失值

Train_data.isnull().sum()

SaleID                  0
name                    0
regDate                 0
model                   1
brand                   0
bodyType             4506
fuelType             8680
gearbox              5981
power                   0
kilometer               0
notRepairedDamage       0
regionCode              0
seller                  0
offerType               0
creatDate               0
price                   0
v_0                     0
v_1                     0
v_2                     0
v_3                     0
v_4                     0
v_5                     0
v_6                     0
v_7                     0
v_8                     0
v_9                     0
v_10                    0
v_11                    0
v_12                    0
v_13                    0
v_14                    0
dtype: int64

# nan可视化
missing = Train_data.isnull().sum()
missing = missing[missing > 0]
missing.sort_values(inplace=True)
missing.plot.bar()

<matplotlib.axes._subplots.AxesSubplot at 0x245a26c4ef0>

# 可视化看下缺省值
msno.bar(Train_data.sample(1000))

<matplotlib.axes._subplots.AxesSubplot at 0x245a26c4ef0>

Test_data.isnull().sum()

SaleID                  0
name                    0
regDate                 0
model                   0
brand                   0
bodyType             1413
fuelType             2893
gearbox              1910
power                   0
kilometer               0
notRepairedDamage       0
regionCode              0
seller                  0
offerType               0
creatDate               0
v_0                     0
v_1                     0
v_2                     0
v_3                     0
v_4                     0
v_5                     0
v_6                     0
v_7                     0
v_8                     0
v_9                     0
v_10                    0
v_11                    0
v_12                    0
v_13                    0
v_14                    0
dtype: int64

missing = Test_data.isnull().sum()
missing = missing[missing > 0]
missing.sort_values(inplace=True)
missing.plot.bar()

<matplotlib.axes._subplots.AxesSubplot at 0x245a2b10d68>

msno.bar(Test_data.sample(1000))

<matplotlib.axes._subplots.AxesSubplot at 0x245a2b10d68>

2.4.2：异常值

Train_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150000 entries, 0 to 149999
Data columns (total 31 columns):
 #   Column             Non-Null Count   Dtype  
---  ------             --------------   -----  
 0   SaleID             150000 non-null  int64  
 1   name               150000 non-null  int64  
 2   regDate            150000 non-null  int64  
 3   model              149999 non-null  float64
 4   brand              150000 non-null  int64  
 5   bodyType           145494 non-null  float64
 6   fuelType           141320 non-null  float64
 7   gearbox            144019 non-null  float64
 8   power              150000 non-null  int64  
 9   kilometer          150000 non-null  float64
 10  notRepairedDamage  150000 non-null  object 
 11  regionCode         150000 non-null  int64  
 12  seller             150000 non-null  int64  
 13  offerType          150000 non-null  int64  
 14  creatDate          150000 non-null  int64  
 15  price              150000 non-null  int64  
 16  v_0                150000 non-null  float64
 17  v_1                150000 non-null  float64
 18  v_2                150000 non-null  float64
 19  v_3                150000 non-null  float64
 20  v_4                150000 non-null  float64
 21  v_5                150000 non-null  float64
 22  v_6                150000 non-null  float64
 23  v_7                150000 non-null  float64
 24  v_8                150000 non-null  float64
 25  v_9                150000 non-null  float64
 26  v_10               150000 non-null  float64
 27  v_11               150000 non-null  float64
 28  v_12               150000 non-null  float64
 29  v_13               150000 non-null  float64
 30  v_14               150000 non-null  float64
dtypes: float64(20), int64(10), object(1)
memory usage: 35.5+ MB

Train_data['notRepairedDamage'].value_counts()

0.0    111361
-       24324
1.0     14315
Name: notRepairedDamage, dtype: int64

Train_data['notRepairedDamage'].replace('-', np.nan, inplace=True)

Train_data['notRepairedDamage'].replace('-', np.nan, inplace=True)

Train_data['notRepairedDamage'].replace('-', np.nan, inplace=True)

2.5：了解预测值的分布

Train_data['price']

0         1850
1         3600
2         6222
3         2400
4         5200
          ... 
149995    5900
149996    9500
149997    7500
149998    4999
149999    4700
Name: price, Length: 150000, dtype: int64

Train_data['price'].value_counts()

500      2337
1500     2158
1200     1922
1000     1850
2500     1821
         ... 
25321       1
8886        1
8801        1
37920       1
8188        1
Name: price, Length: 3763, dtype: int64

## 1) 总体分布概况（无界约翰逊分布等）
import scipy.stats as st
y = Train_data['price']
plt.figure(1); plt.title('Johnson SU')
sns.distplot(y, kde=False, fit=st.johnsonsu)
plt.figure(2); plt.title('Normal')
sns.distplot(y, kde=False, fit=st.norm)
plt.figure(3); plt.title('Log Normal')
sns.distplot(y, kde=False, fit=st.lognorm)

<matplotlib.axes._subplots.AxesSubplot at 0x245a2d78a90>

## 2) 查看skewness and kurtosis
sns.distplot(Train_data['price']);
print("Skewness: %f" % Train_data['price'].skew())
print("Kurtosis: %f" % Train_data['price'].kurt())

Skewness: 3.346487
Kurtosis: 18.995183

sns.distplot(Train_data.kurt(),color='orange',axlabel ='Kurtness')

<matplotlib.axes._subplots.AxesSubplot at 0x245a2d78a90>

# log变换 z之后的分布较均匀，可以进行log变换进行预测，这也是预测问题常用的trick
plt.hist(np.log(Train_data['price']), orientation = 'vertical',histtype = 'bar', color ='red') 
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-w6mWCoZv-1584979187920)(output_36_0.png)]

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-8GOAmLOZ-1584979187922)(output_36_1.png)]

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-u1bpR7Ce-1584979187923)(output_36_2.png)]