import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

In [2]:

data=pd.read_csv(r'../教师文件/air_data.csv')

In [3]:

data.head()

Out[3]:

	Start_time	End_time	Fare	City	Age	Flight_count	Avg_discount	Flight_mileage
0	2011/08/18	2014/03/31	5860.0	.	35.0	10	0.973129	12560
1	2011/01/13	2014/03/31	5561.0	佛山	35.0	12	0.575906	21223
2	2012/08/15	2014/03/31	1089.0	北京	33.0	9	0.635025	19246
3	2012/10/17	2014/03/31	9626.0	绍兴县	53.0	7	0.868571	14070
4	2011/09/04	2014/03/31	4473.0	上海	34.0	13	0.703419	17373

In [4]:

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15000 entries, 0 to 14999
Data columns (total 8 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Start_time      15000 non-null  object 
 1   End_time        15000 non-null  object 
 2   Fare            14989 non-null  float64
 3   City            14490 non-null  object 
 4   Age             14907 non-null  float64
 5   Flight_count    15000 non-null  int64  
 6   Avg_discount    15000 non-null  float64
 7   Flight_mileage  15000 non-null  int64  
dtypes: float64(3), int64(2), object(3)
memory usage: 937.6+ KB

In [5]:

data.describe()

Out[5]:

	Fare	Age	Flight_count	Avg_discount	Flight_mileage
count	14989.000000	14907.000000	15000.000000	15000.000000	15000.000000
mean	3761.743812	42.569531	9.057600	0.728391	12395.706800
std	2720.206579	9.807385	3.946338	0.163550	3588.357291
min	0.000000	16.000000	2.000000	0.136017	4040.000000
25%	1709.000000	35.000000	6.000000	0.625525	9747.000000
50%	3580.000000	41.000000	8.000000	0.713322	11986.500000
75%	5452.000000	48.000000	11.000000	0.803840	14654.000000
max	36602.000000	110.000000	47.000000	1.500000	50758.000000

In [6]:

data=data[data.Fare.notnull()]

In [7]:

data=data[data.Fare!=0]

In [8]:

for index,item in data.iterrows():
    s_year,s_month=item['Start_time'].split('/')[:2]
    e_year,e_month=item['End_time'].split('/')[:2]
    data.loc[index,'Months']=(int(e_year)-int(s_year))*12+(int(e_month)-int(s_month))
data=data.drop(['Start_time','End_time'],axis=1)

In [9]:

data.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 13279 entries, 0 to 14998
Data columns (total 7 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Fare            13279 non-null  float64
 1   City            12809 non-null  object 
 2   Age             13199 non-null  float64
 3   Flight_count    13279 non-null  int64  
 4   Avg_discount    13279 non-null  float64
 5   Flight_mileage  13279 non-null  int64  
 6   Months          13279 non-null  float64
dtypes: float64(4), int64(2), object(1)
memory usage: 1.3+ MB

In [10]:

data=data.drop(['City'],axis=1)
data=(data-data.mean(axis=0))/data.std(axis=0)

In [11]:

data.head()

Out[11]:

	Fare	Age	Flight_count	Avg_discount	Flight_mileage	Months
0	0.643204	-0.781959	0.191752	1.539425	0.019051	-0.616333
1	0.524036	-0.781959	0.700041	-0.935625	2.427818	-0.357005
2	-1.258303	-0.985351	-0.062393	-0.567261	1.878109	-1.060895
3	2.144162	1.048561	-0.570681	0.887939	0.438910	-1.134989
4	0.090408	-0.883655	0.954185	-0.141105	1.357317	-0.653379

In [12]:

plt.figure(figsize=(10,10))
plt.title("Pearson Correlation of Features",y=1.05,size=15)
sns.heatmap(data.astype(float).corr(),linewidths=0.1,vmax=1,square=True,cmap=plt.cm.viridis,linecolor='white',annot=True)

Out[12]:

<AxesSubplot:title={'center':'Pearson Correlation of Features'}>

In [13]:

data=data.drop(['Fare','Age'],axis=1)

In [14]:

from sklearn.cluster import KMeans

In [15]:

kmeans=KMeans(n_clusters=3).fit(data)

In [16]:

kmeans.cluster_centers_

Out[16]:

array([[-0.56475974,  0.54131875, -0.70701626, -0.56628176],
       [-0.06513412, -0.03376272, -0.10437466,  1.24214471],
       [ 0.75090493, -0.63663316,  0.95977635, -0.37662422]])

In [17]:

kmeans.labels_

Out[17]:

array([0, 2, 2, ..., 0, 0, 0])

In [18]:

from collections import defaultdict

In [28]:

label_dict=defaultdict(int)

In [29]:

for label in kmeans.labels_:
    label_dict[label] += 1

In [30]:

label_dict

Out[30]:

defaultdict(int, {0: 5287, 2: 4287, 1: 3705})

In [31]:

kmeans.cluster_centers_

Out[31]:

array([[-0.56475974,  0.54131875, -0.70701626, -0.56628176],
       [-0.06513412, -0.03376272, -0.10437466,  1.24214471],
       [ 0.75090493, -0.63663316,  0.95977635, -0.37662422]])