[Kaggle] Biking Sharing Demand 데이터분석 연습

In [ ]:

import pandas as pd
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats

%matplotlib inline

plt.style.use('ggplot')
mpl.rcParams['axes.unicode_minus'] = False

In [10]:

train = pd.read_csv('train.csv', parse_dates=['datetime'])
train.shape

Out[10]:

(10886, 12)

In [11]:

train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10886 entries, 0 to 10885
Data columns (total 12 columns):
datetime      10886 non-null datetime64[ns]
season        10886 non-null int64
holiday       10886 non-null int64
workingday    10886 non-null int64
weather       10886 non-null int64
temp          10886 non-null float64
atemp         10886 non-null float64
humidity      10886 non-null int64
windspeed     10886 non-null float64
casual        10886 non-null int64
registered    10886 non-null int64
count         10886 non-null int64
dtypes: datetime64[ns](1), float64(3), int64(8)
memory usage: 1020.6 KB

In [14]:

train.head(20)

Out[14]:

	datetime	season	holiday	workingday	weather	temp	atemp	humidity	windspeed	casual	registered	count
0	2011-01-01 00:00:00	1	0	0	1	9.84	14.395	81	0.0000	3	13	16
1	2011-01-01 01:00:00	1	0	0	1	9.02	13.635	80	0.0000	8	32	40
2	2011-01-01 02:00:00	1	0	0	1	9.02	13.635	80	0.0000	5	27	32
3	2011-01-01 03:00:00	1	0	0	1	9.84	14.395	75	0.0000	3	10	13
4	2011-01-01 04:00:00	1	0	0	1	9.84	14.395	75	0.0000	0	1	1
5	2011-01-01 05:00:00	1	0	0	2	9.84	12.880	75	6.0032	0	1	1
6	2011-01-01 06:00:00	1	0	0	1	9.02	13.635	80	0.0000	2	0	2
7	2011-01-01 07:00:00	1	0	0	1	8.20	12.880	86	0.0000	1	2	3
8	2011-01-01 08:00:00	1	0	0	1	9.84	14.395	75	0.0000	1	7	8
9	2011-01-01 09:00:00	1	0	0	1	13.12	17.425	76	0.0000	8	6	14
10	2011-01-01 10:00:00	1	0	0	1	15.58	19.695	76	16.9979	12	24	36
11	2011-01-01 11:00:00	1	0	0	1	14.76	16.665	81	19.0012	26	30	56
12	2011-01-01 12:00:00	1	0	0	1	17.22	21.210	77	19.0012	29	55	84
13	2011-01-01 13:00:00	1	0	0	2	18.86	22.725	72	19.9995	47	47	94
14	2011-01-01 14:00:00	1	0	0	2	18.86	22.725	72	19.0012	35	71	106
15	2011-01-01 15:00:00	1	0	0	2	18.04	21.970	77	19.9995	40	70	110
16	2011-01-01 16:00:00	1	0	0	2	17.22	21.210	82	19.9995	41	52	93
17	2011-01-01 17:00:00	1	0	0	2	18.04	21.970	82	19.0012	15	52	67
18	2011-01-01 18:00:00	1	0	0	3	17.22	21.210	88	16.9979	9	26	35
19	2011-01-01 19:00:00	1	0	0	3	17.22	21.210	88	16.9979	6	31	37

In [13]:

train.temp.describe()

Out[13]:

count    10886.00000
mean        20.23086
std          7.79159
min          0.82000
25%         13.94000
50%         20.50000
75%         26.24000
max         41.00000
Name: temp, dtype: float64

In [17]:

train.isnull().sum()

Out[17]:

datetime      0
season        0
holiday       0
workingday    0
weather       0
temp          0
atemp         0
humidity      0
windspeed     0
casual        0
registered    0
count         0
dtype: int64

In [58]:

corrMatt = train[["temp", "atemp", "casual","registered","humidity","windspeed","count"]]
corrMatt = corrMatt.corr()
print(corrMatt)

mask = np.array(corrMatt)
mask[np.tril_indices_from(mask)] = False

                temp     atemp    casual  registered  humidity  windspeed  \
temp        1.000000  0.984948  0.467097    0.318571 -0.064949  -0.017852   
atemp       0.984948  1.000000  0.462067    0.314635 -0.043536  -0.057473   
casual      0.467097  0.462067  1.000000    0.497250 -0.348187   0.092276   
registered  0.318571  0.314635  0.497250    1.000000 -0.265458   0.091052   
humidity   -0.064949 -0.043536 -0.348187   -0.265458  1.000000  -0.318607   
windspeed  -0.017852 -0.057473  0.092276    0.091052 -0.318607   1.000000   
count       0.394454  0.389784  0.690414    0.970948 -0.317371   0.101369   

               count  
temp        0.394454  
atemp       0.389784  
casual      0.690414  
registered  0.970948  
humidity   -0.317371  
windspeed   0.101369  
count       1.000000  

In [64]:

fig, ax = plt.subplots()
fig.set_size_inches(20,10)
sns.heatmap(corrMatt, mask=mask, vmax=.8, square=True, annot=True)

Out[64]:

<matplotlib.axes._subplots.AxesSubplot at 0x241d8f77588>