2. auto-mpg 데이터 분석 || 2021.06.24

import csv
import pandas as pd

df = pd.read_csv('auto-mpg.csv', header=None)
df.columns = ['mpg','cylinders','displacemente','horepower',\
              'weight','acceleratoin','modelyear','origin','name']
print(df.head())

    mpg  cylinders  displacemente horepower  weight  acceleratoin  modelyear  \
0  18.0          8          307.0     130.0  3504.0          12.0         70   
1  15.0          8          350.0     165.0  3693.0          11.5         70   
2  18.0          8          318.0     150.0  3436.0          11.0         70   
3  16.0          8          304.0     150.0  3433.0          12.0         70   
4  17.0          8          302.0     140.0  3449.0          10.5         70   

   origin                       name  
0       1  chevrolet chevelle malibu  
1       1          buick skylark 320  
2       1         plymouth satellite  
3       1              amc rebel sst  
4       1                ford torino

print(df.corr())

                    mpg  cylinders  displacemente    weight  acceleratoin  \
mpg            1.000000  -0.775396      -0.804203 -0.831741      0.420289   
cylinders     -0.775396   1.000000       0.950721  0.896017     -0.505419   
displacemente -0.804203   0.950721       1.000000  0.932824     -0.543684   
weight        -0.831741   0.896017       0.932824  1.000000     -0.417457   
acceleratoin   0.420289  -0.505419      -0.543684 -0.417457      1.000000   
modelyear      0.579267  -0.348746      -0.370164 -0.306564      0.288137   
origin         0.563450  -0.562543      -0.609409 -0.581024      0.205873   

               modelyear    origin  
mpg             0.579267  0.563450  
cylinders      -0.348746 -0.562543  
displacemente  -0.370164 -0.609409  
weight         -0.306564 -0.581024  
acceleratoin    0.288137  0.205873  
modelyear       1.000000  0.180662  
origin          0.180662  1.000000

print(df[['mpg','weight']].corr())

             mpg    weight
mpg     1.000000 -0.831741
weight -0.831741  1.000000

df.plot(x='weight', y='mpg', kind='scatter')

df.plot(x='mpg', y='weight', kind='scatter')

df[['mpg', 'cylinders']].plot(kind='box')