notebook.community

Edit and run 





In [1]:



    


import pandas as pd
pd.set_option('precision', 2) # 2 decimal places
pd.set_option('display.max_rows', 20)
pd.set_option('display.max_columns', 30)
pd.set_option('display.width', 100) # wide windows



import sklearn
from sklearn.datasets import load_iris
iris = load_iris()

# Extract numpy arrays
X = iris.data 
y = iris.target


# Convert to pandas dataframe 
df = pd.DataFrame(data=X, columns=['sl', 'sw', 'pl', 'pw'])
# create column for labels
df['label'] = pd.Series(iris.target_names[y], dtype='category')



    











In [2]:



    


df



    


















    
Out[2]:











  
    

      
      sl
      sw
      pl
      pw
      label
    

  
  
    

      0
      5.1
      3.5
      1.4
      0.2
      setosa
    

    

      1
      4.9
      3.0
      1.4
      0.2
      setosa
    

    

      2
      4.7
      3.2
      1.3
      0.2
      setosa
    

    

      3
      4.6
      3.1
      1.5
      0.2
      setosa
    

    

      4
      5.0
      3.6
      1.4
      0.2
      setosa
    

    

      5
      5.4
      3.9
      1.7
      0.4
      setosa
    

    

      6
      4.6
      3.4
      1.4
      0.3
      setosa
    

    

      7
      5.0
      3.4
      1.5
      0.2
      setosa
    

    

      8
      4.4
      2.9
      1.4
      0.2
      setosa
    

    

      9
      4.9
      3.1
      1.5
      0.1
      setosa
    

    

      ...
      ...
      ...
      ...
      ...
      ...
    

    

      140
      6.7
      3.1
      5.6
      2.4
      virginica
    

    

      141
      6.9
      3.1
      5.1
      2.3
      virginica
    

    

      142
      5.8
      2.7
      5.1
      1.9
      virginica
    

    

      143
      6.8
      3.2
      5.9
      2.3
      virginica
    

    

      144
      6.7
      3.3
      5.7
      2.5
      virginica
    

    

      145
      6.7
      3.0
      5.2
      2.3
      virginica
    

    

      146
      6.3
      2.5
      5.0
      1.9
      virginica
    

    

      147
      6.5
      3.0
      5.2
      2.0
      virginica
    

    

      148
      6.2
      3.4
      5.4
      2.3
      virginica
    

    

      149
      5.9
      3.0
      5.1
      1.8
      virginica
    

  



150 rows × 5 columns



















In [3]:



    


url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data'
# We made a cached copy since UCI repository is often down
#url = 'https://raw.githubusercontent.com/probml/pyprobml/master/data/mpg.csv'
#column_names = ['mpg','cylinders','displacement','horsepower','weight',
#                'acceleration', 'model_year', 'origin', 'name'] 
column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight',
                'Acceleration', 'Year', 'Origin', 'Name']
df = pd.read_csv(url, names=column_names, sep='\s+', na_values="?")

# The last column (name) is a unique id for the car, so we drop it
df = df.drop(columns=['Name'])



    











In [4]:



    


df



    


















    
Out[4]:











  
    

      
      MPG
      Cylinders
      Displacement
      Horsepower
      Weight
      Acceleration
      Year
      Origin
    

  
  
    

      0
      18.0
      8
      307.0
      130.0
      3504.0
      12.0
      70
      1
    

    

      1
      15.0
      8
      350.0
      165.0
      3693.0
      11.5
      70
      1
    

    

      2
      18.0
      8
      318.0
      150.0
      3436.0
      11.0
      70
      1
    

    

      3
      16.0
      8
      304.0
      150.0
      3433.0
      12.0
      70
      1
    

    

      4
      17.0
      8
      302.0
      140.0
      3449.0
      10.5
      70
      1
    

    

      5
      15.0
      8
      429.0
      198.0
      4341.0
      10.0
      70
      1
    

    

      6
      14.0
      8
      454.0
      220.0
      4354.0
      9.0
      70
      1
    

    

      7
      14.0
      8
      440.0
      215.0
      4312.0
      8.5
      70
      1
    

    

      8
      14.0
      8
      455.0
      225.0
      4425.0
      10.0
      70
      1
    

    

      9
      15.0
      8
      390.0
      190.0
      3850.0
      8.5
      70
      1
    

    

      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    

    

      388
      26.0
      4
      156.0
      92.0
      2585.0
      14.5
      82
      1
    

    

      389
      22.0
      6
      232.0
      112.0
      2835.0
      14.7
      82
      1
    

    

      390
      32.0
      4
      144.0
      96.0
      2665.0
      13.9
      82
      3
    

    

      391
      36.0
      4
      135.0
      84.0
      2370.0
      13.0
      82
      1
    

    

      392
      27.0
      4
      151.0
      90.0
      2950.0
      17.3
      82
      1
    

    

      393
      27.0
      4
      140.0
      86.0
      2790.0
      15.6
      82
      1
    

    

      394
      44.0
      4
      97.0
      52.0
      2130.0
      24.6
      82
      2
    

    

      395
      32.0
      4
      135.0
      84.0
      2295.0
      11.6
      82
      1
    

    

      396
      28.0
      4
      120.0
      79.0
      2625.0
      18.6
      82
      1
    

    

      397
      31.0
      4
      119.0
      82.0
      2720.0
      19.4
      82
      1
    

  



398 rows × 8 columns



















In [ ]:

Content source: probml/pyprobml

Similar notebooks:

notebook.community | gallery | about