notebook.community

Edit and run



In [1]:

    
import pandas as pd
import time



In [33]:

    
X = pd.read_csv('E:/Github/DAT210x-Lab/Module6/Datasets/PUC.csv', sep=';', index_col=None, decimal=',') #, , na_values='?'
X.gender = X.gender.map({'Man':0, 'Woman': 1})
X.z4 = pd.to_numeric(X.z4, errors='coerce')
X.head(5)









    



D:\anaconda\lib\site-packages\IPython\core\interactiveshell.py:2723: DtypeWarning: Columns (17) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)






    Out[33]:






  
    
      
      user
      gender
      age
      how_tall_in_meters
      weight
      body_mass_index
      x1
      y1
      z1
      x2
      y2
      z2
      x3
      y3
      z3
      x4
      y4
      z4
      class
    
  
  
    
      0
      debora
      1
      46
      1.62
      75
      28.6
      -3
      92
      -63
      -23
      18
      -19
      5
      104
      -92
      -150
      -103
      -147.0
      sitting
    
    
      1
      debora
      1
      46
      1.62
      75
      28.6
      -3
      94
      -64
      -21
      18
      -18
      -14
      104
      -90
      -149
      -104
      -145.0
      sitting
    
    
      2
      debora
      1
      46
      1.62
      75
      28.6
      -1
      97
      -61
      -12
      20
      -15
      -13
      104
      -90
      -151
      -104
      -144.0
      sitting
    
    
      3
      debora
      1
      46
      1.62
      75
      28.6
      -2
      96
      -57
      -15
      21
      -16
      -13
      104
      -89
      -153
      -103
      -142.0
      sitting
    
    
      4
      debora
      1
      46
      1.62
      75
      28.6
      -1
      96
      -61
      -13
      20
      -15
      -13
      104
      -89
      -153
      -104
      -143.0
      sitting



In [34]:

    
X.columns









    Out[34]:





Index(['user', 'gender', 'age', 'how_tall_in_meters', 'weight',
       'body_mass_index', 'x1', 'y1', 'z1', 'x2', 'y2', 'z2', 'x3', 'y3', 'z3',
       'x4', 'y4', 'z4', 'class'],
      dtype='object')



In [35]:

    
y = X['class']
y = pd.get_dummies(y)



In [36]:

    
X.drop(['class','user'], axis=1, inplace=True)
X.head(1)









    Out[36]:






  
    
      
      gender
      age
      how_tall_in_meters
      weight
      body_mass_index
      x1
      y1
      z1
      x2
      y2
      z2
      x3
      y3
      z3
      x4
      y4
      z4
    
  
  
    
      0
      1
      46
      1.62
      75
      28.6
      -3
      92
      -63
      -23
      18
      -19
      5
      104
      -92
      -150
      -103
      -147.0



In [37]:

    
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3,random_state=7)



In [ ]:



In [ ]:



In [ ]:

	user	gender	age	how_tall_in_meters	weight	body_mass_index	x1	y1	z1	x2	y2	z2	x3	y3	z3	x4	y4	z4	class
0	debora	1	46	1.62	75	28.6	-3	92	-63	-23	18	-19	5	104	-92	-150	-103	-147.0	sitting
1	debora	1	46	1.62	75	28.6	-3	94	-64	-21	18	-18	-14	104	-90	-149	-104	-145.0	sitting
2	debora	1	46	1.62	75	28.6	-1	97	-61	-12	20	-15	-13	104	-90	-151	-104	-144.0	sitting
3	debora	1	46	1.62	75	28.6	-2	96	-57	-15	21	-16	-13	104	-89	-153	-103	-142.0	sitting
4	debora	1	46	1.62	75	28.6	-1	96	-61	-13	20	-15	-13	104	-89	-153	-104	-143.0	sitting