notebook.community

Edit and run

Homework 2 - Logistic Regression Dataset

This is a clustering dataset for practicing logistic regression





In [1]:



    


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split



    











In [2]:



    


# Basic IO
filename = 'log_reg/parkinsons.data'
dataset  = pd.read_csv(filename)

# Randomize Dataset
dataset = dataset.sample(frac=1,random_state=32).reset_index()
dataset.head()



    


















    
Out[2]:











  
    

      
      index
      name
      MDVP:Fo(Hz)
      MDVP:Fhi(Hz)
      MDVP:Flo(Hz)
      MDVP:Jitter(%)
      MDVP:Jitter(Abs)
      MDVP:RAP
      MDVP:PPQ
      Jitter:DDP
      ...
      Shimmer:DDA
      NHR
      HNR
      status
      RPDE
      DFA
      spread1
      spread2
      D2
      PPE
    

  
  
    

      0
      27
      phon_R01_S06_4
      146.845
      208.701
      81.737
      0.00496
      0.000030
      0.00250
      0.00275
      0.00749
      ...
      0.02650
      0.01328
      25.119
      1
      0.358773
      0.726652
      -6.271690
      0.196102
      2.314209
      0.162999
    

    

      1
      141
      phon_R01_S34_2
      208.083
      253.792
      91.802
      0.00757
      0.000040
      0.00428
      0.00428
      0.01285
      ...
      0.12047
      0.04238
      15.648
      1
      0.606344
      0.665945
      -5.410336
      0.288917
      2.665133
      0.231723
    

    

      2
      140
      phon_R01_S34_1
      170.368
      268.796
      79.543
      0.00571
      0.000030
      0.00232
      0.00269
      0.00696
      ...
      0.05139
      0.02485
      18.540
      1
      0.677131
      0.685057
      -4.796845
      0.397749
      2.963799
      0.277227
    

    

      3
      34
      phon_R01_S07_5
      203.184
      211.526
      196.160
      0.00178
      0.000009
      0.00094
      0.00106
      0.00283
      ...
      0.01403
      0.00065
      33.047
      0
      0.340068
      0.741899
      -7.964984
      0.163519
      1.423287
      0.044539
    

    

      4
      57
      phon_R01_S16_4
      117.274
      129.916
      110.402
      0.00752
      0.000060
      0.00299
      0.00469
      0.00898
      ...
      0.03568
      0.00681
      22.817
      1
      0.530529
      0.817756
      -4.608260
      0.290024
      2.021591
      0.314464
    

  



5 rows × 25 columns



















In [3]:



    


dataset.columns



    


















    
Out[3]:








Index([u'index', u'name', u'MDVP:Fo(Hz)', u'MDVP:Fhi(Hz)', u'MDVP:Flo(Hz)',
       u'MDVP:Jitter(%)', u'MDVP:Jitter(Abs)', u'MDVP:RAP', u'MDVP:PPQ',
       u'Jitter:DDP', u'MDVP:Shimmer', u'MDVP:Shimmer(dB)', u'Shimmer:APQ3',
       u'Shimmer:APQ5', u'MDVP:APQ', u'Shimmer:DDA', u'NHR', u'HNR', u'status',
       u'RPDE', u'DFA', u'spread1', u'spread2', u'D2', u'PPE'],
      dtype='object')

















In [4]:



    


dataset.drop(['index','name'], axis=1, inplace=True)
dataset.head()



    


















    
Out[4]:











  
    

      
      MDVP:Fo(Hz)
      MDVP:Fhi(Hz)
      MDVP:Flo(Hz)
      MDVP:Jitter(%)
      MDVP:Jitter(Abs)
      MDVP:RAP
      MDVP:PPQ
      Jitter:DDP
      MDVP:Shimmer
      MDVP:Shimmer(dB)
      ...
      Shimmer:DDA
      NHR
      HNR
      status
      RPDE
      DFA
      spread1
      spread2
      D2
      PPE
    

  
  
    

      0
      146.845
      208.701
      81.737
      0.00496
      0.000030
      0.00250
      0.00275
      0.00749
      0.01919
      0.198
      ...
      0.02650
      0.01328
      25.119
      1
      0.358773
      0.726652
      -6.271690
      0.196102
      2.314209
      0.162999
    

    

      1
      208.083
      253.792
      91.802
      0.00757
      0.000040
      0.00428
      0.00428
      0.01285
      0.06725
      0.571
      ...
      0.12047
      0.04238
      15.648
      1
      0.606344
      0.665945
      -5.410336
      0.288917
      2.665133
      0.231723
    

    

      2
      170.368
      268.796
      79.543
      0.00571
      0.000030
      0.00232
      0.00269
      0.00696
      0.03273
      0.281
      ...
      0.05139
      0.02485
      18.540
      1
      0.677131
      0.685057
      -4.796845
      0.397749
      2.963799
      0.277227
    

    

      3
      203.184
      211.526
      196.160
      0.00178
      0.000009
      0.00094
      0.00106
      0.00283
      0.00958
      0.085
      ...
      0.01403
      0.00065
      33.047
      0
      0.340068
      0.741899
      -7.964984
      0.163519
      1.423287
      0.044539
    

    

      4
      117.274
      129.916
      110.402
      0.00752
      0.000060
      0.00299
      0.00469
      0.00898
      0.02293
      0.221
      ...
      0.03568
      0.00681
      22.817
      1
      0.530529
      0.817756
      -4.608260
      0.290024
      2.021591
      0.314464
    

  



5 rows × 23 columns



















In [5]:



    


# Split Into Training & Testing Sets
train, test  = train_test_split(dataset,test_size=0.30)
#train, valid = train_test_split(train, test_size=0.20)

# Write to Text Data
train.to_csv('log_reg/parkinsons_train.csv',index=False)
#train.to_csv('log_reg/valid_parkinsons.csv',index=False)
test.to_csv('log_reg/parkinsons_test.csv',index=False)



    











In [6]:



    


print 'Number of Instances Per Set'
print 'Training Set:   %d'%(len(train))
#print 'Validation Set: %d'%(len(valid))
print 'Testing Set:    %d'%(len(test))



    


















    






Number of Instances Per Set
Training Set:   136
Testing Set:    59

Content source: justiceamoh/ENGS108

Similar notebooks:

notebook.community | gallery | about