In [3]:

    

import numpy as np
import pandas as pd

df = pd.read_csv('diabetes.csv')
df.head() #لاستعراض ال5 السجلات الاولى من إطار البيانات


    

    
Out[3]:






  

    

      

      
Pregnancies
      
Glucose
      
BloodPressure
      
SkinThickness
      
Insulin
      
BMI
      
DiabetesPedigreeFunction
      
Age
      
Outcome
    
  
  

    

      
0
      
6
      
148
      
72
      
35
      
0
      
33.6
      
0.627
      
50
      
1
    
    

      
1
      
1
      
85
      
66
      
29
      
0
      
26.6
      
0.351
      
31
      
0
    
    

      
2
      
8
      
183
      
64
      
0
      
0
      
23.3
      
0.672
      
32
      
1
    
    

      
3
      
1
      
89
      
66
      
23
      
94
      
28.1
      
0.167
      
21
      
0
    
    

      
4
      
0
      
137
      
40
      
35
      
168
      
43.1
      
2.288
      
33
      
1
    
  

In [2]:

    

columns = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age']
labels = df['Outcome'].values
features = df[list(columns)].values


    

In [3]:

    

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.30)


    

In [4]:

    

clf = RandomForestClassifier(n_estimators=1)
clf = clf.fit(X_train, y_train)


    

In [5]:

    

accuracy = clf.score(X_train, y_train)
print accuracy*100


    

    




86.4059590317

In [6]:

    

accuracy = clf.score(X_test, y_test)
print accuracy*100


    

    




68.8311688312

In [7]:

    

from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

ypredict = clf.predict(X_train)
print '\nTraining classification report\n', classification_report(y_train, ypredict)


    

    




Training classification report
             precision    recall  f1-score   support

          0       0.88      0.91      0.90       348
          1       0.83      0.78      0.80       189

avg / total       0.86      0.86      0.86       537

In [8]:

    

print "\n Confusion matrix of training \n", confusion_matrix(y_train, ypredict)


    

    




 Confusion matrix of training 
[[317  31]
 [ 42 147]]

In [9]:

    

ypredict = clf.predict(X_test)
print '\nTraining classification report\n', classification_report(y_test, ypredict)
print "\n Confusion matrix of training \n", confusion_matrix(y_test, ypredict)


    

    




Training classification report
             precision    recall  f1-score   support

          0       0.76      0.78      0.77       152
          1       0.55      0.52      0.53        79

avg / total       0.68      0.69      0.69       231


 Confusion matrix of training 
[[118  34]
 [ 38  41]]