In [14]:

    

import numpy as np
import urllib.request
# url with dataset
url = "http://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes/pima-indians-diabetes.data"
# download the file
raw_data = urllib.request.urlopen(url)
# load the CSV file as a numpy matrix
dataset = np.loadtxt(raw_data, delimiter=",")
# separate the data from the target attributes
X = dataset[:,0:8]
y = dataset[:,8]
print("size:",len(dataset))
print("X: ",X[0])
print("y: ",y[0])


    

    




size: 768
X:  [   6.     148.      72.      35.       0.      33.6      0.627   50.   ]
y:  1.0

In [10]:

    

from sklearn import preprocessing
# standardize the data attributes
standardized_X = preprocessing.scale(X)
# normalize the data attributes
normalized_X = preprocessing.normalize(X)


    

In [11]:

    

from sklearn import metrics
from sklearn.ensemble import ExtraTreesClassifier
model = ExtraTreesClassifier()
model.fit(X, y)
# display the relative importance of each attribute
print(model.feature_importances_)


    

    




[ 0.11193263  0.26076795  0.10153987  0.08278266  0.07190955  0.12292174
  0.11527441  0.13287119]

In [12]:

    

from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
# create the RFE model and select 3 attributes
rfe = RFE(model, 3)
rfe = rfe.fit(X, y)
# summarize the selection of the attributes
print(rfe.support_)
print(rfe.ranking_)


    

    




[ True False False False False  True  True False]
[1 2 3 5 6 1 1 4]

In [13]:

    

from sklearn import metrics
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(X, y)
print(model)
# make predictions
expected = y
predicted = model.predict(X)
# summarize the fit of the model
print(metrics.classification_report(expected, predicted))
print(metrics.confusion_matrix(expected, predicted))


    

    




LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)
             precision    recall  f1-score   support

        0.0       0.79      0.90      0.84       500
        1.0       0.74      0.55      0.63       268

avg / total       0.77      0.77      0.77       768

[[448  52]
 [121 147]]

In [18]:

    

from sklearn import metrics
from sklearn.naive_bayes import GaussianNB
model = GaussianNB()
model.fit(X, y)
print(model)
# make predictions
expected = y
predicted = model.predict(X)
# summarize the fit of the model
print(metrics.classification_report(expected, predicted))
print(metrics.confusion_matrix(expected, predicted))


    

    




GaussianNB(priors=None)
             precision    recall  f1-score   support

        0.0       0.80      0.84      0.82       500
        1.0       0.68      0.62      0.64       268

avg / total       0.76      0.76      0.76       768

[[421  79]
 [103 165]]

In [19]:

    

from sklearn import metrics
from sklearn.neighbors import KNeighborsClassifier
# fit a k-nearest neighbor model to the data
model = KNeighborsClassifier()
model.fit(X, y)
print(model)
# make predictions
expected = y
predicted = model.predict(X)
# summarize the fit of the model
print(metrics.classification_report(expected, predicted))
print(metrics.confusion_matrix(expected, predicted))


    

    




KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=5, p=2,
           weights='uniform')
             precision    recall  f1-score   support

        0.0       0.83      0.88      0.85       500
        1.0       0.75      0.65      0.70       268

avg / total       0.80      0.80      0.80       768

[[442  58]
 [ 93 175]]

In [20]:

    

from sklearn import metrics
from sklearn.tree import DecisionTreeClassifier
# fit a CART model to the data
model = DecisionTreeClassifier()
model.fit(X, y)
print(model)
# make predictions
expected = y
predicted = model.predict(X)
# summarize the fit of the model
print(metrics.classification_report(expected, predicted))
print(metrics.confusion_matrix(expected, predicted))


    

    




DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_split=1e-07, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            presort=False, random_state=None, splitter='best')
             precision    recall  f1-score   support

        0.0       1.00      1.00      1.00       500
        1.0       1.00      1.00      1.00       268

avg / total       1.00      1.00      1.00       768

[[500   0]
 [  0 268]]

In [21]:

    

from sklearn import metrics
from sklearn.svm import SVC
# fit a SVM model to the data
model = SVC()
model.fit(X, y)
print(model)
# make predictions
expected = y
predicted = model.predict(X)
# summarize the fit of the model
print(metrics.classification_report(expected, predicted))
print(metrics.confusion_matrix(expected, predicted))


    

    




SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)
             precision    recall  f1-score   support

        0.0       1.00      1.00      1.00       500
        1.0       1.00      1.00      1.00       268

avg / total       1.00      1.00      1.00       768

[[500   0]
 [  0 268]]

In [25]:

    

import numpy as np
from sklearn.linear_model import Ridge
from sklearn.model_selection import GridSearchCV
# prepare a range of alpha values to test
alphas = np.array([1,0.1,0.01,0.001,0.0001,0])
# create and fit a ridge regression model, testing each alpha
model = Ridge()
grid = GridSearchCV(estimator=model, param_grid=dict(alpha=alphas))
grid.fit(X, y)
print(grid)
# summarize the results of the grid search
print(grid.best_score_)
print(grid.best_estimator_.alpha)


    

    




GridSearchCV(cv=None, error_score='raise',
       estimator=Ridge(alpha=1.0, copy_X=True, fit_intercept=True, max_iter=None,
   normalize=False, random_state=None, solver='auto', tol=0.001),
       fit_params={}, iid=True, n_jobs=1,
       param_grid={'alpha': array([  1.00000e+00,   1.00000e-01,   1.00000e-02,   1.00000e-03,
         1.00000e-04,   0.00000e+00])},
       pre_dispatch='2*n_jobs', refit=True, return_train_score=True,
       scoring=None, verbose=0)
0.279617559313
1.0

In [26]:

    

import numpy as np
from scipy.stats import uniform as sp_rand
from sklearn.linear_model import Ridge
from sklearn.model_selection import RandomizedSearchCV
# prepare a uniform distribution to sample for the alpha parameter
param_grid = {'alpha': sp_rand()}
# create and fit a ridge regression model, testing random alpha values
model = Ridge()
rsearch = RandomizedSearchCV(estimator=model, param_distributions=param_grid, n_iter=100)
rsearch.fit(X, y)
print(rsearch)
# summarize the results of the random parameter search
print(rsearch.best_score_)
print(rsearch.best_estimator_.alpha)


    

    




RandomizedSearchCV(cv=None, error_score='raise',
          estimator=Ridge(alpha=1.0, copy_X=True, fit_intercept=True, max_iter=None,
   normalize=False, random_state=None, solver='auto', tol=0.001),
          fit_params={}, iid=True, n_iter=100, n_jobs=1,
          param_distributions={'alpha': <scipy.stats._distn_infrastructure.rv_frozen object at 0x10efc1438>},
          pre_dispatch='2*n_jobs', random_state=None, refit=True,
          return_train_score=True, scoring=None, verbose=0)
0.279617531252
0.998565254036

In [ ]: