import numpy as np
import urllib
# 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.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[:,0:7]
y = dataset[:,8]

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_)

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_)

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_)

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))

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))

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))

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))

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))

import numpy as np
from sklearn.linear_model
import Ridge
from sklearn.grid_search
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)

import numpy as np
from scipy.stats
import uniform as sp_rand
from sklearn.linear_model
import Ridge
from sklearn.grid_search
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)