from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
filename = 'pima-indians-diabetes.csv'
#url = 'https://myfilecsv.com/test.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(filename, names=names)
array = dataframe.values
#splitting the array to input and output
X = array[:,0:8]
Y = array[:,8]
num_folds = 10
seed = 7
kfold = KFold(n_splits = num_folds, random_state = seed)
model = LogisticRegression(solver='liblinear')
results = cross_val_score(model, X, Y, cv=kfold)
print("Mean Estimated Accuracy Logistic Regression: %f " % (results.mean()))
