# Create a pipeline that standardizes (prepares) the data then evaluates a model
import pandas as pd
import numpy as np
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
filename = 'pima-indians-diabetes.data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = pd.read_csv(filename, names=names)
array = dataframe.values
X = array[:,0:8]
y = array[:,8]
# create pipeline
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('lda', LinearDiscriminantAnalysis()))
model = Pipeline(estimators)
# evaluate the model
seed = 7
kfold = KFold(n_splits=10, shuffle=True, random_state=seed)
results = cross_val_score(model, X, y, cv=kfold)
print(results.mean())