Data
# Run Algorithms for n-Times and Determine the Average Value based on Kfold Method
# Data Transformation Method: Rescale
from pandas import read_csv
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.utils import shuffle
from sklearn.preprocessing import MinMaxScaler
# load dataset
url = "https://bit.ly/2GX9wC5"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(url, names=names)
# For plotting
fig, ax = plt.subplots()
# prepare models
model1 = LogisticRegression(solver = 'lbfgs',max_iter=1000) #LR
model2 = LinearDiscriminantAnalysis() #LDA
model3 = KNeighborsClassifier(n_neighbors = 3) #KNN
model4 = GaussianNB() #GNB
model5 = DecisionTreeClassifier(max_depth=5) #DT
model6 = QuadraticDiscriminantAnalysis() #QDA
# evaluate model
resultslr = []
resultslda = []
resultsknn = []
resultsgnb = []
resultsdt = []
resultsqda = []
scoring = 'accuracy'
times = 10 # How many times to repeat
for x in range (times):
# shuffle the data for each times
dataframe = shuffle(dataframe)
array = dataframe.values
X = array[:,0:8]
Y = array[:,8]
# Rescale Data
scaler = MinMaxScaler(feature_range=(0,1))
rescaledX = scaler.fit_transform(X)
kfold = KFold(n_splits=10)
# Logic Regression
cv_results = cross_val_score(model1, rescaledX, Y, cv=kfold, scoring=scoring)
resultslr.append(cv_results.mean()*100)
# Linear Discriminant Analysis
cv_results = cross_val_score(model2, rescaledX, Y, cv=kfold, scoring=scoring)
resultslda.append(cv_results.mean()*100)
# K-Nearest Neighbor
cv_results = cross_val_score(model3, rescaledX, Y, cv=kfold, scoring=scoring)
resultsknn.append(cv_results.mean()*100)
# Gaussian Naive Bayes
cv_results = cross_val_score(model4, rescaledX, Y, cv=kfold, scoring=scoring)
resultsgnb.append(cv_results.mean()*100)
# Decision Tree
cv_results = cross_val_score(model5, rescaledX, Y, cv=kfold, scoring=scoring)
resultsdt.append(cv_results.mean()*100)
# Quadratic Discriminant Analysis
cv_results = cross_val_score(model6, rescaledX, Y, cv=kfold, scoring=scoring)
resultsqda.append(cv_results.mean()*100)
# Plot the result
t = np.arange(1, times+1, 1) # to plot from 1 to n-Times
ax.plot(t,resultslr,t,resultslda,t,resultsknn,t,resultsgnb,t,resultsdt,t,resultsqda)
ax.set(xlabel='times', ylabel='Accuracy (%)',
title='Pima Indian Database')
ax.grid()
ax.set_xlim(1, times)
ax.set_ylim(60, 80)
ax.legend(['Logic Regression','Linear Discriminant Analysis','K-Nearest Neighbor','Gaussian Naive Bayes','Decision Tree','Quadratic Discriminant Analysis'])
plt.show()
Result:
