AlgorithmComparison.py

# -*- coding: utf-8 -*-
"""
Created on Sat Mar  6 20:50:56 2021

@author: Grant
"""

# compare algorithms
import pandas as pd
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.naive_bayes import *

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.cluster import KMeans
from scipy.cluster import hierarchy

# Load dataset
dataset = pd.read_csv('players_df.csv', index_col=False)
dataset.reset_index(drop=True, inplace=True)


# validation dataset
array = dataset.values
X = array[:,0:10]
y = array[:,10]
X_train, X_validation, Y_train, Y_validation = train_test_split(X, y, test_size=0.66, random_state=8, shuffle=True)

# Spot Check Algorithms
models = []
models.append(('LR', LogisticRegression(solver='liblinear', multi_class='ovr')))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC(gamma='auto')))
models.append(('BNB', BernoulliNB()))
#models.append(('CatNB', CategoricalNB()))
models.append(('CompNB', ComplementNB()))
models.append(('MultiNB', MultinomialNB()))
models.append(('KMeans', KMeans()))

# evaluate each model in turn
results = []
names = []
for name, model in models:
	kfold = StratifiedKFold(n_splits=10, random_state=1, shuffle=True)
	cv_results = cross_val_score(model, X_train, Y_train, cv=kfold, scoring='accuracy')
	results.append(cv_results)
	names.append(name)
	print('%s: %f (%f)' % (name, cv_results.mean(), cv_results.std()))
    
# Compare Algorithms
pyplot.boxplot(results, labels=names)
pyplot.title('Algorithm Comparison')
pyplot.show()