k_fold.py

import pandas as pd
import numpy as np
import matplotlib.pyplot  as plt
import csv
import seaborn as sns
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier

dataset = pd.read_csv(r"PreProcess/Datasets/Logistic/exp.txt")
X=dataset.iloc[:,1].values
y=dataset.iloc[:,3].values


#Splitting the data set into Training and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y,train_size=0.75, random_state=0)
X_train = X_train.reshape(-1, 1)
y_train = y_train.ravel()
X_test=X_test.reshape(-1,1)

# prepare configuration for cross validation test harness
seed = 3
# prepare models
models = []
models.append(('LR', LogisticRegression()))
models.append(('RFC', RandomForestClassifier()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))
from sklearn import model_selection
results=[]
names=[]
scoring = 'accuracy'
for name, model in models:
	kfold = model_selection.KFold(n_splits=10, random_state=seed)
	cv_results = model_selection.cross_val_score(model, X_train, y_train, cv=kfold, scoring=scoring)
	results.append(cv_results)
	names.append(name)
	msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
	print(msg)
# boxplot algorithm comparison
fig = plt.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()