},
{
'regwgt': 0.01,
'nh': 8
},
{
'regwgt': 0.05,
'nh': 16
},
{
'regwgt': 0.1,
'nh': 32
},
)
numparams = len(parameters)
trainset, testset = dtl.load_susy(trainsize, testsize)
learnername = cross_validate(3, trainset[0], trainset[1], cls.items())
print('Best parameters for k fold ' + learnername)
learnername = strat_cross_validate(3, trainset[0], trainset[1],
cls.items())
print('Best parameters for Stratified k fold ' + learnername)
errors = {}
for learnername in classalgs:
errors[learnername] = np.zeros((numparams, numruns))
for r in range(numruns):
trainset1, testset1 = dtl.load_susy(trainsize, testsize)
#trainset, testset = dtl.load_susy_complete(trainsize,testsize)
trainset2, testset2 = dtl.load_census(trainsize, testsize)
'regwgt': 0.05,
'nh': 16
},
{
'regwgt': 0.1,
'nh': 32
},
)
numparams = len(parameters)
errors = {}
for learnername in classalgs:
errors[learnername] = np.zeros((numparams, numruns))
for r in range(numruns):
trainset, testset = dtl.load_susy()
#print("a0",trainset[0])
#print("a1", trainset[1])
#print(testset[0], testset[1])
# trainset, testset = dtl.load_susy_complete(trainsize,testsize)
# trainset, testset = dtl.load_census(trainsize,testsize)
print(('Running on train={0} and test={1} samples for run {2}').format(
trainset[0].shape[0], testset[0].shape[0], r))
for p in range(numparams):
params = parameters[p]
for learnername, learner in classalgs.items():
# Reset learner for new parameters
learner.reset(params)
print('Running learner = ' + learnername + ' on parameters ' +
}
numalgs = len(classalgs)
parameters = (
# {'p': 35, 'kernel': 'gaussian', 'centroid_selection_Algo': 'Kmeans', 'beta': 1},
{'p': 35, 'kernel': 'gaussian', 'centroid_selection_Algo': 'Kmeans', 'beta': 0.5},
# {'p': 35, 'kernel': 'gaussian', 'centroid_selection_Algo': 'Kmeans', 'beta': 0.1},
)
numparams = len(parameters)
errors = {}
for learnername in classalgs:
errors[learnername] = np.zeros((numparams,numruns))
for r in range(numruns):
trainset, testset = dtl.load_susy(trainsize,testsize)
# trainset, testset = dtl.load_susy_complete(trainsize, testsize)
print(('Running on train={0} and test={1} samples for run {2}').format(trainset[0].shape[0], testset[0].shape[0],r))
for p in range(numparams):
params = parameters[p]
for learnername, learner in classalgs.items():
# Reset learner for new parameters
learner.reset(params)
print('Running learner = ' + learnername + ' on parameters ' + str(learner.getparams()))
# Train model
learner.learn(trainset[0], trainset[1])
# Test model
predictions = learner.predict(testset[0])
error = geterror(testset[1], predictions)
import import_files
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from dataloader import load_susy
from dataloader import splitdataset
#Load the data
train,test = load_susy(2000,1000)
X_train, y_train = train
X_test, y_test = test
"""
Implementation of Naive Bayes Classifier.
Attributes: class_prior - Prior probabilities.
class_count - unique counts of classes.
mu_ml = Maximum Likelihood of mean parameter. shape = (#classes,#features)
sigma_sq_ml = Maximum Likelihood of variance parameter. shape = (#classes,#features)
classes = unique classes.
remove_ones = boolean value to include features of one.
"""
class NaiveBayes():
""" Gaussian naive Bayes """
# Constructor
def __init__( self, remove_ones = True ):
self.class_prior = None