def testKMeans(self):
data = DataRetriever("../Datasets/metadata.json")
data.retrieveData("computerHardware")
kValue = 15
t = Timer()
t.start()
mediods = KMediods(data.getDataSet(), data.getDataClass(),
data.getDescreteAttributes(),
data.getContinuousAttributes(),
data.getPredictionType(), kValue, 100)
t.stop()
print(f"Time: {t}")
print(mediods)
mediods.to_csv('kmedoids.csv', index=False)
maxItter = 100
kValue = 78
# These are only used for image segmentation and abalone
# frac = .25
# random_state = 69
# kValue = m.floor(frac * kValue)
dataSetUnNormalized = data.getDataSet()
# dataSetUnNormalized[data.getDataClass()] = np.log(dataSetUnNormalized[data.getDataClass()] + 0.001) // This is for Forest Fires
sn = StandardNormalizer(dataSetUnNormalized[data.getContinuousAttributes()])
dataSetUnNormalized[data.getContinuousAttributes()] = sn.train_fit()
dataSetNormalized = dataSetUnNormalized
# dataSetNormalized = dataSetNormalized.sample(frac=frac, random_state=random_state)
# dataSetNormalized = dataSetNormalized.reset_index()
# dataSetNormalized = dataSetNormalized.drop(["idNumber"], axis=1) #// For Glass
medoids = KMediods(dataSetNormalized, data.getDataClass(),
data.getDescreteAttributes(),
data.getContinuousAttributes(), data.getPredictionType(),
kValue, maxItter)
medoids.to_csv('./CSVOutput/' + "normalized" + dataSetName +
'MedoidsClustered.csv',
index=False)
print(f"CSV for " + dataSetName + " has been created!")
train_set = train_set.reset_index(drop=True)
ohe = OneHotEncoder()
discrete_attr = dataRetriever.getDescreteAttributes()
if dataRetriever.getDataClass() in discrete_attr:
discrete_attr.remove(dataRetriever.getDataClass())
train_set = ohe.train_fit(train_set, discrete_attr)
test_set = ohe.fit(test_set)
# Normalize Data
sn = StandardNormalizer(train_set[dataRetriever.getContinuousAttributes()])
train_set[dataRetriever.getContinuousAttributes()] = sn.train_fit()
test_set[dataRetriever.getContinuousAttributes()] = sn.fit(test_set[dataRetriever.getContinuousAttributes()])
# Train network and change architecture in respect to data set
nn = NeuralNetwork(train_set, 2, [6,16], dataRetriever.getPredictionType(), dataRetriever.getDataClass())
fitness_matrix, average_fitness = nn._particle_swarm_optimize(70, max_iter=500)
predictions = nn._feed_forward(test_set.drop(dataRetriever.getDataClass(), axis=1), testing=True)
actual = test_set[dataRetriever.getDataClass()]
metrics = np.asarray(metrics)
fig, ax = plt.subplots(3)
ax[0].plot(fitness_matrix[:,0], label="1")
ax[0].plot(fitness_matrix[:,1], label="34")
ax[0].plot(fitness_matrix[:,2], label="68")
ax[0].plot(fitness_matrix[:,3], label="Best")
ax[0].legend()
print(f"Average Accuracy: {np.asarray(metrics).mean()} ± {metrics.std()}")
import json
dataRetriever = DataRetriever("../Datasets/metadata.json")
dataRetriever.retrieveData("vote")
data = dataRetriever.getDataSet()
data = data.dropna()
data = data.sample(frac=1.0, random_state=93)
data = data.reset_index(drop=True)
# data = data.drop('idNumber', axis=1)
class_col = dataRetriever.getDataClass()
# data[class_col] = np.log(data[class_col] + 0.001)
contAttr = dataRetriever.getContinuousAttributes()
discAttr = dataRetriever.getDescreteAttributes()
predictionType = dataRetriever.getPredictionType()
output_json = {}
iter_num = 0
for test, train in KFolds(data, 5, stratisfied=True, class_col=class_col):
#KFolds doesn't have the capability of returning a validate set
#K is set to desired k/2 and the validate set is half of the test set
sn = StandardNormalizer(train[contAttr])
train[contAttr] = sn.train_fit()
test1 = test.sample(frac=0.5, random_state=13)
test2 = test.drop(test1.index)
def network_tuner(*nodes_per_hidden_layer):
"""
This function is used to calcuate the optimal network architecture
The user should input the dataset they would like to operate with and change the performance metric in accordance to the data set type IE regression or classification
"""
MSEs = []
bestNetwork = {}
learning_rate = 0.0001
maxItter = 500
batch_size = .5
dataRetriever = DataRetriever("../Datasets/metadata.json")
dataRetriever.retrieveData("glass")
dataset = dataRetriever.getDataSet().dropna()
dataset = dataset.reset_index(drop=True)
# This line is used to normalize the data for Forest Fires
# dataset[dataRetriever.getDataClass()] = np.log(dataset[dataRetriever.getDataClass()]+0.1)
dataset[dataRetriever.getContinuousAttributes()] = (dataset[dataRetriever.getContinuousAttributes()]-dataset[dataRetriever.getContinuousAttributes()].mean())/dataset[dataRetriever.getContinuousAttributes()].std()
test_set = dataset.sample(frac=0.1, random_state=69)
train_set = dataset.drop(test_set.index)
test_set = test_set.reset_index(drop=True)
train_set = train_set.reset_index(drop=True)
ohe = OneHotEncoder()
discrete_attr = dataRetriever.getDescreteAttributes()
if dataRetriever.getDataClass() in discrete_attr:
discrete_attr.remove(dataRetriever.getDataClass())
datasetEncoded = ohe.train_fit(train_set, dataRetriever.getDescreteAttributes())
testEncoded = ohe.fit(test_set)
output = None
nn = NeuralNetwork(datasetEncoded, 0, [], dataRetriever.getPredictionType(), dataRetriever.getDataClass())
for i in range(maxItter):
# We don't call an inital feedforward because backpropagate starts with a feedforward call
# batch_size represents the number of data points per batch
output = nn._back_propagate(learning_rate=learning_rate, batch_size=batch_size)
final = nn.test(testEncoded.drop(dataRetriever.getDataClass(), axis=1))
output = nn._feed_forward(testEncoded.drop(dataRetriever.getDataClass(), axis=1), testing=True)
actual = testEncoded[dataRetriever.getDataClass()]
## ===================== Classification =================
correct = 0
acc = 0
for i, row in enumerate(final):
if row == actual.iloc[i]: correct += 1
# final = final.reshape(final.shape[0])
# MSE = ((actual-final)**2).mean()
# MSEs.append(MSE)
bestNetwork['network'] = nn
bestNetwork['acc'] = acc
bestNetwork['arc'] = [0]
# # ============================================
# # ============ Compare Acc to Most Common Class
values = test_set[dataRetriever.getDataClass()].value_counts()
# USED FOR CLASSIFICATION
# print(f'Accuracy: {acc}')
# print(f'Max Class Prior: {values.max()/values.sum()}')
# print(f"Class Distribution:\n{values}")
# print("Final: ", final)
# print("Actual: ", list(actual))
# print()
numOfLayer = len(nodes_per_hidden_layer)
print("Number of Hidden Layers: ", numOfLayer)
for layer in range(numOfLayer):
print(f"Layer Number: {layer + 1}")
combinations = list(itertools.product(*nodes_per_hidden_layer[:layer+1]))
for combo in combinations:
output = None
print("Node Combination: ",list(combo))
print(combo)
nn = NeuralNetwork(datasetEncoded, layer, list(combo), dataRetriever.getPredictionType(), dataRetriever.getDataClass())
for i in range(maxItter):
# We don't call an inital feedforward because backpropagate starts with a feedforward call
# batch_size represents the number of data points per batch
output = nn._back_propagate(learning_rate=learning_rate, batch_size=batch_size)
final = nn.test(testEncoded.drop(dataRetriever.getDataClass(), axis=1))
output = nn._feed_forward(testEncoded.drop(dataRetriever.getDataClass(), axis=1), testing=True)
actual = testEncoded[dataRetriever.getDataClass()]
## ===================== Classification =================
correct = 0
acc = 0
for i, row in enumerate(final):
if row == actual.iloc[i]: correct += 1
acc = correct/len(test_set)
# # # ============================================
# # # ============ Compare Acc to Most Common Class
values = test_set[dataRetriever.getDataClass()].value_counts()
# USED FOR CLASSIFICATION
# print(f'Accuracy: {acc}')
# print(f'Max Class Prior: {values.max()/values.sum()}')
# # print(f"Class Distribution:\n{values}")
# print("Final: ", final)
# print("Actual: ", list(actual))
# print()
if acc > bestNetwork['acc']:
bestNetwork['network'] = nn
bestNetwork['acc'] = acc
bestNetwork['arc'] = combo
# final = final.reshape(final.shape[0])
# MSE = ((actual-final)**2).mean()
# MSEs.append(MSE)
# if MSE < bestNetwork['acc']:
# bestNetwork['network'] = nn
# bestNetwork['acc'] = MSE
# bestNetwork['arc'] = combo
return bestNetwork#, MSEs
ohe = OneHotEncoder()
discrete_attr = dataRetriever.getDescreteAttributes()
if dataRetriever.getDataClass() in discrete_attr:
discrete_attr.remove(dataRetriever.getDataClass())
train_set = ohe.train_fit(train_set, discrete_attr)
test_set = ohe.fit(test_set)
# Normalize Data
sn = StandardNormalizer(train_set[dataRetriever.getContinuousAttributes()])
train_set[dataRetriever.getContinuousAttributes()] = sn.train_fit()
test_set[dataRetriever.getContinuousAttributes()] = sn.fit(
test_set[dataRetriever.getContinuousAttributes()])
# Train network and change architecture in respect to data set
nn = NeuralNetwork(train_set, 2, [2, 2], dataRetriever.getPredictionType(),
dataRetriever.getDataClass())
nn.train(maxIter, learning_rate, batch_size)
# predictions = nn.test(test_set.drop(dataRetriever.getDataClass(), axis=1))
# # ca = ClassifierAnalyzer(test_set[dataRetriever.getDataClass()], predictions)
# correct = 0
# actual = test_set[dataRetriever.getDataClass()]
# for i, row in enumerate(predictions):
# if row == actual.iloc[i]: correct += 1
# metrics.append(correct/len(actual))
break
metrics = np.asarray(metrics)
prior = 1 / dataset[dataRetriever.getDataClass()].nunique()
train_set = train_set.reset_index(drop=True)
ohe = OneHotEncoder()
if dataRetriever.getDataClass() in discrete_attr:
discrete_attr.remove(dataRetriever.getDataClass())
datasetEncoded = ohe.train_fit(train_set,
dataRetriever.getDescreteAttributes())
testEncoded = ohe.fit(test_set)
# ======================= Create Best Individual ================
print(title_text)
best = NeuralNetwork(datasetEncoded, 1, [25],
dataRetriever.getPredictionType(),
dataRetriever.getDataClass())
fitnesses = best.genetic_algorithm(population_size, maxItter, batch_size,
mutation_rate, 10,
cost_func[current_data_set])
# ======================= Test Best Individual ================
final = best.test(testEncoded.drop(dataRetriever.getDataClass(), axis=1))
output = best._feed_forward(testEncoded.drop(dataRetriever.getDataClass(),
axis=1),
testing=True)
actual = testEncoded[dataRetriever.getDataClass()]
if dataRetriever.getPredictionType() == "classification":
# ## ===================== Classification =================
print("Best")
correct = 0