def Neural(X, y):
starttime = time.time()
x1_train, x1_test, y1_train, y1_test = cv.train_test_split(X,
y,
test_size=0.33,
random_state=0)
clf = mlpc(max_iter=300, random_state=1).fit(x1_train, y1_train)
trnscore = clf.score(x1_train, y1_train)
tstscore = clf.score(x1_test, y1_test)
trntime = time.time() - starttime
return (trnscore, tstscore, trntime)
# # XOR Model | Pickle
import numpy as np
import sklearn
import pickle
import os
from sklearn.neural_network import MLPClassifier as mlpc
os.getcwd()
os.listdir()
xs = np.array([0, 0, 0, 1, 1, 0, 1, 1]).reshape(4, 2)
ys = np.array([0, 1, 1, 0]).reshape(4, )
mdl = mlpc(activation='relu', max_iter=10000, hidden_layer_sizes=(4, 2))
mdl.fit(xs, ys)
filename = 'XOR_model.pkl'
pickle.dump(mdl, open(filename, 'wb'))
os.listdir()
# #### 'XOR_model.pkl'
#
# Model has been saved into a 'pkl' file.
# help('modules')
filename = 'XOR_model.pkl'
scaler = StandardScaler()
data_partial = data[data['Sex'] == sex].drop('Sex', axis=1)
# corr_matrix_f, corr_matrix_m = data_f.corr(), data_m.corr()
# plot_corr_matrices(corr_matrix_f, corr_matrix_m)
y = data_partial['EmoState']
X = scaler.fit_transform(data_partial.drop('EmoState', axis=1))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=71)
models = (('DTC', dtc()), ('SVM', svc(C=10)), ('KNN', knc(n_neighbors=10)),
('SGDC', sgdc()), ('GNBC', gnbc()), ('MLPC',
mlpc(max_iter=1000,
learning_rate='adaptive')))
results = []
names = []
seed = 13
scoring = 'accuracy'
for name, model in models:
kfold = model_selection.KFold(n_splits=10, random_state=seed, shuffle=True)
cv_results = model_selection.cross_val_score(model,
X_train,
y_train,
cv=kfold,
scoring=scoring)
results.append(cv_results)
names.append(name)
print('{}: {} ({})'.format(name, round(cv_results.mean(), 2),
test_labels = []
for i in train:
train_set.append(dataset[i])
train_labels.append(target[i])
for i in test:
test_set.append(dataset[i])
test_labels.append(target[i])
'''
uncomment the classifier you want to use. Comment out the others
'''
# classifier = KNeighborsClassifier()
# classifier = nb.GaussianNB()
# classifier = nb.MultinomialNB()
# classifier = svm.SVC()
classifier = mlpc(solver='lbfgs',
hidden_layer_sizes=(5, 15),
max_iter=200)
predicted = classifier.fit(train_set, train_labels).predict(test_set)
score = f1_score(test_labels, predicted, average='weighted')
scores.append(score)
incorrect = (test_labels != predicted).sum()
accuracy = (len(test_set) - incorrect) / len(test_set) * 100.
accuracies.append(accuracy)
print("Maximum accuracy attained ", max(accuracies))
print("f1score ", scores[np.argmax(accuracies)])
print('\n')
print("Maximum accuracy attained ", max(accuracies))
print("f1score ", scores[np.argmax(accuracies)])
from time import time
from split import data_split
X_train, X_test, Y_train, Y_test = data_split()
from sklearn.neural_network import MLPClassifier as mlpc
t0 = time()
clf = mlpc(alpha=1e-5, hidden_layer_sizes=(5, 5), random_state=1)
clf.fit(X_train, Y_train)
print("Training Time: " + str(round(time() - t0, 3)) + "s")
t1 = time()
pred = clf.predict(X_test)
print("Testing Time: " + str(round(time() - t1, 3)) + "s")
from sklearn.metrics import accuracy_score
print(accuracy_score(Y_test, pred))
def __init__(self, pathToData):
self.dataFilePath = pathToData
self.algoname = 'ANN'
self.datasetName = 'Letter'
self.classifier = mlpc(early_stopping=True, learning_rate='adaptive')
self.cv = 5