def neuron(self, p_class, age, sib_sp, par_ch, fare, sex_female, sex_male,
embarked_c, embarked_q, embarked_s):
clf = PNN(verbose=False, std=10)
clf.fit(X_train, y_train)
x_test = np.array([[
p_class, age, sib_sp, par_ch, fare, sex_female, sex_male,
embarked_c, embarked_q, embarked_s
]])
y_predict = clf.predict(x_test)
return float(y_predict)
import pandas as pd
from neupy.algorithms import PNN
# read data from the csv files
train_data = pd.DataFrame(pd.read_csv('processed_input/train.csv'))
test_data = pd.DataFrame(pd.read_csv('processed_input/test.csv'))
# print train_data.describe
# split data in to target and data
X_train = train_data.drop(columns='Made Donation in March 2007', axis=1)
y_train = train_data['Made Donation in March 2007']
X_test = test_data.drop(columns='Made Donation in March 2007', axis=1)
IDs = test_data['ID']
# instantiate the PNN model
pnn = PNN(verbose=True)
# fit to training data and then predict
prediction = pnn.fit(X_train, y_train).predict_proba(X_test)
# concatenate IDs and the prediciton
pred = pd.concat([
IDs,
pd.DataFrame(prediction.astype(float),
columns=['Made Donation in March 2007'])
],
axis=1)
#write prediction to csv
pred.to_csv('output/pnn_prediction.csv', index=False)
cv=cross_validation)
print("")
print("Cross Validation: {0} (+/- {1})".format(abs(score.mean().round(2)),
(score.std() * 2).round(2)))
print("")
#Prediction
Y_predict = pnn.predict(X_test)
print(Y_test.values)
print(Y_predict)
print("Accuracy: {0}".format(
metrics.accuracy_score(Y_test, Y_predict).round(2)))
else:
pnn = GaussianNB()
pnn.fit(X_train, Y_train)
print(
'Sigma: {0}'.format(pnn.sigma_)
) #Standard deviation is estimated using maximum likelihood, so one sigma per variable and per class
# Cross validataion
score = cross_val_score(pnn,
X_train,
Y_train,
scoring='accuracy',
cv=cross_validation)
print("")
print("Cross Validation: {0} (+/- {1})".format(abs(score.mean().round(2)),
(score.std() * 2).round(2)))
print("")
