def main():
print("Importing Data")
((trX, trY),
(teX, teY)) = extractor(file='data/emails.csv').min_max_nomalized()
print(trX[0])
print("Creating Model")
model = FFNN()
print("Training Model")
print(type(trX))
acc, t = model.train(trX[0:100], trY[0:100], teX[0:100], teY[0:100])
print(acc)
return acc, t
def main(name, args={}, norm="minmax", dim=1500):
print("Importing Data")
if norm == "minmax":
((trX, trY),
(teX, teY)) = extractor(file='data/emails.csv').min_max_nomalized()
elif norm == "pca":
((trX, trY), (teX, teY)) = extractor(
file='data/emails.csv').pca_reduced_nomarlize(dim=dim)
print("Creating Model")
model = FFNN(**args)
print("Training Model")
print(type(trX))
acc, t, lr = model.train(trX, trY, teX, teY)
df = pd.DataFrame({
'accuracy': acc,
'epoc': list(range(len(acc))),
'time_per_iteration(s)': t,
'learning_rate': lr
})
df.to_csv("output/{0}.csv".format(name))
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
from sklearn.metrics import precision_recall_fscore_support
import time
validation_list = []
precision_list = []
time_list = []
for i in range(1,10):
# init
start = 0.0
end = 0.0
prediction = dict()
kwarg = {'test_size':i*0.1}
((x_train,x_test),(y_train,y_test)) = extractor(file='data/emails.csv',**kwarg).get()
model = MultinomialNB()
model.fit(x_train,x_test)
#prediction
start = time.time()
prediction["naive_bayes"] = model.predict(y_train)
end = time.time()
precision,recall,fscore,support = precision_recall_fscore_support( y_test,
prediction['naive_bayes'],
average='macro')
precision_list.append(precision)
validation_list.append(kwarg['test_size'])
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from sklearn.metrics import precision_recall_fscore_support
import time
validation_list = []
precision_list = []
time_list = []
for i in range(1, 10):
# init
start = 0.0
end = 0.0
prediction = dict()
kwarg = {'test_size': i * 0.1}
((x_train, x_test), (y_train, y_test)) = extractor(
file='data/emails.csv').min_max_nomalized(on_hot=False)
model = RandomForestClassifier(n_estimators=100,
max_depth=100,
random_state=0)
model.fit(x_train, x_test)
#prediction
start = time.time()
prediction["random_forest"] = model.predict(y_train)
end = time.time()
precision, recall, fscore, support = precision_recall_fscore_support(
y_test, prediction['random_forest'], average='macro')
precision_list.append(precision)
validation_list.append(kwarg['test_size'])