def sections(txt):
txt = remove_tag(txt) # txt da pulire dei tag dell'html
(time,res) = model.predict(txt)
(_, res) = metrics.compute(txt, res)
msg = {'data': res,'query':txt,'time': time}
response = app.response_class(
response=json.dumps(msg, indent=4),
status=200,
mimetype='application/json'
)
return response
def test(txt, type="S"):
model = Doc2Vec_model(type=type)
model.load()
import json
(time, res) = model.predict(txt)
(qnorm, res) = metrics.compute(txt, res)
print(
json.dumps(
{
'query': txt,
'query_normalized': qnorm,
'res': res,
'time': time
},
indent=4,
sort_keys=True))
import pandas as pd
from utils import data
from utils import metrics
from sklearn.naive_bayes import GaussianNB
# Dataset 1 (Latin letters)
# Training
trainX, trainY = data.load_data('train_1.csv')
clf = GaussianNB()
clf.fit(trainX, trainY)
# Testing
testX, testY = data.load_data('test_with_label_1.csv')
predictions = pd.DataFrame(clf.predict(testX))
data.generate_csv(predictions, 'GNB-DS1.csv')
metrics.compute(predictions, testY, 'GNB-DS1.csv')
data.generate_cm(predictions, testY, 'GNB-DS1.png')
# Dataset 2 (Greek letters)
# Training
trainX, trainY = data.load_data('train_2.csv')
clf = GaussianNB()
clf.fit(trainX, trainY)
# Testing
testX, testY = data.load_data('test_with_label_2.csv')
predictions = pd.DataFrame(clf.predict(testX))
data.generate_csv(predictions, 'GNB-DS2.csv')
metrics.compute(predictions, testY, 'GNB-DS2.csv')
data.generate_cm(predictions, testY, 'GNB-DS2.png')
import pandas as pd
from utils import data
from utils import metrics
from sklearn.neural_network import MLPClassifier
# Dataset 1 (Latin letters)
# Training
trainX, trainY = data.load_data('train_1.csv')
clf = MLPClassifier(activation='logistic', solver='sgd')
clf.fit(trainX, trainY)
# Testing
testX, testY = data.load_data('test_with_label_1.csv')
predictions = pd.DataFrame(clf.predict(testX))
data.generate_csv(predictions, 'Base-MLP-DS1.csv')
metrics.compute(predictions, testY, 'Base-MLP-DS1.csv')
data.generate_cm(predictions, testY, 'Base-MLP-DS1.png')
# Dataset 2 (Greek letters)
# Training
trainX, trainY = data.load_data('train_2.csv')
clf = MLPClassifier(activation='logistic', solver='sgd')
clf.fit(trainX, trainY)
# Testing
testX, testY = data.load_data('test_with_label_2.csv')
predictions = pd.DataFrame(clf.predict(testX))
data.generate_csv(predictions, 'Base-MLP-DS2.csv')
metrics.compute(predictions, testY, 'Base-MLP-DS2.csv')
data.generate_cm(predictions, testY, 'Base-MLP-DS2.png')
}
# Dataset 1 (Latin letters)
# Training
trainX, trainY = data.load_data('train_1.csv')
clf = GridSearchCV(DecisionTreeClassifier(), param_grid, verbose=1)
clf.fit(trainX, trainY)
# Validation
validX, validY = data.load_data('val_1.csv')
print(f'Score: {round(clf.score(validX, validY), 3)}')
print(f'Parameters chosen: {clf.best_params_}')
# Testing
testX, testY = data.load_data('test_with_label_1.csv')
predictions = pd.DataFrame(clf.predict(testX))
data.generate_csv(predictions, 'Best-DT-DS1.csv')
metrics.compute(predictions, testY, 'Best-DT-DS1.csv')
data.generate_cm(predictions, testY, 'Best-DT-DS1.png')
# Dataset 2 (Greek letters)
# Training
trainX, trainY = data.load_data('train_2.csv')
clf = GridSearchCV(DecisionTreeClassifier(), param_grid, verbose=1)
clf.fit(trainX, trainY)
# Validation
validX, validY = data.load_data('val_2.csv')
print(f'Score: {round(clf.score(validX, validY), 3)}')
print(f'Parameters chosen: {clf.best_params_}')
# Testing
testX, testY = data.load_data('test_with_label_2.csv')
predictions = pd.DataFrame(clf.predict(testX))
data.generate_csv(predictions, 'Best-DT-DS2.csv')