def machine_learning():
algo_list = ["knn", "svm", "gbc", "rfc", "nn"]
# Check argument
if request.args.get('images_directory') is None :
return 'No "images_directory" given.'
if request.args.get('algorithm') is None :
return 'No "algorithm" given.'
if request.args.get('save_directory') is None :
return 'No "save_directory" given.'
images_directory = request.args.get('images_directory')
algorithm = str(request.args.get('algorithm'))
save_directory = request.args.get('save_directory')
# creates new MachineLearning object
if algorithm == "nn":
ml = MachineLearning(images_directory, save_directory, 32)
else:
ml = MachineLearning(images_directory, save_directory)
# error detection
if len(ml.imgs) == 0 or len(ml.labels) == 0:
app.logger.error("No images were read!")
return "Error: No images were read!"
if algorithm in algo_list:
score_train, score_test = ml.train(algorithm, ml.imgs, ml.labels)
else:
app.logger.warning("Unexpected algorithm choice, choosing default!")
algorithm = "svm"
score_train, score_test = ml.train(algorithm, ml.imgs, ml.labels)
return '\"' + algorithm + '\":{\"train_acc\":'+str(score_train)+' ,\"val_acc\":'+str(score_test)+'}'
import pandas
import config
from sklearn.utils import resample
import MachineLearning
def binary_to_char(value):
return 'N' if value == 0 else 'Y'
ml = MachineLearning.MachineLearning()
data = pandas.read_csv(config.DATA_PATH + 'ortopedia.csv', sep=';')
# Convertendo coluna de classificação para caractere
data.Fusao_de_Vertebras = data.Fusao_de_Vertebras.map(binary_to_char)
# Verificando balanceamento de classes
print(data.Fusao_de_Vertebras.value_counts())
# Separando dados das classes
minor = data[data['Fusao_de_Vertebras'] == 'Y']
major = data[data['Fusao_de_Vertebras'] == 'N']
# Rebalanceando a classe com menor número de registros
minor_up_sample = resample(minor,
replace=True,
n_samples=7900,
random_state=None)
# Criando novo dataframe com os dados balanceados
if __name__ == '__main__':
# load projects data
try:
raise OSError
print('loading processed data...')
f = open('data/projects.bin', 'rb')
projects = pickle.load(f)
outcomes = pickle.load(f)
train_idx = pickle.load(f)
test_idx = pickle.load(f)
f.close()
print('training models')
ml = mlp.MachineLearning()
ml.training_data = projects
ml.training_labels = outcomes[:, 1]
ml.preprocessTrain(0)
ml.preprocessTest()
ml.trainModel(1)
preds = ml.predict()
print('saving prediction to file')
sample = pd.read_csv('./data/sampleSubmission.csv')
sample['is_exciting'] = preds
sample.to_csv('predictions.csv', index=False)
#print projects.ix[train_idx].shape
#print projects.ix[test_idx].shape
