Exemple #1
0
def main():
    targetFile = "../Dados/main-features2.csv"
    trainFile = '../boa.csv'

    trainFeatures = first_dataset(trainFile)

    trainDataSet = load_dataset(trainFile, trainFeatures).drop('id', 1)

    trainFeatures.pop(0)
    trainFeatures.pop()

    targetFeatures = first_dataset(targetFile)
    targetDataSet = load_dataset(targetFile, targetFeatures)

    print(trainFeatures)
    print(targetFeatures)

    createNeuralNetworkClassifier(trainDataSet, trainFeatures, targetDataSet)
Exemple #2
0
def generateOutput():
    data_file = '../boa.csv'

    target_file = '../Dados/main-features2.csv'

    name_of_features = first_dataset(data_file)
    target_features = first_dataset(target_file)

    dataSet = load_dataset(data_file, name_of_features)
    targetDataSet = load_dataset(target_file, target_features)
    dataSet = dataSet.drop('id', 1)

    name_of_features.pop(0)
    name_of_features.pop()

    #target_features.pop(0)

    create_target(dataSet, name_of_features, targetDataSet, target_features)
def main():
    targetFile = "../Dados/main-features2.csv"
    trainFile = '../boa.csv'

    trainFeatures = first_dataset(trainFile)

    trainDataSet = load_dataset(trainFile, trainFeatures).drop('id', 1)

    trainFeatures.pop(0)
    trainFeatures.pop()

    targetFeatures = first_dataset(targetFile)
    targetDataSet = load_dataset(targetFile, targetFeatures)

    print(trainFeatures)
    print(targetFeatures)

    decisionTree = createTreeClassifier(trainDataSet, trainFeatures,
                                        targetDataSet)
    visualize_tree(decisionTree, trainFeatures)
Exemple #4
0
def train():

    file_path = "../Dados/master-features.csv"
    data_file = '../boa.csv'

    name_of_features = first_dataset(data_file)

    dataSet = load_dataset(data_file, name_of_features)
    dataSet = dataSet.drop('id', 1)

    name_of_features.pop(0)
    name_of_features.pop()

    print(name_of_features)
Exemple #5
0
def gridSearch(targetFile, targetFeatures):

    data_file = '../boa.csv'

    name_of_features = first_dataset(data_file)

    dataSet = load_dataset(data_file, name_of_features)
    dataSet = dataSet.drop('id', 1)

    name_of_features.pop(0)
    name_of_features.pop()

    print(name_of_features)

    print(len(name_of_features), len(targetFeatures))

    # prepare a uniform distribution to sample for the alpha parameter
    #param_grid = {'alpha': sp_rand()}

    # create and fit a ridge regression model, testing random alpha values
    model = MLPClassifier()
    parameters = {
        #'learning_rate': ["constant", "invscaling"],
        'hidden_layer_sizes': [(100, 10), (100, 20), (100, 30), (100, 1),
                               (100, 5)],
        'learning_rate': ['constant', 'invscaling'],
        'learning_rate_init': [0.05, 0.01, 0.1],
        #'alpha': [10.0 ** -np.arange(1, 7)],
        'activation': ['identity', 'logistic', 'tanh', 'relu']
    }
    rsearch = model_selection.GridSearchCV(estimator=model,
                                           param_grid=parameters,
                                           n_jobs=-1,
                                           cv=10)
    rsearch.fit(dataSet[name_of_features], dataSet['target'])

    print(rsearch)
    # summarize the results of the random parameter search
    print(rsearch.best_score_)
    print(rsearch.best_estimator_.alpha)
    if targetFile:
        prediction = rsearch.predict(targetFile[targetFeatures])
        cols = ['Predicted']
        cenas = targetFile['id_target']
        features = pd.DataFrame(prediction, columns=cols)
        file_name = "output2.csv"
        features.set_index(cenas, inplace=True)
        features.to_csv(file_name, sep=',', encoding='utf-8')