def __init__(self, config):
BaseAgent.__init__(self, config)
plt.ion()
self.dataset = Dataset('data', self.subsets)
#self.dataset.loadDataset()
self.accs = defaultdict(list)
self.correct = defaultdict(int)
fig, self.ax = plt.subplots(nrows=6, ncols=4)
def uploadDataset():
if not request.json or not 'name' in request.json:
return jsonify({"result": False, "msg": "Failed to Upload Dataset!"})
dataset = Dataset(request.json['name'], request.json['purpose'],
request.json['user'], request.json['datafile'])
result = Dataset.addDataset(dataset, mysql)
if result is True:
return jsonify({
"result": True,
"msg": "Successfully Uploaded Dataset!"
})
return jsonify({"result": False, "msg": "Failed to Upload Dataset!"})
def updateDataset(dataset_id):
if not request.json or not 'name' in request.json or not 'id' in request.json:
return jsonify({"result": False, "msg": "Failed to Update Dataset!"})
dataset = Dataset(request.json['name'],
request.json['purpose'],
request.json['user'],
id=request.json['id'])
result = Dataset.updateDataset(dataset_id, dataset, mysql)
if result is True:
return jsonify({
"result": True,
"msg": "Successfully Updated Dataset!"
})
return jsonify({"result": False, "msg": "Failed to Update Dataset!"})
from models.Dataset import Dataset
from models.NaiveBayes import NaiveBayes
from models.CrossValidation import crossval_predict, crossval_predict_evaluation
from lib.utils import accuracy_score, confusion_matrix, present_matrix, present_accuracies
BANKNOTE_FILE = "data/banknote_authentication.csv"
IRIS_FILE = "data/iris.csv"
CROSS_VAL_FOLDS = 5
# parse selected file
fdb = Dataset(IRIS_FILE)
def run_naive_bayes_example():
print("Naive Bayes @ training data")
# create and train model using the previously loaded file
model = NaiveBayes()
model.fit(fdb.get_data(), fdb.get_labels())
print("Naive Bayes model was trained with data from %s in %s seconds." %
(fdb.get_file_name(), model.get_fit_time()))
# run predictions
predictions = model.predict(fdb.get_data())
actuals = fdb.get_labels()
print("Predictions complete after %s seconds." % model.get_predict_time())
# calculate accuracy
accuracy = accuracy_score(predictions, actuals)