def load(file):
iterator = csv.reader(open(file, "r"))
data = list(iterator)
class_index = utils.get_class_index(data)
for i in range(len(data)):
for j in range(len(data[i])):
val = data[i][j]
data[i][j] = float(val) if j != class_index else val
return data
def get_attr_by_class_probs(self, X, y):
data = utils.merge_attrs(X, y)
class_index = utils.get_class_index(data)
result = self.get_empty_classes_dict([])
for record in data:
class_key = record[class_index]
result[class_key].append(record)
for key in result:
class_X, class_y = utils.horizontal_split(result[key])
result[key] = self.get_attr_probs(class_X, self.empty_bins())
return result
def get_class_probs(self, X, y):
data = utils.merge_attrs(X, y)
class_index = utils.get_class_index(data)
result = self.get_empty_classes_dict(0)
for record in data:
class_key = record[class_index]
result[class_key] += 1
for key in result:
result[key] = result[key] / len(data)
return result
def get_attr_measures(self, X, y):
data = utils.merge_attrs(X, y)
first_attr_index = 0
last_attr_index = utils.get_class_index(data) - 1
result = [[] for _ in range(self.attr_count)]
for record in data:
for attr_index in range(first_attr_index, last_attr_index + 1):
result[attr_index].append(record[attr_index])
for i in range(len(result)):
attr_values = result[i]
mean = np.mean(attr_values)
std = np.std(attr_values)
result[i] = [mean, std]
return result