周报7

def string_to_float_converter(dataset, column):
    for row in dataset:
        row[column] = float(row[column])


#  find_the_min_and_max_of_our_dateset
def find_the_min_and_max_of_our_dateset(dataset):
    min_max_list = list()
    for i in range(len(dataset[0])):
        col_value = [row[i] for row in dataset]
        max_value = max(col_value)
        min_value = min(col_value)
        min_max_list.append([min_value, max_value])
    return min_max_list


#  normalization our data
def normalization(dataset, min_max_list):
    for row in dataset:
        for i in range(len(row)):
            row[i] = (row[i]-min_max_list[i][0])/(min_max_list[i][1] - min_max_list[i][0])


#  split our data
def k_fold_cross_validation_split(dataset, n_folds):
    split_dataset = list()
    copy_dataset = list(dataset)
    every_fold_size = int(len(dataset)/n_folds)
    for i in range(n_folds):
        fold = list()
        while len(fold) < every_fold_size:
            index = randrange(len(copy_dataset))
            fold.append(copy_dataset.pop(index))
        split_dataset.append(fold)
    return split_dataset


#  using root mean squared error method to calculate our model
def rmse_method(actual_data, predicted_data):
    sum_of_error = 0.0
    for i in range(len(actual_data)):
        predicted_error = predicted_data[i] - actual_data[i]
        sum_of_error += (predicted_error**2)
    mean_error = sum_of_error / float(len(actual_data))
    rmse = sqrt(mean_error)
    return rmse