def main():
dcleaner = dclean.DataClean()
data = dcleaner.get_data()
data = [int(val) for val in data]
data.sort()
print("The data set we will use for calculating the range, variance, and standard deviation (std_dev) is:\n\t{}".format(data))
summ_x_sqr, summ, n, avg, rang, pop_variance, samp_variance, pop_std_dev, samp_std_dev = get_std_devs(data)
print("For population:\n\tThe range is: {}\n\tThe variance is: {}\n\tThe std_dev is: {}".format(rang, pop_variance, pop_std_dev))
print("For sample:\n\tThe range is: {}\n\tThe variance is: {}\n\tThe std_dev is: {}".format(rang, samp_variance, samp_std_dev))
mean = get_mean(data)
count = count_std_devs(mean,samp_std_dev,173)
print("173 is {} standard deviations from the mean".format(count))
q1, med, q3, iqr = get_median(data)
print("the median for this data set is {}".format(med[0]))
print("quartile 1 = {}, quartile 3 = {}, irq = {}".format(q1[0], q3[0], iqr))
def main():
dcleaner = dclean.DataClean()
data = dcleaner.get_data()
data = [int(val) for val in data]
data.sort()
print(
"The data set we will use for calculating the range, variance, and standard deviation (std_dev) is:\n\t{}"
.format(data))
summ_x_sqr, summ, n, avg, rang, variance, std_dev = get_std_devs(data)
print(summ_x_sqr)
print("sum: {}\nn: {}\navg: {}".format(summ, n, avg))
print("The range is: {}\nThe variance is: {}\nThe std_dev is: {}".format(
rang, variance, std_dev))
def main():
dcleaner = dclean.DataClean()
family_count = dcleaner.get_data()
family_count = [int(cnt) for cnt in family_count]
bill_low = dcleaner.get_data()
bill_high = dcleaner.get_data()
bill_range = [(int(lo),int(hi)) for lo,hi in zip(bill_low,bill_high)]
data = [(num,rng) for num,rng in zip(family_count,bill_range)]
data.sort(key=lambda tpl:tpl[1][0])
print("The data set we will use for calculating the range, variance, and standard deviation (std_dev) is:\n\t{}".format(data))
summ_x_sqr, summ, n, avg, rang, pop_variance, samp_variance, pop_std_dev, samp_std_dev = get_std_devs([x[0] for x in data])
print("For population:\n\tThe range is: {}\n\tThe variance is: {}\n\tThe std_dev is: {}".format(rang, pop_variance, pop_std_dev))
print("For sample:\n\tThe range is: {}\n\tThe variance is: {}\n\tThe std_dev is: {}".format(rang, samp_variance, samp_std_dev))
mean = get_mean([x[0] for x in data])
count = count_std_devs(mean,samp_std_dev,173)
print("173 is {} standard deviations from the mean".format(count))
q1, med, q3, iqr = get_median([x[0] for x in data])
print("the median for this data set is {}".format(med[0]))
print("quartile 1 = {}, quartile 3 = {}, irq = {}".format(q1[0], q3[0], iqr))
def main():
dcleaner = dclean.DataClean()
print("first, enter the score values for exam1, exam2, and the final")
time.sleep(.5)
data = dcleaner.get_data()
print(
"Now, enter the associated weights, and sorry but you also need to enter any repeat values"
)
time.sleep(.5)
weights = dcleaner.get_data()
data = [int(val) for val in data]
weights = [int(val) for val in weights]
print("data converted to int values is now:\n\t{}".format(data))
print("weights converted to int values is now:\n\t{}".format(weights))
wmean = sum([x * w for x, w in zip(data, weights)]) / sum(weights)
print("the calculated weighted mean is then {}".format(wmean))
def main():
dcleaner = dclean.DataClean()
data = dcleaner.get_data()
data = [int(val) for val in data]
data.sort()
# dset = []
# for val in data:
# if val not in dset:
# dset.append(val)
# tmp = data
# data = dset
# dset = tmp
# del tmp
print(
"The data set we will use for calculating the range, variance, and standard deviation (std_dev) is:\n\t{}"
.format(data))
summ_x_sqr, summ, n, avg, rang, pop_variance, samp_variance, pop_std_dev, samp_std_dev = get_std_devs(
data)
print(
"For population:\n\tThe range is: {}\n\tThe variance is: {}\n\tThe std_dev is: {}"
.format(rang, pop_variance, pop_std_dev))
print(
"For sample:\n\tThe range is: {}\n\tThe variance is: {}\n\tThe std_dev is: {}"
.format(rang, samp_variance, samp_std_dev))
mean = get_mean(data)
count = count_std_devs(mean, samp_std_dev, 173)
print("173 is {} standard deviations from the mean".format(count))
q1, med, q3, iqr = get_median(data)
print("the median for this data set is {}".format(med[0]))
print("quartile 1 = {}, q2==med = {}, quartile 3 = {}, iqr = {}".format(
q1[0], med[0], q3[0], iqr))
print("q1's idx = {}, med's idx = {}, q3's idx = {}, and list len = {}".
format(q1[1], med[1], q3[1], len(data)))
print("the value at the 82% index is: {}".format(data[round(
len(data) * .82)]))
target = 32
print(
"{} occurs at the index position of {} out of {}, for percentage rank of {}"
.format(target, data.index(target), len(data),
(data.index(target) / len(data))))
lo = int(np.floor((strt + stp) / 2))
hi = int(np.ceil((strt + stp) / 2))
return (data[lo] + data[hi]) / 2, int((lo + hi) / 2)
def get_median(data: list):
med, midx = _segment_median(data, 0, len(data))
quart1, q1idx = _segment_median(data, 0, midx)
quart3, q3idx = _segment_median(data, midx, len(data))
iqr = quart3 - quart1
return (quart1, q1idx), (med, midx), (quart3, q3idx), iqr
if __name__ == "__main__":
dcleaner = dclean.DataClean()
data_list = dcleaner.get_data()
data_list = [int(x) for x in data_list]
# print(json.dumps(data_dict, indent=4))
data_list.sort()
mean_q2 = 0
print("the cleaned up data_list is as follow:\n\t{}".format(data_list))
mean1 = get_mean(data_list)
quart1, med, quart3, iqr = get_median(data_list)
print("the median for this data set is {}".format(med[0]))
print("quartile 1 = {}, quartile 3 = {}, irq = {}".format(
quart1[0], quart3[0], iqr))
outliers = []
upper_bound = quart3[0] + iqr * 1.5