def mean(in_list):
"""
Returns mean of given list
:param in_list: list to calculate mean from
:return: float rounded to 5 decimal places
"""
return round(sum(in_list) / zcount.count(in_list), 5)
def zstddev(self):
test_cases = [
([10, 12, 23, 23, 16, 23, 21, 16], 5.24),
([35, 5.2, 156, 1.111, 23, 0.1, 65], 55.84),
([9.14, 8.14, 8.74, 8.77, 9.26, 8.1, 6.13, 3.1, 9.13, 7.26, 4.74], 2.03)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def zstderr(self):
test_cases = [
([21, 568, 48, 543, 21, 2., 23, 798, 8.1], 105.36),
([287, 54, 16, 65, 87, 49, 62], 34.04),
([7, 1, 6, 9, 88, 5, 2], 11.9)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def zvariance(self):
test_cases = [
([8, 10, 13, 14, 17], 12.3),
([4.5, 7.1, 12.3, 17, 20], 42.3),
([0, 1], 0.5)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def test_zmedian(self):
test_cases = [
([0], 0),
([123, 237, 58, 87, 57], 87),
([0, 1.31, 867, .76867, 23, 564, 234, 6575], 128.5)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def test_zmean(self):
test_cases = [
([1, 2, 3, 4, 5, 6, 7, 8, 9, 10], 5.5),
([10, 15.2, 32.12, 9, 41], 21.46),
([0], 0)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def stderr(in_list):
"""
Calculates standard error of mean of given list
:param in_list: list of values
:return: float rounded to 5 decimal places
"""
std_dev = zstddev.stddev(in_list)
n = zcount.count(in_list)
std_err = std_dev / sqrt(n)
return round(std_err, 5)
def test_zmode(self):
test_cases = [
([1, 4, 2, 9, 7, 8, 9, 3, 1, 123, 2.3, 2.3, 5, 2.3, 23, 2.3], 2.3),
([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 123], 1),
([-1, -1, -2, -3, -1, -3, -3, -3, -3], -3)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def test_zcount(self):
test_cases = [
([], 0),
([1, 2, 3, 4, 5, 6], 6),
([1.1, 2.2, 3.3, 4.4, 5.5], 5),
([10, .2, 1032, 3, 75, 5.6], 6)
]
for list_in, expected in test_cases:
with self.subTest(f"{list_in} -> {expected}"):
self.assertEqual(expected, zcount.count(list_in))
def variance(in_list):
"""
Finds variance of given list
:param in_list: list of values
:return: float rounded to 5 decimal places
"""
n = zcount.count(in_list)
mean = zmean.mean(in_list)
d = [(x - mean) ** 2 for x in in_list]
v = sum(d) / (n - 1)
return round(v, 5)
def corr(l1, l2):
"""
Calculates the correlation between two lists of values
:param l1: list of values
:param l2: list of values
:return: float rounded to 5 decimal places
"""
l1_sum = sum(l1)
l2_sum = sum(l2)
l1_times_l2_sum = sum([l1[i] * l2[i] for i in range(len(l1))])
l1_sq_sum = sum([x**2 for x in l1])
l2_sq_sum = sum([x**2 for x in l2])
n = zcount.count(l1)
corr_num = (n * l1_times_l2_sum) - (l1_sum * l2_sum)
corr_den = sqrt(
((n * l1_sq_sum) - (l1_sum**2)) * ((n * l2_sq_sum) - (l2_sum**2)))
corr = corr_num / corr_den
return round(corr, 5)
def csv_reader(file):
reader = csv.DictReader(open(file))
result = {}
for row in reader:
for column, value in row.items():
result.setdefault(column, []).append(float(value))
return result
test = csv_reader(dataOne)
x = [10.0, 8.0, 13.0, 9.0, 11.0, 14.0, 6.0, 4.0, 12.0, 7.0, 5.0]
y = [9.14, 8.14, 8.74, 8.77, 9.26, 8.1, 6.13, 3.1, 9.13, 7.26, 4.74]
print("Count")
print(zcount.count(x))
print("Mean")
print(zmean.mean(x))
print("Mode")
print(zmode.mode(x))
print("Median")
print(zmedian.median(x))
print("Variance")
print(zvariance.variance(x))
print("Standard Deviation")
print(zstderr.stdderr(x))
print("Standard Error")
print(zstddev.stddev(x))
print("Correlation")
print(zcorr.covariance(x, y))
def test_count2(self):
test_data = []
self.assertEqual(len(test_data), zcount.count(test_data))
def test_count1(self):
test_data = [1, 2, 3, 4, 5, 6, 7]
self.assertEqual(len(test_data), zcount.count(test_data))
def test_count3(self):
test_data = [1, 1, 1]
self.assertEqual(len(test_data), zcount.count(test_data))
from statzcw import csvReader, zcount, zmean, zmode, \
zmedian, zvariance, zstddev, zstderr, zcorr
csv_files = ['dataZero.csv', 'dataOne.csv', 'dataTwo.csv', 'dataThree.csv']
for f in csv_files:
print('----------------------')
print('File: ', f)
print('----------------------')
data = csvReader.read_csv(f)
x = data[0]
y = data[1]
# x list
print('x list')
print('------')
print('Count X: ', zcount.count(x))
print('Mean X: ', zmean.mean(x))
print('Median X ', zmedian.median(x))
print('Mode X: ', zmode.mode(x))
print('Variance X: ', zvariance.variance(x))
print('Standard Deviation X: ', zstddev.stddev(x))
print('Standard Error X: ', zstderr.stderr(x))
# y list
print('-------')
print('y list:')
print('-------')
print('Count Y: ', zcount.count(y))
print('Mean Y: ', zmean.mean(y))
print('Median Y ', zmedian.median(y))
print('Mode Y: ', zmode.mode(y))
