def Pop_correlation_coefficient(x_data, y_data):
x_mean = mean(x_data)
y_mean = mean(y_data)
a = []
b = []
tot_sum = 0
x = st_dev(x_data)
y = st_dev(y_data)
for i in x_data:
new1 = subtraction(x_mean, i)
zx = division(new1, x)
a.append(zx)
for i in y_data:
new2 = subtraction(y_mean, i)
zy = division(new2, y)
b.append(zy)
for i in range(len(x_data)):
ab = multiplication(a[i], b[i])
tot_sum = addition(tot_sum, ab)
cal_result = division(tot_sum, subtraction(1, len(x_data)))
return cal_result
def Pop_correlation_coefficient():
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
x_data = [1, 25, 34, 4, 51]
y_data = [6, 7, 8, 9, 10]
x_mean = mean(x_data)
y_mean = mean(y_data)
a = []
b = []
ab = []
x = st_dev(x_data)
y = st_dev(y_data)
divisor = multiplication(x, y)
z = len(lst)
for i in x_data:
new1 = subtraction(x_mean, i)
zx = division(new1, x)
a.append(zx)
# (zx)i = (xi – x̄) / s x
for i in y_data:
new2 = subtraction(y_mean, i)
zy = division(new2, y)
b.append(zy)
ab = [a[i] * b[i] for i in range(len(x_data))]
tot_sum = sum(ab)
result = tot_sum / 4
return result
def st_dev(lst):
diffs = 0
m = mean(lst)
for l in lst:
diffs = addition(diffs, square(subtraction(l, m)))
sd = division(diffs, subtraction(1, len(lst)))
x = root(sd)
return x
def confidenceinterval(lst, conf):
x = mean(lst)
std = st_dev(lst)
if conf == 95:
t = 1.96
elif conf == 90:
t = 1.64
elif conf == 99:
t = 2.58
else: # 95 default confidence percentage
t = 1.96
std_error = division(std, root(len(lst)))
conf_upper = addition(x, multiplication(t, std_error))
conf_upper = round(conf_upper, 2)
conf_lower = subtraction(multiplication(t, std_error), x)
conf_lower = round(conf_lower, 2)
return conf_upper, conf_lower
def zscore(lst):
m = mean(lst)
s = st_dev(lst)
for z in lst:
return division(subtraction(m, z), s)
def samp_mean(lst):
ss = random.randint(1, len(lst))
new_values = getSample(lst, ss)
new_mean = mean(new_values)
actual_mean = statistics.mean(new_values) # to compare calculated result
return new_mean, actual_mean
def newmean(self, a):
self.result = mean(a)
return self.result
def zscore(lst):
raw_value = 16
m = mean(lst)
s = st_dev(lst)
return division(subtraction(m, raw_value), s)
