shandou

import numpy as np

r = - 0.654 # Pearson's r from sampled data
z_prime = 0.5 * np.log((1 + r) / (1 - r))

n = 34 # Sample size
se = 1 / np.sqrt(n - 3) # Sample standard error

CI_lower = z_prime - z_critical * se
CI_upper = z_prime + z_critical * se

shandou

import scipy.stats
import numpy as np

alpha = 0.05 / 2 # Two-tail test
z_critical = scipy.stats.norm.ppf(1 - alpha)

shandou

import scipy.stats

n = 25 # Number of samples n
df = n - 2 # Degrees of freedom
alpha = 0.05 # Significant level

# Non-direction tests for computing t-critical value
t_critical = scipy.stats.t.ppf(1 - alpha / 2, df)