collection of function useful for doing statistical analysis

python stats util

# Pearson correlation coeficient
# x, y are two arrays
np.corrcoef(x,y)[0,1]

def ecdf(list):
    """
      Empirical cumulative distribution function
      Afterwards can be called
      plt.plot(x, y, marker='.')
    """
    x = np.sort(list)
    y = np.arange(1, len(list) + 1) / len(list)
    return x, y
    
    
def bootsrap_replicate(list, fx):
    """
        Apply a function (np.mean, np.std) to a newly sampled list with replacement
        Used to make large simulated mesurements (of the applied) function for determining the 
        normal distribution of an event
    """
    bootstrap_list = np.random.choice(list, len(list))
    return fx(bootstrap_list)
    
def permutation_sample(a, b):
    """
        Generate a permutation sample from two arrays
    """

    # Concatenate the data sets: data
    data = np.concatenate((a, b))

    # Permute the concatenated array: permuted_data
    permuted_data = np.random.permutation(data)

    # Split the permuted array into two: 
    sample_1 = permuted_data[:len(a)]
    sample_2 = permuted_data[len(a):]

    return sample_1, sample_2