#  Python 3
#  File: Assignment2_Exercise1_read_data.py
#  For Computational Statistics class, Fall 2026
#  Authors: Jonathan Goodman, goodman@cims.nyu.edu
#  class web site: https://math.nyu.edu/~goodman/teaching/ComputationalStatistics2026/ComputationalStatistics.html

"""  
    Read a pandas dataframe in parquet format and do a simple computation
    with it.  To be modified for Exercise 1 of assignment 2
"""

import numpy             as np    # load the nympy library, call it np
import matplotlib.pyplot as plt   # the plotting package
import pandas            as pd    # the pandas library

filename = "Assignment2_Exercise1_dataset1.parquet"

def log_r(x,         # the data value
          nu = 3.,   # the number of degrees of freedom
          r = .5     # the lengthscale
    ):               # return log( r(x, params) ), see notes for definition
   return x*x    # replace with correct function

# read into a pandas dataframe
df = pd.read_parquet(filename)  # read into a pandas dataframe

# calculate log(r(x)) for each x in the dataset
log_like_terms = df["X_k"].map(log_r)  # calculate log(r(x))

log_likelihood_sum = log_like_terms.sum()   # add the numbers, for no reason
print("the log likelihood sum is " + str(log_likelihood) )