cmantas

        WITH impressions AS(
            SELECT serve_id, MIN(dt) AS dt
            FROM little_sister_kraken_events
            WHERE event_name = 'impression'
            AND get_json_object(event_details, '$.trackable_type') = 'Post'
            AND page IN ('Dashboard', 'DashboardTab')
            AND uuid_type = 'u'
            AND uuid != ''
            AND dt BETWEEN '2022-05-16' AND '2022-05-23'
            GROUP BY serve_id

cmantas

def cdf(data, label, show = True):
    data_size=len(data)

    # Set bins edges
    data_set=sorted(set(data))
    bins=np.append(data_set, data_set[-1]+1)

    # Use the histogram function to bin the data
    counts, bin_edges = np.histogram(data, bins=bins, density=False)

cmantas

from random import shuffle
import requests
from urllib.parse import urlparse, parse_qs
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.ERROR)
import matplotlib.pyplot as plt

def read_data(fname, token='#'):
    with open(fname) as f:
        lines = f.readlines()

cmantas

# careful!, a and b should have the same elements

# Kendall's tau (τ) measure for any two arrays
# @param a[Array] an array (sorted by a ranking)
# @param b[Array] array having the same elements as a, sorted by another ranking
# @return [Float] in range [-1, 1]
def kendal(a, b)
  pairs = a.combination(2) # note that for each of those pairs, the position of
  # the second element in array `a` is subsequent to the position of the first.
  # (aka, if a = ['a', 'b', 'c'], value ['c','b'] cannot exist in `pairs`)