IA - 2022-11-09

# 6.py
import numpy
import numpy as np
import time

import math
import random

def randomCol(
    pHowManyEls:int=10
):
    col = list()
    walk = range(pHowManyEls)
    for step in walk:
        f = random.random() # [0, 1[
        f *= random.randint(10, 1000) # [10, 1000]
        col.append(f)
    # for
    return col
# def randomCol

"""
chiSquare rewritten to take advantage
of broadcasting ops with numpy arrays
"""
def chiSquare_v2(pO, pE):
    pO = numpy.array(pO)
    pE = numpy.array(pE)

    if(len(pO)==len(pE)):
        v = (pO-pE)**2/pE
        return v.sum()
    else:
        return False
    # if-else
# def chiSquare_v2

def chiSquare(
    pColObservedValues:list,
    pColExpectedValues:list
)->float | bool:
    iHowManyObserved = len(pColObservedValues)
    iHowManyExpected = len(pColExpectedValues)
    bCanCalculate = iHowManyObserved == iHowManyExpected
    if (bCanCalculate):
        sum = 0
        for walk in range(iHowManyExpected):
            o = pColObservedValues[walk]
            e = pColExpectedValues[walk]
            dist = o-e # <0 if e>o
            #dist = dist**2
            dist = math.pow(dist, 2)
            parcel = dist/e
            sum += parcel
        # for
        return sum
    else:
        # collections do NOT have the same size, can NOT
        # calculate the chi-square statistic
        return False
    # if-else
# def chiSquare

"""
at some stage during class time,
we changed the "feedback" function to be able
to work with any implementation of the
chiSquare function
To achieve so, it began having a 3rd param
to represent whatever function we wanted
"""
def feedback(pC1:list, pC2:list, pDescription:str, pFChiSquare):
    strMsg = f"{pDescription} between\n"
    strMsg += f"observed:{pC1[:2]}...\nexpected:{pC2[:2]}...\n"
    #strMsg +=f"observed:{pC1}\nexpected:{pC2}\n"

    ti = time.time()
    chi_square = pFChiSquare(pC1, pC2)
    tf = time.time()
    timeItTook = tf - ti

    strMsg +=f"is {chi_square}\n"
    strMsg += f"Computation time: {timeItTook}\n"
    print(strMsg)
# def feedback

col1 = randomCol(55555) # 5 elements
feedback(col1, col1, "via chiSquare", chiSquare)
feedback(col1, col1, "via chiSquare_v2", chiSquare_v2)

col2 = randomCol(55555)
feedback(col1, col2, "via chiSquare", chiSquare)
feedback(col1, col2, "via chiSquare_v2", chiSquare_v2)

#*******************************+ Jaccard - index

def jaccardIndex(pA:list, pB:list):
    sA:set = set(pA)
    sB:set = set(pB)
    intersection = sA.intersection(sB)
    reunion = sA.union(sB)
    cardinalityOfI = len(intersection)
    cardinalityOfR = len(reunion)
    j = cardinalityOfI/cardinalityOfR
    return j
# def jaccardIndex

feedback(
    [10, 20, 30],
    [10, 40, 30],
    "J-index",
    jaccardIndex
)

**********

CC: Coordinating conjunction
CD: Cardinal number
DT: Determiner
EX: Existential there
FW: Foreign word
IN: Preposition or subordinating conjunction
JJ: Adjective
VP: Verb Phrase
JJR: Adjective, comparative
JJS: Adjective, superlative
LS: List item marker
MD: Modal
NN: Noun, singular or mass
NNS: Noun, plural
PP: Preposition Phrase
NNP: Proper noun, singular Phrase
NNPS: Proper noun, plural
PDT: Pre determiner
POS: Possessive ending
PRP: Personal pronoun Phrase
PRP: Possessive pronoun Phrase
RB: Adverb
RBR: Adverb, comparative
RBS: Adverb, superlative
RP: Particle
S: Simple declarative clause
SBAR: Clause introduced by a (possibly empty) subordinating conjunction
SBARQ: Direct question introduced by a wh-word or a wh-phrase.
SINV: Inverted declarative sentence, i.e. one in which the subject follows the tensed verb or modal.
SQ: Inverted yes/no question, or main clause of a wh-question, following the wh-phrase in SBARQ.
SYM: Symbol
VBD: Verb, past tense
VBG: Verb, gerund or present participle
VBN: Verb, past participle
VBP: Verb, non-3rd person singular present
VBZ: Verb, 3rd person singular present
WDT: Wh-determiner
WP: Wh-pronoun
WP: Possessive wh-pronoun
WRB: Wh-adverb