def compute_information_gain(vectorizer: CountVectorizer, word: str, dataTrain: csr_matrix, targetTrain: [int]) \
-> float:
"""Compute information gain of given word and return value"""
word = word.lower()
parentEntropy = computeEntropy(targetTrain)
numRows = dataTrain.get_shape()[0]
wordYesSplit = {0: 0, 1: 0}
wordNoSplit = {0: 0, 1: 0}
for count in range(numRows):
simpleSentence = vectorizer.inverse_transform(dataTrain[count])[0]
if word in simpleSentence:
wordYesSplit[targetTrain[count]] += 1
else:
wordNoSplit[targetTrain[count]] += 1
wordYesArray = wordYesSplit[0] * [0] + wordYesSplit[1] * [1]
#print("lenYesArr: {}, YesDict: {}".format(len(wordYesArray), wordYesSplit))
wordNoArray = wordNoSplit[0] * [0] + wordNoSplit[1] * [1]
#print("lenNoArr: {}, NoDict: {}".format(len(wordNoArray), wordNoSplit))
yesSplitEntropy = computeEntropy(wordYesArray)
noSplitEntropy = computeEntropy(wordNoArray)
probYes = len(wordYesArray) / numRows
probNo = len(wordNoArray) / numRows
#print("parEnt: {}, YesEnt: {}, NoEnt: {}".format(parentEntropy, yesSplitEntropy, noSplitEntropy))
#print("probYes= {}, probNo= {}".format(probYes, probNo))
return parentEntropy - (yesSplitEntropy * probYes +
noSplitEntropy * probNo)
