def checkDistributions():
matFileName = "../../data/EgoAlterTransmissions.mat"
examplesList = ExamplesList.readFromMatFile(matFileName)
numFeatures = examplesList.getDataFieldSize("X", 1)
X = examplesList.getDataField("X")[:, 0:numFeatures/2]
Z = examplesList.getDataField("X")[:, numFeatures/2:numFeatures]
y = examplesList.getDataField("y")
A = Z[y==-1, :]
#Now load directly from the CSV file
#Learn the distribution of the egos
eCsvReader = EgoCsvReader()
egoFileName = "../../data/EgoData.csv"
alterFileName = "../../data/AlterData.csv"
egoQuestionIds = eCsvReader.getEgoQuestionIds()
alterQuestionIds = eCsvReader.getAlterQuestionIds()
(X2, titles) = eCsvReader.readFile(egoFileName, egoQuestionIds)
X2[:, eCsvReader.ageIndex] = eCsvReader.ageToCategories(X2[:, eCsvReader.ageIndex])
(mu, sigma) = Util.computeMeanVar(X)
(mu2, sigma2) = Util.computeMeanVar(X2)
(mu3, sigma3) = Util.computeMeanVar(Z)
(mu4, sigma4) = Util.computeMeanVar(A)
#Seems okay. Next check alters
print(("Mean " + str(mu - mu4)))
print(("Variance " + str(numpy.diag(sigma - sigma4))))
"""
Analysis between the Egos in EgoData.csv and those in EgoAlterTransmissions.mat
reveals that the distributions match closely. The main differences are
in the means and variances in Q44A - D, but this isn't too suprising.
"""
"""
#checkDistributions()
"""
We will read ego and alters data, and check they have the same values.
"""
egoFileName = "../../data/EgoData.csv"
alterFileName = "../../data/AlterData.csv"
eCsvReader = EgoCsvReader()
egoQuestionIds = eCsvReader.getEgoQuestionIds()
alterQuestionIds = eCsvReader.getAlterQuestionIds()
missing = 0
(egoX, titles) = eCsvReader.readFile(egoFileName, egoQuestionIds, missing)
egoX[:, eCsvReader.ageIndex] = eCsvReader.ageToCategories(egoX[:, eCsvReader.ageIndex])
(alterX, titles) = eCsvReader.readFile(alterFileName, alterQuestionIds, missing)
alterX[:, eCsvReader.ageIndex] = eCsvReader.ageToCategories(alterX[:, eCsvReader.ageIndex])
numFeatures = egoX.shape[1]
numEgoExamples = egoX.shape[0]
numAlterExamples = alterX.shape[0]
for i in range(0, numFeatures):
(histE, uniqElementsE) = Util.histogram(egoX[:, i])
(histA, uniqElementsA) = Util.histogram(alterX[:, i])
print((str(i) + " " + str(egoQuestionIds[i])))
print(("Ego " + str(uniqElementsE)))
print(("Alter " + str(uniqElementsA)))
