def generateSolutions(self, queriesFile, solutionsFile):
# get queries set from queires file
querySet = getInputData(queriesFile)
# open solutions file for writing
outfile = open(solutionsFile, 'w')
# loop over each queries set
for i in range(0, len(querySet)):
# get prediction for each record in queries set
prediction = mdclassify(querySet[i], self.tree)
if ('<=50K' in prediction):
prediction = '<=50K'
else:
prediction = '>50K'
# format a string for output
tempstr = "tst" + str(i + 1) + "," + prediction
# write to file
print(tempstr, file = outfile)
# close output file
outfile.close()
def generateSolutions(self, queriesFile, solutionsFile):
# get queries set from queires file
querySet = getInputData(queriesFile)
# open solutions file for writing
outfile = open(solutionsFile, 'w')
# loop over each queries set
for i in range(0, len(querySet)):
# get prediction for each record in queries set
prediction = mdclassify(querySet[i], self.tree)
if ('<=50K' in prediction):
prediction = '<=50K'
else:
prediction = '>50K'
# format a string for output
tempstr = "tst" + str(i + 1) + "," + prediction
# write to file
print(tempstr, file=outfile)
# close output file
outfile.close()
def generateSolutions(self, queriesFile, solutionsFile):
# get queries set from queires file
querySet = getInputData(queriesFile)
# open solutions file for writing
outfile = open(solutionsFile, 'w')
# loop over each queries set
for i in range(0, len(querySet)):
# get prediction for each record in queries set
prediction = self.knnestimate(querySet[i], k = 5)
# format a string for output
tempstr = "tst" + str(i + 1) + "," + prediction
# write to file
print(tempstr, file = outfile)
# close output file
outfile.close()
# Salary Prediction System
# to classify employees' salaries.
#
# Implemented Decision Tree and KNN models.
# Solutions are generated using Dicision Tree.
'''
from classes.knn import knn
from functions.crossvalidate import crossValidate
from functions.function import getInputData
if __name__ == '__main__':
print("Start processing...")
''' load training data '''
# get training data from data source file
sourceData = getInputData('./../data/trainingset.txt')
''' cross validate training data '''
# split source data to training set and test set randomly by multiple times
# calculate the mean accuracy
# select the model that generates the highest accuracy
print("cross validating training data...")
# knn
correct = crossValidate(knn, sourceData, 10, 0.05)
print("knn correct: " + str(correct))
# decision tree
#correct = crossValidate2(buildtree, sourceData, 10, 0.05)
#print("knn correct: " + str(correct))
''' export predictions '''
# Implemented Decision Tree and KNN models.
# Solutions are generated using Dicision Tree.
'''
from classes.knn import knn
from functions.crossvalidate import crossValidate
from functions.function import getInputData
if __name__ == '__main__':
print ("Start processing...")
''' load training data '''
# get training data from data source file
sourceData = getInputData('./../data/trainingset.txt')
''' cross validate training data '''
# split source data to training set and test set randomly by multiple times
# calculate the mean accuracy
# select the model that generates the highest accuracy
print ("cross validating training data...")
# knn
correct = crossValidate(knn, sourceData, 10, 0.05)
print("knn correct: " + str(correct))
# decision tree
#correct = crossValidate2(buildtree, sourceData, 10, 0.05)
#print("knn correct: " + str(correct))
