def main():
data = extractData.readData(
"http://research.cs.queensu.ca/home/cords2/annualIncome.txt")
data_test = extractData.makeTestSet(data)
data_train = extractData.makeTrainingSet(data)
dataless_50k, datamore_50k = classifierBuild.processSets(data)
print(len(data))
print(len(dataless_50k))
print(len(datamore_50k))
print()
dataStructures(data_train, dataless_50k, datamore_50k)
def main():
# extractData functions
print("Reading in data")
data = extractData.readData("http://research.cs.queensu.ca/home/cords2/annualIncome.txt")
print("Making training and test files")
data_test = extractData.makeTestSet(data)
data_train = extractData.makeTrainingSet(data)
# classifierBuild function
print("Building classifier")
data_model_less, data_model_more = classifierBuild.dataStructures(data_train)
# classifierTest functions
print("Classifying test data")
prediction_points, incorrectly_classified, percent_accuracy = classifierTest.predictData(data_test, data_model_less, data_model_more)
print("Classified Correctly: ", +prediction_points)
print("Classified Incorrectly: ", + incorrectly_classified)
print("Accuracy: ", str(percent_accuracy) + "%")
else:
counter_greater50 += 1
# Return the records predicted correctly, records predicted incorrectly and percent accuracy
return prediction_points, (total_sum - prediction_points), round(
(prediction_points / total_sum) * 100, 2)
# Testing for each function
if __name__ == "__main__":
import extractData # imported for testing purposes
import classifierBuild
print("\n TESTING DATA ON A 15 RECORD SAMPLE")
data = extractData.readData(
"http://research.cs.queensu.ca/home/cords2/annualIncome.txt")
data_test = extractData.makeTestSet(data[:30])
data_train = extractData.makeTrainingSet(data[:30])
data_model_less, data_model_more = classifierBuild.dataStructures(
data_train)
# classifierTest functions
prediction_points, incorrectly_classified, percent_accuracy = predictData(
data_test, data_model_less, data_model_more)
print("\nClassified Correctly: ", +prediction_points)
print("Classified Incorrectly: ", +incorrectly_classified)
print("Accuracy: ", str(percent_accuracy) + "%")
# predictData module test