Errors in python code when running in terminal

Question

import csv
import random
import math

def loadCsv(filename):
    lines = csv.reader(open(filename, "rb"))
    dataset = list(lines)
    for i in range(len(dataset)):
        dataset[i] = [float(x) for x in dataset[i]]
    return dataset

def splitDataset(dataset, splitRatio):
    trainSize = int(len(dataset) * splitRatio)
    trainSet = []
    copy = list(dataset)
    while len(trainSet) < trainSize:
        index = random.randrange(len(copy))
        trainSet.append(copy.pop(index))
    return [trainSet, copy]

def separateByClass(dataset):
    separated = {}
    for i in range(len(dataset)):
        vector = dataset[i]
        if (vector[-1] not in separated):
            separated[vector[-1]] = []
        separated[vector[-1]].append(vector)
    return separated

def mean(numbers):
    return sum(numbers)/float(len(numbers))

def stdev(numbers):
    avg = mean(numbers)
    variance = sum([pow(x-avg,2) for x in numbers])/float(len(numbers)-1)
    return math.sqrt(variance)

def summarize(dataset):
    summaries = [(mean(attribute), stdev(attribute)) for attribute in 
    zip(*dataset)]
    del summaries[-1]
    return summaries

def summarizeByClass(dataset):
    separated = separateByClass(dataset)
    summaries = {}
    for classValue, instances in separated.iteritems():
        summaries[classValue] = summarize(instances)
    return summaries

def calculateProbability(x, mean, stdev):
    exponent = math.exp(-(math.pow(x-mean,2)/(2*math.pow(stdev,2))))
    return (1 / (math.sqrt(2*math.pi) * stdev)) * exponent

def calculateClassProbabilities(summaries, inputVector):
    probabilities = {}
    for classValue, classSummaries in summaries.iteritems():
        probabilities[classValue] = 1
        for i in range(len(classSummaries)):
            mean, stdev = classSummaries[i]
            x = inputVector[i]
            probabilities[classValue] *= calculateProbability(x, mean, stdev)
    return probabilities

def predict(summaries, inputVector):
    probabilities = calculateClassProbabilities(summaries, inputVector)
    bestLabel, bestProb = None, -1
    for classValue, probability in probabilities.iteritems():
        if bestLabel is None or probability > bestProb:
            bestProb = probability
            bestLabel = classValue
    return bestLabel

def getPredictions(summaries, testSet):
    predictions = []
    for i in range(len(testSet)):
        result = predict(summaries, testSet[i])
        predictions.append(result)
    return predictions

def getAccuracy(testSet, predictions):
    correct = 0
    for i in range(len(testSet)):
        if testSet[i][-1] == predictions[i]:
            correct += 1
    return (correct/float(len(testSet))) * 100.0

def main():
    filename = 'processed.cleveland.data.csv'
    splitRatio = 0.67
    dataset = loadCsv(filename)
    trainingSet, testSet = splitDataset(dataset, splitRatio)
    print('Split {0} rows into train={1} and test={2} rows').format(len(dataset), len(trainingSet), len(testSet))
    summaries = summarizeByClass(trainingSet)
    predictions = getPredictions(summaries, testSet)
    accuracy = getAccuracy(testSet, predictions)
    print('Accuracy: {0}%').format(accuracy)

main()

The code above is a naive Bayes machine learning python script. I am trying to use the code on a dataset that is stored in processed.cleveland.data.csv. However, I keep getting the following errors:

Traceback (most recent call last):
File "./naivebayespython.py", line 101, in <module>
main()
File "./naivebayespython.py", line 91, in main
dataset = loadCsv(filename)
File "./naivebayespython.py", line 10, in loadCsv
dataset[i] = [float(x) for x in dataset[i]]
ValueError: could not convert string to float: ?

Could somebody please tell me what I am doing wrong and suggest how to fix this? I am relatively new to Python, so an explanation would also be helpful. Thanks!

Apparently one of the elements in your dataset is '?', not a number. — melpomene
– melpomene, Commented Dec 30, 2017 at 16:05
Possible duplicate of ValueError: could not convert string to float: id — wwii
– wwii, Commented Dec 30, 2017 at 16:47
@melpomene It seems to not work even after I take out the rows with '?' — Krishi Kishore
– Krishi Kishore, Commented Dec 30, 2017 at 17:26

Patrick Artner · Accepted Answer · 2017-12-30 16:13:58Z

1

You can catch conversion errors with try: and except: but aware of what is conversable to float - see this answer for an exhaustive list: https://stackoverflow.com/a/20929881/7505395

Modification to capture wrong conversion

def checkIfFloatable(something): # change the name ;)
    try:
        if float(something):
            return True
    except:
        return False

def loadCsv(filename):
    lines = csv.reader(open(filename, "rb"))
    dataset = list(lines)
    for i in range(len(dataset)):
        dataset[i] = [float(x) for x in dataset[i] if checkIfFloatable(x)] # else None
    return dataset

answered Dec 30, 2017 at 16:13

Patrick Artner

51.9k10 gold badges50 silver badges79 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Errors in python code when running in terminal

1 Answer 1

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related