Python 2 bis 3 Fehler. Typeerror: unorderable Typen: int() <= str()

Question

Ich habe ein Programm, das auf k means-Algorithmus basiert. Wenn ich das Programm auf Python 2 ausführen, gibt es keine Probleme. Wenn ich es auf Python 3 zu verwenden, habe ich die folgenden Fehlermeldungen erhalten:

Traceback (most recent call last): 
    File "kmeans.py", line 111, in <module> 
    main() 
    File "kmeans.py", line 13, in main 
    clusters = kmeans(points, num_cluster, cutoff) 
    File "kmeans.py", line 67, in kmeans 
    initial = random.sample(points, k) # generating k random points for initial centroids 
    File "/afs/cad/linux/anaconda3/anaconda/pkgs/python-3.5.2-1/lib/python3.5/random.py", line 314, in sample 
    if not 0 <= k <= n: 
TypeError: unorderable types: int() <= str() 

Dies ist der Code habe ich so weit, ich kann nicht scheinen, um herauszufinden, wie zu beheben.

import sys 
import math 
import random 

def main(): 
    points = readDataFile("datafile.txt") 
    print ('Original dataset: \n' + str(points) + '\n') 

    # generating clusters 
    # num_cluster = 2 # k for default testing value 
    num_cluster = input ('Please declare number of clusters k: ') #k 
    cutoff = 0.5 # iter cut off 
    clusters = kmeans(points, num_cluster, cutoff) 

    # Print our clusters 
    for i,c in enumerate(clusters): 
     print ("Cluster " + str(i) + "\t" + str(c)) 

# reading in data points from file 
def readDataFile(filename): 
    points = [] 
    lines = [line.rstrip('\n') for line in open(filename)] 
    for line in lines: 
     pieces = line.split(' ') 
     points.append(Point([int(pieces[0]), int(pieces[1])])) 
    return points 

# point class to contain a set of 2d coordinates 
class Point: 
    def __init__(self, coords): 
     self.coords = coords 
     self.n = len(coords) 

    def __repr__(self): 
     return str(self.coords) 

# cluster class to define cluster functionality 
class Cluster: 
    # constructor 
    def __init__(self, points): 
     self.points = points 
     self.n = points[0].n 
     self.centroid = self.calculateCentroid() 

    # to string method 
    def __repr__(self): 
     return str(self.points) 

    # updates the current loc 
    def update(self, points): 
     old_centroid = self.centroid 
     self.points = points 
     self.centroid = self.calculateCentroid() 
     shift = getDistance(old_centroid, self.centroid) 
     return shift 

    # calculates new location of centroid based on mean 
    def calculateCentroid(self): 
     numPoints = len(self.points) # finding center point 
     coords = [p.coords for p in self.points] # list of all coordinates in curr cluster 
     unzipped = zip(*coords) 
     centroid_coords = [math.fsum(dList)/numPoints for dList in unzipped] # mean for each point 
     return Point(centroid_coords) 

# kmean algo to cluster data 
def kmeans(points, k, cutoff): 
    initial = random.sample(points, k) # generating k random points for initial centroids 
    clusters = [Cluster([p]) for p in initial] # creating k clusters using generated centroids 

    loopCounter = 0 # looping thru data until the clusters stabilize 
    while True: 
     # list of lists to hold point objects 
     lists = [ [] for c in clusters] 
     clusterCount = len(clusters) 
     loopCounter += 1 

     for p in points: 
      # dist bw curr to first centroid 
      smallest_distance = getDistance(p, clusters[0].centroid) 
      clusterIndex = 0 

      for i in range(clusterCount - 1): 
       # calc point to point diff in distances 
       distance = getDistance(p, clusters[i+1].centroid) 
       # setting cluster index based on dist 
       if distance < smallest_distance: 
        smallest_distance = distance 
        clusterIndex = i+1 
      lists[clusterIndex].append(p) # appending point to cluster 

     biggest_shift = 0.0 # resetting biggest_shift to zero for curr iteration 
     for i in range(clusterCount): 
      # calc centroid movement dist 
      shift = clusters[i].update(lists[i]) 
      # keeping track of the largest move from all cluster centroid updates 
      biggest_shift = max(biggest_shift, shift) 

     # checking if centroids movement is not vast (convergence) 
     if biggest_shift < cutoff: 
      break 
    return clusters 


# generates euclidean distance between two points 
def getDistance(a, b): 
    ret = reduce(lambda x,y: x + pow((a.coords[y]-b.coords[y]), 2),range(a.n),0.0) 
    return math.sqrt(ret) 

# init 
if __name__ == "__main__": 
    main() 

Auch meine data.txt Datei sieht wie folgt aus:

0 0 
0 1 
1 0 
10 10 
10 11 
11 10 
11 11 

Jede Hilfe wäre sehr dankbar.

Answer 1

num_cluster = input ('Please declare number of clusters k: ') #k 
cutoff = 0.5 # iter cut off 
clusters = kmeans(points, num_cluster, cutoff) 

input gibt einen String zurück, so dass Sie es zu einem int konvertieren müssen:

num_cluster = int(input ('Please declare number of clusters k: ')) #k