AttributeError：“函数”对象没有属性“ labels_”

Question

When I execute this code I get the following error:

AttributeError: 'function' object has no attribute 'labels_'

I understand that this message is triggered by the method: clusterWithFewestSamples

by lines like:

minSamples = len(model.labels_)

Any hint on what's wrong or what's lacking?

Many thanks in advance.

Jordi

import pandas as pd
from datetime import timedelta
import matplotlib.pyplot as plt
import matplotlib
from sklearn.cluster import KMeans

matplotlib.style.use('ggplot')


def model(self, num):
    return

def showandtell(title=None):
    if title != None: plt.savefig(title + ".png", bbox_inches='tight', dpi=300)
    plt.show()
    exit()

def clusterInfo(model):
    print "Cluster Analysis Inertia: ", model.inertia_  
    print '------------------------------------------'
    for i in range(len(model.cluster_centers_)):
      print "\n  Cluster ", i
      print "    Centroid ", model.cluster_centers_[i]
      print "    #Samples ", (model.labels_==i).sum() # NumPy Power

def clusterWithFewestSamples(model):
    minSamples = len(model.labels_)
    minCluster = 0
    for i in range(len(model.cluster_centers_)):
        if minSamples > (model.labels_==i).sum():
            minCluster = i
            minSamples = (model.labels_==i).sum()
        print "\n Cluster With Fewest Samples: ", minCluster
    return (model.labels_==minCluster)

def doKMeans(data, clusters=0):
    df_user1 = data.loc[:, ['TowerLon', 'TowerLat']]
    kmeans = KMeans(n_clusters=clusters)
    kmeans.fit(df_user1)
    labels = kmeans.predict(df_user1)
    centroids = kmeans.cluster_centers_
    ax.scatter(centroids[:,0], centroids[:,1], marker='x', c='red', alpha=0.5, linewidths=3, s=169)
    print centroids
    return model

df = pd.read_csv('Datasets/CDR.csv')
df.CallDate = pd.to_datetime(df.CallDate, errors='coerce')
df.CallTime = pd.to_timedelta(df.CallTime, errors='coerce')

PhoneList = df["In"].unique()

print "\n\nExamining person: ", 0

user1 = df[df.In == PhoneList[0]]
user1 = user1[(user1.DOW != 'Sat') & (user1.DOW != 'Sun')]
user1 = user1[(user1.CallTime > '09:00:00') | (user1.CallTime < '17:00:00')]

fig = plt.figure()

ax = fig.add_subplot(111)
ax.scatter(user1.TowerLon,user1.TowerLat, c='g', marker='o', alpha=0.2)
ax.set_title('Weekday Calls (>7:306am or <17p)')

model = doKMeans(user1, 2)

midWayClusterIndices = clusterWithFewestSamples(model)
midWaySamples = user1[midWayClusterIndices]
print " Its Waypoint Time: ", midWaySamples.CallTime.mean()

ax.scatter(model.cluster_centers_[:,1], model.cluster_centers_[:,0], s=169, c='r', marker='x', alpha=0.8, linewidths=2)

showandtell('Weekday Calls Centroids')

Answer 1

Where does model come from?

def doKMeans(data, clusters=0):
    ...
    return model

model = doKMeans(user1, 2)

In doKMeans() nothing ever gets assigned to model , I'm surprised it doesn't throw a NameError exception. Maybe it should be

def doKMeans(data, clusters=0):
    ...
    return kmeans

An sklearn.cluster.KMeans object does have a labels_ attribute.

---

You expect model to have a labels_ attribute but you have defined model as a function that returns None

def model(self, num):
    return

When doKMeans is called, it returns the function named model

def doKMeans(data, clusters=0):
    ...
    return model

So the statement model = doKMeans(user1, 2) does nothing:

>>> def f(a,b):
    return
>>> f
<function f at 0x00000000034A9840>

>>> def g(a,b):
    return f

>>> f = g(1,2)
>>> f
<function f at 0x00000000034A9840>

Neither the function, model , or its return value, None have a labels_ attribute.