[FIXED] array.array() takes no keyword arguments

Issue

Trying to do a k means clustering on FARS dataset, getting the array.array() takes no keyword arguments error and don't understand why or how to correct it.

Initially was getting errors for int32 which I changed to np.int32 and that corrected but now I am getting the array error and can't figure out how to fix it.

Full error:

    TypeError                                 Traceback (most recent call last)
    <ipython-input-11-29801179ab6c> in <cell line: 5>()
          3 kmeans = KMeans(n_clusters=2, random_state=0, n_init="auto").fit(X)
          4 kmeans.labels_
    ----> 5 array([1, 1, 1, 0, 0, 0], dtype=np.int32)
          6 kmeans.predict([[0, 0], [12, 3]])
          7 array([1, 0], dtype=np.int32)

TypeError: array.array() takes no keyword arguments

Code:

X = np.array([[1, 2], [1, 4], [1, 0],
...               [10, 2], [10, 4], [10, 0]])
kmeans = KMeans(n_clusters=2, random_state=0, n_init="auto").fit(X)
kmeans.labels_
array([1, 1, 1, 0, 0, 0], dtype=np.int32)
kmeans.predict([[0, 0], [12, 3]])
array([1, 0], dtype=np.int32)
kmeans.cluster_centers_
array([[10.,  2.],
       [ 1.,  2.]])

Solution

Don't copy/paste your code as it, some lines are the output of the previous line. This lines are not intended to be used as statements:

>>> kmeans.labels_
array([1, 1, 1, 0, 0, 0], dtype=np.int32)  # this is the output of kmeans.labels_

>>> kmeans.predict([[0, 0], [12, 3]])
array([1, 0], dtype=np.int32)  # this is the output of kmeans.predict(...)

>>> kmeans.cluster_centers_
array([[10.,  2.],  # this is the output of kmean.cluster_centers_
       [ 1.,  2.]])

The code should be:

import numpy as np
from sklearn.cluster import KMeans

X = np.array([[1, 2], [1, 4], [1, 0],
              [10, 2], [10, 4], [10, 0]])

kmeans = KMeans(n_clusters=2, random_state=0, n_init="auto").fit(X)
labels = kmeans.labels_
preds = kmeans.predict([[0, 0], [12, 3]])
centroids = kmeans.cluster_centers_

Usage:

>>> labels
array([1, 1, 1, 0, 0, 0], dtype=int32)

>>> preds
array([1, 0], dtype=int32)

>>> centroids
array([[10.,  2.],
       [ 1.,  2.]])

The documentation said:

Our notational convention is that $ denotes the shell prompt while >>> denotes the Python interpreter prompt:

Answered By - Corralien