TypeError: float() argument must be a string or a number, array = np.array(array, dtype=dtype, order=order, copy=copy) - error-handling

Question

Im applying K-means clustering to data frame from cvs and excel files
ref: http://scikit-learn.org/stable/auto_examples/cluster/plot_cluster_iris.html#example-cluster-plot-cluster-iris-py
I try to run the code with my data from the csv file, data looks like:
DataFile
However receive following errors:
Traceback (most recent call last):
File "", line 1, in
runfile('/Users/nadiastraton/Documents/workspacePython/02450Toolbox_Python/Thesis/Scripts/Clustering/cluster3.py', wdir='/Users/nadiastraton/Documents/workspacePython/02450Toolbox_Python/Thesis/Scripts/Clustering')
File "/Applications/anaconda2/lib/python2.7/site-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 699, in runfile
execfile(filename, namespace)
File "/Applications/anaconda2/lib/python2.7/site-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 81, in execfile
builtins.execfile(filename, *where)
File "/Users/cluster3.py", line 46, in
est.fit(x.as_matrix)
File "/Applications/anaconda2/lib/python2.7/site-packages/sklearn/cluster/k_means_.py", line 812, in fit
X = self._check_fit_data(X)
File "/Applications/anaconda2/lib/python2.7/site-packages/sklearn/cluster/k_means_.py", line 786, in _check_fit_data
X = check_array(X, accept_sparse='csr', dtype=np.float64)
File "/Applications/anaconda2/lib/python2.7/site-packages/sklearn/utils/validation.py", line 373, in check_array
array = np.array(array, dtype=dtype, order=order, copy=copy)
TypeError: float() argument must be a string or a number
print(doc)
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import pandas as pd
from sklearn.cluster import KMeans
np.random.seed(5)
centers = [[1, 1], [-1, -1], [1, -1]]
data=pd.read_csv('/DataVisualisationSample.csv')
print(data.head())
x = pd.DataFrame(data,columns = ['Post_Share_Count','Post_Like_Count','Comment_Count'])
y = pd.DataFrame(data,columns = ['Comment_Like_Count'])
print(x.info())
estimators = {'k_means_data_3': KMeans(n_clusters=3),
'k_means_data_8': KMeans(n_clusters=12),
'k_means_data_bad_init': KMeans(n_clusters=3, n_init=1,
init='random')}
fignum = 1
for name, est in estimators.items():
fig = plt.figure(fignum, figsize=(4, 3))
plt.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)
plt.cla()
est.fit(x.as_matrix)
labels = est.labels_
ax.scatter(x[:, 2], x[:, 0], x[:, 1], c=labels.astype(np.int))
ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Post_Share_Count')
ax.set_ylabel('Post_Like_Count')
ax.set_zlabel('Comment_Count')
fignum = fignum + 1
# Plot the ground truth
fig = plt.figure(fignum, figsize=(4, 3))
plt.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)
plt.cla()
for name, label in [('Popular', 0),
('Not Popular', 1),
('Least Popular', 2)]:
ax.text3D(x[y == label, 2].mean(),
x[y == label, 0].mean() + 1.5,
x[y == label, 1].mean(), name,
horizontalalignment='center',
bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))
# Reorder the labels to have colors matching the cluster results
y = np.choose(y, [1, 2, 0]).astype(np.int)
ax.scatter(x[:, 2], x[:, 0], x[:, 1], c=y).astype(np.int)
ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Post_Share_Count')
ax.set_ylabel('Post_Like_Count')
ax.set_zlabel('Comment_Count')
plt.show()
Tried to fix errors:
(est.fit(x.as_matrix) instead of est.fit(x))
and
(c=labels.astype(np.int) instead of c=labels.astype(np.float)) - (all values in my file are int.)
However changing from np.float to np.int does not fix it.