Loading files to perform Kmean using sklearn - python-2.7

Question

I have 100 files that contain system call traces. Each files is presented as seen below:
setpgrp ioctl setpgrp ioctl ioctl ....
I am trying to load these files and perform kmean calculation on them to cluster them based on similarities. Based on a tutorial on the sklearn webpage I written the following:
from sklearn.decomposition import TruncatedSVD
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import Normalizer
from sklearn import metrics
from sklearn.datasets import load_files
from sklearn.cluster import KMeans, MiniBatchKMeans
import numpy as np
# parse commandline arguments
op = OptionParser()
op.add_option("--lsa",
dest="n_components", type="int",
help="Preprocess documents with latent semantic analysis.")
op.add_option("--no-minibatch",
action="store_false", dest="minibatch", default=True,
help="Use ordinary k-means algorithm (in batch mode).")
op.add_option("--use-idf",
action="store_false", dest="use_idf", default=True,
help="Disable Inverse Document Frequency feature weighting.")
op.add_option("--n-features", type=int, default=10000,
help="Maximum number of features (dimensions)"
" to extract from text.")
op.add_option("--verbose",
action="store_true", dest="verbose", default=False,
help="Print progress reports inside k-means algorithm.")
print(__doc__)
op.print_help()
(opts, args) = op.parse_args()
if len(args) > 0:
op.error("this script takes no arguments.")
sys.exit(1)
print("Loading training data:")
trainingdata = load_files('C:\data\Training data')
print("%d documents" % len(trainingdata.data))
print()
print("Extracting features from the training trainingdata using a sparse vectorizer")
if opts.use_idf:
vectorizer = TfidfVectorizer(input="file",min_df=1)
X = vectorizer.fit_transform(trainingdata.data)
print("n_samples: %d, n_features: %d" % X.shape)
print()
if opts.n_components:
print("Performing dimensionality reduction using LSA")
# Vectorizer results are normalized, which makes KMeans behave as
# spherical k-means for better results. Since LSA/SVD results are
# not normalized, we have to redo the normalization.
svd = TruncatedSVD(opts.n_components)
lsa = make_pipeline(svd, Normalizer(copy=False))
X = lsa.fit_transform(X)
explained_variance = svd.explained_variance_ratio_.sum()
print("Explained variance of the SVD step: {}%".format(
int(explained_variance * 100)))
print()
However it seems that none of the files in the dataset directory get loaded into the memory when though all files are available. I get the following error when executing the program:
raise ValueError("empty vocabulary; perhaps the documents only"
ValueError: empty vocabulary; perhaps the documents only contain stop words
Can anyone tell me why the dataset is not being loaded? What am I doing wrong?

Answer 1

I finally managed to load the files. The approach to use Kmean in sklearn is to vectorize the training data (using tfidf or count_vectorizer), then transform your test data using the vectorization of your training data. Once that is done you can initialize the Kmean parameters, use the training data set vectors to create the kmean cluster. Finally you can cluster your test data around your training data centroid.
The following code does what is explained above.
#Read the data in a directory:
def readfile(dataDir):
data_set = []
for file in os.listdir(dataDir):
trainingfiles = os.path.join(dataDir, file)
if os.path.isfile(trainingfiles):
data = open(trainingfiles, 'r')
dataread=str.decode(data.read())
data_set.append(dataread)
return data_set
#fitting tfidf transfrom for training data
tfidf_vectorizer_trainingset = tfidf_vectorizer.fit_transform(readfile(trainingdataDir)).toarray()
#transform the test set based on the training set
tfidf_vectorizer_testset = tfidf_vectorizer.transform(readfile(testingdataDir)).toarray()
# Kmean Clustering parameters
kmean_parameters = KMeans(n_clusters=number_of_clusters, init='k-means++', max_iter=100, n_init=1)
#Cluster the training data based on the parameters
KmeanAnalysis_training = kmean_parameters.fit(tfidf_vectorizer_trainingset)
#transform the test data based on the clustering of the training data
KmeanAnalysis_test = kmean_parameters.transform(tfidf_vectorizer_testset)