def get_accuracy(data_file, data_format, knn_output, alg, k, d, N):
# Get ground truth
print "getting ground truth"
ground_truth = run_sklearn.get_knn_graph(data_file, data_format, k, d, N, 'brute')
print "finished getting ground truth"
if alg == "chen":
# Get knn graph file in numpy array
print "creating numpy knn graph from chen's output"
knn_graph = np.zeros((N,N), dtype=np.int)
print "created graph; opening file to fill graph"
with open(knn_output, 'r') as f:
for line in f:
line.strip()
line = line.split()
j = int(line[0]) - 1
i = int(line[1]) - 1
knn_graph[i][j] = 1
print "finished reading file, converting to sparse matrix"
knn_sparse = sparse.csr_matrix(knn_graph)
print "finished converting to sparse matrix"
elif alg == "sklearn":
knn_sparse = knn_output
print "getting n_correct"
n_incorrect = (ground_truth - knn_sparse).nnz
accuracy = 1 - n_incorrect/(N*N+0.0)
return accuracy
def get_accuracy(data_file, data_format, knn_output, alg, k, d, N):
# Get ground truth
print "getting ground truth"
ground_truth = run_sklearn.get_knn_graph(data_file, data_format, k, d, N, "brute")
print "finished getting ground truth"
if alg == "chen":
# Get knn graph file in numpy array
print "creating numpy knn graph from chen's output"
knn_graph = np.zeros((N, N), dtype=np.int)
print "created graph; opening file to fill graph"
with open(knn_output, "r") as f:
for line in f:
line.strip()
line = line.split()
j = int(line[0]) - 1
i = int(line[1]) - 1
knn_graph[i][j] = 1
print "finished reading file, converting to sparse matrix"
knn_sparse = sparse.csr_matrix(knn_graph)
print "finished converting to sparse matrix"
elif alg == "sklearn":
knn_sparse = knn_output
print "getting n_correct"
n_incorrect = (ground_truth - knn_sparse).nnz
accuracy = 1 - n_incorrect / (N * N + 0.0)
return accuracy
import sys
import run_sklearn
poker = ["/scratch/02234/kmcardle/data/poker.t", 'libsvm', 10, 1000000, 8]
rna = ["/scratch/02234/kmcardle/data/cod-rna.t", 'libsvm', 8, 271617, 8]
cadata = ["/scratch/02234/kmcardle/data/cadata", 'libsvm', 8, 20640, 8]
covtype = [
"/scratch/02234/kmcardle/data/covtype.libsvm.binary", 'libsvm', 54, 581012,
8
]
year = [
"/scratch/02234/kmcardle/data/YearPredictionMSD", 'libsvm', 90, 463715, 8
]
aloi = ["/scratch/02234/kmcardle/data/aloi", 'libsvm', 128, 108000, 8]
datasets = [poker, rna, cadata, covtype, year, aloi]
for dataset in datasets:
print dataset[0], ' -----------------------'
algs = ['kd_tree', 'ball_tree', 'brute']
for alg in algs:
print alg, ": +++++++++++++"
# get_knn_graph(data_file, data_format, k, d, N, alg):
run_sklearn.get_knn_graph(dataset[0], dataset[1], dataset[4],
dataset[2], dataset[3], alg)
import sys
import run_sklearn
poker = ["/scratch/02234/kmcardle/data/poker.t", "libsvm", 10, 1000000, 8]
rna = ["/scratch/02234/kmcardle/data/cod-rna.t", "libsvm", 8, 271617, 8]
cadata = ["/scratch/02234/kmcardle/data/cadata", "libsvm", 8, 20640, 8]
covtype = ["/scratch/02234/kmcardle/data/covtype.libsvm.binary", "libsvm", 54, 581012, 8]
year = ["/scratch/02234/kmcardle/data/YearPredictionMSD", "libsvm", 90, 463715, 8]
aloi = ["/scratch/02234/kmcardle/data/aloi", "libsvm", 128, 108000, 8]
datasets = [poker, rna, cadata, covtype, year, aloi]
for dataset in datasets:
print dataset[0], " -----------------------"
algs = ["kd_tree", "ball_tree", "brute"]
for alg in algs:
print alg, ": +++++++++++++"
# get_knn_graph(data_file, data_format, k, d, N, alg):
run_sklearn.get_knn_graph(dataset[0], dataset[1], dataset[4], dataset[2], dataset[3], alg)
