def script_compareHashWithToyExperiment(params):
in_file = params.in_file;
num_hash_tables_all = params.num_hash_tables_all;
key_type = params.key_type;
out_file_indices = params.out_file_indices;
out_file_pres = params.out_file_pres;
out_file_html = params.out_file_html;
rel_path = params.rel_path;
[features_test,features_train,labels_test,labels_train,_,_,indices,_]=pickle.load(open(in_file,'rb'));
visualize.saveMatAsImage(indices,out_file_indices);
hammings=[];
for out_file_pre,num_hash_tables in zip(out_file_pres,num_hash_tables_all):
indices_hash = getIndicesHash(features_test,features_train,num_hash_tables,key_type);
visualize.saveMatAsImage(indices_hash,out_file_pre+'.png');
hamming=util.getHammingDistance(indices,indices_hash);
pickle.dump([indices_hash,indices,hamming],open(out_file_pre+'.p','wb'));
hammings.append(np.mean(hamming));
sizes = scipy.misc.imread(out_file_indices);
sizes = sizes.shape
im_files_html=[];
captions_html=[];
for idx,out_file_pre in enumerate(out_file_pres):
out_file_curr=out_file_pre+'.png'
key_str=str(key_type);
key_str=key_str.replace('<type ','').replace('>','');
caption_curr='NN Hash. Num Hash Tables: '+str(num_hash_tables_all[idx])+' '+'Hamming Distance: '+str(hammings[idx]);
im_files_html.append([out_file_indices.replace(rel_path[0],rel_path[1]),out_file_curr.replace(rel_path[0],rel_path[1])])
captions_html.append(['NN cosine',caption_curr]);
visualize.writeHTML(out_file_html,im_files_html,captions_html,sizes[0]/2,sizes[1]/2);
def count(s, p, d):
len_s = len(s)
len_p = len(p)
res = 0
for x in range(len_s - len_p + 1):
c = s[x:x + len_p]
if getHammingDistance(p, c) <= d:
res += 1
return res
def d_row(p, s):
k = len(p)
minScore = k
for i in range(len(s) - k + 1):
match = s[i:i + k]
d = getHammingDistance(p, match)
if d < minScore:
minScore = d
if minScore == 0:
break
return minScore
def script_compareHashWithToyExperiment(params):
in_file = params.in_file
num_hash_tables_all = params.num_hash_tables_all
key_type = params.key_type
out_file_indices = params.out_file_indices
out_file_pres = params.out_file_pres
out_file_html = params.out_file_html
rel_path = params.rel_path
[
features_test, features_train, labels_test, labels_train, _, _,
indices, _
] = pickle.load(open(in_file, 'rb'))
visualize.saveMatAsImage(indices, out_file_indices)
hammings = []
for out_file_pre, num_hash_tables in zip(out_file_pres,
num_hash_tables_all):
indices_hash = getIndicesHash(features_test, features_train,
num_hash_tables, key_type)
visualize.saveMatAsImage(indices_hash, out_file_pre + '.png')
hamming = util.getHammingDistance(indices, indices_hash)
pickle.dump([indices_hash, indices, hamming],
open(out_file_pre + '.p', 'wb'))
hammings.append(np.mean(hamming))
sizes = scipy.misc.imread(out_file_indices)
sizes = sizes.shape
im_files_html = []
captions_html = []
for idx, out_file_pre in enumerate(out_file_pres):
out_file_curr = out_file_pre + '.png'
key_str = str(key_type)
key_str = key_str.replace('<type ', '').replace('>', '')
caption_curr = 'NN Hash. Num Hash Tables: ' + str(
num_hash_tables_all[idx]) + ' ' + 'Hamming Distance: ' + str(
hammings[idx])
im_files_html.append([
out_file_indices.replace(rel_path[0], rel_path[1]),
out_file_curr.replace(rel_path[0], rel_path[1])
])
captions_html.append(['NN cosine', caption_curr])
visualize.writeHTML(out_file_html, im_files_html, captions_html,
sizes[0] / 2, sizes[1] / 2)
def dContains(s, p, d):
k = len(p)
for i in range(len(s) - k + 1):
if util.getHammingDistance(s[i:i + k], p) <= d:
return True
return False
from util import getHammingDistance
if __name__ == '__main__':
t = raw_input()
s = raw_input()
d = int(raw_input())
len_s = len(s)
len_t = len(t)
res = []
for i in range(0, len_s - len_t + 1):
ss = s[i:i + len_t]
if getHammingDistance(t, ss) <= d:
res.append(i)
print ' '.join([str(x) for x in res])
