def check_spelling(checked_word, dist, word_list):
alphabet = "abcdefghijklmnopqrstuvwxyz"
s_m = student.build_scoring_matrix(alphabet, 2, 1, 0)
result = []
for word in word_list:
a_m = student.compute_alignment_matrix(checked_word, word, s_m, True)
score = student.compute_global_alignment(checked_word, word, s_m, a_m)
changes = len(checked_word) + len(word) - score[0]
if changes <= dist:
result.append(word)
print score[1], score[2]
return result
def check_spelling(checked_word, dist, word_list):
alphabet = "abcdefghijklmnopqrstuvwxyz"
s_m = student.build_scoring_matrix(alphabet, 2, 1, 0)
result = []
for word in word_list:
a_m = student.compute_alignment_matrix(checked_word, word, s_m, True)
score = student.compute_global_alignment(checked_word, word, s_m, a_m)
changes = len(checked_word) + len(word) - score[0]
if changes <= dist:
result.append(word)
print score[1], score[2]
return result
def generate_null_distribution(seq_x, seq_y, scoring_matrix, num_trials):
scoring_distribution = {}
for i in xrange(num_trials):
rand_y = list(seq_y)
random.shuffle(rand_y)
a_m = student.compute_alignment_matrix(seq_x, rand_y, scoring_matrix, False)
alignment = student.compute_local_alignment(seq_x, rand_y, scoring_matrix, a_m)
score = alignment[0]
scoring_distribution[score] = scoring_distribution.get(score, 0) + 1
print i
#print alignment[1]
#print alignment[2]
return scoring_distribution
def generate_null_distribution(seq_x, seq_y, scoring_matrix, num_trials):
scoring_distribution = {}
for i in xrange(num_trials):
rand_y = list(seq_y)
random.shuffle(rand_y)
a_m = student.compute_alignment_matrix(seq_x, rand_y, scoring_matrix,
False)
alignment = student.compute_local_alignment(seq_x, rand_y,
scoring_matrix, a_m)
score = alignment[0]
scoring_distribution[score] = scoring_distribution.get(score, 0) + 1
print i
#print alignment[1]
#print alignment[2]
return scoring_distribution
def distance(word1, word2, s_m):
alphabet = "abcdefghijklmnopqrstuvwxyz"
a_m = student.compute_alignment_matrix(word1, word2, s_m, True)
score = student.compute_global_alignment(word1, word2, s_m, a_m)
changes = len(word1) + len(word2) - score[0]
return changes
for word in checked_set:
if word in word_dict:
result_set.update(word_dict[word])
result = []
for word in result_set:
if distance(checked_word, word, s_m) <= dist:
result.append(word)
return result
timer = time.time()
words = set(read_words(WORD_LIST_URL))
new_words = new_keys(words)
print len(new_words)
new_words = new_keys_dict(new_words)
print len(new_words)
#print new_keys_dict(new_keys(["cat"]))
alphabet = "abcdefghijklmnopqrstuvwxyz"
s_m = student.build_scoring_matrix(alphabet, 2, 1, 0)
print "Generating took ", time.time() - timer
timer = time.time()
print "humble", len(check_spelling("humble", 2, new_words, s_m))
print "Time :", time.time() - timer
timer = time.time()
print "firefly", len(check_spelling("firefly", 2, new_words, s_m))
print "Time :", time.time() - timer
timer = time.time()
print "fireflyfosjfoijsfoidsj", len(
check_spelling("fireflyfosjfoijsfoidsj", 2, new_words, s_m))
print "Time :", time.time() - timer
def distance(word1, word2, s_m):
alphabet = "abcdefghijklmnopqrstuvwxyz"
a_m = student.compute_alignment_matrix(word1, word2, s_m, True)
score = student.compute_global_alignment(word1, word2, s_m, a_m)
changes = len(word1) + len(word2) - score[0]
return changes
result_set = set([])
for word in checked_set:
if word in word_dict:
result_set.update(word_dict[word])
result = []
for word in result_set:
if distance(checked_word, word, s_m) <= dist:
result.append(word)
return result
timer = time.time()
words = set(read_words(WORD_LIST_URL))
new_words = new_keys(words)
print len(new_words)
new_words = new_keys_dict(new_words)
print len(new_words)
# print new_keys_dict(new_keys(["cat"]))
alphabet = "abcdefghijklmnopqrstuvwxyz"
s_m = student.build_scoring_matrix(alphabet, 2, 1, 0)
print "Generating took ", time.time() - timer
timer = time.time()
print "humble", len(check_spelling("humble", 2, new_words, s_m))
print "Time :", time.time() - timer
timer = time.time()
print "firefly", len(check_spelling("firefly", 2, new_words, s_m))
print "Time :", time.time() - timer
timer = time.time()
print "fireflyfosjfoijsfoidsj", len(check_spelling("fireflyfosjfoijsfoidsj", 2, new_words, s_m))
print "Time :", time.time() - timer