def check_spelling(checked_word, dist, word_list):
alphabet = set('abcdefghijklmnopqrstuvwxyz')
scoring_matrix = student.build_scoring_matrix(alphabet, 2, 1, 0)
result = list()
for word in word_list:
align = student.compute_alignment_matrix(checked_word, word, scoring_matrix, True)
scores = student.compute_global_alignment(checked_word, word, scoring_matrix, align)
if (len(checked_word) + len(word) - scores[0]) <= dist:
result.append(word)
return result
def check_spelling(checked_word, dist, word_list):
scoring_matrix = student.build_scoring_matrix(
set('abcdefghijklmnopqrstuvwxyz'), 2, 1, 0)
def score(x, y):
alignment_matrix = student.compute_alignment_matrix(
x, y, scoring_matrix, True)
return student.compute_global_alignment(x, y, scoring_matrix,
alignment_matrix)[0]
return list(word for word in word_list if len(checked_word) + len(word) -
score(checked_word, word) == dist)
def check_spelling(checked_word, dist, word_list):
"""
Iterates through word_list and returns the set of all words that are within
edit distance dist of the string checked_word.
"""
alphabet = string.ascii_lowercase + '-'
sample_matrix = student.build_scoring_matrix(alphabet, 2, 1, 0)
words = set([])
for word in set(word_list):
if len(word) + len(checked_word) - student.global_alignment(
word, checked_word, sample_matrix)[0] <= dist:
words.add(word)
return words
def question7(seq_x, seq_y):
""" determine scoring matrix of edit distance algorithm """
diag_score = 2
off_diag_score = 1
dash_score = 0
alphabet = "abcdefghijklmnopqrstuvwxyz"
score_matrix = student.build_scoring_matrix(alphabet, diag_score, off_diag_score, dash_score)
align_matrix = student.compute_alignment_matrix(seq_x, seq_y, score_matrix, True)
score, align_x, align_y = student.compute_global_alignment(seq_x, seq_y, score_matrix, align_matrix)
edit_distance = len(seq_x) + len(seq_y) - score
print "Edit distance: " + str(edit_distance)
print align_x
print align_y
def check_spelling(checked_word, dist, word_list):
diag_score = 2
off_diag_score = 1
dash_score = 0
chars = 'abcdefghijklmnopqrstuvwxyz'
alphabet = set([char for char in chars])
len_checkedword = len(checked_word)
scoring_matrix = student.build_scoring_matrix(alphabet, diag_score,
off_diag_score, dash_score)
similar_word_list = []
for word in word_list:
global_alignment_matrix = student.compute_alignment_matrix(
checked_word, word, scoring_matrix, True)
global_alignment_score = student.compute_global_alignment(
checked_word, word, scoring_matrix, global_alignment_matrix)[0]
edit_dist = len_checkedword + len(word) - global_alignment_score
if edit_dist <= dist:
similar_word_list.append(word)
return similar_word_list
def check_spelling(checked_word, dist, word_list):
""" helper function to determine all words edit distance away """
diag_score = 2
off_diag_score = 1
dash_score = 0
alphabet = "abcdefghijklmnopqrstuvwxyz"
score_matrix = student.build_scoring_matrix(alphabet, diag_score, off_diag_score, dash_score)
words = []
for word in word_list:
align_matrix = student.compute_alignment_matrix(checked_word, word, score_matrix, True)
score, align_x, align_y = student.compute_global_alignment(checked_word, word,
score_matrix, align_matrix)
edit_distance = len(checked_word) + len(word) - score
if edit_distance <= dist:
words.append(word)
return words
def check_spelling(checked_word, dist, word_list):
"""
input:
iterates through word_list and returns the set of all words
that are within edit distance dist of the string checked_word
output:
the set of all words that are within edit distance dist of
the string checked_word
"""
result_set = set([])
diag_score = 2
off_diag_score = 1
dash_score = 0
alphabet = set('abcdefghijklmnopqrstuvwxyz')
matrix_M = student.build_scoring_matrix(alphabet, diag_score, off_diag_score, dash_score)
for word in word_list:
matrix_S = student.compute_alignment_matrix(checked_word, word, matrix_M, True)
global_align_word = student.compute_global_alignment(checked_word, word, matrix_M, matrix_S)
if len(checked_word) + len(word) - global_align_word[0] <= dist:
result_set.add(word)
return result_set
FruitflyEyelessProtein,
PAM50, False)
result_Q5 = student.compute_local_alignment(HumanEyelessProtein,
FruitflyEyelessProtein, PAM50,
alignment_matrix_Q5)
z_value = (result_Q5[0] - mean) / sigma
print 'mean : ' + str(mean)
print 'standard deviation : ' + str(sigma)
print 'z value : ' + str(z_value)
# Q8
word_list = read_words(WORD_LIST_URL)
scoring_matrix = student.build_scoring_matrix('abcdefghijklmnopqrstuvwxyz', 2,
1, 0)
def check_spelling(checked_word, dist, word_list):
answer = []
for word in word_list:
alignment_matrix = student.compute_alignment_matrix(
checked_word, word, scoring_matrix, True)
result = student.compute_local_alignment(checked_word, word,
scoring_matrix,
alignment_matrix)
if (len(checked_word) + len(word) - result[0]) <= dist:
answer.append(word)
return answer
import alg_application4_provided
import alg_project4_solution as student
import string
alphabet = list(string.ascii_lowercase) + list(string.ascii_uppercase)
scoring_matrix = student.build_scoring_matrix(alphabet, 2, 1, 0)
def check_spelling(checked_word, dist, word_list):
"""
input: word, target distance, and word list
output: return a subset of word list which the distance between input word < target distance
"""
result = set()
x = len(checked_word)
for item in word_list:
y = len(item)
if abs(x - y) <= dist:
alignment_matrix = student.compute_alignment_matrix(checked_word, item, scoring_matrix, True)
score = max(map(max, alignment_matrix))
if (x + y - score) <= dist:
result = result.union(set([item]))
return result
WORD_LIST_URL = "http://storage.googleapis.com/codeskulptor-assets/assets_scrabble_words3.txt"
word_list = alg_application4_provided.read_words(WORD_LIST_URL)
import time, itertools
import alg_application4_provided
import alg_project4_solution as student
import string
alphabet = list(string.ascii_lowercase) + list(string.ascii_uppercase)
scoring_matrix = student.build_scoring_matrix(alphabet, 2, 1, 0)
def check_spelling(checked_word, dist, word_list):
"""
input: word, target distance, and word list
output: return a subset of word list which the distance between input word < target distance
"""
result = set()
x = len(checked_word)
for item in word_list:
y = len(item)
if abs(x - y) <= dist:
alignment_matrix = student.compute_alignment_matrix(
checked_word, item, scoring_matrix, True)
score = max(map(max, alignment_matrix))
if (x + y - score) <= dist:
result = result.union(set([item]))
return result
WORD_LIST_URL = "http://storage.googleapis.com/codeskulptor-assets/assets_scrabble_words3.txt"
word_list = alg_application4_provided.read_words(WORD_LIST_URL)
import time, itertools
tStart = time.time()
def check_spelling(checked_word, dist, word_list):
scoring_matrix = student.build_scoring_matrix(set('abcdefghijklmnopqrstuvwxyz'), 2, 1, 0)
def score(x, y):
alignment_matrix = student.compute_alignment_matrix(x, y, scoring_matrix, True)
return student.compute_global_alignment(x, y, scoring_matrix, alignment_matrix)[0]
return list(word for word in word_list if len(checked_word) + len(word) - score(checked_word, word) == dist)
