def main():
print(
"Hello this is the Edit Distance Program that performs the distance of words in three different tests cases.\nTest 1 performs it on two distinct ones that so happen to be my favorite phrase together.\nTest 2 performs it on the same word.\nTest 3 performs it on one word and an empty string."
)
print("")
print("Then allow you to compare your own words.\nLet's initiate: ")
print("")
print("Test 1: ")
#Test case 1
word_1 = "fire"
word_2 = "dynasty"
print("Words being compared are '", word_1, "' and '", word_2, "'.")
print("\t\t...calculating their distance...\n")
print("Distance between them: ", end='')
print(ed.EditDistance(word_1, word_2, len(word_1), len(word_2)))
print("")
print("Test 2: ")
#Test case 2
word_1 = "elvis"
word_2 = "elvis"
print("Words being compared are '", word_1, "' and '", word_2, "'.")
print("\t\t...calculating their distance...\n")
print("Distance between them: ", end='')
print(ed.EditDistance(word_1, word_2, len(word_1), len(word_2)))
print("")
print("Test 3: ")
#Test case 3
word_1 = "styles"
word_2 = ""
print("The two words being compared are '", word_1, "' and '", word_2,
"'.")
print("\t\t...calculating their distance...\n")
print("Distance between them: ", end='')
print(ed.EditDistance(word_1, word_2, len(word_1), len(word_2)))
print("")
print("Now that the test are completed...")
print("Would you like to try two words for yourself? Yes or No")
user_sel = input()
if (user_sel == 'yes' or user_sel == 'Yes' or user_sel == 'YES'):
print("Excellent! Now, which two words would you like to try?")
print("Word 1: ")
word_1 = input()
print("Word 2: ")
word_2 = input()
print("The two words being compared are '", word_1, "' and '", word_2,
"'.")
print("\t\t...calculating their distance...\n")
print("Distance between them: ", end='')
print(ed.EditDistance(word_1, word_2, len(word_1), len(word_2)))
print("")
print("Program complete!\nThank you for participating")
elif (user_sel == 'no' or user_sel == 'No' or user_sel == 'NO'):
print("Okay.")
print("See you again soon!")
else:
print("ERROR!\nInput invalid!")
print("Terminating...\nGoodbye!")
def test_almost_right(self):
targeted_score = comment_score["almost right"]
assert ed.LevenshteinMethod(
"flocinaucinihilipilification",
"floccinaucinihilipilification") == targeted_score, error_toast
assert ed.LevenshteinMethod("owll",
"owl") == targeted_score, error_toast
assert ed.LevenshteinMethod(
"pseudopseudohipoparathyroidism",
"pseudopseudohypoparathyroidism") == targeted_score, error_toast
def test_a_bit_confusing(self):
targeted_score = comment_score["a bit confusing"]
assert ed.LevenshteinMethod("plez",
"please") == targeted_score, error_toast
assert ed.LevenshteinMethod("cnoke",
"knock") == targeted_score, error_toast
assert ed.LevenshteinMethod("reqid",
"required") == targeted_score, error_toast
assert ed.LevenshteinMethod(
"pneumonoultramicroscopiccilikovolkanokoniosis",
"pneumonoultramicroscopicsilicovolcanokoniosis"
) == targeted_score, error_toast
def normalize_recursion(function, s1, s2, *args):
result = 0
time = np.zeros(5)
for i in range(0, time.size):
temp1, temp2 = ed.calc_runtime(function, s1, s2, *args)
time[i] = temp1
result = temp2
return result, np.average(time)
def load_channel_model(self, fp):
''' Takes in a file pointer as input
and should initialize the SpellChecker object’s
channel_model data member to a default EditDistanceFinder
and then load the stored language model (e.g. ed.pkl)
from fp into that data member. '''
self.channel_model = EditDistance.EditDistanceFinder()
self.channel_model.load(fp)
def iterator(head_start, end, function, function2, s1, s2, *args):
result = np.zeros(end)
time = np.zeros(end)
for i in range(head_start, end):
temp1, temp2 = ed.calc_runtime(function, function2, s1[i], s2[i],
*args)
time[i] = temp1
result[i] = temp2[0]
return np.average(result), np.delete(time, np.arange(0, head_start))
def recursion(path2, folder):
for root, subdirs, files in os.walk(path2):
for filename in files:
if filename[-4:] == ".xml":
path = os.path.join(root, filename)
text, emails = out1_pro.callMe(path)
if text != None:
w = EditDistance.textToMapping(text, emails)
for item in w:
# print(item, w[item],filename[:-4], folder)
try:
fire(w[item], item, filename[:-4], folder)
except Exception as e:
print("Exception in database updation " + str(e))
def recursion(path2, folder):
for root, subdirs, files in os.walk(path2):
for filename in files:
if filename[-4:] == ".xml":
path = os.path.join(root, filename)
text,emails = out1_pro.callMe(path)
if text != None:
w = EditDistance.textToMapping(text,emails)
for item in w:
# print(item, w[item],filename[:-4], folder)
try:
fire(w[item], item, filename[:-4], folder)
except Exception as e:
print("Exception in database updation " + str(e))
def recurse(folder):
for root, subdirs, files in os.walk(folder):
for filename in files:
if filename[-4:] == ".xml":
path = os.path.join(root, filename)
path = os.path.join(root, filename)
text, emails = out1_pro.callMe(path)
if text != None:
w = EditDistance.textToMapping(text, emails)
print "\n---from FINAL----" #, w#text,'\n\n ---- ',w
# if len(Emails)!=0:
# print "$$$$$$",Emails
for item in w:
print item, w[item], filename[:-4]
fire(w[item], item, filename[:-4])
# print os.path.abspath(os.path.join(path, os.pardir))
# print os.pardir
print "-----------------------xxxxxxxxxxxxxxxxxxxxxxxxxxxx"
def recurse(folder):
for root, subdirs, files in os.walk(folder):
for filename in files:
if filename[-4:] == ".xml":
path = os.path.join(root, filename)
path = os.path.join(root, filename)
text,emails = out1_pro.callMe(path)
if text != None:
w = EditDistance.textToMapping(text,emails)
print "\n---from FINAL----"#, w#text,'\n\n ---- ',w
# if len(Emails)!=0:
# print "$$$$$$",Emails
for item in w:
print item, w[item],filename[:-4]
fire(w[item], item, filename[:-4])
# print os.path.abspath(os.path.join(path, os.pardir))
# print os.pardir
print"-----------------------xxxxxxxxxxxxxxxxxxxxxxxxxxxx"
def callback():
if var.get() == 1:
result = (ed.calc_runtime_md(ed.med_classic_gui, e1.get(), e2.get()))
var2.set("RUNNING TIME : %s seconds" % result[0])
var3.set("{} {}".format("MINIMUM EDIT DISTANCE :", result[1]))
var4.set(result[2])
var5.set(result[3])
var6.set(result[4])
#print("RUNNING TIME : %s seconds" % result[0])
# print(var2.set(ed.calc_runtime(ed.med_classic, )))
if var.get() == 2:
result1 = ed.hirschberge(e1.get(), e2.get())
result = (ed.calc_runtime_md(ed.calcByRow, e1.get(), e2.get()))
var2.set("RUNNING TIME : %s seconds" % result[0])
var3.set("{} {}".format("MINIMUM EDIT DISTANCE :", result[1]))
var4.set(result1[0])
var5.set(result1[1])
var6.set(result1[2])
if var.get() == 3:
result = (ed.calc_runtime_md(ed.med_recursive, e1.get(), e2.get()))
var2.set("RUNNING TIME : %s seconds" % result[0])
var3.set("{} {}".format("MINIMUM EDIT DISTANCE :", result[1]))
if var.get() == 4:
result = (ed.calc_runtime_md(ed.med_branch, e1.get(), e2.get(),
int(E5.get()),
abs(len(e1.get()) - len(e2.get())) + 1))
var2.set("RUNNING TIME : %s seconds" % result[0])
var3.set("{} {}".format("MINIMUM EDIT DISTANCE :", result[1]))
if var.get() == 5:
result = (ed.calc_runtime_md(ed.med_k_gui, e1.get(), e2.get(),
E3.get()))
var2.set("RUNNING TIME : %s seconds" % result[0])
var3.set("{} {}".format("MINIMUM EDIT DISTANCE :", result[1]))
var4.set(result[3])
var5.set(result[4])
var6.set(result[5])
if var.get() == 6:
result = (ed.calc_runtime_md(ed.med_greedy, e1.get(), e2.get(),
int(E4.get())))
var2.set("RUNNING TIME : %s seconds" % result[0])
var3.set("{} {}".format("MINIMUM EDIT DISTANCE :", result[1]))
def test_quite_close(self):
targeted_score = comment_score["quite close"]
assert ed.LevenshteinMethod("ples",
"please") == targeted_score, error_toast
assert ed.LevenshteinMethod("reqird",
"required") == targeted_score, error_toast
assert ed.LevenshteinMethod("rnser",
"answer") == targeted_score, error_toast
assert ed.LevenshteinMethod(
"antidisestablishmentaraniasm",
"antidisestablishmentarianism") == targeted_score, error_toast
assert ed.LevenshteinMethod("wol",
"owl") == targeted_score, error_toast
assert ed.LevenshteinMethod(
"humuhumunukunukuapuaua‘a",
"humuhumunukunukuapua‘a") == targeted_score, error_toast
def protein_database_processor(data):
result = np.arange(data.__len__())
for i in range(0, data.__len__()):
result[i] = ed.med_classic(data[0], data[i])[0]
# print(result[i])
return result
import time
from EditDistance import *
str1 = 'miners'
str2 = 'money'
print('the first string (word) is:')
print(str1)
print()
print('the second string (word) is:')
print(str2)
print()
start = time.time()
EditDistance(str1, str2)
end = time.time()
print('Running time:')
print(end - start)
print('seconds.')
def test_very_confusing(self):
targeted_score = comment_score["very confusing"]
assert ed.LevenshteinMethod(
"mispeln", "misspelling") == targeted_score, error_toast
assert ed.LevenshteinMethod("mestipenk",
"mistyping") == targeted_score, error_toast
def test_right(self):
targeted_score = comment_score["totally correct"]
assert ed.LevenshteinMethod("Jiang",
"Jiang") == targeted_score, error_toast
assert ed.LevenshteinMethod("Chibin",
"Chibin") == targeted_score, error_toast
def load_channel_model(self, fp):
self.channel_model = EditDistance.EditDistanceFinder()
self.channel_model.load(fp)
def classify_comment(rightspelling, *misspellings):
score_comment = {value: key for key, value in comment_score.items()}
for mis in misspellings:
edit_dist = ed.LevenshteinMethod(mis, rightspelling)
yield mis + "\t" + str(edit_dist) + "\t" + score_comment[edit_dist]
