def dotest(terms, expected, which):
files = filelist(rootdir)
terms = words(terms)
# print(terms)
if which == 0:
linear_docs = linear_search(files, terms)
# print(filenames(linear_docs))
names = filenames(linear_docs)
names.sort()
expected.sort()
#assert filenames(linear_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
elif which == 1:
index = create_index(files)
index_docs = index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
else:
index = myhtable_create_index(files)
index_docs = myhtable_index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
def dotest(terms, expected, which):
files = filelist(rootdir)
terms = words(terms)
# print(terms)
if which == 0:
linear_docs = linear_search(files, terms)
# print(filenames(linear_docs))
names = filenames(linear_docs)
names.sort()
expected.sort()
#assert filenames(linear_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
elif which == 1:
index = create_index(files)
index_docs = index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
else:
index = myhtable_create_index(files)
index_docs = myhtable_index_search(files, index, terms)
# print(filenames(index_docs))
names = filenames(index_docs)
names.sort()
expected.sort()
#assert filenames(index_docs) == expected
assert names == expected, "found "+str(names)+" != expected "+str(expected)
def time_check(choice: str, ite: int):
l = []
lim = 10000000
if choice == 'sorted':
for i in range(lim):
l.append(random.randint(0, lim))
l.sort()
elif choice == 'normalized':
for i in range(lim):
l.append(i)
inter = []
seq = []
bnry = []
indexed = []
for i in range(0, ite):
value = random.randint(0, lim)
if (choice == 'normalized'):
start2 = time.clock()
ret1 = interpolation_search(l, value)
end2 = time.clock()
if ret1 == True:
time2 = end2 - start2
inter.append(time2)
start1 = time.clock()
ret2 = linear_search(l, value)
end1 = time.clock()
if ret2 == True:
time1 = end1 - start1
seq.append(time1)
start3 = time.clock()
ret3 = binary_search(l, value)
end3 = time.clock()
if ret3 == True:
time3 = end3 - start3
bnry.append(time3)
start4 = time.clock()
ret4 = index_search(l, value)
end4 = time.clock()
if ret4 == True:
time4 = end4 - start4
indexed.append(time4)
plt.xlabel('Iterations')
plt.ylabel('Time')
if len(inter) != 0:
plt.plot(inter, color='red', label='interpolation')
plt.plot(seq, color='green', label='sequential')
plt.plot(bnry, color='blue', label='binary')
plt.plot(indexed, color='purple', label='indexed')
plt.legend()
plt.grid(True)
plt.show()
def test_index_berlitz():
terms = "hawaii travel"
files = filelist(rootdir)
terms = words(terms)
index = create_index(files)
index_docs = index_search(files, index, terms)
expected = ['HistoryHawaii.txt']
assert filenames(index_docs) == expected
def test_index_berlitz_none():
terms = "missspellinnng"
files = filelist(rootdir)
terms = words(terms)
index = create_index(files)
index_docs = index_search(files, index, terms)
expected = []
assert filenames(index_docs) == expected
def test_index_berlitz_none():
terms = "missspellinnng"
files = filelist(rootdir)
terms = words(terms)
index = create_index(files)
index_docs = index_search(files, index, terms)
expected = []
assert filenames(index_docs) == expected
def test_index_berlitz():
terms = "hawaii travel"
files = filelist(rootdir)
terms = words(terms)
index = create_index(files)
index_docs = index_search(files, index, terms)
expected = ['HistoryHawaii.txt']
assert filenames(index_docs) == expected
# files = files[:100]
N = len(files)
print N, "files"
index = None
while True:
terms = raw_input("Search terms: ")
terms = words(terms)
if impl == 'linear':
docs = linear_search(files, terms)
elif impl == 'index':
if index is None:
index = create_index(files)
print "Index complete"
docs = index_search(files, index, terms)
elif impl == 'myhtable':
if index is None:
index = myhtable_create_index(files)
print "Index complete"
docs = myhtable_index_search(files, index, terms)
else:
print "Invalid search type:", impl
break
page = results(docs, terms)
f = open("/tmp/results.html", "w")
f.write(page)
f.close()
webbrowser.open_new_tab("file:///tmp/results.html")
# Uncomment the next line to test just the first 100 files instead of all files
# files = files[:100]
N = len(files)
print(N, "files")
index = None
while True:
terms = input("Search terms: ")
terms = words(terms)
if impl=='linear':
docs = linear_search(files, terms)
elif impl == 'index':
if index is None:
index = create_index(files)
print("Index complete")
docs = index_search(files, index, terms)
elif impl == 'myhtable':
if index is None:
index = myhtable_create_index(files)
print("Index complete")
docs = myhtable_index_search(files, index, terms)
else:
print("Invalid search type:", impl)
break
page = results(docs, terms)
with open("/tmp/results.html", "w", encoding='UTF-8') as f:
f.write(page)
webbrowser.open_new_tab("file:///tmp/results.html")
def time_check(choice: str, ite: int):
l = []
lim = 1000000
if choice == 'sorted':
for i in range(lim):
l.append(random.randint(0, lim))
l.sort()
elif choice == 'normalized':
for i in range(lim):
l.append(i)
inter_time = []
seq_time = []
bnry_time = []
indexed_time = []
inter_counter = []
seq_counter = []
bnry_counter = []
indexed_counter = []
for i in range(0, ite):
value = random.randint(0, lim)
if (choice == 'normalized'):
start1 = time.clock()
counter1 = interpolation_search(l, value)
end1 = time.clock()
time1 = end1 - start1
inter_time.append(time1)
inter_counter.append(counter1)
start2 = time.clock()
counter2 = linear_search(l, value)
end2 = time.clock()
time2 = end2 - start2
seq_time.append(time2)
seq_counter.append(counter2)
start3 = time.clock()
counter3 = binary_search(l, value)
end3 = time.clock()
time3 = end3 - start3
bnry_time.append(time3)
bnry_counter.append(counter3)
start4 = time.clock()
counter4 = index_search(l, value)
end4 = time.clock()
time4 = end4 - start4
indexed_time.append(time4)
indexed_counter.append(counter4)
#print(seq_counter.shape)
plt.title("Counter x Number of searchs")
plt.xlabel('Steps')
plt.ylabel('Number of searchs')
if len(inter_time) != 0:
plt.subplot(2, 2, 1)
plt.hist(inter_counter, color='red', label='interpolation')
plt.xlabel('Steps')
plt.ylabel('Number of searchs')
plt.legend()
plt.grid(True)
plt.subplot(2, 2, 2)
plt.hist(seq_counter, color='green', label='sequential')
plt.xlabel('Steps')
plt.ylabel('Number of searchs')
plt.legend()
plt.grid(True)
plt.subplot(2, 2, 3)
plt.hist(bnry_counter, color='blue', label='binary')
plt.xlabel('Steps')
plt.ylabel('Number of searchs')
plt.legend()
plt.grid(True)
plt.subplot(2, 2, 4)
plt.hist(indexed_counter, color='purple', label='indexed')
plt.xlabel('Steps')
plt.ylabel('Number of searchs')
plt.legend()
plt.grid(True)
plt.show()
plt.title("Number of searchs x Time")
plt.xlabel('Number of searchs')
plt.ylabel('Time')
if len(inter_time) != 0:
plt.plot(inter_time, color='red', label='interpolation')
plt.plot(seq_time, color='green', label='sequential')
plt.plot(bnry_time, color='blue', label='binary')
plt.plot(indexed_time, color='purple', label='indexed')
plt.legend()
plt.grid(True)
plt.show()
