def go(code):
verify_closings = errors.unclosed_symbols_verification(code)
if len(verify_closings) > 1:
if verify_closings[1] == "char":
errors.pup_error(
errors.get_error("0004", str(verify_closings[2] + 1)))
elif verify_closings[1] == "str":
errors.pup_error(
errors.get_error("0005", str(verify_closings[2] + 1)))
elif verify_closings[1] == "too_much_opening_parn":
errors.pup_error(
errors.get_error("0006", str(verify_closings[2] + 1)))
elif verify_closings[1] == "too_much_closing_parn":
errors.pup_error(
errors.get_error("0007", str(verify_closings[2] + 1)))
else:
for i in tokenizer.go(code):
for i2 in i:
print(i2)
print("-----------")
def try_several_h(h_list, x_validate_1, x_validate_2, N_classify):
x_mix, label_real = rand_gen.rand_mix(N_classify)
for h in h_list:
# Estimate densities with parzen
px_given_1 = parzen_estimate(x_validate_1, x_mix, h)
px_given_2 = parzen_estimate(x_validate_2, x_mix, h)
# Bayesian classification
label_test = by.bayesian_classify(px_given_1, px_given_2)
# Plot
myplt.plot_est_vs_theo(x_mix, px_given_1, px_given_2, 'o',
'h=' + str(h))
# Error
error_rate = err.get_error(label_real, label_test)
print("h=" + str(h) + " error=" + str(error_rate))
def tokenize_line(line, line_counter, return_raw=False):
line_result_raw = []
line_result = []
adder = 0
counter = -1
line += "."
for i2 in line:
counter += 1
if i2 in info.tokenizing_symbols:
line_result_raw.append(line[adder:counter])
line_result_raw.append(i2)
adder = counter + 1
if return_raw:
return line_result_raw
opened_str = False
opened_char = False
build_str = ""
build_char = ""
i3_counter = 0
for i3 in line_result_raw:
if opened_str:
if not i3 == "\"":
build_str += i3
continue
if opened_char:
if not i3 == "\'":
build_char += i3
continue
if not opened_str and not opened_char and not i3 == "\"" and not i3 == "\'":
line_result.append(i3)
if i3 == "\"":
if not opened_str:
build_str += i3
opened_str = True
else:
build_str += i3
line_result.append(build_str)
build_str = ""
opened_str = False
elif i3 == "\'":
if not opened_char:
build_char += i3
opened_char = True
else:
build_char += i3
line_result.append(build_char)
build_char = ""
opened_char = False
line_result_copy = []
line_result_copy_1 = []
line_result_final = []
counter_1 = 0
x = 0
line_result.append("/")
line_result.append("/")
precedent_i8 = ""
for i8 in line_result:
if not i8.strip() == "":
line_result_copy.append(i8.strip())
for i9 in line_result_copy:
if i9 == "/":
x = 0
try:
char_after = line_result_copy[counter_1 + 1]
if char_after == "/":
break
except:
x += 1
else:
line_result_copy_1.append(i9)
counter_1 += 1
# Symbols-Repetition Errors Verification (fast) #
last_symb = ""
symb_black = [";", ",", ".", "!", "{",
"}"] # Symbols to prevent from repeating in the code
for i10 in line_result_copy_1[0:len(line_result_copy_1) - 1]:
if last_symb == i10 and i10 in symb_black:
errors.pup_error(
errors.get_error("0003", str(line_counter + 2), i10,
str(counter)))
last_symb = i10
##############################################################
if line_result_copy_1[len(
line_result_copy_1
) - 2] == ";": # Detects and remove an eventually existing semicolon at the end of the line.
line_result_copy_1.pop(len(line_result_copy_1) - 2) #
return line_result_copy_1[0:len(line_result_copy_1) - 1]
print('ITEM d) Bayes classifier with parzen and knn estimation')
# Generate mixture distribution
N_test = 100
x_test, label_real = rand_gen.rand_mix(N_test)
# Bayesian classification with parzen estimate
h = 0.3
px_given_1_parzen = parzen.parzen_estimate(x_samples_1, x_test, h)
px_given_2_parzen = parzen.parzen_estimate(x_samples_2, x_test, h)
label_test_parzen = by.bayesian_classify(px_given_1_parzen, px_given_2_parzen)
myplt.plot_with_labels(
x_test, label_real, label_test_parzen,
'Clasificacion bayesiana con estimacion Parzen, h=' + str(h))
err_parzen = err.get_error(label_real, label_test_parzen)
print('Error with parzen is: ' + str(err_parzen))
# Bayesian classification with knn estimate
for k in k_list:
px_given_1_knn = knn.knn_estimate(k, x_samples_1, x_test)
px_given_2_knn = knn.knn_estimate(k, x_samples_2, x_test)
label_test_knn = by.bayesian_classify(px_given_1_knn, px_given_2_knn)
myplt.plot_with_labels(
x_test, label_real, label_test_knn,
'Clasificacion bayesiana con estimacion KNN, k=' + str(k))
err_knn = err.get_error(label_real, label_test_knn)
print('Error with knn is: ' + str(err_knn) + " k=" + str(k))
print('ITEM e) knn classifier')
k_list = [1, 11, 51]
import sys
import info
import errors
import start_modules
counter = 0
file_to_interpret = ""
for i in sys.argv:
if i.startswith("--"):
raw_arg = i[2:len(i)]
if raw_arg.lower() == "file":
try:
err_test = sys.argv[counter + 1]
except:
errors.pup_error(errors.get_error("0001"))
file_name = " "
for i2 in range(counter + 1, len(sys.argv)):
if not sys.argv[i2].startswith("--"):
file_name += sys.argv[i2] + " "
else:
break
file_name = file_name.strip()
file_read = ""
try:
fstream = open(file_name)
file_read = fstream.read()
fstream.close()