#
#-------------------------------------------------------------------------------
# Section 2.9.b
#-------------------------------------------------------------------------------
T = 5
L = 1
pct_train_accuracy, pct_val_accuracy = \
p1.perceptron_accuracy(train_bow_features,val_bow_features,train_labels,val_labels,T=T)
print("{:35} {:.4f}".format("Training accuracy for perceptron:",
pct_train_accuracy))
print("{:35} {:.4f}".format("Validation accuracy for perceptron:",
pct_val_accuracy))
avg_pct_train_accuracy, avg_pct_val_accuracy = \
p1.average_perceptron_accuracy(train_bow_features,val_bow_features,train_labels,val_labels,T=T)
print("{:43} {:.4f}".format("Training accuracy for average perceptron:",
avg_pct_train_accuracy))
print("{:43} {:.4f}".format("Validation accuracy for average perceptron:",
avg_pct_val_accuracy))
avg_pa_train_accuracy, avg_pa_val_accuracy = \
p1.average_passive_aggressive_accuracy(train_bow_features,val_bow_features,train_labels,val_labels,T=T,L=L)
print("{:50} {:.4f}".format(
"Training accuracy for average passive-aggressive:",
avg_pa_train_accuracy))
print("{:50} {:.4f}".format(
"Validation accuracy for average passive-aggressive:",
avg_pa_val_accuracy))
##-------------------------------------------------------------------------------
#
# avg_peg_tune_results_L = utils.tune_pegasos_L(best_T, Ls, *data)
# utils.plot_tune_results('Perceptron', 'T', Ts, *pct_tune_results)
# utils.plot_tune_results('Avg Perceptron', 'T', Ts, *avg_pct_tune_results)
# utils.plot_tune_results('Pegasos', 'T', Ts, *avg_peg_tune_results_T)
# utils.plot_tune_results('Pegasos', 'L', Ls, *avg_peg_tune_results_L)
#-------------------------------------------------------------------------------
#
#-------------------------------------------------------------------------------
# Section 2.11a
#
# Call one of the accuracy functions that you wrote in part 2.9.a and report
# the hyperparameter and accuracy of your best classifier on the test data.
# The test data has been provided as test_bow_features and test_labels.
x = p1.average_perceptron_accuracy(train_bow_features, test_bow_features, train_labels, test_labels, T=25)
print(x)
#-------------------------------------------------------------------------------
# pass
#-------------------------------------------------------------------------------
#
#-------------------------------------------------------------------------------
# Section 2.11b
#
# Assign to best_theta, the weights (and not the bias!) learned by your most
# accurate algorithm with the optimal choice of hyperparameters.
#-------------------------------------------------------------------------------
best_theta = p1.average_perceptron(test_bow_features, test_labels, T=25)[0]
wordlist = [word for (idx, word) in sorted(zip(dictionary.values(), dictionary.keys()))]
# # After constructing a final feature representation, use code similar to that in # sections 2.9b and 2.10 to assess its performance on the validation set. # You may use your best classifier from before as a baseline. # When you are satisfied with your features, evaluate their accuracy on the test # set using the same procedure as in section 2.11a. #------------------------------------------------------------------------------- ## Base Case dictionary = p1.bag_of_words(train_texts) train_final_features = p1.extract_final_features(train_texts, dictionary) val_final_features = p1.extract_final_features(val_texts, dictionary) test_final_features = p1.extract_final_features(test_texts, dictionary) print(p1.average_perceptron_accuracy(train_final_features,val_final_features,train_labels,val_labels,T=15)) print(p1.average_perceptron_accuracy(val_final_features,test_final_features,val_labels,test_labels,T=15)) ## Improve 1 dictionary = p1.bag_of_better_words(train_texts) train_final_features = p1.extract_final_features(train_texts, dictionary) val_final_features = p1.extract_final_features(val_texts, dictionary) test_final_features = p1.extract_final_features(test_texts, dictionary) #data = (train_final_features, train_labels, val_final_features, val_labels) # ## values of T and lambda to try #Ts = [1, 5, 10, 15, 25, 50, 100] # #avg_pct_tune_results = utils.tune_avg_perceptron(Ts, *data)
# utils.plot_tune_results('Pegasos', 'T', Ts, *avg_peg_tune_results_T)
# utils.plot_tune_results('Pegasos', 'L', Ls, *avg_peg_tune_results_L)
#-------------------------------------------------------------------------------
#
#-------------------------------------------------------------------------------
# Section 2.11a
#
# Call one of the accuracy functions that you wrote in part 2.9.a and report
# the hyperparameter and accuracy of your best classifier on the test data.
# The test data has been provided as test_bow_features and test_labels.
#-------------------------------------------------------------------------------
best_T_case = 15
print(
p1.average_perceptron_accuracy(train_bow_features, test_bow_features,
train_labels, test_labels, best_T_case))
#-------------------------------------------------------------------------------
#
#-------------------------------------------------------------------------------
# Section 2.11b
#
# Assign to best_theta, the weights (and not the bias!) learned by your most
# accurate algorithm with the optimal choice of hyperparameters.
#-------------------------------------------------------------------------------
# best_theta = p1.average_perceptron(train_bow_features, train_labels, 50)[0]
# wordlist = [word for (idx, word) in sorted(zip(dictionary.values(), dictionary.keys()))]
# sorted_word_features = utils.most_explanatory_word(best_theta, wordlist)
# print("Most Explanatory Word Features")
# print(sorted_word_features[:10])
#-------------------------------------------------------------------------------