def main():
"""
Test the heldout dataset using the trained classifier and features
"""
prepare_data()
# Get the pickled classifier model and features
with open('svmclassifier.pkl', 'rb') as infile:
model = pickle.load(infile)
with open('label_names.pkl', 'rb') as lab_names:
labels_names = pickle.load(lab_names)
with open('count_vect.pkl', 'rb') as count_v:
count_vect = pickle.load(count_v)
test_resumes = data_dict['data'][:]
test_counts = count_vect.transform(test_resumes)
tfidf_test = tfidftransform(test_counts)
predicted_score = model.predict(tfidf_test)
predicted_decision = model.decision_function(tfidf_test)
predicted = []
for i in range(1):
predicted_dec_dup = predicted_decision[i]
predicted_dec_dup_sorted = sorted(predicted_dec_dup, reverse=True)
top_five_predictions = []
predicted.append(labels_names[predicted_decision[i].tolist().index(predicted_dec_dup_sorted[0])])
for j in range(5):
top_five_predictions.append(labels_names[predicted_decision[i].tolist().index(predicted_dec_dup_sorted[j])])
print "Predicted top5: " + ", ".join(top_five_predictions)
def main():
"""
Test the heldout dataset using the trained classifier and features
"""
prepare_data()
# Get the pickled classifier model and features
with open('svmclassifier_new_0418_h.pkl', 'rb') as infile:
model = pickle.load(infile)
with open('label_names_0418_h.pkl', 'rb') as lab_names:
labels_names = pickle.load(lab_names)
with open('count_vect_0418_h.pkl', 'rb') as count_v:
count_vect = pickle.load(count_v)
test_resumes = data_dict['data'][:]
test_counts = count_vect.transform(test_resumes)
tfidf_test = tfidftransform(test_counts)
predicted_score = model.predict(tfidf_test)
predicted_decision = model.decision_function(tfidf_test)
predicted = []
for i in range(1):
predicted_dec_dup = predicted_decision[i]
predicted_dec_dup_sorted = sorted(predicted_dec_dup, reverse=True)
top_five_predictions = []
predicted.append(labels_names[predicted_decision[i].tolist().index(predicted_dec_dup_sorted[0])])
for j in range(5):
top_five_predictions.append(labels_names[predicted_decision[i].tolist().index(predicted_dec_dup_sorted[j])])
print "Predicted top5: " + ", ".join(top_five_predictions)
def main():
"""
Test the heldout dataset using the trained classifier and features
"""
prepare_data()
# Get the pickled classifier model and features
with open('svmclassifier_new_0418_h.pkl', 'rb') as infile:
model = pickle.load(infile)
with open('label_names_0418_h.pkl', 'rb') as lab_names:
labels_names = pickle.load(lab_names)
with open('count_vect_0418_h.pkl', 'rb') as count_v:
count_vect = pickle.load(count_v)
test_resumes = data_dict['data'][:]
test_labels = data_dict['label'][:]
test_counts = count_vect.transform(test_resumes)
tfidf_test = tfidftransform(test_counts)
predicted_score = model.predict(tfidf_test)
predicted_decision = model.decision_function(tfidf_test)
predicted = []
actual_vs_predicted = []
for i in range(len(test_labels)):
actual_label = test_labels[i]
predicted_dec_dup = predicted_decision[i]
predicted_dec_dup_sorted = sorted(predicted_dec_dup, reverse=True)
top_five_predictions = []
predicted.append(labels_names[predicted_decision[i].tolist().index(
predicted_dec_dup_sorted[0])])
for j in range(5):
top_five_predictions.append(
labels_names[predicted_decision[i].tolist().index(
predicted_dec_dup_sorted[j])])
actual_vs_predicted.append([actual_label, top_five_predictions])
n = 0
for l in actual_vs_predicted:
print "\nActual: " + l[0]
print "Predicted: " + predicted[n]
print "Predicted top5: " + ", ".join(l[1])
n += 1
accuracy_list = []
accuracy_list_top_5 = []
for i in range(len(test_labels)):
accuracy_list.append(0)
accuracy_list_top_5.append(0)
for j in range(len(test_labels)):
if actual_vs_predicted[j][0] in actual_vs_predicted[j][1]:
accuracy_list_top_5[j] = 1
if predicted[j] == test_labels[j]:
accuracy_list[j] = 1
print "Actual Accuracy: " + str(sum(accuracy_list) / len(accuracy_list))
print "New Accuracy (Label present in one of the 5 predictions): " + str(
sum(accuracy_list_top_5) / len(accuracy_list_top_5))
def main():
"""
Test the heldout dataset using the trained classifier and features
"""
prepare_data()
# Get the pickled classifier model and features
with open("svmclassifier_new_0418_h.pkl", "rb") as infile:
model = pickle.load(infile)
with open("label_names_0418_h.pkl", "rb") as lab_names:
labels_names = pickle.load(lab_names)
with open("count_vect_0418_h.pkl", "rb") as count_v:
count_vect = pickle.load(count_v)
test_resumes = data_dict["data"][:]
test_labels = data_dict["label"][:]
test_counts = count_vect.transform(test_resumes)
tfidf_test = tfidftransform(test_counts)
predicted_score = model.predict(tfidf_test)
predicted_decision = model.decision_function(tfidf_test)
predicted = []
actual_vs_predicted = []
for i in range(len(test_labels)):
actual_label = test_labels[i]
predicted_dec_dup = predicted_decision[i]
predicted_dec_dup_sorted = sorted(predicted_dec_dup, reverse=True)
top_five_predictions = []
predicted.append(labels_names[predicted_decision[i].tolist().index(predicted_dec_dup_sorted[0])])
for j in range(5):
top_five_predictions.append(labels_names[predicted_decision[i].tolist().index(predicted_dec_dup_sorted[j])])
actual_vs_predicted.append([actual_label, top_five_predictions])
n = 0
for l in actual_vs_predicted:
print "\nActual: " + l[0]
print "Predicted: " + predicted[n]
print "Predicted top5: " + ", ".join(l[1])
n += 1
accuracy_list = []
accuracy_list_top_5 = []
for i in range(len(test_labels)):
accuracy_list.append(0)
accuracy_list_top_5.append(0)
for j in range(len(test_labels)):
if actual_vs_predicted[j][0] in actual_vs_predicted[j][1]:
accuracy_list_top_5[j] = 1
if predicted[j] == test_labels[j]:
accuracy_list[j] = 1
print "Actual Accuracy: " + str(sum(accuracy_list) / len(accuracy_list))
print "New Accuracy (Label present in one of the 5 predictions): " + str(
sum(accuracy_list_top_5) / len(accuracy_list_top_5)
)