def main():
train_word_list, train_pos_list, train_ne_list = getTrainingData(HMM=True)
test_word_list, test_pos_list, test_idx_list = getTestData(HMM=True)
# tag_seq_preds = getTestPreds(train_pos_list, train_ne_list, test_pos_list, smooth=True)
# tag_seq_preds = getTestPreds(train_word_list, train_ne_list, test_word_list, smooth=True)
tag_seq_preds = getTestPreds(train_word_list, train_ne_list, test_word_list, smooth=True, similarity=True)
formatted_preds = formatTestPreds(tag_seq_preds, test_idx_list)
savePredictionsToCSV(formatted_preds)
def main():
train_word_list, _, train_ne_list = getTrainingData(HMM=True)
test_word_list, test_pos_list, test_idx_list = getTestData(HMM=True)
feature_type = 'text_features'
low_frequency_probabilities = json.load(open(dir_path + 'Training_Test_Data/{0}'.format(feature_type)))
tag_seq_preds = getTestPreds(train_word_list, train_ne_list, test_word_list, low_frequency_probabilities, smooth=None, similarity_based=True, test_pos_list=test_pos_list)
formatted_preds = formatTestPreds(tag_seq_preds, test_idx_list)
savePredictionsToCSV(formatted_preds)
def main():
train_word_list, train_pos_list, train_ne_list = getTrainingData(HMM=True)
test_word_list, test_pos_list, test_idx_list = getTestData(HMM=True)
# tag_seq_preds = getTestPreds(train_pos_list, train_ne_list, test_pos_list, smooth=True)
# tag_seq_preds = getTestPreds(train_word_list, train_ne_list, test_word_list, smooth=True)
tag_seq_preds = getTestPreds(train_word_list,
train_ne_list,
test_word_list,
smooth=True,
similarity=True)
formatted_preds = formatTestPreds(tag_seq_preds, test_idx_list)
savePredictionsToCSV(formatted_preds)
def main():
train_word_list, _, train_ne_list = getTrainingData(HMM=True)
test_word_list, test_pos_list, test_idx_list = getTestData(HMM=True)
feature_type = 'text_features'
low_frequency_probabilities = json.load(
open(dir_path + 'Training_Test_Data/{0}'.format(feature_type)))
tag_seq_preds = getTestPreds(train_word_list,
train_ne_list,
test_word_list,
low_frequency_probabilities,
smooth=None,
similarity_based=True,
test_pos_list=test_pos_list)
formatted_preds = formatTestPreds(tag_seq_preds, test_idx_list)
savePredictionsToCSV(formatted_preds)
def main():
training_data, largest_key_size = getTrainingData()
context, pos, index = getTestData()
predictions = makePredictions(training_data, context, pos, index, largest_key_size)
savePredictionsToCSV(predictions)
def main():
training_data = getTrainingData()
context, pos, index = getTestData()
predictions = makePredictions(training_data, context, pos, index)
savePredictionsToCSV(predictions)
'''
Repurposed plotting code found here:
http://matplotlib.org/examples/pylab_examples/barchart_demo.html
'''
__author__ = 'Jonathan Simon'
from DataProcessing.LoadData import getTrainingData, getTestData
import matplotlib.pyplot as plt
from collections import Counter
import numpy as np
train_word_list, train_pos_list, train_ne_list = getTrainingData(HMM=True)
test_word_list, test_pos_list, test_idx_list = getTestData(HMM=True)
# Get POS counts in training set
all_train_pos = []
for sentence in train_pos_list:
for pos in sentence:
all_train_pos.append(pos)
train_pos_counter = Counter(all_train_pos)
train_pos_names, train_pos_counts = zip(*train_pos_counter.most_common())
# Get POS counts in test set
all_test_pos = []
for sentence in test_pos_list:
for pos in sentence:
all_test_pos.append(pos)
test_pos_counter = Counter(
def main():
training_data = getTrainingData()
context, pos, index = getTestData()
predictions = makePredictions(training_data, context, pos, index)
savePredictionsToCSV(predictions)
def main():
training_data, largest_key_size = getTrainingData()
context, pos, index = getTestData()
predictions = makePredictions(training_data, context, pos, index,
largest_key_size)
savePredictionsToCSV(predictions)
