plt.plot(base_zero_false_positives,
base_zero_true_positives,
label='Base rate model (zeros)')
plt.plot(base_random_false_positives,
base_random_true_positives,
label='Base rate model (random)')
# plt.plot([0, 1], [0, 1], linestyle='--', label='Random guessing expectation')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.legend()
show_plot_and_save_figure('roc_auc_curve')
if __name__ == '__main__':
model: LogisticRegressionModel = read_pickle(
GENERATED_LOGISTIC_REGRESSION_MODEL)
dev_data = read_pickle(GENERATED_LR_PREPROCESSED_DEV_DATA)
dev_input, dev_expected = extract_input_and_expected(dev_data)
model_prediction = model.get_predictions(dev_input, args.bias_corrected)
baserate_prediction = get_baserate_predictions(model_prediction)
# predictions
print('Evaluation preditions (int 0|1)')
print('Predictions Baserate AUC: {:.2f}'.format(
roc_auc_score(dev_expected, baserate_prediction)))
print('Predictions Model AUC: {:.2f}'.format(
roc_auc_score(dev_expected, model_prediction)))
print('*' * 40)
# probabilities
import random
import unicodedata
import pandas as pd
from termcolor import colored
from dataaccess.files_constants import get_wiki_batch_path, GENERATED_WIKI_PAGE_MAPPINGS_PATH
from dataaccess.files_io import read_pickle
from model.wiki_document import WikiDocument, WikiLine
wiki_page_mapping: pd.DataFrame = read_pickle(GENERATED_WIKI_PAGE_MAPPINGS_PATH)
def retrieve_wiki_page(page_id: str) -> WikiDocument:
page_id = page_id.strip()
# account for some special cases, like u'Beyonce\u0301' != 'Beyoncé'
page_id = unicodedata.normalize('NFC', page_id)
# Find correct batch file and read only relevant line
batch_id, line = wiki_page_mapping.loc[page_id].values
wiki_batch_path = get_wiki_batch_path(batch_id)
with open(wiki_batch_path) as fp:
for i, json_line in enumerate(fp):
if i == line:
return WikiDocument(json_line)
# If this code runs, a mapping error occured
print(colored('Error: Line {} not found in wiki-page {}'.format(line, batch_id), 'red'))
import argparse
import pandas as pd
from _4_B_fit_LR_model import fit_and_get_model, LOSS_HISTORY_FREQUENCY
from dataaccess.files_constants import GENERATED_LOGISTIC_REGRESSION_MODEL, \
GENERATED_LOGISTIC_REGRESSION_LOSS_HISTORY, GENERATED_LR_PREPROCESSED_TRAINING_DATA
from dataaccess.files_io import read_pickle, write_pickle
from util.LR_NN_preprocessing import extract_input_and_expected
from util.plots import plot_loss_values
parser = argparse.ArgumentParser()
parser.add_argument('--debug', help='use less data and less learning iterations', action='store_true')
parser.add_argument('--num_iterations', type=int, default=100000)
parser.add_argument('--learning_rate', type=float, default=0.1)
args = parser.parse_args()
if __name__ == '__main__':
training_data: pd.DataFrame = read_pickle(GENERATED_LR_PREPROCESSED_TRAINING_DATA)
train_input, train_expected = extract_input_and_expected(training_data)
model, loss_values = fit_and_get_model(train_input, train_expected, args.num_iterations, args.learning_rate)
write_pickle(GENERATED_LOGISTIC_REGRESSION_LOSS_HISTORY, loss_values) # for plotting
write_pickle(GENERATED_LOGISTIC_REGRESSION_MODEL, model)
plot_loss_values(args.num_iterations, args.learning_rate, loss_values, LOSS_HISTORY_FREQUENCY)
def __init__(self, preprocessed_pickle_path: str):
preprocessed_dataset: pd.DataFrame = read_pickle(preprocessed_pickle_path)
inputs, labels = extract_input_and_expected(preprocessed_dataset)
self.inputs = inputs
self.labels = labels
def plot_multiple_loss_values(learning_rates: list,
multiple_loss_values: list):
prepare_seaborn_plots()
plt.xlabel('Iterations')
plt.ylabel('Cross-Entropy Loss')
# Fixed n for the given trained models
plt.figtext(0.68, 0.56, r'$n = {:,}$'.format(100000))
for i, values in enumerate(multiple_loss_values):
label = r'$\alpha = {:,}$'.format(float(learning_rates[i]))
x_axis = [i * LOSS_HISTORY_FREQUENCY for i in range(len(values))]
plt.plot(x_axis, values, linewidth=2, label=label)
plt.legend(loc='upper right')
show_plot_and_save_figure(
'logistic_regression_loss_values_comparision.png')
if __name__ == '__main__':
# load the pre-computed values
learning_rates = ['0.0001', '0.001', '0.01', '0.1', '1.0']
filepaths = [
'./generated/logistic_regression_loss_{}.p'.format(rate)
for rate in learning_rates
]
loss_values = [read_pickle(path) for path in filepaths]
plot_multiple_loss_values(learning_rates, loss_values)