def make_annotations(ann: dict):
r = {}
for k, v in ann.items():
if isinstance(v, dict):
r[k] = plac.Annotation(**v)
elif isinstance(v, (tuple, list)):
r[k] = plac.Annotation(*v)
else:
r[k] = v
return r
while True:
src_phrase = " ".join(srctext[i]
for i in range(e_start, e_end + 1))
trg_phrase = " ".join(trgtext[i]
for i in range(fs, fe + 1))
yield (src_phrase, trg_phrase)
fe += 1
if fe in f_aligned or fe == trglen:
break
fs -= 1
if fs in f_aligned or fs < 0:
break
@plac.annotations(source_file=plac.Annotation("Source file", 'option', 's',
str),
target_file=plac.Annotation("Target file", 'option', 't',
str),
aligment_file=plac.Annotation("Alignment file", 'option',
'a', str),
output_file=plac.Annotation("Output file", 'option', 'o',
str),
max_ngram=plac.Annotation("Max N-gram length", 'option', 'm',
int))
def main(source_file, target_file, aligment_file, output_file, max_ngram=5):
assert source_file and target_file and aligment_file and output_file, 'missing arguments'
sources = read_file(source_file)
targets = read_file(target_file)
alignments = map(convert_alignment, read_file(aligment_file))
'''Loads cross validation dictionaries used for the experiment'''
filter_fpath = os.path.join(cross_val_folder, 'user_item_filter.dat')
user_items_to_filter = load_dict_from_file(filter_fpath)
val_tags_fpath = os.path.join(cross_val_folder, 'user_val_tags.dat')
user_validation_tags = load_dict_from_file(val_tags_fpath)
test_tags_fpath = os.path.join(cross_val_folder, 'user_test_tags.dat')
user_test_tags = load_dict_from_file(test_tags_fpath)
return user_items_to_filter, user_validation_tags, user_test_tags
@plac.annotations(
db_fpath=plac.Annotation('H5 database file', type=str),
db_name=plac.Annotation('H5 database name', type=str),
cross_val_folder=plac.Annotation('Folder with cross validation files',
type=str),
param_value=plac.Annotation('Parameter Value', type=float),
est_name=plac.Annotation('Estimator to perform grid search',
type=str,
choices=['lda', 'smooth'],
kind='option'),
rand_seed=plac.Annotation('Random seed to use (None = default seed)',
type=int,
kind='option'),
num_cores=plac.Annotation('Number of cores to use', type=int))
def main(db_fpath,
db_name,
cross_val_folder,
import os
import sys
import plac # pylint: disable=F0401
from gossamer.main import dispatch
from gossamer.constant import modes, exits, states, \
DEFAULT_WEBDRIVER, DEFAULT_TESTFILE, \
DEFAULT_DIFFCOLOR, DEFAULT_SCREENSIZE, \
DEFAULT_BROWSER
from gossamer import util, exc
from gossamer import __version__
@plac.annotations(
names=plac.Annotation('Test case name(s) to use, comma-separated', ),
postdata=plac.Annotation('File for POST data or - for stdin'),
testfile=plac.Annotation('Test file(s) to use',
'option',
'f',
str,
metavar='GLOB'),
record=plac.Annotation('Record a new test', 'flag', 'r'),
rerecord=plac.Annotation('Re-run the test but take new screenshots',
'flag', 'rr'),
selenium=plac.Annotation('Selenium WebDriver URL to use',
'option',
's',
metavar=DEFAULT_WEBDRIVER),
browser=plac.Annotation(
'Browser to use, either firefox, chrome, phantomjs, ie, or opera',
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#NOTE plac is cool but is an other dependency, should replace by optparse
import plac
import logbook
log = logbook.Logger('Database::Manager')
from neuronquant.data.database import Manager
@plac.annotations(symbols=plac.Annotation("Add provided stocks to db",
'option', 'a'),
sync=plac.Annotation("Update quotes stored in db", 'flag',
's'),
create=plac.Annotation("Create database from written models",
'flag', 'c'))
def main(sync, create, symbols=None):
''' MySQL Stocks database manager '''
db = Manager()
if create:
log.info('Creating database...')
db.create_database()
elif sync:
log.info('Synchronizing quotes database...')
db.sync_quotes()
# -*- coding: future_fstrings -*-
# Standard modules
import pathlib
# External modules
import plac
# Local modules
from obd_influx.storage import create_recorder
@plac.annotations(
config_json=plac.Annotation(
"json configuration file to check",
type=pathlib.Path)
)
def check_config_json(config_json: pathlib.Path):
"""Verify that config.json file correctly defines Recorder."""
recorder = create_recorder(config_json=config_json)
print(
f"{config_json.resolve()} successfully initialized recorder")
try:
recorder.check_settings()
print("recorder settings check out")
except ImportError:
print("recorder has no check_settings method")
if __name__ == '__main__':
plac.call(check_config_json)
import os
import cv2
import numpy as np
import plac
import json
from yolo2.frontend import YOLO
#Set environment variables to run it on cpu
os.environ['CUDA_DEVICE_ORDER'] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
@plac.annotations(weights_path=plac.Annotation("Model path", type=str),
image_path=plac.Annotation("Image path", type=str))
def main(weights_path, image_path):
if not os.path.exists(weights_path):
raise Exception("The model file doesn't exist in this path " +
str(weights_path))
if not os.path.exists(image_path):
raise Exception("The image file doesn't exist in this path " +
str(image_path))
with open('config.json') as config_buffer:
config = json.load(config_buffer)
yolo = YOLO(backend=config['model']['backend'],
input_size=config['model']['input_size'],
labels=config['model']['labels'],
max_box_per_image=config['model']['max_box_per_image'],
anchors=config['model']['anchors'])
def save_dict_to_file(fpath, dict_data):
'''
Saves a dict with sets/lists as values to a file. Each line of the file will
be:
key - val1, val2, val3 ...
'''
with open(fpath, 'w') as out_file:
for key in dict_data:
print(key, '-', file=out_file, end=' ')
print(' '.join(str(x) for x in dict_data[key]), file=out_file)
@plac.annotations(db_fpath=plac.Annotation('H5 database file', type=str),
db_name=plac.Annotation('H5 database name', type=str),
cross_val_folder=plac.Annotation(
'Folder with cross validation files', type=str))
def main(db_fpath, db_name, cross_val_folder):
user_items_to_filter, user_validation_items, user_test_items = \
load_train_test_validation(cross_val_folder)
validation_dict = defaultdict(set)
test_dict = defaultdict(set)
with AnnotReader(db_fpath) as reader:
reader.change_table(db_name)
#Generate 50 random tags not used by any user in validation or test
#validate that the Cloud Network exists
# if port_check.status_code != 200:
# print(f"Could not validate server {cs_id}! Cloud Servers "
# f"API returns code {cs_check.status_code}. Exiting!")
# exit(1)
# def get_port_ids(cloud_network, cn_endpoint, cs_list, headers):
# port_ids = []
# for cs in cs_list:
#
#begin main function
@plac.annotations(
region=plac.Annotation("Rackspace Cloud Servers region"),
cs_ids=plac.Annotation("At least 2 Cloud Server IDs, separated by commas"),
cloud_network=plac.Annotation(
"Cloud Network or 'public' for Public Network"),
ip_version=plac.Annotation("IP version", choices=["4", "6"]))
def main(region, cs_ids, cloud_network, ip_version):
username, password = getset_keyring_credentials()
auth_token, headers = get_auth_token(username, password)
cn_endpoint = find_endpoints(auth_token,
headers,
region,
desired_service="cloudNetworks")
cs_endpoint = find_endpoints(auth_token,
print("example upload commands:")
print("#curl -vX %s \"%s\" --data-binary @%s" %
(method, temp_url, cf_object))
print("#curl -vX %s \"%s\" --data-binary @%s" %
(method, snet_temp_url, cf_object))
if method == "GET":
print("example download commands:")
print("#curl -vX %s \"%s\" -o %s" % (method, temp_url, cf_object))
print("#curl -vX %s \"%s\" -o %s" % (method, snet_temp_url, cf_object))
print(
"Remember, curl tries to put the entire file into memory before copying!"
)
@plac.annotations(
method=plac.Annotation("HTTP method : GET or PUT"),
duration=plac.Annotation(
"Time to live for TempURL. Use M for Minutes, H for hours and D for days"
),
region=plac.Annotation("Rackspace datacenter"),
container=plac.Annotation("name of Cloud Files container to use."),
cf_object=plac.Annotation(
"name of Cloud Files object that will be uploaded via the tempURL"))
def main(method, duration, region, container, cf_object):
duration, unit = parse_units(duration)
duration_in_seconds = calculate_ttl(duration, unit)
username, password = getset_keyring_credentials()
auth_token = get_auth_token(username, password)
cf_endpoint, cf_username = find_endpoint_and_user(auth_token, region)
temp_url_key = get_temp_url_key(cf_endpoint, cf_username, auth_token)
object_url = check_and_make_container(method, cf_endpoint, container,
self.add_execution(
# prev + daemonize if in time, now + daemonize if in delay
max(prev_time, time.time()) + self.daemons[item[1]],
item[1])
finally:
self.lock.release()
return item
def stop(self):
self.graceful_stop = True
@plac.annotations(
cfg_file_path=plac.Annotation('path to the config file', 'option', 'c'),
resume=plac.Annotation('resume crawling from last process', 'flag'),
reset_elasticsearch=plac.Annotation('reset Elasticsearch indexes', 'flag'),
reset_json=plac.Annotation('reset JSON files', 'flag'),
reset_mysql=plac.Annotation('reset MySQL database', 'flag'),
reset_all=plac.Annotation('combines all reset options', 'flag'),
no_confirm=plac.Annotation('skip confirm dialogs', 'flag'))
def cli(cfg_file_path, resume, reset_elasticsearch, reset_mysql, reset_json,
reset_all, no_confirm):
"A generic news crawler and extractor."
if reset_all:
reset_elasticsearch = True
reset_json = True
reset_mysql = True
if done:
eval_rewards.append(reward)
eval_actions.append(episode_actions)
eval_summaries.append(info['summary'])
episode_actions = []
obs = eval_env.reset()
n_episodes += 1
if n_episodes % 100 == 0:
print(n_episodes)
return eval_rewards, eval_summaries, eval_actions
@plac.annotations(
model_path=plac.Annotation("Path to model", type=str),
)
def main(model_path):
# load model
class LeadBaselineModel():
def __init__(self, summary_len: int = 4):
self.summary_len = summary_len
def predict(self, obs):
summary = obs[-self.summary_len:]
for i in range(len(obs)):
if sum(summary[min(i, self.summary_len - 1)]) == 0:
return i, 0
if model_path == 'experiments/baseline':
model = LeadBaselineModel()
#!/usr/bin/env python
import os
import sys
import plac
import importlib
from pathlib import Path
from spacy.util import get_package_path
from spacy.compat import symlink_to
@plac.annotations(lang=plac.Annotation(help='Language code'),
lang_path=plac.Annotation(help='Language path'))
def link_lang_spacy(lang, lang_path):
origin_path = os.path.join(
str(get_package_path('spacy').resolve()),
'lang',
lang,
)
try:
symlink_to(
Path(origin_path),
os.path.abspath(lang_path),
)
try:
importlib.import_module('spacy.lang.{}'.format(lang))
print('link created')
except Exception as e:
print('link not created')
raise e
except Exception as e:
depth_maps.flush()
logger.log("Saved DNN depth maps to {}.".format(dnn_depth_map_path))
return depth_maps
except Exception:
logger.log(
"\nError occurred during creation of depth maps - deleting {}.".
format(dnn_depth_map_path))
os.remove(dnn_depth_map_path)
raise
@plac.annotations(
video_path=plac.Annotation("The path to the input video.",
kind="option",
type=str,
abbrev="i"),
model_path=plac.Annotation(
"The path to the depth estimation model weights.",
kind="option",
type=str,
abbrev="m"),
video_output_path=plac.Annotation("The path to the write the output to.",
kind="option",
type=str,
abbrev="o"),
batch_size=plac.Annotation(
"The mini-batch size to use for the depth estimation network.",
kind="option",
type=int),
)
import plac
import spacy
@plac.annotations(
output_dir=plac.Annotation("Connection string", type=str))
def main(output_dir):
nlp = spacy.blank('en')
nlp.add_pipe(nlp.create_pipe('ner'))
nlp.add_pipe(nlp.create_pipe('sentencizer'))
nlp.begin_training()
nlp.to_disk(output_dir)
if __name__ == '__main__':
plac.call(main)
import re
import nltk
import plac
@plac.annotations(filepath=plac.Annotation('The text file to parse', type=str))
def main(filepath):
with open(filepath, 'r') as f:
text = f.read()
"""Create a parser."""
grammar = r"""
NBAR:
{<DT>?<NN.*|JJ>*<NN.*>} # Nouns and Adjectives, terminated with Nouns
NP:
{<NBAR>(<IN|CC><NBAR>)*} # Above, connected with in/of/etc...
"""
chunker = nltk.RegexpParser(grammar)
pattern = re.compile(r"^(\d(\.\d)*\s+)?[A-Z]\w*(\s(&|\w+))*$",
flags=re.MULTILINE)
sections = []
for match in re.finditer(pattern, text):
start, end = match.span()
sections.append((match.group(0), end + 1))
# print(match.group(0), match.span(), text[start:end])
for i, title_index_pair in enumerate(sections):
section, start = title_index_pair
mesh = TriangleMesh.create_from_point_cloud_ball_pivoting(
pcd=point_cloud, radii=o3d.utility.DoubleVector([radius, 2 * radius]))
logger.log("Created triangle mesh {}/{}.".format(frame_i + 1, num_frames))
mesh_filename = "{:04d}.ply".format(frame_i)
mesh_path = os.path.join(output_path, mesh_filename)
write_triangle_mesh(filename=mesh_path, mesh=mesh)
logger.log("Saved triangle mesh for frame {}/{} to {}.".format(
frame_i + 1, num_frames, mesh_path))
return mesh
@plac.annotations(
video_path=plac.Annotation('The path to the source video file.',
type=str,
kind='option',
abbrev='i'),
workspace_path=plac.Annotation(
"Where to save and load intermediate results to and from.",
type=str,
kind="option"))
def main(video_path, workspace_path="workspace"):
print(dict(
video_path=video_path,
workspace_path=workspace_path,
))
video_name = Path(video_path).stem
workspace_path = os.path.join(os.path.abspath(workspace_path), video_name)
colmap_path = os.path.join(workspace_path, "parsed_colmap_output.pkl")
'firefox': webdriver.Firefox,
'chrome': webdriver.Chrome,
'ie': webdriver.Ie,
'opera': webdriver.Opera
}
CAPABILITIES = {
'firefox': webdriver.DesiredCapabilities.FIREFOX,
'chrome': webdriver.DesiredCapabilities.CHROME,
'ie': webdriver.DesiredCapabilities.INTERNETEXPLORER,
'opera': webdriver.DesiredCapabilities.OPERA
}
@plac.annotations(
url=plac.Annotation('URL to hit'),
filename=plac.Annotation('Test file location'),
postdata=plac.Annotation('File for POST data or - for stdin'),
record=plac.Annotation('Record a test', 'flag', 'r', metavar='URL'),
rerecord=plac.Annotation('Re-run the test but take new screenshots',
'flag', 'R'),
sleepfactor=plac.Annotation('Sleep interval multiplier',
'option',
'f',
float,
metavar='FLOAT'),
browser=plac.Annotation(
'Browser to use, either firefox, chrome, phantomjs, ie or opera.',
'option',
'b',
str,
np.savetxt(rgr_pred_fpath, rgr_pred)
np.savetxt(rgr_true_fpath, rgr_true)
print('Micro F1: ', f1_score(clf_true, clf_pred, average='micro'))
print('Macro F1: ', f1_score(clf_true, clf_pred, average='macro'))
print()
print('R2: ', r2_score(rgr_true, rgr_pred))
print('MAE: ', mae(rgr_true, rgr_pred))
print('MSE: ', mse(rgr_true, rgr_pred))
print()
print_importance(feature_ids,
clf_model.best_estimator_.feature_importances_,
rgr_model.best_estimator_.feature_importances_)
@plac.annotations(partial_features_fpath=plac.Annotation('Partial Features',
type=str),
tag_categ_fpath=plac.Annotation('Tags file', type=str),
tseries_fpath=plac.Annotation('Time series file', type=str),
num_days_to_use=plac.Annotation('Num Days Series', type=int),
assign_fpath=plac.Annotation('Series assignment file',
type=str),
out_foldpath=plac.Annotation('Output folder', type=str))
def main(partial_features_fpath, tag_categ_fpath, tseries_fpath,
num_days_to_use, assign_fpath, out_foldpath):
X, feature_ids, feature_names = \
create_input_table(partial_features_fpath, tseries_fpath,
tag_categ_fpath, num_pts = num_days_to_use)
#Sort X by upload date
up_date_col = feature_names['A_UPLOAD_DATE']
vulnerability_specific_columns = [
'message_score', 'changed_files_score', 'git_diff_score',
'message_score_reference_content', 'changed_files_score_code_tokens'
]
universal_columns = [
'n_hunks', 'avg_hunk_size', 'n_changed_files', 'vulnerability_timestamp'
]
columns_to_drop = [
'path_similarity_score', 'git_diff_score_code_tokens',
'message_score_code_tokens', 'changed_files_score_reference_content',
'git_diff_score_reference_content'
]
@plac.annotations(
vulnerability_id=plac.Annotation("A vulnerability ID (typically a CVE)",
type=str),
verbose=plac.Annotation(
"Definition of verbose: containing more words than necessary: WORDY",
'flag', 'v'),
description=plac.Annotation("The vulnerability description",
"option",
type=str),
published_timestamp=plac.Annotation(
"The timestamp at which the vulnerability is published (int)",
"option",
type=int),
repo_url=plac.Annotation(
"The affected repository (typically a GitHub URL)", "option",
type=str),
project_name=plac.Annotation(
"The name of the affected project (typically a GitHub URL)",
r = huxleymain(testname,
url,
filename,
postdata,
remote=REMOTE_WEBDRIVER_URL,
sleepfactor=sleepfactor,
autorerecord=not playback_only,
save_diff=save_diff,
screensize=screensize)
print
if r != 0:
new_screenshots.set_value(True)
@plac.annotations(
names=plac.Annotation('Test case name(s) to use, comma-separated', ),
testfile=plac.Annotation('Test file(s) to use',
'option',
'f',
str,
metavar='GLOB'),
record=plac.Annotation('Record a new test', 'flag', 'r'),
playback_only=plac.Annotation('Don\'t write new screenshots', 'flag', 'p'),
concurrency=plac.Annotation('Number of tests to run in parallel',
'option',
'c',
int,
metavar='NUMBER'),
save_diff=plac.Annotation(
'Save information about failures as last.png and diff.png', 'flag',
'e'),
from statistics import mean
from xml.etree import ElementTree
import plac
import spacy
@plac.annotations(filepath=plac.Annotation(
'The XML file to calculate the average sentence length for.', type=str))
def main(filepath):
tree = ElementTree.parse(filepath)
root = tree.getroot()
nlp = spacy.load('en')
sentence_lengths = []
for section in root.findall('section'):
section_text = section.find('text').text
span = nlp(section_text)
for sent in span.sents:
sentence_lengths.append(len(sent))
print('Mean Sentence Length: %.2f' % mean(sentence_lengths))
if __name__ == '__main__':
plac.call(main)
from typing import Optional
from xml.dom import minidom
from xml.etree import ElementTree
import plac
@plac.annotations(
files=plac.Annotation('The list of annotated XML files to merge.',
type=str),
output_path=plac.Annotation(
'Where to save the output file. '
'If set to None, the merged file is printed to stdout.',
type=str,
kind='option',
abbrev='o'),
)
def main(output_path: Optional[str] = None, *files):
"""Merge annotations from multiple XML files into a single XML file."""
if len(files) > 0:
tree = ElementTree.ElementTree(element=ElementTree.Element('document'))
document_sections = [
ElementTree.parse(file).getroot().findall('section')
for file in files
]
for i, sections in enumerate(zip(*document_sections)):
for section in sections[1:]:
annotations = sections[0].find('annotations')
lexers.JsonLexer(),
formatters.TerminalFormatter())
data = {}
data['forms'] = form_urls
data['compressed'] = compressed_urls
full_path = '%sreport-%s.json' % (loot_dir, str(now))
with open(full_path, 'a') as fd:
_LOGGER.info('* Writing out report')
json.dump(data, fd, ensure_ascii=False, indent=4)
print(form_colorful_json)
print(compressed_colorful_json)
@plac.annotations(
url=plac.Annotation('URL to navigate to',
kind='option',
abbrev='url',
type=str),
log_level=plac.Annotation(
'Logging level [LOG_LEVEL]', 'option', 'l', str,
['debug', 'info', 'warn', 'warning', 'error']), # noqa: E501
log_format=plac.Annotation('Logging format [LOG_FORMAT]', 'option', 'f',
str, ['json', 'text']),
url_file=plac.Annotation('File with newline separated URLs',
kind='option',
type=str),
loot_dir=plac.Annotation('Directory to add loot and logging',
kind='option',
type=str),
)
def main(url, url_file, loot_dir='loot/', log_level='info', log_format='json'):
user_items_to_filter = load_dict_from_file(filter_fpath)
val_tags_fpath = os.path.join(cross_val_folder, 'user_val_tags.dat')
user_validation_tags = load_dict_from_file(val_tags_fpath)
test_tags_fpath = os.path.join(cross_val_folder, 'user_test_tags.dat')
user_test_tags = load_dict_from_file(test_tags_fpath)
test_items_fpath = os.path.join(cross_val_folder, 'user_test_items.dat')
user_test_items = load_dict_from_file(test_items_fpath)
return user_items_to_filter, user_validation_tags, user_test_tags, \
user_test_items
@plac.annotations(
db_fpath = plac.Annotation('H5 database file', type=str),
db_name = plac.Annotation('H5 database name', type=str),
cross_val_folder = plac.Annotation('Folder with cross validation files',
type=str),
probs_folder = plac.Annotation('Probabilities Folder', type=str))
def main(db_fpath, db_name, cross_val_folder, probs_folder):
#get cross validation dicts
user_items_to_filter, user_validation_tags, user_test_tags, \
user_test_items = load_train_test_validation(cross_val_folder)
with AnnotReader(db_fpath) as reader:
reader.change_table(db_name)
annot_filter = FilteredUserItemAnnotations(user_items_to_filter)
import torch
from torchvision.transforms import Compose
import loaddata_demo as loaddata
import utils
from models.midas_net import MidasNet
from models.transforms import NormalizeImage, PrepareForNet, Resize
plt.set_cmap("gray")
@plac.annotations(
image_path=plac.Annotation(
'The path to an RGB image or a directory containing RGB images.',
type=str,
kind='option',
abbrev='i'),
model_path=plac.Annotation('The path to the pre-trained model weights.',
type=str,
kind='option',
abbrev='m'),
output_path=plac.Annotation('The path to save the model output to.',
type=str,
kind='option',
abbrev='o'),
)
def main(image_path, model_path='model.pt', output_path=None):
print("Loading model...")
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
import plac
from selenium import webdriver
from src.udemy import Udemy
from src.errors import Error, LoginNotFound
import configparser
from config import UDEMY, COUPONS, Config
@plac.annotations(pages=plac.Annotation("Number of pages to scan", "option"),
keywords=plac.Annotation("Path to the keywords file",
"option"),
driverpath=plac.Annotation("Path to the web driver",
"option"),
config=plac.Annotation("Path to the config file", "option"))
def main(pages, keywords, driverpath, config=".config/config.ini"):
try:
options = Config(config, pages, keywords, driverpath)
except configparser.Error:
print("Impossible to parse the config file")
exit(1)
except KeyError:
print("Invalid configuration file")
exit(1)
except ValueError:
print("Configuration value given is invalid")
exit(1)
try:
keys = list(options.keywords())
except (IOError, FileNotFoundError):
from typing import Optional
import plac
from crypto.ciphers.caesar import CaesarCipher, CaesarCipherKey
from crypto.ciphers.utils import is_valid
from crypto.common_attacks import LetterFrequencyAttack, DictionaryAttack, LanguageAnalysisAttack
from crypto.metrics import print_attack_summary
from crypto.strategies import ExhaustiveSampling
from crypto.types import Message
@plac.annotations(key=plac.Annotation(
"The key to use for the caesar cipher. This is typically an integer in the range [0, 25]."
"If not specified then a key is chosen at random.",
kind='option',
type=int),
filename=plac.Annotation(
'The name of a file to use as the message.',
kind='option',
type=str,
abbrev='f'))
def main(key: Optional[int] = None, filename: Optional[str] = None) -> int:
"""A demonstration of the Caesar cipher."""
if filename:
with open(filename, 'r') as f:
message = Message(f.read())
else:
message = Message(input('Enter a message to encrypt: '))
import PyPDF2
import os
import json
import plac
from pathlib import Path
import codecs
from io import StringIO
import string
import csv
from modules import cleaner
@plac.annotations(
command=plac.Annotation("command", type=str),
input_source=plac.Annotation("Connection string", type=Path),
output_file=plac.Annotation("Connection string", type=Path),
label=plac.Annotation("Label", 'option', 'l', type=str),
extend=plac.Annotation("Extend an exsiting dataset", 'flag', 'e'))
def main(command, input_source, output_file, label, extend):
output_mode = 'a' if extend else 'w'
if command == 'pdf':
# Convert the pdfs of the given directory or if the input is a single file only this file
with open(str(output_file), output_mode) as jsonl_file:
if str(input_source).endswith(".pdf"):
text = pdf_to_text(str(input_source))
jsonl_file.write(json.dumps({"text": text.strip('\n')}) + '\n')
else:
data = set([spl[1]])
else:
data = set(token.strip() for token in spl[2:])
class_num = classes[curr_line]
to_cmp[class_num].update(data)
return to_cmp
def asym_jaccard(first_set, second_set):
intersect = first_set.intersection(second_set)
return len(intersect) / len(first_set)
@plac.annotations(features_fpath=plac.Annotation('Tags file', type=str),
classes_fpath=plac.Annotation('Video classes file',
type=str),
user_users=plac.Annotation('Use user_names instead of tags',
kind='flag',
abbrev='u',
type=bool))
def main(features_fpath, classes_fpath, user_users=False):
initialize_matplotlib()
classes = np.loadtxt(classes_fpath)
num_classes = len(set(classes))
to_compare = load_text_file(features_fpath, classes, user_users)