def entry_generator(self):
col_zakon = utils.get_collection(
const.CONF_MONGO_ZAKON, self.conf, const.CONF_MONGO_PARSED, self.db
)
col_tlac = utils.get_collection(
const.CONF_MONGO_HLASOVANIETLAC, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in col_zakon.iterate_all():
zakon = col_tlac.get({const.MONGO_ID: entry[const.MONGO_ID]})
hlasovania = zakon.get(const.HLASOVANIETLAC_LIST, {})
zmeny = entry.get(const.ZAKON_ZMENY, {})
ids = sorted(zmeny.keys())
names = [zmeny[i][const.ZAKON_ZMENY_PREDKLADATEL].split(",")[0] for i in ids]
hlas_text = pd.Series({
key: value[const.HLASOVANIE_NAZOV].split("Hlasovanie")[-1]
for key, value in hlasovania.items()
if "druhé čítanie" in value[const.HLASOVANIE_NAZOV]
})
if len(hlas_text) == 0:
continue
counts = [0] * len(ids)
for j, name in enumerate(names):
if names.count(name) > 1:
counts[j] = names[:j+1].count(name)
for j, i in enumerate(ids):
hlas_name = hlas_text[hlas_text.str.contains(names[j][:-1])]
if counts[j] > 0:
hlas_name = hlas_name[hlas_name.str.contains("{}. návrh".format(counts[j]))]
for id_hlas, text in hlas_name.items():
if not "dopracovanie" in text and not "preložiť" in text:
yield {
const.NEO4J_BEGINNING_ID: int(id_hlas),
const.NEO4J_ENDING_ID: int(i)
}
def create_optimizer(self, optimizer=None):
model = get_collection('model')
inputs = get_collection('inputs')
alpha, l1_ratio = self.alpha, self.l1_ratio
(x, y, class_weights, learning_rate, theta, logits, probabilities,
predictions) = (inputs['x'], inputs['y'], inputs['class_weights'],
inputs['learning_rate'], model['theta'],
model['logits'], model['probabilities'],
model['predictions'])
with tf.name_scope('metrics'):
xe = cross_entropy(self.n_classes, logits=logits, labels=y)
loss = tf.reduce_mean(xe, name='loss')
weights = tf.reduce_sum(class_weights * y, axis=1)
weighted_loss = tf.reduce_mean(xe * weights, name='weighted_loss')
penalty = elastic_net(theta, l1_ratio=l1_ratio)
penalized_loss = tf.add(weighted_loss,
alpha * penalty,
name='penalized_loss')
targets = tf.argmax(y, axis=1, name='targets')
match = tf.cast(tf.equal(predictions, targets), tf.float32)
accuracy = tf.reduce_mean(match, name='accuracy')
add_to_collection('metrics', loss, penalized_loss, accuracy)
with tf.name_scope('training'):
opt = tf.train.GradientDescentOptimizer(learning_rate)
training_op = opt.minimize(penalized_loss)
add_to_collection('training', training_op)
def create_optimizer(self, optimizer=None):
model = get_collection('model')
inputs = get_collection('inputs')
x, y, logits, probabilities, predictions = (
inputs['x'],
inputs['y'],
model['logits'],
model['probabilities'],
model['predictions']
)
with tf.name_scope('metrics'):
xe = cross_entropy(self.n_classes, logits=logits, labels=y)
loss = tf.reduce_mean(xe, name='loss')
targets = tf.argmax(y, axis=1, name='targets')
match = tf.cast(tf.equal(predictions, targets), tf.float32)
accuracy = tf.reduce_mean(match, name='accuracy')
add_to_collection('metrics', loss, accuracy)
with tf.name_scope('training'):
if optimizer is None:
optimizer = tf.train.GradientDescentOptimizer
opt = optimizer(inputs['learning_rate'])
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
training_op = opt.minimize(loss)
add_to_collection('training', training_op)
def __init__(self, db, conf, source_collection=None, target_collection=None):
self.db = db
self.conf = conf
if source_collection is None:
source_collection = utils.get_collection(
self, self.conf, const.CONF_MONGO_RAW, self.db)
if target_collection is None:
target_collection = utils.get_collection(
self, self.conf, const.CONF_MONGO_PARSED, self.db)
self.source_collection = source_collection
self.target_collection = target_collection
self.log = logging.getLogger(str(self.__class__).split("'")[1])
self.unique_ids = [const.MONGO_ID]
def score(self, X, y):
"""Scores model quality on testing dataset, returning dictionary with
model's metrics.
"""
self._check_if_session_exists()
graph = self.graph
with graph.as_default():
inputs = get_collection('inputs')
metrics = get_collection('metrics')
feed = self.generate_feed(tensors=inputs, x=X, y=y, training=False)
scores = self._session.run(metrics, feed)
return scores
def predict_proba(self, X):
"""Predicts classes probabilities for dataset."""
self._check_if_session_exists()
graph = self.graph
with graph.as_default():
inputs = get_collection('inputs')
model = get_collection('model')
probabilities = model['probabilities']
feed = self.generate_feed(tensors=inputs, x=X, training=False)
probs = self._session.run(probabilities, feed)
return probs
def worker():
source_urls = get_source_urls()
papers = utils.get_newspapers(source_urls)
processed_articles = []
for paper in papers:
processed_articles += utils.process_articles_for_paper(paper)
curator = ArticleCurator(processed_articles)
curator.curate()
# Make sure we actually have new articles first
if curator.curated_articles:
# get and empty collection before filling with new articles
articles_collection = utils.get_collection('newsarticles')
articles_collection.remove()
# put new curated articles in the collection
for article in curator.curated_articles:
articles_collection.insert({
'title': article.title,
'summary': article.summary,
'image_url': article.top_image,
'url': article.url,
'keywords': article.keywords
})
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_HLASOVANIE, self.conf, const.CONF_MONGO_PARSED, self.db)
for entry in source_collection.iterate_all():
del entry[const.MONGO_TIMESTAMP]
del entry[const.HLASOVANIE_INDIVIDUALNE]
yield entry
def get_raw_gt_data():
gt_raw = get_collection('lwevents',
query_filter={"name": "gatherTownUsersCheck"},
db=get_mongo_db_object())
gt_raw['time'] = gt_raw['properties'].str['time']
gt_raw['gatherTownUsers'] = gt_raw['properties'].str['gatherTownUsers']
return gt_raw
def test_std_doc():
doc = StdDoc(field1="lolz", field2="", field3=12)
assert not hasattr(doc, "_id")
doc.save()
assert hasattr(doc, "_id")
assert find_valid_parent_docs(type(doc)) == []
# not mutable field
mutated = False
try:
doc["field3"] = 1
mutated = True
except:
pass
assert mutated is False
# mutable field but wrong type
mutated = False
try:
doc["field1"] = 1
mutated = True
except:
pass
assert mutated is False
# mutable and should have no errors
doc["field1"] = "looo"
doc.save()
assert doc["field1"] == "looo"
collec = get_collection(doc)
elts = list(collec.find({"_id": doc._id}))
assert len(elts) == 1
assert elts[0]["field1"] == "looo"
def update_doubt():
id = request.args.get('id')
doubt = request.json.get('doubt')
answer = request.json.get('answer')
topic = request.json.get('topic')
if isinstance(doubt, str) and isinstance(answer, str):
documents = get_collection('doubts')
query = {'_id': ObjectId(id)}
if documents.find_one(query):
new_values = {
'$set': {
'doubt': doubt,
'answer': answer,
'topic': topic
}
}
documents.update_one(query, new_values, upsert=True)
return 'Accepted', 202
else:
return 'Doubt not found', 404
else:
return 'Bad request', 400
def entry_generator(self):
vybory = [
entry[const.MONGO_ID]
for entry in storage.MongoCollection(self.db, "nodes_vybor").iterate_all()
]
source_collection = utils.get_collection(
const.CONF_MONGO_ZAKON, self.conf, const.CONF_MONGO_PARSED, self.db
)
def result_form(entry, vybor, lehota):
return {
const.NEO4J_BEGINNING_ID: vybor,
const.NEO4J_ENDING_ID: entry[const.MONGO_ID],
const.NAVRHNUTY_LEHOTA: lehota
}
for entry in source_collection.iterate_all():
if const.ZAKON_ROZHODNUTIE_VYBORY in entry:
sprava = entry[const.ZAKON_ROZHODNUTIE_VYBORY]
if sprava == "":
break
lehota = self.get_lehota(sprava)
for vybor in vybory:
flag = False
if vybor in sprava:
result = result_form(entry, vybor, lehota)
result[const.NAVRHNUTY_TYP] = const.NAVRHNUTY_DOPLNUJUCI
flag = True
if vybor in entry[const.ZAKON_ROZHODNUTIE_GESTORSKY]:
result = result_form(entry, vybor, lehota)
result[const.NAVRHNUTY_TYP] = const.NAVRHNUTY_GESTORSKY
flag = True
if flag:
yield result
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_ZMENA, self.conf, const.CONF_MONGO_PARSED, self.db)
for entry in source_collection.iterate_all():
entry.pop(const.ZMENA_PODPISANI, None)
entry.pop(const.ZMENA_DALSI, None)
entry.pop(const.ZMENA_PREDKLADATEL)
yield entry
def restore_ensemble_model(self):
self.ensemble_graph = tf.Graph()
self.ensemble_session = U.get_session(self.ensemble_graph)
with self.ensemble_graph.as_default():
saver = tf.train.import_meta_graph("checkpoint/ensemble.meta")
saver.restore(self.ensemble_session, "checkpoint/ensemble")
names = ["probs", "logits", "temperature_ph", "inputs"]
self.ensemble_model = dict(
zip(names, U.get_collection(names, self.ensemble_graph)))
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_ZAKON, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for zmena_id in entry.get(const.ZAKON_ZMENY, {}):
yield {
const.NEO4J_BEGINNING_ID: int(zmena_id),
const.NEO4J_ENDING_ID: entry[const.MONGO_ID]
}
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_HLASOVANIETLAC, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for hlasovanie_id in entry.get(const.HLASOVANIETLAC_LIST, {}):
yield {
const.NEO4J_BEGINNING_ID: int(hlasovanie_id),
const.NEO4J_ENDING_ID: entry[const.MONGO_ID]
}
def ingest_derivative():
for bag in list_missing_ingest():
mmsid = get_mmsid(bag)
collection = get_collection(mmsid) if mmsid else None
if collection is not None:
pass
# call islandora remote worker to ingest bag
# update digital catalog
else:
print("Could not determine collection for: {0}".format(bag))
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_POSLANEC, self.conf, const.CONF_MONGO_PARSED, self.db)
orgs = set()
for entry in source_collection.iterate_all():
for org in entry[const.POSLANEC_CLENSTVO]:
if const.POSLANEC_DELEGACIA.lower() in org.lower():
orgs.add(org)
for org in orgs:
yield {const.MONGO_ID: org}
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_ZMENA, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for poslanec in entry.get(const.ZMENA_PODPISANI, []):
yield {
const.NEO4J_BEGINNING_ID: utils.get_poslanec_id(self.db, poslanec),
const.NEO4J_ENDING_ID: entry[const.MONGO_ID]
}
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_ZAKON, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
if const.ZAKON_GESTORSKY in entry:
yield {
const.NEO4J_BEGINNING_ID: entry[const.ZAKON_GESTORSKY],
const.NEO4J_ENDING_ID: entry[const.MONGO_ID]
}
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_LEGISLATIVNAINICIATIVA,
self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for zakon_id in entry.get(const.PREDLOZILZAKON_LIST, {}):
yield {
const.NEO4J_BEGINNING_ID: entry[const.MONGO_ID],
const.NEO4J_ENDING_ID: int(zakon_id)
}
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_ROZPRAVA, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for vystupenie in entry[const.ROZPRAVA_VYSTUPENIA]:
if const.ROZPRAVA_TLAC in vystupenie:
yield {
const.NEO4J_BEGINNING_ID: vystupenie[const.MONGO_ID],
const.NEO4J_ENDING_ID: vystupenie[const.ROZPRAVA_TLAC]
}
def worker():
temperature_data = get_system_temp()
temperature_data_collection = utils.get_collection('systemtemperaturedatas')
try:
temperature_data_collection.insert(temperature_data)
except:
# TODO: Add some logging should this fail
return
else:
tweeter = CPUTemperatureTweeter()
tweeter.tweet_it()
def create_model(self):
inputs = get_collection('inputs')
with tf.name_scope('model'):
init = tf.truncated_normal((self.n_features, self.n_classes))
theta = tf.Variable(init, name='theta')
bias = tf.Variable(0.0, name='bias')
logits = tf.add(tf.matmul(inputs['x'], theta), bias, name='logits')
activate = tf.nn.sigmoid if self.n_classes == 2 else tf.nn.softmax
probabilities = activate(logits, name='probabilities')
predictions = tf.argmax(probabilities, axis=1, name='predictions')
add_to_collection('model', theta, logits, probabilities, predictions)
def delete_doubt():
id = request.args.get('id')
documents = get_collection('doubts')
query = {'_id': ObjectId(id)}
if documents.find_one(query):
documents.remove(query)
return 'Accepted', 202
else:
return 'Doubt not found', 404
def create_model(self):
inputs = get_collection('inputs')
with tf.name_scope('model'):
x = inputs['x']
for layer_config in self.config:
layer = Dense(**layer_config)
x = layer.build(x, training=inputs['training'])
logits = tf.layers.dense(x, units=self.n_classes, name='logits')
activate = tf.nn.sigmoid if self.n_classes == 2 else tf.nn.softmax
probabilities = activate(logits, name='probabilities')
predictions = tf.argmax(probabilities, axis=1, name='predictions')
add_to_collection('model', logits, probabilities, predictions)
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_HLASOVANIE, self.conf, const.CONF_MONGO_PARSED, self.db
)
last_entry = source_collection.get({}, projection=[const.HLASOVANIE_INDIVIDUALNE],
sort=[(const.MONGO_ID, -1)])
hlasy = last_entry[const.HLASOVANIE_INDIVIDUALNE].values()
kluby = [value[const.HLASOVANIE_KLUB] for value in hlasy]
values, counts = np.unique(kluby, return_counts=True)
for val, count in zip(values, counts):
val = utils.parse_klub(val)
entry = {const.MONGO_ID: val, const.KLUB_POCET: int(count)}
yield entry
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_POSLANEC, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for org, typ in entry[const.POSLANEC_CLENSTVO].items():
if const.POSLANEC_DELEGACIA.lower() in org.lower():
result = {
const.NEO4J_BEGINNING_ID: entry[const.MONGO_ID],
const.NEO4J_ENDING_ID: org,
const.CLEN_TYP: const.CLEN_TYP_DICT[typ]
}
yield result
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_HLASOVANIE, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for poslanec_id, poslanec in entry[const.HLASOVANIE_INDIVIDUALNE].items():
hlas = {
const.NEO4J_BEGINNING_ID: int(poslanec_id),
const.NEO4J_ENDING_ID: entry[const.MONGO_ID],
const.HLASOVAL_HLAS: const.HLASOVAL_HLAS_DICT[poslanec[const.HLASOVANIE_HLAS]],
const.HLASOVAL_KLUB: utils.parse_klub(poslanec[const.HLASOVANIE_KLUB])
}
yield hlas
def setUpClass(cls):
coll = get_collection(GeometryModel)
GeometryModel.objects.create(geom=cls.point)
GeometryModel.objects.create(geom=cls.line)
GeometryModel.objects.create(geom=cls.polygon)
GeometryModel.objects.create(geom=cls.multi_point)
GeometryModel.objects.create(geom=cls.multi_line)
GeometryModel.objects.create(geom=cls.multi_polygon)
GeometryModel.objects.create(geom=cls.geom_collection)
# not sure why the tests don't create the index...
coll.ensure_index([('geom', pymongo.GEOSPHERE)])
def get_doubts():
documents = get_collection('doubts')
output = []
for document in documents.find({}):
output.append({
'_id': str(document['_id']),
'doubt': document['doubt'],
'answer': document['answer'],
'topic': document['topic'],
'user': document['user'],
})
return jsonify(output), 200
def get_topics_from_user():
user = request.args.get('user')
if user_exists(user):
documents = get_collection('doubts')
topics = []
query = {'user': user}
for document in documents.find(query):
if not document['topic'] in topics:
topics.append(document['topic'])
return jsonify(topics), 200
else:
return 'User not found', 404
def entry_generator(self):
source_collection = utils.get_collection(
const.CONF_MONGO_ROZPRAVA, self.conf, const.CONF_MONGO_PARSED, self.db
)
for entry in source_collection.iterate_all():
for vystupenie in entry[const.ROZPRAVA_VYSTUPENIA]:
klub = vystupenie[const.ROZPRAVA_POSLANEC_KLUB]
klub = const.KLUB_DICT.get("Klub " + klub, const.NEO4J_NULLVALUE)
yield {
const.NEO4J_BEGINNING_ID: entry[const.MONGO_ID],
const.NEO4J_ENDING_ID: vystupenie[const.MONGO_ID],
const.ROZPRAVA_POSLANEC_KLUB: klub,
const.ROZPRAVA_POSLANEC_TYP: vystupenie[const.ROZPRAVA_POSLANEC_TYP]
}
def run_import(csv_input_file, db_host, db_port, db_name, db_collection):
"""
Imports to the CSV data to a MongoDB database.
"""
print('Started CSV import - {0}'.format(datetime.now()))
collection = utils.get_collection(db_host, db_port, db_name, db_collection)
with open(csv_input_file, encoding='utf-8', errors='ignore') as csv_file:
reader = csv.DictReader(csv_file)
for json_obj in create_json(reader):
collection.insert_one(json_obj)
print('Finished: CSV import - {0}'.format(datetime.now()))
def worker():
storage_data = get_system_storage()
storage_data_collection = utils.get_collection('systemstoragedatas')
storage_data_collection.insert(storage_data)
def worker():
config_data = get_system_config()
config_data_collection = utils.get_collection('systemconfigdatas')
config_data_collection.insert(config_data)
def get_collection_view(request):
ret = utils.get_collection(request)
return public.success_result_http(ret)
def worker():
memory_data = get_system_memory()
memory_data_collection = utils.get_collection('systemmemorydatas')
memory_data_collection.insert(memory_data)
def test_map_reduce(self, inline=False):
mapfunc = """
function map() {
for(i=0; i<this.n; ++i) {
emit(this._id, this.m)
}
}
"""
reducefunc = """
function reduce(key, values) {
var res = 0
values.forEach(function(x) { res += x})
return res
}
"""
if inline:
map_reduce = MapReduceModel.objects.inline_map_reduce
else:
map_reduce = partial(MapReduceModel.objects.map_reduce,
out='m/r-out')
map_reduce = partial(map_reduce, mapfunc, reducefunc)
random_numbers = [
(3, 4),
(6, 19),
(5, 8),
(0, 20), # This instance won't be emitted by `map`.
(2, 77),
(300, 10),
]
for n, m in random_numbers:
MapReduceModel(n=n, m=m).save()
# Test mapfunc + reducefunc.
documents = map_reduce()
documents = list(documents)
self.assertEqual(len(documents), len(random_numbers) - 1)
self.assertEqual(sum(doc.value for doc in documents),
sum(n * m for n, m in random_numbers))
# Test MapReduceResult.
obj = documents[0].model.objects.get(id=documents[0].key)
self.assert_(isinstance(obj, MapReduceModel))
self.assertEqual((obj.n, obj.m), random_numbers[0])
self.assert_(obj.id)
# Collection should not have been perished.
if not inline:
result_collection = get_collection('m/r-out')
self.assertEqual(result_collection.count(),
len(random_numbers) - 1)
# Test drop_collection.
map_reduce(drop_collection=True).next()
self.assertEqual(get_collection('m/r-out').count(), 0)
# Test arbitrary kwargs.
documents = list(map_reduce(limit=3))
self.assertEqual(len(documents), 3)
self.assertEqual(sum(doc.value for doc in documents),
sum(n * m for n, m in random_numbers[:3]))
# Test with .filter(...).
qs = MapReduceModel.objects.filter(n__lt=300).filter(~Q(m__in=[4]))
if inline:
documents = qs.inline_map_reduce(mapfunc, reducefunc)
else:
documents = list(qs.map_reduce(mapfunc,
reducefunc, out='m/r-out'))
self.assertEqual(len(documents), len(random_numbers) - 2 - 1)
self.assertEqual(sum(doc.value for doc in documents),
sum(n * m for n, m in random_numbers[1:-1]))
import utils
import csv
def create_feature_dict(names, values):
output = {}
for x in range(2, len(values)):
output[names[x]] = float(values[x])
return output
collection = utils.get_collection()
f = open('data/danfeatures.mar102011.csv', 'rb')
reader = csv.reader(f, delimiter=',')
is_header = True
headers = []
for row in reader:
if is_header:
headers = row
is_header = False
continue
doc = utils.find_doc(int(row[0]), int(row[1]))
if doc is not None:
features = create_feature_dict(headers, row)
gender = 'female'
if int(row[0]) == doc['male_id']:
gender = 'male'
key = 'lexical_features.' + gender
collection.update({'_id':doc['_id']}, {'$set': {key: features}}, False, True)
