def lose_it_upload(request):
session = Session()
# TODO: duplicate detection
input_file = request.POST['file'].file
reader = LoseItDataReader(input_file)
existing_for_date = {}
ignored = []
for entry in reader:
existing_food = session.query(Food).filter_by(name=entry.name).all()
food = None
if len(existing_food) == 0:
food = Food(entry.name)
session.add(food)
else:
food = existing_food[0]
if not entry.date in existing_for_date:
existing_entries = session.query(FoodEntry).filter_by(date=entry.date).all()
existing_for_date[entry.date] = existing_entries
if existing_for_date[entry.date]:
ignored.append(entry)
else:
new_entry = FoodEntry(food, entry.calories, entry.date)
session.add(new_entry)
session.commit()
if ignored:
return {'title': 'Existing Data Not Imported', 'ignored': ignored}
else:
return HTTPFound('/food_entry/lose_it_upload_form')
def food_edit_food_tags(request):
food_id = request.matchdict['id']
tag_ids = map(int, request.params.getall('tag_id'))
session = Session()
food = session.query(Food).filter_by(id=food_id).first()
already_tagged = []
to_remove = []
for food_tag in food.food_tags:
if not food_tag.id in tag_ids:
to_remove.append(food_tag)
else:
already_tagged.append(food_tag.id)
for tag in to_remove:
food.food_tags.remove(tag)
to_add = session.query(FoodTag).filter(FoodTag.id.in_(set(tag_ids)-set(already_tagged))).all()
food.food_tags.extend(to_add)
session.commit()
session = Session()
food = session.query(Food).filter_by(id=food_id).first()
session.close()
if request.is_xhr:
return {'request': request, 'food': food}
else:
return HTTPFound('/food/list')
def add_job(self, valid_datetime, job_type, details):
session = Session()
new_job = Job(timestamp_when_valid=valid_datetime,
job_type=job_type,
details=details)
session.add(new_job)
session.commit()
session.close()
def food_tag_add(request):
name = request.params['name']
session = Session()
new_tag = FoodTag(name)
session.add(new_tag)
session.commit()
return HTTPFound('/food_tag/list')
def init_result():
session = Session()
entry = Session(Result).filter(Result.id == 1).one_or_none()
# 如数据不存在，就新增一条为1的空数据
if not entry:
session.add(Result(modules="", total_time="", data="", dev=""))
session.commit()
else:
pass
session.close()
def commit_entry(self, staged_entry):
session = Session()
indicator_values = {}
for indicator in self.indicators_metadata:
value_location = self.location_engine.convert_postcode(
staged_entry.postcode,
self.indicators_metadata[indicator]['resolution'])
previous_value_entry = session.query(IndicatorValue)\
.filter(IndicatorValue.indicator == indicator,
IndicatorValue.location == value_location,
IndicatorValue.date < staged_entry.date)\
.order_by(IndicatorValue.date.desc())\
.first()
following_value_entry = session.query(IndicatorValue)\
.filter(IndicatorValue.indicator == indicator,
IndicatorValue.location == value_location,
IndicatorValue.date > staged_entry.date)\
.order_by(IndicatorValue.date)\
.first()
if previous_value_entry is None and following_value_entry is None:
value = None
indicator_date = None
elif following_value_entry is None \
or abs((previous_value_entry.date - staged_entry.date).days) \
< abs((following_value_entry.date - staged_entry.date).days):
value = previous_value_entry.value
indicator_date = previous_value_entry.date
else:
value = following_value_entry.value
indicator_date = following_value_entry.date
# Check if value falls within frequency range
if indicator_date is not None and (abs(staged_entry.date - indicator_date)).days\
> (FREQUENCY_DAY_COUNTS[self.indicators_metadata[indicator]['frequency']] / 2):
value = None
indicator_values[indicator] = value
new_entry = TargetEntry(
entry_id=staged_entry.entry_id,
sale_id=staged_entry.sale_id,
date=staged_entry.date,
value=staged_entry.value,
PDD_type=staged_entry.PDD_type,
postcode=staged_entry.postcode,
town_or_city=staged_entry.town_or_city,
district=staged_entry.district,
county=staged_entry.county,
new_property_flag=staged_entry.new_property_flag,
property_type=staged_entry.property_type,
tenure_type=staged_entry.tenure_type)
for indicator in indicator_values:
setattr(new_entry, indicator, indicator_values[indicator])
session.add(new_entry)
session.commit()
session.close()
def set_result(data):
session = Session()
entry = Session(Result).filter(Result.id == data["id"]).one_or_none()
if entry:
entry.modules = data["modules"]
entry.total_time = data["total_time"]
entry.data = data["data"]
entry.dev = data["dev"]
session.commit()
else:
print("实体类不存在")
session.close()
def add_new_model(self, settings):
new_model_name = settings['name']
new_model = Model(settings)
self.models[new_model_name] = new_model
self.save_model(new_model_name)
new_model_record = ModelEntry(name=settings['name'],
type=settings['type'],
dataset=settings['dataset'],
state='untrained')
session = Session()
session.add(new_model_record)
session.commit()
session.close()
def main():
engine = create_engine('postgresql://[email protected]/my_metrics')
Base.metadata.create_all(engine)
Session.configure(bind=engine)
session = Session()
food_entries = session.query(FoodEntry).order_by(FoodEntry.date)
for entry in food_entries:
food_name = entry.name
existing_food = session.query(Food).filter_by(name=food_name).all()
if len(existing_food) == 0:
new_food = Food(food_name)
session.add(new_food)
session.commit()
def pull_land_registry(self):
session = Session()
data = request.urlopen(LAND_REGISTRY_URL).read()
data = str(data, 'utf-8')
data_frame = pandas.read_csv(StringIO(data),
header=None,
names=LAND_REGISTRY_DATA_HEADERS)
# Only include entries with PPD type A
# data_frame = [data_frame.PDD_type == 'A']
# Convert date strings to date objects
data_frame['date'] = pandas.to_datetime(
data_frame['date'], format=LAND_REGISTRY_TIMESTAMP_FORMAT)
# Reorder columns
data_frame = data_frame[STAGED_ENTRY_HEADERS]
# Convert old or new character value to boolean
data_frame['new_property_flag'] = data_frame['new_property_flag'].map(
dict(Y=True, N=False))
current_highest_id = -1
latest_entry = session.query(StagedEntry).order_by(
desc(StagedEntry.entry_id)).first()
if latest_entry is not None:
current_highest_id = latest_entry.id
batch_start_id = current_highest_id + 1
batch_end_id = batch_start_id + len(data_frame)
# Add id column
data_frame.insert(0, 'entry_id', range(batch_start_id, batch_end_id))
data_frame.to_sql('staged_entries',
con=self.database_engine,
if_exists='append',
index=False)
# Process deletion entries
deletion_entries = session.query(StagedEntry).filter(
StagedEntry.record_type == 'D')
for deletion_entry in deletion_entries:
session.query(TargetEntry).filter(
TargetEntry.sale_id == deletion_entry.sale_id).delete()
deletion_entry.delete()
# Get update entries
update_entries = session.query(StagedEntry).filter(
StagedEntry.record_type == 'C')
for update_entry in update_entries:
existing_entry = session.query(TargetEntry).filter(
TargetEntry.sale_id == update_entry.sale_id).one()
if existing_entry is not None:
update_entry_from_land_registry(update_entry, existing_entry)
update_entry.delete()
session.commit()
session.close()
return str(batch_end_id)
def delete_model(self, model_name):
session = Session()
model_record = session.query(ModelEntry).filter(
ModelEntry.name == model_name)
model_record.delete()
session.commit()
del self.models[model_name]
os.remove(model_name)
# Update max inputs value
self.max_inputs = 0
for model_name in self.get_trained_model_names():
model_input_count = len(self.get_model_inputs(model_name))
if model_input_count > self.max_inputs:
self.max_inputs = model_input_count
session.close()
def main():
engine = create_engine('postgresql://[email protected]/my_metrics')
Base.metadata.create_all(engine)
Session.configure(bind=engine)
session = Session()
foods = session.query(Food)
foods_by_name = {}
for food in foods:
foods_by_name[food.name] = food
food_entries = session.query(FoodEntry).order_by(FoodEntry.date)
for entry in food_entries:
food = foods_by_name[entry.name]
entry.food = food
session.commit()
def food_entry_add(request):
name = request.params['name']
calories = int(request.params['calories'])
day = date.today() - timedelta(int(request.params['days_ago']))
session = Session()
existing_food = session.query(Food).filter_by(name=food_name).all()
food = None
if len(existing_food) == 0:
food = Food(food_name)
session.add(food)
else:
food = existing_food[0]
new_entry = FoodEntry(food, calories, day)
session.add(new_entry)
session.commit()
return HTTPFound('/food_entry/add_form')
def update_entries_from_source(self, source_entry_date, frequency,
indicators, area_resolution):
session = Session()
frequency_radius_delta = relativedelta(
FREQUENCY_DAY_COUNTS[frequency] / 2)
lower_threshold_date = source_entry_date - frequency_radius_delta
upper_threshold_date = source_entry_date + frequency_radius_delta
# noinspection PyComparisonWithNone
entries_to_update = session.query(TargetEntry).filter(
getattr(TargetEntry, indicators[0]) == None,
TargetEntry.date >= lower_threshold_date,
TargetEntry.date <= upper_threshold_date)
for entry in entries_to_update:
location = self.location_engine.convert_postcode(
entry.postcode, area_resolution)
for indicator in indicators:
value = session.query(IndicatorValue).filter(
IndicatorValue == source_entry_date,
IndicatorValue.location == location)
setattr(entry, indicator, value)
session.commit()
session.close()
def train_model(self, model_name):
session = Session()
model_record = session.query(ModelEntry).filter(ModelEntry.name == model_name).one()
model_record.state = 'training'
session.commit()
parent_models = self.model_manager.models[model_name].input_models
for parent_model in parent_models:
# Train any untrained parent models
if session.query(ModelEntry).filter(ModelEntry.name == parent_model, ModelEntry.state == 'untrained')\
is not None:
self.train_model(parent_model)
# Wait for any parent models that are still in training, in cases where another process started the training
while session.query(ModelEntry).filter(ModelEntry.name == parent_model,
ModelEntry.state == 'training').one_or_none()\
is not None:
time.sleep(30)
model = self.model_manager.models[model_name]
dataset_name = model.dataset
entry_count = model.training_entry_count
if dataset_name == 'core_dataset':
dataframe = pandas.read_sql(session.query(Base.metadata.tables['core_dataset']).order_by(func.rand()).limit(entry_count).statement,
self.database_engine)
else:
dataframe = pandas.read_csv(DEFAULT_DATA_PATH, sep='\s+', names=DEFAULT_DATA_HEADERS)
if entry_count > len(dataframe):
entry_count = len(dataframe)
dataframe = dataframe.sample(entry_count)
for parent_model in parent_models:
self.recursive_process(parent_model, dataframe)
model.train(dataframe)
self.model_manager.save_model(model_name)
model_record.state = 'trained'
session.commit()
# Update the model manager max input count - done here to happen at the end of training
self.model_manager.update_max_inputs(len(self.model_manager.get_model_inputs(model_name)))
session.close()
qset291= session.query(func.count(Emp.ename)).filter(Emp.job=='董事长').filter(Emp.sal>15000).first()
qset292= session.query(func.count(Emp.ename)).filter(Emp.job=='经理').filter(Emp.sal>15000).first()
qset293= session.query(func.count(Emp.ename)).filter(Emp.job=='分析师').filter(Emp.sal>15000).first()
qset294= session.query(func.count(Emp.ename)).filter(Emp.job=='销售员').filter(Emp.sal>15000).first()
qset295= session.query(func.count(Emp.ename)).filter(Emp.job=='文员').filter(Emp.sal>15000).first()
print('\033[35;1m工资大于15000的董事长有%s位\033[0m' % qset291)
print('\033[35;1m工资大于15000的经理有%s位\033[0m' % qset292)
print('\033[35;1m工资大于15000的分析师有%s位\033[0m' % qset293)
print('\033[35;1m工资大于15000的销售员有%s位\033[0m' % qset294)
print('\033[35;1m工资大于15000的文员有%s位\033[0m' % qset295)
print(38*"*")
# #第30题
# print(38*"*")
# print('\033[31;1m第二十九题:统计工资大于 15000 的每个工作岗位人数,并且该工作岗位的人数大于等于 3\033[0m')
# qset301= session.query(Emp).filter(func.sum(Emp.sal,Emp.COMM)>15000)
# # qset302= session.query(func.count(Emp.ename)).filter(Emp.job=='经理').filter(Emp.sal>15000).first()
# # qset303= session.query(func.count(Emp.ename)).filter(Emp.job=='分析师').filter(Emp.sal>15000).first()
# # qset304= session.query(func.count(Emp.ename)).filter(Emp.job=='销售员').filter(Emp.sal>15000).first()
# # qset305= session.query(func.count(Emp.ename)).filter(Emp.job=='文员').filter(Emp.sal>15000).first()
# print(qset301)
# for data in qset301:
# print('%s' % (data.ename))
# # print(data)
# 确认
session.commit()
# 关闭
session.close()