def show_user():
model.connect()
user_id = request.args.get("id")
user = model.get_user_by_id(user_id)
# user_profile = model.user_name.get_posts()
return render_template("user_profile.html", user= user)
def main():
# DB stuff
connect()
init()
globalized.init()
# TCP stuff
listener = listen()
# REST stuff
launch()
def start():
u = Updater( model.connect() )
u.next([
create_table_link_projection,
create_table_response_cache,
])
u.execute()
def query_CAISONetImports_hrly_Series():
"""specifically gets import data"""
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
s = model.connect()
imports_obj = s.execute(
'SELECT time_start, sum(mw_imports) FROM "HistoricCAISONetImports" where time_start between \'2014-01-01 07:00:00.000000\' and \'2015-01-01 00:00:00.000000\' GROUP BY time_start '
)
imports_entry = imports_obj.fetchall()
imports_df = DataFrame(imports_entry)
imports_df.columns = ['time_start', 'mw_demand']
dict_with_datetime_keys = {}
for idx, row in enumerate(imports_df.values):
time_start = row[0]
# check date, since logs show we're missing a few
if check_if_bad_date(time_start) != True:
# turn dict into a series. will auto-index on dict keys
mw_imports = row[1]
dict_with_datetime_keys[time_start] = mw_imports
return Series(dict_with_datetime_keys)
def query_CAISODemand_hrly_Series():
"""specifically gets demand data"""
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
s = model.connect()
demand_obj = s.execute(
'SELECT time_start, mw_demand FROM "HistoricCAISODemands" WHERE caiso_tac=\'CA ISO-TAC\' and time_start between \'2014-01-01 07:00:00.000000\' and \'2015-01-01 00:00:00.000000\' '
)
demand_entry = demand_obj.fetchall()
demand_df = DataFrame(demand_entry)
demand_df.columns = ['time_start', 'mw_demand']
dict_with_datetime_keys = {}
for idx, row in enumerate(demand_df.values):
time_start = row[0]
# check date, since logs show we're missing a few
if check_if_bad_date(time_start) != True:
# turn dict into a series. will auto-index on dict keys
mw_demand = row[1]
dict_with_datetime_keys[time_start] = mw_demand
return Series(dict_with_datetime_keys)
def load_demographics():
with open('seed_data/SlimmerData_Consolidated.csv', 'rU') as csvfile:
reader = csv.reader(csvfile, dialect='excel')
for row in reader:
print "row:", row
# row = troubleshooting. If issue, see where.
try:
session = model.connect()
demo_obj = model.Demographic()
demo_obj.zipcode = row[0]
demo_obj.popdensity = float(row[1])
demo_obj.pctemployed = float(row[2])
demo_obj.pctmnf = float(row[3])
demo_obj.pctlogistics = float(row[4])
demo_obj.pctit = float(row[5])
demo_obj.pctprof = float(row[6])
demo_obj.hhincq10 = int(row[7])
demo_obj.hhincq30 = int(row[8])
demo_obj.hhincq50 = int(row[9])
demo_obj.hhincq70 = int(row[10])
demo_obj.hhincq90 = int(row[11])
demo_obj.hhincq95 = int(row[12])
demo_obj.pctheatelec = float(row[13])
session.add(demo_obj)
session.commit()
except:
print "Error for row data:", row
f = open('log_file.txt', 'a')
f.write("\nError. Failure for row:" + str(row))
f.close
def insert_row_db(date, hr, adict):
"""imports model, and inserts web scraped data into the db"""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
session = model.connect()
for k,v in adict.items():
fuel_obj = model.HistoricCAISOProdByFuel()
fuel_obj.date = datetime.strptime(date,'%Y%m%d')
fuel_obj.time_start = hr
fuel_obj.fuel_type = k
fuel_obj.mw_gen = v
session.add(fuel_obj)
print fuel_obj
session.commit()
def query_CAISOProdByFuel_Series(ea_fuel):
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
s = model.connect()
ea_fuel_obj = s.execute('SELECT time_start, fuel_type, mw_gen FROM "HistoricCAISOProdByFuels" WHERE fuel_type=\'%s\' and time_start between \'2014-01-01 07:00:00.000000\' and \'2015-01-01 00:00:00.000000\' ' % ea_fuel)
ea_fuel_entry = ea_fuel_obj.fetchall()
ea_fuel_df = DataFrame(ea_fuel_entry)
ea_fuel_df.columns = ['time_start', 'fuel_type', 'mw_gen']
dict_with_datetime_keys = { }
for idx,row in enumerate(ea_fuel_df.values):
time_start = row[0]
# check date, since logs show we're missing a few
if check_if_bad_date(time_start)!=True:
mw_gen = row[2]
dict_with_datetime_keys[time_start] = mw_gen
# turn dict into a series. will auto-index on dict keys
return Series(dict_with_datetime_keys)
def retrieve_from_db_usa():
"""imports model, pulls mwh production data from db, and places into pandas df.
Also pulls state for each plant_name, and places into dict."""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
s = model.connect()
# retrive DECEMBER production data, for all turbines at all power plants in California
USA_gen_dec13_obj = s.execute('SELECT plant_name, state, fuel_type, dec_mwh_gen FROM "ProdGensDec2013" ')
USA_gen_dec13_data = USA_gen_dec13_obj.fetchall()
df_dec2013 = DataFrame(USA_gen_dec13_data)
df_dec2013.columns = ['plant_name', 'state', 'fuel_type', 'dec_mwh_gen']
# retrive JAN-NOV 2014 production data, for all turbines at all power plants in USA
USA_gen_2014_obj = s.execute('SELECT plant_name, state, fuel_type, jan_mwh_gen, feb_mwh_gen, mar_mwh_gen, apr_mwh_gen, may_mwh_gen, jun_mwh_gen, jul_mwh_gen, aug_mwh_gen, sep_mwh_gen, oct_mwh_gen, nov_mwh_gen FROM "ProdGens" ')
USA_gen_2014_data = USA_gen_2014_obj.fetchall()
df_2014 = DataFrame(USA_gen_2014_data)
df_2014.columns = ['plant_name', 'state', 'fuel_type', 'jan_mwh_gen', 'feb_mwh_gen', 'mar_mwh_gen', 'apr_mwh_gen', 'may_mwh_gen', 'jun_mwh_gen', 'jul_mwh_gen', 'aug_mwh_gen', 'sep_mwh_gen', 'oct_mwh_gen', 'nov_mwh_gen']
return df_dec2013, df_2014
def insert_row_imports_db(date, list_of_dicts):
"""Takes in a list of dicts, with each list item equal to a timepoint. inserts into HistoricCAISODemand"""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
session = model.connect()
from datetime import datetime
for timept_dict in list_of_dicts:
imports_obj = model.HistoricCAISONetImport()
opr_date = timept_dict['opr_date']
imports_obj.date = datetime.strptime(opr_date, '%Y-%m-%d')
imports_obj.time_start = timept_dict['time_start']
imports_obj.time_end = timept_dict['time_end']
imports_obj.resource = (timept_dict['resource']).strip()
imports_obj.mw_imports = float(timept_dict['mw_imports'])
session.add(imports_obj)
session.commit()
def query_CAISODemand_hrly_Series():
"""specifically gets demand data"""
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
s = model.connect()
demand_obj = s.execute('SELECT time_start, mw_demand FROM "HistoricCAISODemands" WHERE caiso_tac=\'CA ISO-TAC\' and time_start between \'2014-01-01 07:00:00.000000\' and \'2015-01-01 00:00:00.000000\' ')
demand_entry = demand_obj.fetchall()
demand_df = DataFrame(demand_entry)
demand_df.columns = ['time_start','mw_demand']
dict_with_datetime_keys = { }
for idx,row in enumerate(demand_df.values):
time_start = row[0]
# check date, since logs show we're missing a few
if check_if_bad_date(time_start)!=True:
# turn dict into a series. will auto-index on dict keys
mw_demand = row[1]
dict_with_datetime_keys[time_start] = mw_demand
return Series(dict_with_datetime_keys)
def query_CAISONetImports_hrly_Series():
"""specifically gets import data"""
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
s = model.connect()
imports_obj = s.execute('SELECT time_start, sum(mw_imports) FROM "HistoricCAISONetImports" where time_start between \'2014-01-01 07:00:00.000000\' and \'2015-01-01 00:00:00.000000\' GROUP BY time_start ')
imports_entry = imports_obj.fetchall()
imports_df = DataFrame(imports_entry)
imports_df.columns = ['time_start','mw_demand']
dict_with_datetime_keys = { }
for idx,row in enumerate(imports_df.values):
time_start = row[0]
# check date, since logs show we're missing a few
if check_if_bad_date(time_start)!=True:
# turn dict into a series. will auto-index on dict keys
mw_imports = row[1]
dict_with_datetime_keys[time_start] = mw_imports
return Series(dict_with_datetime_keys)
def retrieve_from_db_usa():
"""imports model, pulls mwh production data from db, and places into pandas df.
Also pulls state for each plant_name, and places into dict."""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
s = model.connect()
# retrive DECEMBER production data, for all turbines at all power plants in California
USA_gen_dec13_obj = s.execute(
'SELECT plant_name, state, fuel_type, dec_mwh_gen FROM "ProdGensDec2013" '
)
USA_gen_dec13_data = USA_gen_dec13_obj.fetchall()
df_dec2013 = DataFrame(USA_gen_dec13_data)
df_dec2013.columns = ['plant_name', 'state', 'fuel_type', 'dec_mwh_gen']
# retrive JAN-NOV 2014 production data, for all turbines at all power plants in USA
USA_gen_2014_obj = s.execute(
'SELECT plant_name, state, fuel_type, jan_mwh_gen, feb_mwh_gen, mar_mwh_gen, apr_mwh_gen, may_mwh_gen, jun_mwh_gen, jul_mwh_gen, aug_mwh_gen, sep_mwh_gen, oct_mwh_gen, nov_mwh_gen FROM "ProdGens" '
)
USA_gen_2014_data = USA_gen_2014_obj.fetchall()
df_2014 = DataFrame(USA_gen_2014_data)
df_2014.columns = [
'plant_name', 'state', 'fuel_type', 'jan_mwh_gen', 'feb_mwh_gen',
'mar_mwh_gen', 'apr_mwh_gen', 'may_mwh_gen', 'jun_mwh_gen',
'jul_mwh_gen', 'aug_mwh_gen', 'sep_mwh_gen', 'oct_mwh_gen',
'nov_mwh_gen'
]
return df_dec2013, df_2014
def insert_row_imports_db(date, list_of_dicts):
"""Takes in a list of dicts, with each list item equal to a timepoint. inserts into HistoricCAISODemand"""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
session = model.connect()
from datetime import datetime
for timept_dict in list_of_dicts:
imports_obj = model.HistoricCAISONetImport()
opr_date = timept_dict['opr_date']
imports_obj.date = datetime.strptime(opr_date,'%Y-%m-%d')
imports_obj.time_start = timept_dict['time_start']
imports_obj.time_end = timept_dict['time_end']
imports_obj.resource = (timept_dict['resource']).strip()
imports_obj.mw_imports = float(timept_dict['mw_imports'])
session.add(imports_obj)
session.commit()
def query_CAISOProdByFuel_Series(ea_fuel):
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
s = model.connect()
ea_fuel_obj = s.execute(
'SELECT time_start, fuel_type, mw_gen FROM "HistoricCAISOProdByFuels" WHERE fuel_type=\'%s\' and time_start between \'2014-01-01 07:00:00.000000\' and \'2015-01-01 00:00:00.000000\' '
% ea_fuel)
ea_fuel_entry = ea_fuel_obj.fetchall()
ea_fuel_df = DataFrame(ea_fuel_entry)
ea_fuel_df.columns = ['time_start', 'fuel_type', 'mw_gen']
dict_with_datetime_keys = {}
for idx, row in enumerate(ea_fuel_df.values):
time_start = row[0]
# check date, since logs show we're missing a few
if check_if_bad_date(time_start) != True:
mw_gen = row[2]
dict_with_datetime_keys[time_start] = mw_gen
# turn dict into a series. will auto-index on dict keys
return Series(dict_with_datetime_keys)
def load_geographics():
with open('seed_data/zip_code_database.csv', 'rb') as csvfile:
reader = csv.reader(csvfile, dialect='excel')
for row in reader:
print("row:", row)
# row = troubleshooting. If issue, see where.
try:
session = model.connect()
geo_obj = model.Geographic()
geo_obj.zipcode = row[0]
geo_obj.type_addy = row[1]
geo_obj.primary_city = row[2]
geo_obj.acceptable_cities = row[3]
geo_obj.unacceptable_cities = row[4]
geo_obj.state = row[5]
geo_obj.county = row[6]
geo_obj.timezone = row[7]
geo_obj.area_codes = row[8]
geo_obj.latitude = float(row[9])
geo_obj.longitude = float(row[10])
geo_obj.world_region = row[11]
geo_obj.country = row[12]
geo_obj.decommissioned = row[13]
geo_obj.estimated_population = int(row[14])
geo_obj.notes = row[15]
session.add(geo_obj)
session.commit()
except:
print "Error for row data:", row
f = open('log_file.txt', 'a')
f.write("\nError. failure for row:" + str(row))
f.close
def is_stressful(data_point_time, bpm):
"""This takes a datetime object as its parameter and determines if
data associated with it indicates stress by comparing to filtered datapoints from the preceeding week.
The caller should expect a Boolean to be returned."""
# Determine the startbound for the query:
d = timedelta(days=-7)
sb = data_point_time + d
dbsession = connect()
dataset = dbsession.query(HRDataPoint).filter(
and_(HRDataPoint.start_datetime > sb,
HRDataPoint.start_datetime < data_point_time)).all()
bpm_list = []
for each in dataset:
bpm_list.append(each.bpm)
mean_of_dataset = numpy.mean(bpm_list)
if bpm > (mean_of_dataset + 9):
return True
return False
def load_geographics():
with open('seed_data/zip_code_database.csv', 'rb') as csvfile:
reader = csv.reader(csvfile, dialect='excel')
for row in reader:
print ("row:", row)
# row = troubleshooting. If issue, see where.
try:
session=model.connect()
geo_obj = model.Geographic()
geo_obj.zipcode = row[0]
geo_obj.type_addy = row[1]
geo_obj.primary_city = row[2]
geo_obj.acceptable_cities = row[3]
geo_obj.unacceptable_cities = row[4]
geo_obj.state = row[5]
geo_obj.county = row[6]
geo_obj.timezone = row[7]
geo_obj.area_codes = row[8]
geo_obj.latitude = float(row[9])
geo_obj.longitude = float(row[10])
geo_obj.world_region = row[11]
geo_obj.country = row[12]
geo_obj.decommissioned = row[13]
geo_obj.estimated_population = int(row[14])
geo_obj.notes = row[15]
session.add(geo_obj)
session.commit()
except:
print "Error for row data:", row
f = open('log_file.txt','a')
f.write("\nError. failure for row:"+str(row))
f.close
def load_demographics():
with open('seed_data/SlimmerData_Consolidated.csv', 'rU') as csvfile:
reader = csv.reader(csvfile, dialect='excel')
for row in reader:
print "row:", row
# row = troubleshooting. If issue, see where.
try:
session=model.connect()
demo_obj = model.Demographic()
demo_obj.zipcode = row[0]
demo_obj.popdensity = float(row[1])
demo_obj.pctemployed = float(row[2])
demo_obj.pctmnf = float(row[3])
demo_obj.pctlogistics = float(row[4])
demo_obj.pctit = float(row[5])
demo_obj.pctprof = float(row[6])
demo_obj.hhincq10 = int(row[7])
demo_obj.hhincq30 = int(row[8])
demo_obj.hhincq50 = int(row[9])
demo_obj.hhincq70 = int(row[10])
demo_obj.hhincq90 = int(row[11])
demo_obj.hhincq95 = int(row[12])
demo_obj.pctheatelec = float(row[13])
session.add(demo_obj)
session.commit()
except:
print "Error for row data:", row
f = open('log_file.txt','a')
f.write("\nError. Failure for row:"+str(row))
f.close
def write_all_user_predictions_to_sql(): # user_index_to_id, movie_id_to_index = load_json_indexes() # user_id_to_index = load_user_id_to_index_index() session = model.connect() existing_ratings = get_existing_ratings_from_file() for user_index in xrange(70000): #fixme write_one_user_prediction_to_sql(user_index, session, existing_ratings)
def setServiceParent(self, parent):
log.msg("Starting DB Status handler")
self.orig_parent = parent
base.StatusReceiverMultiService.setServiceParent(self, parent)
# Skip doing anything if we're just doing a checkconfig. We don't want to
# potentially change the state of the database on a checkconfig.
if isinstance(parent, checkconfig.ConfigLoader):
return
# Keep a local reference to the session maker On a buildbot reconfig,
# model.Session will be reset to None, and we might get
# stepStarted/stepFinished notifications while the reconfig is
# happening.
try:
self.Session = model.connect(self.dburl, pool_recycle=60)
# Let our subscribers know about the database connection
# This gives them the opportunity to set up their own tables, etc.
for sub in self.subscribers:
if hasattr(sub, 'databaseConnected'):
try:
sub.databaseConnected(model.metadata.bind)
except:
log.msg("DBERROR: Couldn't notify subscriber %s of database connection" % sub)
log.err()
self.setup()
except:
if sys.exc_info()[0] is not sqlalchemy.exc.OperationalError:
log.msg("DBERROR: Couldn't connect to database")
log.err()
self.lostConnection()
def __init__(self, src_path, output, ext_pool='.pdf', ignore_hidden=True):
self.db = model.connect()
if not os.path.exists(media_path):
os.makedirs(media_path)
self.ext_pool = ext_pool
self.ignore_hidden = ignore_hidden
self.src_path = src_path
self.output = output
self.flag = True
def main(session):
# You'll call each of the load_* functions with the session as an argument
# load_users(session) # comment this out when seed users have been loaded
# load_movies(session) # comment this out when seed movies have been loaded
# load_ratings(session) # comment this out when seed ratings have been loaded
if __name__ == "__main__":
s = model.connect()
main(s)
def main():
# You'll call each of the load_* functions with the session as an argument
session = model.connect()
load_user(session)
print "user loaded"
load_item(session)
print "movies loaded"
load_data(session)
print "ratings loaded"
def main(session):
# You'll call each of the load_* functions with the session as an argument
session = model.connect()
# load_users(session)
# print "loaded users"
load_movies(session)
print "loaded movies"
load_ratings(session)
print "loaded ratings"
def __init__(self, src_path, output, ext_pool='.pdf', ignore_hidden=True):
self.db = model.connect()
if not os.path.exists(media_path):
os.makedirs(media_path)
self.ext_pool = ext_pool
self.ignore_hidden = ignore_hidden
self.src_path = src_path
self.output = output
self.flag = True
def retrieve_from_db(state_code):
"""imports model, pulls mwh production data from db, and places into pandas df.
Also pulls county for each plant_name, and places into dict."""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
s = model.connect()
# retrive DECEMBER production data, for all turbines at all power plants in California
CA_gen_dec13_obj = s.execute(
'SELECT plant_name, state, fuel_type, dec_mwh_gen FROM "ProdGensDec2013" WHERE state=\'%s\' '
% state_code)
CA_gen_dec13_data = CA_gen_dec13_obj.fetchall()
df_dec2013 = DataFrame(CA_gen_dec13_data)
df_dec2013.columns = ['plant_name', 'state', 'fuel_type', 'dec_mwh_gen']
# retrive JAN-NOV 2014 production data, for all turbines at all power plants in California
CA_gen_2014_obj = s.execute(
'SELECT plant_name, state, fuel_type, jan_mwh_gen, feb_mwh_gen, mar_mwh_gen, apr_mwh_gen, may_mwh_gen, jun_mwh_gen, jul_mwh_gen, aug_mwh_gen, sep_mwh_gen, oct_mwh_gen, nov_mwh_gen FROM "ProdGens" WHERE state=\'%s\' '
% state_code)
CA_gen_2014_data = CA_gen_2014_obj.fetchall()
df_2014 = DataFrame(CA_gen_2014_data)
df_2014.columns = [
'plant_name', 'state', 'fuel_type', 'jan_mwh_gen', 'feb_mwh_gen',
'mar_mwh_gen', 'apr_mwh_gen', 'may_mwh_gen', 'jun_mwh_gen',
'jul_mwh_gen', 'aug_mwh_gen', 'sep_mwh_gen', 'oct_mwh_gen',
'nov_mwh_gen'
]
# retrieve county name, assigned to each turbine at each plant in California
CA_counties_obj = s.execute(
'SELECT plant_name, county FROM "StatsGens" WHERE state=\'%s\' GROUP BY plant_name, county'
% state_code)
CA_plant_counties = CA_counties_obj.fetchall()
df_counties = DataFrame(CA_plant_counties)
df_counties.columns = ['plant_name', 'county']
# now convert into dict, so caan easily add county to other df.
dict_counties = {}
for idx, row in enumerate(df_counties.values):
plant_name, county = row
# clean the county name
county = unicodedata.normalize('NFKD',
county).encode('ascii', 'ignore')
county = county.lower().title()
county = county.replace(" County", "")
dict_counties[plant_name] = county
return df_dec2013, df_2014, dict_counties
def main(session):
# when running for real, remove echo = true
# You'll call each of the load_* functions with the session as an argument
# load_movies(session, 'seed_data/u.item')
#load_ratings(session, 'seed_data/u.data')
# load_users(session,'seed_data/u.user')
if __name__ == "__main__":
s= model.connect()
main(s)
def main(session):
# if dataset hasn't already been imported into DB, call the following:
# load_users(session)
# load_movies(session)
# load_ratings(session)
if __name__ == "__main__":
s = model.connect()
main(s)
def display_provider():
"""Given a unique identifier for a doctor, display a page with the doctor's
contact information"""
npi = request.args.get("id")
session = model.connect()
provider = session.query(model.Provider).get(npi)
return render_template('provider_page.html', provider = provider)
def load_users(session):
# use u.user
with open ('seed_data/u.user', 'rb') as csvfile:
reader = csv.reader(csvfile)
session = model.connect()
for row in reader:
row = row.pop().split("|")
user = model.User (None, None, row[1], row[4])
user.id = row[0]
session.add(user)
session.commit()
def query_EIA_fuel_monthly_Series(ea_fuel):
"""specifically gets EIA data from ProdGen"""
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
s = model.connect()
fuel_codes = {
'coal':
"('BIT','ANT','LIG','SUB','RC','WC','CBL','SC', 'SGC')",
'gas':
"('NG','BFG','OG','PG','OTH')",
'nuclear':
'NUC',
'solar':
'SUN',
'hydro':
'WAT',
'wind':
'WND',
'other':
"('DFO','RFO','JF','KER','WO','PC','SG','AB','MSW','OBS','WDS','OBL','SLW','BLQ','WDL','OBG','GEO','LFG','TDF','MSB','MSN','WH','PUR','SGP','MWH')"
}
if (ea_fuel == 'nuclear') or (ea_fuel == 'solar') or (
ea_fuel == 'wind') or (ea_fuel == 'hydro'):
code = fuel_codes[ea_fuel]
mo_fuel_obj = s.execute(
'SELECT sum(jan_mwh_gen), sum(feb_mwh_gen), sum(mar_mwh_gen), sum(apr_mwh_gen), sum(may_mwh_gen), sum(jun_mwh_gen), sum(jul_mwh_gen), sum(aug_mwh_gen), sum(sep_mwh_gen), sum(oct_mwh_gen), sum(nov_mwh_gen) FROM "ProdGens" WHERE fuel_type=\'%s\' and state=\'CA\' '
% code)
if (ea_fuel == 'coal') or (ea_fuel == 'gas') or (ea_fuel == 'other'):
list_of_codes = fuel_codes[ea_fuel]
mo_fuel_obj = s.execute(
'SELECT sum(jan_mwh_gen), sum(feb_mwh_gen), sum(mar_mwh_gen), sum(apr_mwh_gen), sum(may_mwh_gen), sum(jun_mwh_gen), sum(jul_mwh_gen), sum(aug_mwh_gen), sum(sep_mwh_gen), sum(oct_mwh_gen), sum(nov_mwh_gen) FROM "ProdGens" WHERE state=\'CA\' and fuel_type IN %s '
% list_of_codes)
mo_fuel_entry = mo_fuel_obj.fetchall()
# turn into dict
list_of_months = [
'jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct',
'nov'
]
mo_fuel_entry_dict = {}
for i in range(11):
mo_fuel_entry_dict[list_of_months[i]] = mo_fuel_entry[0][i]
# can now turn dict into Series
return Series(mo_fuel_entry_dict)
def before_request():
engine, DB = model.connect()
g.db = DB()
id = session.get('id', None)
if id:
g.me = g.db.query(Person).filter_by(id = id).first()
else:
g.me = Person()
g.db.add(g.me)
g.db.commit()
session['id'] = g.me.id
def format_data_day(day_string):
"""Takes a single date as parameter and returns a dict of times during the
day as keys and boolean values.
This will take a string parameter formatted like this: '2015-24-02' """
dbsession = connect()
db_result = dbsession.query(HRDataPoint).filter_by(
day_of_point=day_string).all()
# Need to extract the time from the datetime attribute,
# so make a dict of {<time> : <boolean>} pairs:
dict_day_booleans = {}
for each_point in db_result:
dt = each_point.start_datetime
hour_of_point = dt.hour
# Create a dictionary of the data to display with a *datetime* object as the key
dict_day_booleans[hour_of_point] = [
each_point.is_stressful, each_point.bpm
]
# Reference the dict indexed by time and create the dict to return, which uses a string as key instead:
to_display = {}
dict_keys = dict_day_booleans.keys()
for a_key in dict_keys:
if a_key < 10:
to_display['9 am'] = dict_day_booleans.get(a_key)
elif a_key < 11:
to_display['10 am'] = dict_day_booleans.get(a_key)
elif a_key < 12:
to_display['11 am'] = dict_day_booleans.get(a_key)
elif a_key < 13:
to_display['noon'] = dict_day_booleans.get(a_key)
elif a_key < 14:
to_display['1 pm'] = dict_day_booleans.get(a_key)
elif a_key < 15:
to_display['2 pm'] = dict_day_booleans.get(a_key)
elif a_key < 16:
to_display['3 pm'] = dict_day_booleans.get(a_key)
elif a_key < 17:
to_display['4 pm'] = dict_day_booleans.get(a_key)
elif a_key < 18:
to_display['5 pm'] = dict_day_booleans.get(a_key)
elif a_key < 19:
to_display['6 pm'] = dict_day_booleans.get(a_key)
else:
pass
return to_display
def main(session):
#read_directions_files(session)
#read_directions_files_same_airport(session)
#load_directions(session)
#load_distance(session)
#load_cities(session)
#load_flight_data(session)
if __name__ == "__main__":
s= model.connect()
main(s)
def test_connect(self):
connexions = Counter()
Counter.ensure_0()
config = type('ConfigMock', (), {})()
# mocking a model
DummyModel = type('ModelMock', (), {})
def mocked_connect(test):
def _connect(conf):
connexions.inc()
test.assertIs(conf, config)
return _connect
model1 = DummyModel()
model1.connect = mocked_connect(self)
model2 = DummyModel()
model2.connect = mocked_connect(self)
model._models_registry = set([model1, model2])
model.connect(config)
self.assertEqual(connexions.num, 2)
def load_ratings(session):
# use u.data
with open ('seed_data/u.data', 'rb') as csvfile:
reader = csv.reader(csvfile)
session = model.connect()
for row in reader:
row = row.pop().split("\t")
rating = model.Rating(row[1], row[2], row[0])
session.add(rating)
session.commit()
pass
def result(*args, **kwargs):
with model.connect(db_path) as connection:
context = Context(db_logic=model.DBLogic(connection))
context.db_logic.initialize_db()
context.debug = debug
try:
return func(context, *args, **kwargs)
# Bottle returns all responses via Exceptions. Yuck :(
except bottle.HTTPResponse:
raise
# Format real exceptions.
except Exception as e:
if not context.debug or srvcfg.CTF_DIFFICULTY >= 3:
raise
return context.render_exception(e)
def save_to_db(data_as_string):
""" 'each' is a dictionary. 'each' will become a single DB record; this loop
parses the json and assigns its values to the datapoint object, then adds it to the SQL
session to commit at the end."""
data_dict = json.loads(data_as_string)
dbsession = model.connect()
for each in data_dict['point']:
# Create a datapoint oject
datapoint = model.HRDataPoint()
# Assign its attributes according to the dictionary contents.
datapoint.user_id = 1 # Need to hardcode this to me until multiple users/logins are supported.
datapoint.bpm = each['value'][0]['fpVal']
datapoint.start_time = each['startTimeNanos']
datapoint.end_time = each['endTimeNanos']
datapoint.start_datetime = convert_to_datetime(datapoint.start_time)
datapoint.end_datetime = convert_to_datetime(datapoint.end_time)
sdt = convert_to_datetime(datapoint.start_time)
time_of_sdt = sdt.time()
# Make sure the point is in working hours before writing it to the DB:
if not (time_of_sdt > WORK_START) & (time_of_sdt < WORK_END):
continue #I expect this to go to the next point in data_dict in line 16
datapoint.day_of_point = sdt.strftime('%Y-%m-%d')
# Check if the datapoint is stressful when compared to existing DB data
datapoint.is_stressful = data_filter.is_stressful(datapoint.start_datetime, datapoint.bpm)
# Make sure elevated bpm isn't motion related before writing it to the DB
if datapoint.is_stressful:
if data_filter.is_motion_related(datapoint.start_time):
print "the datapoint is stressful, using continue."
continue
# Add the datapoint to the db session
dbsession.add(datapoint)
# Putting the commit *inside* the loop so that the
# is_stressful function can use the committed datapoints
# when it calls the db. Not as performant but it
# makes the calculations more accurate.
dbsession.commit()
def neighborhoods_in_county():
import model
import os
Zillow_key = os.environ["ZILLOW_ZWSID"]
from urllib2 import Request, urlopen, URLError
from xml.dom import minidom
url_zillow_neighborhood = "http://www.zillow.com/webservice/GetRegionChildren.htm?zws-id=" + Zillow_key + "&state=CA&county=Alameda"
response = urlopen(url_zillow_neighborhood)
dom_zillow_neighborhood = minidom.parse(response)
# need only region tags in the list
list_regions = dom_zillow_neighborhood.getElementsByTagName("list")
for node in dom_zillow_neighborhood.getElementsByTagName("region"):
name = (handleTok(
node.getElementsByTagName("name"))).encode("utf8").strip()
latitude = (handleTok(
node.getElementsByTagName("latitude"))).encode("utf8").strip()
longitude = (handleTok(
node.getElementsByTagName("longitude"))).encode("utf8").strip()
print "NEW NEIGHBORHOOD"
print name
print latitude
print longitude
try:
session = model.connect()
Zdemo_obj = model.zillow_neighborhood()
Zdemo_obj.name = name
Zdemo_obj.latitude = float(latitude)
Zdemo_obj.longitude = float(longitude)
session.add(Zdemo_obj)
session.commit()
except:
print "Error for row data:", name
f = open('log_file.txt', 'a')
f.write("\nError. failure for row:" + str(name))
f.close
def retrieve_from_db(state_code):
"""imports model, pulls mwh production data from db, and places into pandas df.
Also pulls county for each plant_name, and places into dict."""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
s = model.connect()
# retrive DECEMBER production data, for all turbines at all power plants in California
CA_gen_dec13_obj = s.execute('SELECT plant_name, state, fuel_type, dec_mwh_gen FROM "ProdGensDec2013" WHERE state=\'%s\' ' % state_code)
CA_gen_dec13_data = CA_gen_dec13_obj.fetchall()
df_dec2013 = DataFrame(CA_gen_dec13_data)
df_dec2013.columns = ['plant_name', 'state', 'fuel_type', 'dec_mwh_gen']
# retrive JAN-NOV 2014 production data, for all turbines at all power plants in California
CA_gen_2014_obj = s.execute('SELECT plant_name, state, fuel_type, jan_mwh_gen, feb_mwh_gen, mar_mwh_gen, apr_mwh_gen, may_mwh_gen, jun_mwh_gen, jul_mwh_gen, aug_mwh_gen, sep_mwh_gen, oct_mwh_gen, nov_mwh_gen FROM "ProdGens" WHERE state=\'%s\' ' % state_code)
CA_gen_2014_data = CA_gen_2014_obj.fetchall()
df_2014 = DataFrame(CA_gen_2014_data)
df_2014.columns = ['plant_name', 'state', 'fuel_type', 'jan_mwh_gen', 'feb_mwh_gen', 'mar_mwh_gen', 'apr_mwh_gen', 'may_mwh_gen', 'jun_mwh_gen', 'jul_mwh_gen', 'aug_mwh_gen', 'sep_mwh_gen', 'oct_mwh_gen', 'nov_mwh_gen']
# retrieve county name, assigned to each turbine at each plant in California
CA_counties_obj = s.execute('SELECT plant_name, county FROM "StatsGens" WHERE state=\'%s\' GROUP BY plant_name, county' % state_code)
CA_plant_counties = CA_counties_obj.fetchall()
df_counties = DataFrame(CA_plant_counties)
df_counties.columns = ['plant_name', 'county']
# now convert into dict, so caan easily add county to other df.
dict_counties={}
for idx, row in enumerate(df_counties.values):
plant_name, county = row
# clean the county name
county = unicodedata.normalize('NFKD', county).encode('ascii', 'ignore')
county = county.lower().title()
county = county.replace(" County", "")
dict_counties[plant_name] = county
return df_dec2013, df_2014, dict_counties
def load_movies(session):
# use u.item
with open ('seed_data/u.item', 'rb') as csvfile:
session = model.connect()
reader = csv.reader(csvfile, delimiter = '|')
for row in reader:
print row
title = row[1]
title = title.decode("latin-1")
if row[2]:
row[2] = datetime.strptime(row[2], '%d-%b-%Y')
else:
row[2] = None
movie = model.Movie(title, row[2], row[4])
session.add(movie)
session.commit()
def fetch_weeks_data(week_number):
"""Takes as parameter a week number (so 1 through 52) and returns a list of data
point objects that ocurred in that week. It currently assumes the year is 2015; this will
need to be refactored in later iterations."""
dbsession = connect()
requested_week = Week(2015, week_number)
# These functions return datetime objects. I <3 the isoweek library zomg.
startbound = requested_week.monday()
endbound = requested_week.saturday(
) #This doesn't *include* data from the endbound day, just up to that day.
one_weeks_data = dbsession.query(HRDataPoint).filter(
HRDataPoint.start_datetime > startbound,
HRDataPoint.start_datetime < endbound).all()
return one_weeks_data
def check_for_new_bpm():
"""This queries the DB for a user to see when the last bpm data refresh
was for that user, and if the last pull was > 24 hours ago, it calls
fetch_data to add recent bpm data for that user. The user is currently
hardcoded to me."""
dbsession = connect()
result = dbsession.execute(
'select * from "HRDataPoints" order by start_datetime desc limit 1')
latest_datapoint = result.first()
latest_timestamp = int(latest_datapoint.end_time)
now_in_nanotime = nanotime.now()
# If the timestamp on the most recent datapoint is more than a day old, call Google for updated data
if latest_timestamp < (int(nanotime.now()) - DAY_IN_NANOSECS):
endbound = str(int(nanotime.now())
) # Get now in nanotime for the endbound of the dataset
# convert latest_timestamp to int so I can increment it up a second
int_latest_timestamp = int(latest_timestamp)
int_latest_timestamp += 1000000000
latest_timestamp = str(int_latest_timestamp)
new_data = foa.fetch_data(data_type='bpm',
startbound=latest_datapoint.end_time,
endbound=endbound)
try:
data_dict = json.loads(new_data)
except:
print "This is what new_data looks like: ", new_data
return "There was an unexpected error."
data_point_store.save_to_db(new_data)
return True
else:
return False
def query_EIA_fuel_monthly_Series(ea_fuel):
"""specifically gets EIA data from ProdGen"""
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0,parentdir)
import model
s = model.connect()
fuel_codes = {
'coal': "('BIT','ANT','LIG','SUB','RC','WC','CBL','SC', 'SGC')",
'gas': "('NG','BFG','OG','PG','OTH')",
'nuclear': 'NUC',
'solar':'SUN',
'hydro':'WAT',
'wind':'WND',
'other': "('DFO','RFO','JF','KER','WO','PC','SG','AB','MSW','OBS','WDS','OBL','SLW','BLQ','WDL','OBG','GEO','LFG','TDF','MSB','MSN','WH','PUR','SGP','MWH')"}
if (ea_fuel=='nuclear') or (ea_fuel=='solar') or (ea_fuel=='wind') or (ea_fuel == 'hydro'):
code = fuel_codes[ea_fuel]
mo_fuel_obj = s.execute('SELECT sum(jan_mwh_gen), sum(feb_mwh_gen), sum(mar_mwh_gen), sum(apr_mwh_gen), sum(may_mwh_gen), sum(jun_mwh_gen), sum(jul_mwh_gen), sum(aug_mwh_gen), sum(sep_mwh_gen), sum(oct_mwh_gen), sum(nov_mwh_gen) FROM "ProdGens" WHERE fuel_type=\'%s\' and state=\'CA\' ' % code)
if (ea_fuel=='coal') or (ea_fuel=='gas') or (ea_fuel=='other'):
list_of_codes = fuel_codes[ea_fuel]
mo_fuel_obj = s.execute('SELECT sum(jan_mwh_gen), sum(feb_mwh_gen), sum(mar_mwh_gen), sum(apr_mwh_gen), sum(may_mwh_gen), sum(jun_mwh_gen), sum(jul_mwh_gen), sum(aug_mwh_gen), sum(sep_mwh_gen), sum(oct_mwh_gen), sum(nov_mwh_gen) FROM "ProdGens" WHERE state=\'CA\' and fuel_type IN %s ' % list_of_codes )
mo_fuel_entry = mo_fuel_obj.fetchall()
# turn into dict
list_of_months = ['jan','feb','mar','apr','may','jun','jul','aug','sep','oct','nov']
mo_fuel_entry_dict ={}
for i in range(11):
mo_fuel_entry_dict[list_of_months[i]] = mo_fuel_entry[0][i]
# can now turn dict into Series
return Series(mo_fuel_entry_dict)
def main():
dbsession = model.connect()
hr_json = open('./raw_data/psql_output.txt').read()
lines = hr_json.split('\n')
for each_line in lines:
# separate on pipes
db_record_as_list = each_line.split('|')
point = model.HRDataPoint()
point.user_id = db_record_as_list[1].strip()
point.bpm = db_record_as_list[2].strip()
point.start_time = db_record_as_list[3].strip()
point.end_time = db_record_as_list[4].strip()
point.start_datetime = datetime.strptime(db_record_as_list[5].strip(),
"%Y-%m-%d %H:%M:%S")
point.end_datetime = datetime.strptime(db_record_as_list[6].strip(),
"%Y-%m-%d %H:%M:%S")
point.day_of_point = db_record_as_list[7].strip()
# convert the t or f to an actual bool
if db_record_as_list[8].strip() == 't':
stressful = True
elif db_record_as_list[8].strip() == 'f':
stressful = False
else:
stressful = None
point.is_stressful = stressful
print "Here's the current data point: ", point
dbsession.add(point)
dbsession.commit()
def insert_row_db(date, hr, adict):
"""imports model, and inserts web scraped data into the db"""
# add parent directory to the path, so can import model.py
# need model in order to update the database when this task is activated by cron
import os
parentdir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
os.sys.path.insert(0, parentdir)
import model
session = model.connect()
for k, v in adict.items():
fuel_obj = model.HistoricCAISOProdByFuel()
fuel_obj.date = datetime.strptime(date, '%Y%m%d')
fuel_obj.time_start = hr
fuel_obj.fuel_type = k
fuel_obj.mw_gen = v
session.add(fuel_obj)
print fuel_obj
session.commit()
if row[0] == '#':
continue
else:
for i in range(len(row)):
row[i] = row[i].decode('utf-8')
trad, simp, pinyin = row[0], row[1], row[2]
definition = ''.join(row[3:])
pinyin = pinyin.strip('"')
definition = definition.strip('"')
entry = model.Entry(simplified=simp,
traditional=trad,
pinyin=pinyin,
definition=definition)
session.add(entry)
try:
session.commit()
except sqlalchemy.exc.IntegrityError, e:
session.rollback()
def main(session):
load_dict(session)
if __name__ == "__main__":
session = model.connect()
main(session)
new_movie = model.Movie(id=row[0], name=title, released_at=formatted_date , imdb_url=row[4])
session.add(new_movie)
session.commit()
def load_data(session):
with open('seed_data/u.data', 'rb') as csvfile:
data_db = csv.reader(csvfile, delimiter = '\t')
for row in data_db:
timestamp = int(row[3])
formatted_timestamp = datetime.datetime.utcfromtimestamp(timestamp)
new_data= model.Rating(user_id=row[0], movie_id=row[1], rating=row[2], timestamp=formatted_timestamp)
session.add(new_data)
session.commit()
def main():
# You'll call each of the load_* functions with the session as an argument
session = model.connect()
load_user(session)
print "user loaded"
load_item(session)
print "movies loaded"
load_data(session)
print "ratings loaded"
if __name__ == "__main__":
s = model.connect()
main(s)
from model import (connect, get_session,
Question, Picture, Group, GroupMember)
connect()
db_session = get_session()
''' Function of Accessing Database '''
def get_group_list():
query = (db_session
.query(Group.id,
Group.name)
.select_from(Group)
.filter(Group.status == 1)
.all())
group_dict = {}
group_list = []
for groupId, group_name in query:
if(groupId not in group_dict):
group_dict[groupId] = "yes"
group_list.append({
"id": groupId,
"name": group_name
})
groupList = {
"group": group_list
}
print("[DB] get groupList success")
return groupList
parser.add_argument('--lon', type=float, required=True, help='longitude')
parser.add_argument('--dlat',
type=float,
required=True,
help='destination latitude')
parser.add_argument('--dlon',
type=float,
required=True,
help='destination longitude')
parser.add_argument('--id', default='new', help='bike id')
args = parser.parse_args()
model.connect('mydb')
if args.id == 'new':
b = model.Bike()
else:
b = model.Bike.objects.with_id(args.id)
b.point = [args.lon, args.lat]
b.destination = [args.dlon, args.dlat]
b.update(new_point=[args.lon, args.lat])
b.save()
print b
rating = Rating(user_id-user_id, movie_id=id)
db_session.add(rating)
else:
flash("Rating updated", "success")
rating.rating = rating_number
db_session.commit()
return redirect(url_for("view_movie", id=id))
@app.route("/my_ratings")
def my_ratings():
if not g.user_id:
flash("Please log in", "warning")
return redirect(url_for("index"))
ratings = db_session.query(Rating).filter_by(user_id=g.user_id).all()
return render_template("my_ratings.html", ratings=ratings)
@app.route("/logout")
def logout:
del session['user_id']
return redirect(url_for("index"))
if __name__ == "__main__":
db_uri = app.config.get('SQLALCHEMY_DATABASE_URI')
if not db_uri:
db_uri = "sqlite:///ratings.db"
model.connect(db_uri)
app.run(debug = True, port=8080, host='0.0.0.0')
def index():
model.connect()
users = model.get_users()
return render_template("index.html", users=users)
def main(session):
# You'll call each of the load_* functions with the session as an argument
## Sample code to test geo function call
# lat,lng = geo.geocode("84 Madrid place, Fremont, CA, 94539", "false")
# return lat,lng
#Call geo code function to load latlng for addresses where latlng is missing
load_latlng()
#Get all latlngs available in the Address table to calculate ceter using kmeans clustering. Return data as Tuple
query = model.session.query(model.Address).all()
latlng_list = get_latlng(query)
#Format latlngs into numpy array to calculate centroids usig kmeans clusterig technique.
data = numpy.array(latlng_list)
centers = get_latlng_clustercenter(data,6)
# print "Centers are: ", centers
# print "idx is:," ,idx
if __name__ == "__main__":
session= model.connect()
main(session)
if str_time != "0":
movie_title = line[1].decode("latin-1")
movie_title = movie_title[:-6].strip()
release_datetime = datetime.strptime(str_time, "%d-%b-%Y")
new_movie = model.Movie(id=line[0], movie_title=movie_title,
release_date=release_datetime, IMDB=line[4])
# add new movie to session
session.add(new_movie)
# commit all movies from session
session.commit()
def load_ratings(session):
# use u.data
with open("seed_data/u.data") as r:
reader = csv.reader(r, delimiter="\t")
for line in reader:
new_rating = model.Rating(user_id=line[0], movie_id=line[1], rating=line[2])
session.add(new_rating)
session.commit()
def main(session):
# You'll call each of the load_* functions with the session as an argument
load_users(session)
load_movies(session)
load_ratings(session)
if __name__ == "__main__":
s= model.connect()
main(s)