def facility_vs_building_set(s):
print s
conn = uo.connect('all')
if s == 'AI':
ids = gbs.get_cat_set(['A', 'I'], conn)
elif s == 'covered':
ids = gbs.get_covered_set()
df_f = pd.read_csv(os.getcwd() + '/input/FY/covered/Covered_Facilities_All Energy mmBTUs_FY14_EISA07Sec432_input.csv')
facility_eisa = set(df_f['Facility_Number'].tolist())
facility_eisa = [x[:8] for x in facility_eisa if type(x) != float]
f_ids = [x for x in ids if '0000' in x]
# for x in sorted(f_ids):
# print x
b_ids = [x for x in ids if not '0000' in x]
print 'total {0}, facility {1}, building {2}'.format(len(ids), len(f_ids), len(b_ids))
bf_ids = ['{0}0000{1}'.format(x[:2], x[-2:]) for x in b_ids]
print len(common)
common = (set(bf_ids).intersection(f_ids))
for y in common:
print y
print [x for x in b_ids if '{0}0000{1}'.format(x[:2], x[-2:]) == y]
if s == 'covered':
print 'eisa facility', len(facility_eisa)
print 'common ids from eisa', len(set(f_ids).intersection(facility_eisa))
print 'different ids from eisa', (set(f_ids).difference(facility_eisa))
common = (set(f_ids).difference(facility_eisa))
for y in common:
print y
print [x for x in b_ids if '{0}0000{1}'.format(x[:2], x[-2:]) == y]
def facility_vs_building_set(s):
print s
conn = uo.connect('all')
if s == 'AI':
ids = gbs.get_cat_set(['A', 'I'], conn)
elif s == 'covered':
ids = gbs.get_covered_set()
df_f = pd.read_csv(
os.getcwd() +
'/input/FY/covered/Covered_Facilities_All Energy mmBTUs_FY14_EISA07Sec432_input.csv'
)
facility_eisa = set(df_f['Facility_Number'].tolist())
facility_eisa = [x[:8] for x in facility_eisa if type(x) != float]
f_ids = [x for x in ids if '0000' in x]
# for x in sorted(f_ids):
# print x
b_ids = [x for x in ids if not '0000' in x]
print 'total {0}, facility {1}, building {2}'.format(
len(ids), len(f_ids), len(b_ids))
bf_ids = ['{0}0000{1}'.format(x[:2], x[-2:]) for x in b_ids]
print len(common)
common = (set(bf_ids).intersection(f_ids))
for y in common:
print y
print[x for x in b_ids if '{0}0000{1}'.format(x[:2], x[-2:]) == y]
if s == 'covered':
print 'eisa facility', len(facility_eisa)
print 'common ids from eisa', len(
set(f_ids).intersection(facility_eisa))
print 'different ids from eisa', (set(f_ids).difference(facility_eisa))
common = (set(f_ids).difference(facility_eisa))
for y in common:
print y
print[x for x in b_ids if '{0}0000{1}'.format(x[:2], x[-2:]) == y]
def table_for_robust_set():
conn = uo.connect('all')
study_set = gbs.get_energy_set('eui').intersection(gbs.get_cat_set(['A', 'I'], conn))
df = pd.read_csv(os.getcwd() + '/plot_FY_weather/html/table/action_saving.csv')
df = df[df['Building_Number'].isin(study_set)]
df.sort('Building_Number', inplace=True)
df.to_csv(os.getcwd() + '/plot_FY_weather/html/table/action_saving_robustset.csv', index=False)
return
def table_for_robust_set():
conn = uo.connect('all')
study_set = gbs.get_energy_set('eui').intersection(
gbs.get_cat_set(['A', 'I'], conn))
df = pd.read_csv(os.getcwd() +
'/plot_FY_weather/html/table/action_saving.csv')
df = df[df['Building_Number'].isin(study_set)]
df.sort('Building_Number', inplace=True)
df.to_csv(os.getcwd() +
'/plot_FY_weather/html/table/action_saving_robustset.csv',
index=False)
return
def study_set_plot():
conn = uo.connect('all')
with conn:
# df1 = pd.read_sql('SELECT DISTINCT Building_Number, Fiscal_Year FROM EUAS_monthly', conn)
df1 = pd.read_sql(
'SELECT DISTINCT Building_Number, Fiscal_Year FROM eui_by_fy',
conn)
df2 = pd.read_sql('SELECT Building_Number, Cat FROM EUAS_category',
conn)
meter_set = gbs.get_action_set('high_level_ECM', ['Advanced Metering'])
df = pd.merge(df1, df2, on='Building_Number', how='left')
df = df[df['Fiscal_Year'] > 2006]
df = df[df['Fiscal_Year'] < 2016]
df3 = df.groupby('Building_Number').filter(lambda x: len(x) > 5)
ai_set = gbs.get_cat_set(['A', 'I'], conn)
# invest = gbs.get_invest_set()[-1]
invest = gbs.get_ecm_set()
all_building = set(df3['Building_Number'].tolist())
print 'all building > 5 years of data: {0}'.format(len(all_building))
print 'all building > 5 years of data + ecm: {0}'.format(
len(all_building.intersection(invest)))
print 'all building > 5 years of data + meter: {0}'.format(
len(all_building.intersection(meter_set)))
df4 = df[df['Cat'].isin(
['A', 'I'])].groupby('Building_Number').filter(lambda x: len(x) > 5)
ai_building = set(df4['Building_Number'].tolist())
print 'A + I building > 5 years of data: {0}'.format(len(ai_building))
print 'A + I building > 5 years of data + ecm: {0}'.format(
len(ai_building.intersection(invest)))
print 'A + I building > 5 years of data + meter: {0}'.format(
len(ai_building.intersection(meter_set)))
print 'elec ', len(gbs.get_energy_set('elec').intersection(ai_set))
print 'elec + ecm', len(
gbs.get_energy_set('elec').intersection(ai_set).intersection(invest))
print 'elec + meter', len(
gbs.get_energy_set('elec').intersection(ai_set).intersection(
meter_set))
print 'gas ', len(gbs.get_energy_set('gas').intersection(ai_set))
print 'gas + ecm', len(
gbs.get_energy_set('gas').intersection(ai_set).intersection(invest))
print 'gas + meter', len(
gbs.get_energy_set('gas').intersection(ai_set).intersection(meter_set))
print 'eui', len(gbs.get_energy_set('eui').intersection(ai_set))
print 'eui + ecm', len(
gbs.get_energy_set('eui').intersection(ai_set).intersection(invest))
print 'eui + meter', len(
gbs.get_energy_set('eui').intersection(ai_set).intersection(meter_set))
return
def invest_cnt():
conn = uo.connect('all')
with conn:
df = pd.read_sql(
'SELECT DISTINCT Building_Number, high_level_ECM, detail_level_ECM FROM EUAS_ecm WHERE detail_level_ECM != \'GSALink\'',
conn)
eng_set = gbs.get_energy_set('eui')
ai_set = gbs.get_cat_set(['A', 'I'], conn)
study_set = eng_set.intersection(ai_set)
df = df[df['Building_Number'].isin(study_set)]
print df.groupby(['high_level_ECM', 'detail_level_ECM']).count()
print len(df)
df = df.groupby(['Building_Number']).filter(lambda x: len(x) == 1)
print len(df)
print df.head()
print df.groupby(['high_level_ECM', 'detail_level_ECM']).count()
return
def count_invest():
conn = uo.connect('all')
with conn:
df1 = pd.read_sql(
'SELECT DISTINCT Building_Number, high_level_ECM FROM EUAS_ecm WHERE high_level_ECM != \'GSALink\'',
conn)
df2 = pd.read_sql(
'SELECT DISTINCT Building_Number, ECM_program FROM EUAS_ecm_program',
conn)
eng_set = gbs.get_energy_set('eui')
ai_set = gbs.get_cat_set(['A', 'I'], conn)
study_set = eng_set.intersection(ai_set)
df1.dropna(subset=['high_level_ECM'], inplace=True)
df2.dropna(subset=['ECM_program'], inplace=True)
df1 = df1[df1['Building_Number'].isin(study_set)]
df2 = df2[df2['Building_Number'].isin(study_set)]
print df1['high_level_ECM'].value_counts()
print df2['ECM_program'].value_counts()
return