def parcels_derived_features(control, transactions_df):
'return new df by merging df and the geo features'
# merge in census tract features
census_tract_df = pd.read_csv(
control.path_in_parcels_features_census_tract, index_col=0)
check_feature_names(transactions_df)
check_feature_names(census_tract_df)
m1 = transactions_df.merge(
census_tract_df,
how='inner',
left_on=transactions_df[transactions.census_tract],
right_on=census_tract_df.census_tract,
)
check_feature_names(m1)
print 'm1 shape', m1.shape
cc('commercial', m1)
# merge in zip5 features
zip5_df = pd.read_csv(control.path_in_parcels_features_zip5, index_col=0)
check_feature_names(m1)
check_feature_names(zip5_df)
m2 = m1.merge(
zip5_df,
how='inner',
left_on=m1[transactions.zip5],
right_on=zip5_df.zip5,
)
# remove duplicated field zip5_x, zip5_y
assert 'zip5_x' in m2.columns
assert 'zip5_y' in m2.columns
assert (m2.zip5_x == m2.zip5_y).all()
assert 'zip5' not in m2.columns
pu.df_remove_column(m2, 'zip5_x')
pu.df_rename_column(m2, 'zip5_y', 'zip5')
check_feature_names(m2)
print 'm2 shape', m2.shape
return m2
def parcels_derived_features(control, transactions_df):
'return new df by merging df and the geo features'
# merge in census tract features
census_tract_df = pd.read_csv(control.path_in_parcels_features_census_tract, index_col=0)
check_feature_names(transactions_df)
check_feature_names(census_tract_df)
m1 = transactions_df.merge(
census_tract_df,
how='inner',
left_on=transactions_df[transactions.census_tract],
right_on=census_tract_df.census_tract,
)
check_feature_names(m1)
print 'm1 shape', m1.shape
cc('commercial', m1)
# merge in zip5 features
zip5_df = pd.read_csv(control.path_in_parcels_features_zip5, index_col=0)
check_feature_names(m1)
check_feature_names(zip5_df)
m2 = m1.merge(
zip5_df,
how='inner',
left_on=m1[transactions.zip5],
right_on=zip5_df.zip5,
)
# remove duplicated field zip5_x, zip5_y
assert 'zip5_x' in m2.columns
assert 'zip5_y' in m2.columns
assert (m2.zip5_x == m2.zip5_y).all()
assert 'zip5' not in m2.columns
pu.df_remove_column(m2, 'zip5_x')
pu.df_rename_column(m2, 'zip5_y', 'zip5')
check_feature_names(m2)
print 'm2 shape', m2.shape
return m2
def main(argv):
control = make_control(argv)
sys.stdout = Logger(base_name=control.arg.base_name)
print control
# NOTE: Organize the computation to minimize memory usage
# so that this code can run on smaller-memory systems
def ps(name, value):
s = value.shape
print ' %20s shape (%d, %d)' % (name, s[0], s[1])
# create dataframes
n_read_if_test = 10000
deeds_g_al = deeds.read_g_al(
control.path,
n_read_if_test if control.test else None,
)
parcels_sfr = parcels.read(
control.path,
10000 if control.test else None,
just_sfr=True,
)
ps('original deeds g al', deeds_g_al)
ps('original parcels sfr', parcels_sfr)
# augment parcels to include a zip5 field (5-digit zip code)
# drop samples without a zipcode
# rationale: we use the zip5 to join the features derived from parcels
# and zip5 is derived from zipcode
zipcode_present = parcels_sfr[parcels.zipcode].notnull()
parcels_sfr = parcels_sfr[zipcode_present]
parcels.add_zip5(parcels_sfr)
# augment parcels and deeds to include a better APN
print 'adding best apn column for parcels'
new_column_parcels = best_apn(parcels_sfr, parcels.apn_formatted,
parcels.apn_unformatted)
parcels_sfr.loc[:, parcels.
best_apn] = new_column_parcels # generates an ignorable warning
print 'adding best apn column for deeds'
new_column_deeds = best_apn(deeds_g_al, deeds.apn_formatted,
deeds.apn_unformatted)
deeds_g_al.loc[:, deeds.best_apn] = new_column_deeds
ps('revised deeds_g_al', deeds_g_al)
ps('revised parcels_sfr', parcels_sfr)
# join the deeds and parcels files
print 'starting to merge'
check_feature_names(deeds_g_al)
check_feature_names(parcels_sfr)
m1 = deeds_g_al.merge(parcels_sfr,
how='inner',
left_on=deeds.best_apn,
right_on=parcels.best_apn,
suffixes=('_deed', '_parcel'))
check_feature_names(m1)
del deeds_g_al
del parcels_sfr
ps('m1 merge deed + parcels', m1)
# add in derived parcels features
m2 = parcels_derived_features(control, m1)
check_feature_names(m2)
ps('ms added parcels_derived', m2)
del m1
# add in census data
census_features_df = read_census_features(control)
m3 = m2.merge(
census_features_df,
left_on=transactions.census_tract,
right_on="census_tract",
)
assert 'census_tract_x' in m3.columns
assert 'census_tract_y' in m3.columns
assert (m3.census_tract_x == m3.census_tract_y).all()
assert 'census_tract' not in m3.columns
pu.df_remove_column(m3, 'census_tract_x')
pu.df_rename_column(m3, 'census_tract_y', 'census_tract')
check_feature_names(m3)
del m2
ps('m3 merged census features', m3)
# add in GPS coordinates
geocoding_df = read_geocoding(control)
m4 = m3.merge(
geocoding_df,
left_on="best_apn",
right_on="G APN",
)
del geocoding_df
del m3
ps('m4 merged geocoding', m4)
final = m4
print 'final columns'
for c in final.columns:
print c,
print
cc('fraction',
final) # verify that fraction_owner_occupied is in the output
print 'final shape', final.shape
# write merged,augmented dataframe
print 'writing final dataframe to csv file'
final.to_csv(control.path_out_transactions)
# write out all the column names
print 'all column names in final dataframe'
for name in final.columns:
print name
if '_y' in name:
print 'found strange suffix'
pdb.set_trace()
print control
if control.test:
print 'DISCARD OUTPUT: test'
print 'done'
return
def main(argv):
control = make_control(argv)
sys.stdout = Logger(base_name=control.arg.base_name)
print control
# NOTE: Organize the computation to minimize memory usage
# so that this code can run on smaller-memory systems
def ps(name, value):
s = value.shape
print ' %20s shape (%d, %d)' % (name, s[0], s[1])
# create dataframes
n_read_if_test = 10000
deeds_g_al = deeds.read_g_al(
control.path,
n_read_if_test if control.test else None,
)
parcels_sfr = parcels.read(
control.path,
10000 if control.test else None,
just_sfr=True,
)
ps('original deeds g al', deeds_g_al)
ps('original parcels sfr', parcels_sfr)
# augment parcels to include a zip5 field (5-digit zip code)
# drop samples without a zipcode
# rationale: we use the zip5 to join the features derived from parcels
# and zip5 is derived from zipcode
zipcode_present = parcels_sfr[parcels.zipcode].notnull()
parcels_sfr = parcels_sfr[zipcode_present]
parcels.add_zip5(parcels_sfr)
# augment parcels and deeds to include a better APN
print 'adding best apn column for parcels'
new_column_parcels = best_apn(parcels_sfr, parcels.apn_formatted, parcels.apn_unformatted)
parcels_sfr.loc[:, parcels.best_apn] = new_column_parcels # generates an ignorable warning
print 'adding best apn column for deeds'
new_column_deeds = best_apn(deeds_g_al, deeds.apn_formatted, deeds.apn_unformatted)
deeds_g_al.loc[:, deeds.best_apn] = new_column_deeds
ps('revised deeds_g_al', deeds_g_al)
ps('revised parcels_sfr', parcels_sfr)
# join the deeds and parcels files
print 'starting to merge'
check_feature_names(deeds_g_al)
check_feature_names(parcels_sfr)
m1 = deeds_g_al.merge(parcels_sfr, how='inner',
left_on=deeds.best_apn, right_on=parcels.best_apn,
suffixes=('_deed', '_parcel'))
check_feature_names(m1)
del deeds_g_al
del parcels_sfr
ps('m1 merge deed + parcels', m1)
# add in derived parcels features
m2 = parcels_derived_features(control, m1)
check_feature_names(m2)
ps('ms added parcels_derived', m2)
del m1
# add in census data
census_features_df = read_census_features(control)
m3 = m2.merge(census_features_df,
left_on=transactions.census_tract,
right_on="census_tract",
)
assert 'census_tract_x' in m3.columns
assert 'census_tract_y' in m3.columns
assert (m3.census_tract_x == m3.census_tract_y).all()
assert 'census_tract' not in m3.columns
pu.df_remove_column(m3, 'census_tract_x')
pu.df_rename_column(m3, 'census_tract_y', 'census_tract')
check_feature_names(m3)
del m2
ps('m3 merged census features', m3)
# add in GPS coordinates
geocoding_df = read_geocoding(control)
m4 = m3.merge(geocoding_df,
left_on="best_apn",
right_on="G APN",
)
del geocoding_df
del m3
ps('m4 merged geocoding', m4)
final = m4
print 'final columns'
for c in final.columns:
print c,
print
cc('fraction', final) # verify that fraction_owner_occupied is in the output
print 'final shape', final.shape
# write merged,augmented dataframe
print 'writing final dataframe to csv file'
final.to_csv(control.path_out_transactions)
# write out all the column names
print 'all column names in final dataframe'
for name in final.columns:
print name
if '_y' in name:
print 'found strange suffix'
pdb.set_trace()
print control
if control.test:
print 'DISCARD OUTPUT: test'
print 'done'
return
