def validate_metadata_two_candsets(C, D):
assert_equal(sorted(C.columns), sorted(D.columns))
assert_equal(em.get_key(D), em.get_key(C))
assert_equal(em.get_property(D, 'fk_ltable'),
em.get_property(C, 'fk_ltable'))
assert_equal(em.get_property(D, 'fk_rtable'),
em.get_property(C, 'fk_rtable'))
def validate_data(C, expected_ids=None):
if expected_ids:
lid = em.get_property(C, 'fk_ltable')
rid = em.get_property(C, 'fk_rtable')
C_ids = C[[lid, rid]].set_index([lid, rid])
actual_ids = sorted(C_ids.index.values.tolist())
assert_equal(expected_ids, actual_ids)
else:
assert_equal(len(C), 0)
def validate_data(C, expected_ids=None):
if expected_ids:
lid = em.get_property(C, 'fk_ltable')
rid = em.get_property(C, 'fk_rtable')
C_ids = C[[lid, rid]].set_index([lid, rid])
actual_ids = sorted(C_ids.index.values.tolist())
assert_equal(expected_ids, actual_ids)
else:
assert_equal(len(C), 0)
def validate_metadata(C, l_output_attrs=None, r_output_attrs=None,
l_output_prefix='ltable_', r_output_prefix='rtable_',
l_key='ID', r_key='ID'):
s1 = ['_id', l_output_prefix + l_key, r_output_prefix + r_key]
if l_output_attrs:
s1 += [l_output_prefix + x for x in l_output_attrs if x != l_key]
if r_output_attrs:
s1 += [r_output_prefix + x for x in r_output_attrs if x != r_key]
s1 = sorted(s1)
assert_equal(s1, sorted(C.columns))
assert_equal(em.get_key(C), '_id')
assert_equal(em.get_property(C, 'fk_ltable'), l_output_prefix + l_key)
assert_equal(em.get_property(C, 'fk_rtable'), r_output_prefix + r_key)
def validate_metadata(C, l_output_attrs=None, r_output_attrs=None,
l_output_prefix='ltable_', r_output_prefix='rtable_',
l_key='ID', r_key='ID'):
s1 = ['_id', l_output_prefix + l_key, r_output_prefix + r_key]
if l_output_attrs:
s1 += [l_output_prefix + x for x in l_output_attrs if x != l_key]
if r_output_attrs:
s1 += [r_output_prefix + x for x in r_output_attrs if x != r_key]
s1 = sorted(s1)
assert_equal(s1, sorted(C.columns))
assert_equal(em.get_key(C), '_id')
assert_equal(em.get_property(C, 'fk_ltable'), l_output_prefix + l_key)
assert_equal(em.get_property(C, 'fk_rtable'), r_output_prefix + r_key)
def validate_metadata_two_candsets(C, D):
assert_equal(sorted(C.columns), sorted(D.columns))
assert_equal(em.get_key(D), em.get_key(C))
assert_equal(em.get_property(D, 'fk_ltable'), em.get_property(C, 'fk_ltable'))
assert_equal(em.get_property(D, 'fk_rtable'), em.get_property(C, 'fk_rtable'))
import warnings
import numpy as np
import re
warnings.filterwarnings('ignore')
#Reading A and B
A = em.read_csv_metadata("/mnt/c/Users/sreya/Downloads/DS/bestbuy_music.csv",
key="ID")
B = em.read_csv_metadata(
"/mnt/c/Users/sreya/Downloads/DS/metacritic_music.csv", key="ID")
# Setting the Keys
em.set_key(A, 'ID')
em.set_key(B, 'ID')
em.get_property(A, 'key')
#Reading in the Sampled Candidate set (450 tuples) obtained after blocking
G = em.read_csv_metadata(
"/mnt/c/Users/sreya/Downloads/DS/sampled_candidate_set.csv",
key='_id',
ltable=A,
rtable=B,
fk_ltable='ltable_ID',
fk_rtable='rtable_ID')
#Split into I and J (train and test)
IJ = em.split_train_test(G, train_proportion=0.7, random_state=0)
I = IJ['train']
J = IJ['test']