A = mg.load_dataset('table_A')
B = mg.load_dataset('table_B')
ab = mg.AttrEquivalenceBlocker()
C = ab.block_tables(A, B, 'zipcode', 'zipcode', ['name'], ['name'])
mg.init_jvm()
#L = mg.label_table(C, 'gold')
#L.to_csv('label.csv')
L = mg.read_csv('label.csv', ltable=A, rtable=B)
feature_table = mg.get_features_for_matching(A, B)
G = mg.extract_feature_vecs(L, feature_table=feature_table, attrs_after='gold')
m = mg.LinRegMatcher()
t = cv_matcher_and_trigger(
m,
None,
table=G,
exclude_attrs=['_id', 'ltable.ID', 'rtable.ID', 'gold'],
target_attr='gold',
k=5,
metric='precision',
random_state=0)
res = mg.select_matcher(
[m],
table=G,
exclude_attrs=['_id', 'ltable.ID', 'rtable.ID', 'gold'],
target_attr='gold',
k=5,
metric='f1',
random_state=0)
print res['cv_stats']
s_prime # In[35]: # Fitting/Predicting # Create a set of matchers nb = mg.NBMatcher() # naive bayes dt = mg.DTMatcher() # decision tree rf = mg.RFMatcher() # random forest # In[36]: # Select a matcher using cross validation m = mg.select_matcher([nb, dt, rf], x=s_prime[list(feat_table['feature_name'])], y=s_prime['gold_label'], k=5 ) # In[37]: # see what was selected and the stats m # In[38]: # instead of a single matcher, we can choose ensemble of matchers mc, stats = mg.selector_matcher_combiner([nb, dt, rf], ['majority'], x=s_prime[list(feat_table['feature_name'])], y=s_prime['gold_label'], k=5) # In[39]:
# display feature vector table
s_prime
# In[35]:
# Fitting/Predicting
# Create a set of matchers
nb = mg.NBMatcher() # naive bayes
dt = mg.DTMatcher() # decision tree
rf = mg.RFMatcher() # random forest
# In[36]:
# Select a matcher using cross validation
m = mg.select_matcher([nb, dt, rf],
x=s_prime[list(feat_table['feature_name'])],
y=s_prime['gold_label'],
k=5)
# In[37]:
# see what was selected and the stats
m
# In[38]:
# instead of a single matcher, we can choose ensemble of matchers
mc, stats = mg.selector_matcher_combiner([nb, dt, rf], ['majority'],
x=s_prime[list(
feat_table['feature_name'])],
y=s_prime['gold_label'],
k=5)