def test_select_matcher_valid_3(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
# C = read_csv_metadata(path_c, ltable=A, rtable=B, fk_ltable='ltable.id',
# fk_rtable='rtable.id', key='_id')
# labels = [0] * 7
# labels.extend([1] * 8)
# C['labels'] = labels
# feature_table = get_features_for_matching(A, B)
# feature_vectors = extract_feature_vecs(C, feature_table=feature_table, attrs_after='gold')
# feature_vectors.fillna(0, inplace=True)
feature_vectors = read_csv_metadata(path_f, ltable=A, rtable=B)
dtmatcher = DTMatcher()
nbmatcher = NBMatcher()
rfmatcher = RFMatcher()
svmmatcher = SVMMatcher()
linregmatcher = LinRegMatcher()
logregmatcher = LogRegMatcher()
matchers = [dtmatcher, nbmatcher, rfmatcher, svmmatcher, linregmatcher, logregmatcher]
col_list = list(feature_vectors.columns)
l = list_diff(col_list, [cm.get_key(feature_vectors), cm.get_fk_ltable(feature_vectors),
cm.get_fk_rtable(feature_vectors),
'gold'])
X = feature_vectors[l]
Y = feature_vectors['gold']
result = select_matcher(matchers, x=X, y=Y, metric='recall')
header = ['Name', 'Matcher', 'Num folds']
result_df = result['cv_stats']
self.assertEqual(set(header) == set(list(result_df.columns[[0, 1, 2]])), True)
self.assertEqual('Mean score', result_df.columns[len(result_df.columns) - 1])
d = result_df.set_index('Name')
p_max = d.ix[result['selected_matcher'].name, 'Mean score']
a_max = pd.np.max(d['Mean score'])
self.assertEqual(p_max, a_max)
def test_select_matcher_target_attr_not_present(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
# C = read_csv_metadata(path_c, ltable=A, rtable=B, fk_ltable='ltable.id',
# fk_rtable='rtable.id', key='_id')
# labels = [0] * 7
# labels.extend([1] * 8)
# C['labels'] = labels
# feature_table = get_features_for_matching(A, B)
# feature_vectors = extract_feature_vecs(C, feature_table=feature_table, attrs_after='gold')
# feature_vectors.fillna(0, inplace=True)
feature_vectors = read_csv_metadata(path_f, ltable=A, rtable=B)
dtmatcher = DTMatcher()
nbmatcher = NBMatcher()
rfmatcher = RFMatcher()
svmmatcher = SVMMatcher()
linregmatcher = LinRegMatcher()
logregmatcher = LogRegMatcher()
matchers = [dtmatcher, nbmatcher, rfmatcher, svmmatcher, linregmatcher, logregmatcher]
col_list = list(feature_vectors.columns)
l = list_diff(col_list, [cm.get_fk_ltable(feature_vectors),
cm.get_fk_rtable(feature_vectors)
])
feature_vectors = feature_vectors[l]
result = select_matcher(matchers, x=None, y=None, table=feature_vectors,
exclude_attrs='_id',
target_attr='labels1', k=2)
def test_select_matcher_valid_1(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
# C = read_csv_metadata(path_c, ltable=A, rtable=B, fk_ltable='ltable.id',
# fk_rtable='rtable.id', key='_id')
# C['labels'] = labels
feature_vectors = read_csv_metadata(path_f, ltable=A, rtable=B)
dtmatcher = DTMatcher()
nbmatcher = NBMatcher()
rfmatcher = RFMatcher()
svmmatcher = SVMMatcher()
linregmatcher = LinRegMatcher()
logregmatcher = LogRegMatcher()
matchers = [dtmatcher, nbmatcher, rfmatcher, svmmatcher, linregmatcher, logregmatcher]
result = select_matcher(matchers, x=None, y=None, table=feature_vectors,
exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='gold', k=7)
header = ['Name', 'Matcher', 'Num folds']
result_df = result['cv_stats']
self.assertEqual(set(header) == set(list(result_df.columns[[0, 1, 2]])), True)
self.assertEqual('Mean score', result_df.columns[len(result_df.columns) - 1])
d = result_df.set_index('Name')
p_max = d.ix[result['selected_matcher'].name, 'Mean score']
a_max = pd.np.max(d['Mean score'])
self.assertEqual(p_max, a_max)
def test_debug_rf_matcher_valid_2(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
labels = [0] * 7
labels.extend([1] * 8)
C['labels'] = labels
feature_table = get_features_for_matching(A, B)
feature_vectors = extract_feature_vecs(C, feature_table=feature_table,
attrs_after='labels')
rf = RFMatcher()
rf.fit(table=feature_vectors, exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels')
debug_randomforest_matcher(rf.clf, A.ix[1], B.ix[2], feat_table=feature_table,
fv_columns=feature_vectors.columns,
exclude_attrs=['ltable_ID', 'rtable_ID', '_id', 'labels'])
def test_vis_tuple_debug_rf_matcher_valid_1(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
labels = [0] * 7
labels.extend([1] * 8)
C['labels'] = labels
feature_table = get_features_for_matching(A, B)
feature_vectors = extract_feature_vecs(C, feature_table=feature_table,
attrs_after='labels')
rf = RFMatcher()
rf.fit(table=feature_vectors, exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels')
s = pd.DataFrame(feature_vectors.ix[0])
s1 = s.T
vis_tuple_debug_rf_matcher(rf, s1,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'])
def test_valid_names_for_matchers(self):
matchers1 = {
"DT": DTMatcher(),
"LinReg": LinRegMatcher(),
"LogReg": LogRegMatcher(),
"NB": NBMatcher(),
"RF": RFMatcher(),
"SVM": SVMMatcher()
}
matchers2 = {
"DT": DTMatcher(name='temp'),
"LinReg": LinRegMatcher(name='temp'),
"LogReg": LogRegMatcher(name='temp'),
"NB": NBMatcher(name='temp'),
"RF": RFMatcher(name='temp'),
"SVM": SVMMatcher(name='temp')
}
for m_name, matcher in six.iteritems(matchers1):
self.assertEqual(isinstance(matcher.name, six.string_types), True)
for m_name, matcher in six.iteritems(matchers2):
self.assertEqual(matcher.name, 'temp')
def test_vis_debug_matcher_rf_label_col_wi_sp_name(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
labels = [0] * 7
labels.extend([1] * 8)
C['_predicted'] = labels
feature_table = get_features_for_matching(A, B)
feature_vectors = extract_feature_vecs(C, feature_table=feature_table,
attrs_after='_predicted')
rf = RFMatcher()
train_test = mu.train_test_split(feature_vectors)
train = train_test['train']
test = train_test['test']
_vis_debug_rf(rf, train, test,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID'],
target_attr='_predicted', show_window=False)
def test_vis_debug_matcher_rf_ex_attrs_notin_test(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
labels = [0] * 7
labels.extend([1] * 8)
C['labels'] = labels
feature_table = get_features_for_matching(A, B)
feature_vectors = extract_feature_vecs(C, feature_table=feature_table,
attrs_after='labels')
rf = RFMatcher()
train_test = mu.train_test_split(feature_vectors)
train = train_test['train']
test = train_test['test']
test.drop('_id', inplace=True, axis=1)
_vis_debug_rf(rf, train, test,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels', show_window=False)
def test_vis_debug_matcher_rf_invalid_tar_attr(self):
_vis_debug_rf(RFMatcher(), pd.DataFrame(), pd.DataFrame(),
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr=None, show_window=False)
