def test_ml_matcher_return_probs_true_predict_diff_colname(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
train.drop('ltable.id', axis=1, inplace=True)
train.drop('rtable.id', axis=1, inplace=True)
test.drop('ltable.id', axis=1, inplace=True)
test.drop('rtable.id', axis=1, inplace=True)
test.drop('gold', axis=1, inplace=True)
dt.fit(table=train, exclude_attrs='_id', target_attr='gold')
predictions = dt.predict(table=test, exclude_attrs='_id',
target_attr='predicted', probs_attr='probas',
inplace=False, append=True, return_probs=True)
self.assertNotEqual(id(predictions), id(test))
self.assertEqual(len(predictions), len(test))
self.assertEqual(set(list(test.columns)).issubset(list(predictions.columns)), True)
p_col = predictions.columns[len(predictions.columns)-2]
self.assertEqual(p_col, 'predicted')
r_col = predictions.columns[len(predictions.columns) - 1]
self.assertEqual(r_col, 'probas')
self.assertEqual(sum((predictions[r_col] >= 0.0) & (predictions[r_col] <= 1.0)),
len(predictions))
def test_ml_matcher_inplace_false_predict(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
train.drop('ltable.id', axis=1, inplace=True)
train.drop('rtable.id', axis=1, inplace=True)
test.drop('ltable.id', axis=1, inplace=True)
test.drop('rtable.id', axis=1, inplace=True)
test.drop('gold', axis=1, inplace=True)
dt.fit(table=train, exclude_attrs='_id', target_attr='gold')
predictions = dt.predict(table=test,
exclude_attrs='_id',
target_attr='predicted',
inplace=False,
append=True)
self.assertNotEqual(id(predictions), id(test))
self.assertEqual(len(predictions), len(test))
self.assertEqual(
set(list(test.columns)).issubset(list(predictions.columns)), True)
p_col = predictions.columns[len(predictions.columns) - 1]
self.assertEqual(p_col, 'predicted')
def test_ml_matcher_invalid_input_combn_fit(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
dt.fit(x=train, table=train)
def test_ml_matcher_invalid_input_combn_fit(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
dt.fit(x=train, table=train)
def test_ml_matcher_invalid_df_predict(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
dt.fit(table=train, exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'], target_attr='gold')
_ = dt.predict(table="", exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='predicted',
append=True)
def test_ml_matcher_target_attr_not_present_fit(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
train.drop('ltable.id', axis=1, inplace=True)
train.drop('rtable.id', axis=1, inplace=True)
test.drop('ltable.id', axis=1, inplace=True)
test.drop('rtable.id', axis=1, inplace=True)
dt.fit(table=train, exclude_attrs='_id', target_attr='gold1')
def test_ml_matcher_target_attr_not_present_fit(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
train.drop('ltable.id', axis=1, inplace=True)
train.drop('rtable.id', axis=1, inplace=True)
test.drop('ltable.id', axis=1, inplace=True)
test.drop('rtable.id', axis=1, inplace=True)
dt.fit(table=train, exclude_attrs='_id', target_attr='gold1')
def test_ml_matcher_invalid_df_predict(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
dt.fit(table=train,
exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='gold')
_ = dt.predict(table="",
exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='predicted',
append=True)
def test_select_matcher_invalid_no_display_drill_down(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
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'],
metrics_to_display=['precision'],
target_attr='gold',
k=7)
result_df_p = result['drill_down_cv_stats']['recall']
def test_select_matcher_valid_cv_stats_3(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
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'],
metric_to_select_matcher='recall',
metrics_to_display='recall',
target_attr='gold',
k=7)
header = ['Matcher', 'Average recall']
result_df = result['cv_stats']
result_df_r = result['drill_down_cv_stats']['recall']
self.assertEqual(
set(header) == set(list(result_df.columns[[0, 1]])), True)
d = result_df.set_index('Matcher')
p_max = d.loc[result['selected_matcher'].name, 'Average recall']
a_max = np.max(result_df_r['Mean score'])
self.assertEqual(p_max, a_max)
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()
# xgmatcher = XGBoostMatcher()
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['drill_down_cv_stats']['precision']
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.loc[result['selected_matcher'].name, 'Mean score']
a_max = pd.np.max(d['Mean score'])
self.assertEqual(p_max, a_max)
def test_ml_matcher_valid_1(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
dt.fit(table=train, exclude_attrs=['ltable.id', 'rtable.id', '_id'], target_attr='gold')
predictions = dt.predict(table=test, exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='predicted',
append=True)
self.assertEqual(len(predictions), len(test))
self.assertEqual(set(list(predictions.columns)).issubset(list(test.columns)), True)
p_col = predictions.columns[len(predictions.columns)-1]
self.assertEqual(p_col, 'predicted')
def test_select_matcher_valid_multiple_metrics(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
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_p = result['drill_down_cv_stats']['precision']
result_df_f = result['drill_down_cv_stats']['f1']
result_df_r = result['drill_down_cv_stats']['recall']
# Check header of precision dataframe
self.assertEqual(set(header) == set(list(result_df_p.columns[[0, 1, 2]])), True)
self.assertEqual('Mean score', result_df_p.columns[len(result_df_p.columns) - 1])
# Check header of f1 dataframe
self.assertEqual(set(header) == set(list(result_df_f.columns[[0, 1, 2]])), True)
self.assertEqual('Mean score', result_df_f.columns[len(result_df_f.columns) - 1])
# Check header of recall dataframe
self.assertEqual(set(header) == set(list(result_df_r.columns[[0, 1, 2]])), True)
self.assertEqual('Mean score', result_df_p.columns[len(result_df_r.columns) - 1])
d = result_df_p.set_index('Name')
p_max = d.loc[result['selected_matcher'].name, 'Mean score']
a_max = pd.np.max(d['Mean score'])
self.assertEqual(p_max, a_max)
def test_select_matcher_valid_2(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)
header = ['Name', 'Matcher', 'Num folds']
result_df = result['drill_down_cv_stats']['precision']
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.loc[result['selected_matcher'].name, 'Mean score']
a_max = pd.np.max(d['Mean score'])
self.assertEqual(p_max, a_max)
def test_vis_debug_matcher_dt_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')
dt = DTMatcher()
train_test = mu.split_train_test(feature_vectors)
train = train_test['train']
test = train_test['test']
_vis_debug_dt(
dt,
train,
test,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels',
show_window=False)
def test_visualize_tree_invalid_df(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')
dt = DTMatcher()
dt.fit(table=feature_vectors, exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels')
visualize_tree(dt.clf, feature_vectors.columns, exclude_attrs=['_id', 'ltable_ID',
'rtable_ID', 'labels'])
def test_select_matcher_target_attr_not_series(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), 'gold'
])
X = feature_vectors[l]
Y = feature_vectors[['gold']]
result = select_matcher(matchers, x=X, y=Y)
def test_debug_dt_matcher_valid(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')
dt = DTMatcher()
dt.fit(table=feature_vectors, exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels')
debug_decisiontree_matcher(dt, A.ix[1], B.ix[2], feature_table=feature_table,
table_columns=feature_vectors.columns,
exclude_attrs=['ltable_ID', 'rtable_ID', '_id', 'labels'])
def test_vis_debug_matcher_dt_invalid_tar_attr(self):
_vis_debug_dt(
DTMatcher(),
pd.DataFrame(),
pd.DataFrame(),
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr=None,
show_window=False)
def test_ml_matcher_valid_2(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
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 = train[l]
Y = train['gold']
dt.fit(x=X, y=Y)
predictions = dt.predict(test[l])
self.assertEqual(len(predictions), len(test))
def test_ml_matcher_append_false_predict(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
train.drop('ltable.id', axis=1, inplace=True)
train.drop('rtable.id', axis=1, inplace=True)
test.drop('ltable.id', axis=1, inplace=True)
test.drop('rtable.id', axis=1, inplace=True)
test.drop('gold', axis=1, inplace=True)
dt.fit(table=train, exclude_attrs='_id', target_attr='gold')
predictions = dt.predict(table=test, exclude_attrs='_id',
target_attr='predicted',
append=False)
self.assertEqual(len(predictions), len(test))
def test_ml_matcher_valid_with_id_in_y(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
col_list = list(feature_vectors.columns)
l = list_diff(col_list, [
cm.get_fk_ltable(feature_vectors),
cm.get_fk_rtable(feature_vectors), 'gold'
])
X = train[l]
Y = train[['_id', 'gold']]
dt.fit(x=X, y=Y)
predictions = dt.predict(test[l])
self.assertEqual(len(predictions), len(test))
def test_vis_tuple_debug_dt_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')
dt = DTMatcher()
dt.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_dt_matcher(dt.clf, s1,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'])
def test_visualize_tree_invalid_df(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')
dt = DTMatcher()
dt.fit(table=feature_vectors,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels')
visualize_tree(
dt.clf,
feature_vectors.columns,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'])
def test_ml_matcher_ex_attrs_not_list(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
train.drop('ltable.id', axis=1, inplace=True)
train.drop('rtable.id', axis=1, inplace=True)
test.drop('ltable.id', axis=1, inplace=True)
test.drop('rtable.id', axis=1, inplace=True)
dt.fit(table=train, exclude_attrs='_id', target_attr='gold')
predictions = dt.predict(table=test, exclude_attrs=['_id', 'gold'],
target_attr='predicted',
append=True)
self.assertEqual(len(predictions), len(test))
l = len(set(list(predictions.columns)).difference(list(test.columns)))
self.assertEqual(l, 0)
p_col = predictions.columns[len(predictions.columns)-1]
self.assertEqual(p_col, 'predicted')
def test_ml_matcher_target_attr_present_in_ex_attrs(self):
A = read_csv_metadata(fpath_a, key='id')
B = read_csv_metadata(fpath_b, key='id')
feature_vectors = read_csv_metadata(fpath_f, ltable=A, rtable=B)
train_test = mu.split_train_test(feature_vectors)
train, test = train_test['train'], train_test['test']
dt = DTMatcher(name='DecisionTree')
dt.fit(table=train,
exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='gold')
predictions = dt.predict(
table=test,
exclude_attrs=['ltable.id', 'rtable.id', '_id', 'gold'],
target_attr='predicted',
append=True)
self.assertEqual(len(predictions), len(test))
l = len(set(list(predictions.columns)).difference(list(test.columns)))
self.assertEqual(l, 0)
p_col = predictions.columns[len(predictions.columns) - 1]
self.assertEqual(p_col, 'predicted')
def test_vis_tuple_debug_dt_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')
dt = DTMatcher()
dt.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_dt_matcher(
dt, s1, exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'])
def test_debug_dt_matcher_valid(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')
dt = DTMatcher()
dt.fit(table=feature_vectors,
exclude_attrs=['_id', 'ltable_ID', 'rtable_ID', 'labels'],
target_attr='labels')
debug_decisiontree_matcher(
dt,
A.ix[1],
B.ix[2],
feature_table=feature_table,
table_columns=feature_vectors.columns,
exclude_attrs=['ltable_ID', 'rtable_ID', '_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_select_matcher_invalid_metric_to_select_matcher(self):
A = read_csv_metadata(path_a, key='id')
B = read_csv_metadata(path_b, key='id')
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'],
metric_to_select_matcher='test',
target_attr='gold', k=7)
def test_ml_matcher_set_name(self):
dt = DTMatcher()
dt.set_name('Decision Tree')
self.assertEqual(dt.get_name(), 'Decision Tree')
def test_ml_matcher_invalid_df_1(self):
dt = DTMatcher(name='DecisionTree')
dt.fit(x="", y="")
def test_ml_matcher_invalid_df(self):
dt = DTMatcher(name='DecisionTree')
dt.fit(table="", exclude_attrs=['ltable.id', 'rtable.id', '_id'], target_attr='gold')
def test_ml_matcher_invalid_df(self):
dt = DTMatcher(name='DecisionTree')
dt.fit(table="",
exclude_attrs=['ltable.id', 'rtable.id', '_id'],
target_attr='gold')
def test_ml_matcher_set_name(self):
dt = DTMatcher()
dt.set_name('Decision Tree')
self.assertEqual(dt.get_name(), 'Decision Tree')
def test_ml_matcher_invalid_df_1(self):
dt = DTMatcher(name='DecisionTree')
dt.fit(x="", y="")
def test_ml_invalid_predict_sign(self):
dt = DTMatcher(name='DecisionTree')
dt.predict()
def test_ml_invalid_predict_sign(self):
dt = DTMatcher(name='DecisionTree')
dt.predict()
