def test_set_key_valid():
df = mg.read_csv_metadata(path_for_A)
mg.set_key(df, 'ID')
assert_equal(mg.get_key(df), 'ID')
mg.del_property(df, 'key')
assert_equal(len(mg.get_all_properties(df)), 0)
def test_del_property_valid():
df = mg.read_csv_metadata(path_for_A)
mg.set_key(df, 'ID')
assert_equal(mg.get_key(df), 'ID')
mg.del_property(df, 'key')
assert_equal(mg.is_property_present_for_df(df, 'key'), False)
mg.del_catalog()
def setup(self):
p = mg.get_install_path()
path_for_A = os.sep.join(
[p, 'datasets', 'example_datasets', 'bikes', 'A.csv'])
path_for_B = os.sep.join(
[p, 'datasets', 'example_datasets', 'bikes', 'B.csv'])
l_key = 'id'
r_key = 'id'
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, l_key)
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, r_key)
l_block_attr_1 = 'city_posted'
r_block_attr_1 = 'city_posted'
l_output_attrs = [
'bike_name', 'city_posted', 'km_driven', 'price', 'color',
'model_year'
]
r_output_attrs = [
'bike_name', 'city_posted', 'km_driven', 'price', 'color',
'model_year'
]
self.ab = mg.AttrEquivalenceBlocker()
self.C = self.ab.block_tables(self.A,
self.B,
l_block_attr_1,
r_block_attr_1,
l_output_attrs,
r_output_attrs,
verbose=False)
self.l_block_attr = 'model_year'
self.r_block_attr = 'model_year'
def test_get_catalog_valid():
df = mg.read_csv_metadata(path_for_A)
mg.set_key(df, 'ID')
assert_equal(len(mg.get_all_properties(df)), 1)
c = mg.get_catalog()
assert_equal(len(c), 1)
mg.del_catalog()
def setup(self):
path_for_A = os.sep.join([datasets_path, 'electronics', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'electronics', 'B.csv'])
self.l_block_attr = 'Brand'
self.r_block_attr = 'Brand'
self.l_output_attrs = ['Brand', 'Amazon_Price']
self.r_output_attrs = ['Brand', 'Price']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'restaurants', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'restaurants', 'B.csv'])
self.l_block_attr = 'PHONENUMBER'
self.r_block_attr = 'PHONENUMBER'
self.l_output_attrs = ['NAME', 'PHONENUMBER', 'ADDRESS']
self.r_output_attrs = ['NAME', 'PHONENUMBER', 'ADDRESS']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'anime', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'anime', 'B.csv'])
self.l_block_attr = 'Year'
self.r_block_attr = 'Year'
self.l_output_attrs = ['Title', 'Year', 'Episodes']
self.r_output_attrs = ['Title', 'Year', 'Episodes']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'citations', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'citations', 'B.csv'])
self.l_block_attr = 'year'
self.r_block_attr = 'year'
self.l_output_attrs = ['title', 'author', 'year', 'ENTRYTYPE']
self.r_output_attrs = ['title', 'author', 'year', 'ENTRYTYPE']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'anime', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'anime', 'B.csv'])
self.l_block_attr = 'Year'
self.r_block_attr = 'Year'
self.l_output_attrs = ['Title', 'Year', 'Episodes']
self.r_output_attrs = ['Title', 'Year', 'Episodes']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'electronics', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'electronics', 'B.csv'])
self.l_block_attr = 'Brand'
self.r_block_attr = 'Brand'
self.l_output_attrs = ['Brand', 'Amazon_Price']
self.r_output_attrs = ['Brand', 'Price']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'citations', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'citations', 'B.csv'])
self.l_block_attr = 'year'
self.r_block_attr = 'year'
self.l_output_attrs = ['title', 'author', 'year', 'ENTRYTYPE']
self.r_output_attrs = ['title', 'author', 'year', 'ENTRYTYPE']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'restaurants', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'restaurants', 'B.csv'])
self.l_block_attr = 'PHONENUMBER'
self.r_block_attr = 'PHONENUMBER'
self.l_output_attrs = ['NAME', 'PHONENUMBER', 'ADDRESS']
self.r_output_attrs = ['NAME', 'PHONENUMBER', 'ADDRESS']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'anime', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'anime', 'B.csv'])
A = mg.read_csv_metadata(path_for_A)
mg.set_key(A, 'ID')
B = mg.read_csv_metadata(path_for_B)
mg.set_key(B, 'ID')
self.C = ab.block_tables(A, B, 'Year', 'Year',
['Title', 'Year', 'Episodes'],
['Title', 'Year', 'Episodes'])
self.l_block_attr = 'Episodes'
self.r_block_attr = 'Episodes'
def setup(self):
path_for_A = os.sep.join([datasets_path, 'books', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'books', 'B.csv'])
A = mg.read_csv_metadata(path_for_A)
mg.set_key(A, 'ID')
B = mg.read_csv_metadata(path_for_B)
mg.set_key(B, 'ID')
self.C = ab.block_tables(A, B, 'Author', 'Author',
['Title', 'Author', 'ISBN13', 'Publisher'],
['Title', 'Author', 'ISBN13', 'Publisher'])
self.l_block_attr = 'ISBN13'
self.r_block_attr = 'ISBN13'
def setup(self):
path_for_A = os.sep.join([datasets_path, 'books', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'books', 'B.csv'])
A = mg.read_csv_metadata(path_for_A)
mg.set_key(A, 'ID')
B = mg.read_csv_metadata(path_for_B)
mg.set_key(B, 'ID')
self.C = ab.block_tables(A, B, 'Author', 'Author',
['Title', 'Author', 'ISBN13', 'Publisher'],
['Title', 'Author', 'ISBN13', 'Publisher'])
self.l_block_attr = 'ISBN13'
self.r_block_attr = 'ISBN13'
def setup(self):
path_for_A = os.sep.join([datasets_path, 'anime', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'anime', 'B.csv'])
A = mg.read_csv_metadata(path_for_A)
mg.set_key(A, 'ID')
B = mg.read_csv_metadata(path_for_B)
mg.set_key(B, 'ID')
self.C = ab.block_tables(A, B, 'Year', 'Year',
['Title', 'Year', 'Episodes'],
['Title', 'Year', 'Episodes'])
self.l_block_attr = 'Episodes'
self.r_block_attr = 'Episodes'
def setup(self):
path_for_A = os.sep.join([datasets_path, 'books', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'books', 'B.csv'])
self.l_block_attr = 'Author'
self.r_block_attr = 'Author'
self.l_output_attrs = ['Title', 'Author', 'ISBN13', 'Publisher',
'Publication_Date']
self.r_output_attrs = ['Title', 'Author', 'ISBN13', 'Publisher',
'Publication_Date']
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
path_for_A = os.sep.join([datasets_path, 'books', 'A.csv'])
path_for_B = os.sep.join([datasets_path, 'books', 'B.csv'])
self.l_block_attr = 'Author'
self.r_block_attr = 'Author'
self.l_output_attrs = [
'Title', 'Author', 'ISBN13', 'Publisher', 'Publication_Date'
]
self.r_output_attrs = [
'Title', 'Author', 'ISBN13', 'Publisher', 'Publication_Date'
]
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, 'ID')
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, 'ID')
def setup(self):
p = mg.get_install_path()
path_for_A = os.sep.join([p, 'datasets', 'example_datasets', 'bikes', 'A.csv'])
path_for_B = os.sep.join([p, 'datasets', 'example_datasets', 'bikes', 'B.csv'])
l_key = 'id'
r_key = 'id'
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, l_key)
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, r_key)
self.l_block_attr = 'city_posted'
self.r_block_attr = 'city_posted'
self.l_output_attrs = ['bike_name', 'city_posted', 'km_driven', 'price',
'color', 'model_year']
self.r_output_attrs = ['bike_name', 'city_posted', 'km_driven', 'price',
'color', 'model_year']
self.ab = mg.AttrEquivalenceBlocker()
def setUp(self):
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, l_key)
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, r_key)
self.ab = mg.AttrEquivalenceBlocker()
def setUp(self):
self.A = mg.read_csv_metadata(path_for_A)
mg.set_key(self.A, l_key)
self.B = mg.read_csv_metadata(path_for_B)
mg.set_key(self.B, r_key)
self.ab = mg.AttrEquivalenceBlocker()
def test_set_key_invalid_mv():
df = mg.read_csv_metadata(path_for_A_dup)
status = mg.set_key(df, 'ID')
assert_equal(status, False)
# # mg.set_key(A, 'ID') # # # mg.set_metadata(A, 'key', 'ID') # # print mg.get_metadata(A, 'key') # # print mg.get_key(A) # # print mg.is_dfinfo_present(B) # # mg.set_metadata(B, 'key', 'ID') # # print mg.get_metadata(B, 'key') # mg.set_key(B, 'ID') # # print mg.is_dfinfo_present(B) # print mg.is_property_present_for_df(B, 'ltable') # # print mg.get_catalog_len() # # mg.del_property(B, 'key') # print mg.is_property_present_for_df(B, 'ID') # # # mg.del_all_properties(A) # print mg.get_catalog_len() A = mg.read_csv_metadata(path_for_A) print A print mg._catalog mg.set_key(A, 'ID') print 'xyx'