def test_build_table_download_file_handle_list__repeated_file_handles():
syn = synapseclient.client.Synapse(debug=True, skip_checks=True)
#patch the cache so we don't look there in case FileHandle ids actually exist there
patch.object(syn.cache, "get", return_value=None)
cols = [
Column(name='Name', columnType='STRING', maximumSize=50),
Column(name='filehandle', columnType='FILEHANDLEID')
]
schema = Schema(name='FileHandleTest', columns=cols, parent='syn420')
#using some large filehandle numbers so i don
data = [["ayy lmao", 5318008], ["large numberino", 0x5f3759df],
["repeated file handle", 5318008],
["repeated file handle also", 0x5f3759df]]
## need columns to do cast_values w/o storing
table = Table(schema,
data,
headers=[SelectColumn.from_column(col) for col in cols])
file_handle_associations, file_handle_to_path_map = syn._build_table_download_file_handle_list(
table, ['filehandle'])
#verify only 2 file_handles are added (repeats were ignored)
assert_equals(2, len(file_handle_associations))
assert_equals(0,
len(file_handle_to_path_map)) #might as well check anyways
def test_list_of_rows_table():
data = [["John Coltrane", 1926, 8.65, False],
["Miles Davis", 1926, 9.87, False],
["Bill Evans", 1929, 7.65, False],
["Paul Chambers", 1935, 5.14, False],
["Jimmy Cobb", 1929, 5.78, True],
["Scott LaFaro", 1936, 4.21, False],
["Sonny Rollins", 1930, 8.99, True],
["Kenny Burrel", 1931, 4.37, True]]
cols = [Column(id='1', name='Name', columnType='STRING'),
Column(id='2', name='Born', columnType='INTEGER'),
Column(id='3', name='Hipness', columnType='DOUBLE'),
Column(id='4', name='Living', columnType='BOOLEAN')]
schema1 = Schema(name='Jazz Guys', columns=cols, id="syn1000002", parent="syn1000001")
# need columns to do cast_values w/o storing
table = Table(schema1, data, headers=[SelectColumn.from_column(col) for col in cols])
for table_row, expected_row in zip(table, data):
assert table_row == expected_row
rowset = table.asRowSet()
for rowset_row, expected_row in zip(rowset.rows, data):
assert rowset_row['values'] == expected_row
table.columns = cols
df = table.asDataFrame()
assert list(df['Name']) == [r[0] for r in data]
def test_pandas_to_table():
pd = _try_import_pandas('test_pandas_to_table')
df = pd.DataFrame(dict(a=[1, 2, 3], b=["c", "d", "e"]))
schema = Schema(name="Baz",
parent="syn12345",
columns=as_table_columns(df))
print("\n", df, "\n\n")
## A dataframe with no row id and version
table = Table(schema, df)
for i, row in enumerate(table):
print(row)
assert row[0] == (i + 1)
assert row[1] == ["c", "d", "e"][i]
assert len(table) == 3
## If includeRowIdAndRowVersion=True, include empty row id an versions
## ROW_ID,ROW_VERSION,a,b
## ,,1,c
## ,,2,d
## ,,3,e
table = Table(schema, df, includeRowIdAndRowVersion=True)
for i, row in enumerate(table):
print(row)
assert row[0] is None
assert row[1] is None
assert row[2] == (i + 1)
## A dataframe with no row id and version
df = pd.DataFrame(index=["1_7", "2_7", "3_8"],
data=dict(a=[100, 200, 300], b=["c", "d", "e"]))
print("\n", df, "\n\n")
table = Table(schema, df)
for i, row in enumerate(table):
print(row)
assert row[0] == ["1", "2", "3"][i]
assert row[1] == ["7", "7", "8"][i]
assert row[2] == (i + 1) * 100
assert row[3] == ["c", "d", "e"][i]
## A dataframe with row id and version in columns
df = pd.DataFrame(
dict(ROW_ID=["0", "1", "2"],
ROW_VERSION=["8", "9", "9"],
a=[100, 200, 300],
b=["c", "d", "e"]))
print("\n", df, "\n\n")
table = Table(schema, df)
for i, row in enumerate(table):
print(row)
assert row[0] == ["0", "1", "2"][i]
assert row[1] == ["8", "9", "9"][i]
assert row[2] == (i + 1) * 100
assert row[3] == ["c", "d", "e"][i]
def test_RowSetTable_len():
schema = Schema(parentId="syn123",
id='syn456',
columns=[Column(name='column_name', id='123')])
rowset = RowSet(schema=schema,
rows=[Row(['first row']),
Row(['second row'])])
row_set_table = RowSetTable(schema, rowset)
assert_equals(2, len(row_set_table))
def test_dict_to_table():
d = dict(a=[1, 2, 3], b=["c", "d", "e"])
df = pd.DataFrame(d)
schema = Schema(name="Baz", parent="syn12345", columns=as_table_columns(df))
with patch.object(CsvFileTable, "from_data_frame") as mocked_from_data_frame:
Table(schema, d)
# call_agrs is a tuple with values and name
agrs_list = mocked_from_data_frame.call_args[0]
# getting the second argument
df_agr = agrs_list[1]
assert df_agr.equals(df)
def test_pandas_to_table():
df = pd.DataFrame(dict(a=[1, 2, 3], b=["c", "d", "e"]))
schema = Schema(name="Baz",
parent="syn12345",
columns=as_table_columns(df))
# A dataframe with no row id and version
table = Table(schema, df)
for i, row in enumerate(table):
assert_equals(row[0], (i + 1))
assert_equals(row[1], ["c", "d", "e"][i])
assert_equals(len(table), 3)
# If includeRowIdAndRowVersion=True, include empty row id an versions
# ROW_ID,ROW_VERSION,a,b
# ,,1,c
# ,,2,d
# ,,3,e
table = Table(schema, df, includeRowIdAndRowVersion=True)
for i, row in enumerate(table):
assert_is_none(row[0])
assert_is_none(row[1])
assert_equals(row[2], (i + 1))
# A dataframe with no row id and version
df = pd.DataFrame(index=["1_7", "2_7", "3_8"],
data=dict(a=[100, 200, 300], b=["c", "d", "e"]))
table = Table(schema, df)
for i, row in enumerate(table):
assert_equals(row[0], ["1", "2", "3"][i])
assert_equals(row[1], ["7", "7", "8"][i])
assert_equals(row[2], (i + 1) * 100)
assert_equals(row[3], ["c", "d", "e"][i])
# A dataframe with row id and version in columns
df = pd.DataFrame(
dict(ROW_ID=["0", "1", "2"],
ROW_VERSION=["8", "9", "9"],
a=[100, 200, 300],
b=["c", "d", "e"]))
table = Table(schema, df)
for i, row in enumerate(table):
assert_equals(row[0], ["0", "1", "2"][i])
assert_equals(row[1], ["8", "9", "9"][i])
assert_equals(row[2], (i + 1) * 100)
assert_equals(row[3], ["c", "d", "e"][i])
def test_list_of_rows_table():
data = [["John Coltrane", 1926, 8.65, False],
["Miles Davis", 1926, 9.87, False],
["Bill Evans", 1929, 7.65, False],
["Paul Chambers", 1935, 5.14, False],
["Jimmy Cobb", 1929, 5.78, True],
["Scott LaFaro", 1936, 4.21, False],
["Sonny Rollins", 1930, 8.99, True],
["Kenny Burrel", 1931, 4.37, True]]
cols = []
cols.append(Column(id='1', name='Name', columnType='STRING'))
cols.append(Column(id='2', name='Born', columnType='INTEGER'))
cols.append(Column(id='3', name='Hipness', columnType='DOUBLE'))
cols.append(Column(id='4', name='Living', columnType='BOOLEAN'))
schema1 = Schema(name='Jazz Guys',
columns=cols,
id="syn1000002",
parent="syn1000001")
## need columns to do cast_values w/o storing
table = Table(schema1,
data,
headers=[SelectColumn.from_column(col) for col in cols])
for table_row, expected_row in zip(table, data):
assert table_row == expected_row
rowset = table.asRowSet()
for rowset_row, expected_row in zip(rowset.rows, data):
assert rowset_row['values'] == expected_row
table.columns = cols
## test asDataFrame
try:
import pandas as pd
df = table.asDataFrame()
assert all(df['Name'] == [r[0] for r in data])
except ImportError as e1:
sys.stderr.write(
'Pandas is apparently not installed, skipping asDataFrame portion of test_list_of_rows_table.\n\n'
)
def test_RowSetTable():
row_set_json = {
'etag': 'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee',
'headers': [
{'columnType': 'STRING', 'id': '353', 'name': 'name'},
{'columnType': 'DOUBLE', 'id': '355', 'name': 'x'},
{'columnType': 'DOUBLE', 'id': '3020', 'name': 'y'},
{'columnType': 'INTEGER', 'id': '891', 'name': 'n'}],
'rows': [{
'rowId': 5,
'values': ['foo', '1.23', '2.2', '101'],
'versionNumber': 3},
{'rowId': 6,
'values': ['bar', '1.34', '2.4', '101'],
'versionNumber': 3},
{'rowId': 7,
'values': ['foo', '1.23', '2.2', '101'],
'versionNumber': 4},
{'rowId': 8,
'values': ['qux', '1.23', '2.2', '102'],
'versionNumber': 3}],
'tableId': 'syn2976298'}
row_set = RowSet.from_json(row_set_json)
assert row_set.etag == 'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee'
assert row_set.tableId == 'syn2976298'
assert len(row_set.headers) == 4
assert len(row_set.rows) == 4
schema = Schema(id="syn2976298", name="Bogus Schema", columns=[353, 355, 3020, 891], parent="syn1000001")
table = Table(schema, row_set)
assert table.etag == 'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee'
assert table.tableId == 'syn2976298'
assert len(table.headers) == 4
assert len(table.asRowSet().rows) == 4
df = table.asDataFrame()
assert df.shape == (4, 4)
assert list(df['name']) == ['foo', 'bar', 'foo', 'qux']
def test_schema():
schema = Schema(name='My Table', parent="syn1000001")
assert not schema.has_columns()
schema.addColumn(Column(id='1', name='Name', columnType='STRING'))
assert schema.has_columns()
assert schema.properties.columnIds == ['1']
schema.removeColumn('1')
assert not schema.has_columns()
assert schema.properties.columnIds == []
schema = Schema(name='Another Table', parent="syn1000001")
schema.addColumns([
Column(name='Name', columnType='STRING'),
Column(name='Born', columnType='INTEGER'),
Column(name='Hipness', columnType='DOUBLE'),
Column(name='Living', columnType='BOOLEAN')])
assert schema.has_columns()
assert len(schema.columns_to_store) == 4
assert Column(name='Name', columnType='STRING') in schema.columns_to_store
assert Column(name='Born', columnType='INTEGER') in schema.columns_to_store
assert Column(name='Hipness', columnType='DOUBLE') in schema.columns_to_store
assert Column(name='Living', columnType='BOOLEAN') in schema.columns_to_store
schema.removeColumn(Column(name='Living', columnType='BOOLEAN'))
assert schema.has_columns()
assert len(schema.columns_to_store) == 3
assert Column(name='Living', columnType='BOOLEAN') not in schema.columns_to_store
assert Column(name='Hipness', columnType='DOUBLE') in schema.columns_to_store
def test_schema():
schema = Schema(name='My Table', parent="syn1000001")
assert not schema.has_columns()
schema.addColumn(Column(id='1', name='Name', columnType='STRING'))
assert schema.has_columns()
assert schema.properties.columnIds == ['1']
schema.removeColumn('1')
assert not schema.has_columns()
assert schema.properties.columnIds == []
schema = Schema(name='Another Table', parent="syn1000001")
schema.addColumns([
Column(name='Name', columnType='STRING'),
Column(name='Born', columnType='INTEGER'),
Column(name='Hipness', columnType='DOUBLE'),
Column(name='Living', columnType='BOOLEAN')
])
assert schema.has_columns()
assert len(schema.columns_to_store) == 4
assert Column(name='Name', columnType='STRING') in schema.columns_to_store
assert Column(name='Born', columnType='INTEGER') in schema.columns_to_store
assert Column(name='Hipness',
columnType='DOUBLE') in schema.columns_to_store
assert Column(name='Living',
columnType='BOOLEAN') in schema.columns_to_store
schema.removeColumn(Column(name='Living', columnType='BOOLEAN'))
assert schema.has_columns()
assert len(schema.columns_to_store) == 3
assert Column(name='Living',
columnType='BOOLEAN') not in schema.columns_to_store
assert Column(name='Hipness',
columnType='DOUBLE') in schema.columns_to_store
def test_Schema__max_column_check():
table = Schema(name="someName", parent="idk")
table.addColumns(
Column(name="colNum%s" % i, columnType="STRING")
for i in range(synapseclient.table.MAX_NUM_TABLE_COLUMNS + 1))
assert_raises(ValueError, syn.store, table)
def test_csv_table():
## Maybe not truly a unit test, but here because it doesn't do
## network IO to synapse
data = [["1", "1", "John Coltrane", 1926, 8.65, False],
["2", "1", "Miles Davis", 1926, 9.87, False],
["3", "1", "Bill Evans", 1929, 7.65, False],
["4", "1", "Paul Chambers", 1935, 5.14, False],
["5", "1", "Jimmy Cobb", 1929, 5.78, True],
["6", "1", "Scott LaFaro", 1936, 4.21, False],
["7", "1", "Sonny Rollins", 1930, 8.99, True],
["8", "1", "Kenny Burrel", 1931, 4.37, True]]
filename = None
cols = []
cols.append(Column(id='1', name='Name', columnType='STRING'))
cols.append(Column(id='2', name='Born', columnType='INTEGER'))
cols.append(Column(id='3', name='Hipness', columnType='DOUBLE'))
cols.append(Column(id='4', name='Living', columnType='BOOLEAN'))
schema1 = Schema(id='syn1234',
name='Jazz Guys',
columns=cols,
parent="syn1000001")
#TODO: use StringIO.StringIO(data) rather than writing files
try:
## create CSV file
with tempfile.NamedTemporaryFile(delete=False) as temp:
filename = temp.name
with io.open(filename, mode='w', encoding="utf-8", newline='') as temp:
writer = csv.writer(temp,
quoting=csv.QUOTE_NONNUMERIC,
lineterminator=str(os.linesep))
headers = ['ROW_ID', 'ROW_VERSION'] + [col.name for col in cols]
writer.writerow(headers)
for row in data:
writer.writerow(row)
table = Table(schema1, filename)
assert isinstance(table, CsvFileTable)
## need to set column headers to read a CSV file
table.setColumnHeaders([
SelectColumn(name="ROW_ID", columnType="STRING"),
SelectColumn(name="ROW_VERSION", columnType="STRING")
] + [SelectColumn.from_column(col) for col in cols])
## test iterator
for table_row, expected_row in zip(table, data):
assert table_row == expected_row
## test asRowSet
rowset = table.asRowSet()
for rowset_row, expected_row in zip(rowset.rows, data):
assert rowset_row['values'] == expected_row[2:]
assert rowset_row['rowId'] == expected_row[0]
assert rowset_row['versionNumber'] == expected_row[1]
## test asDataFrame
try:
import pandas as pd
df = table.asDataFrame()
assert all(df['Name'] == [row[2] for row in data])
assert all(df['Born'] == [row[3] for row in data])
assert all(df['Living'] == [row[5] for row in data])
assert all(df.index == ['%s_%s' % tuple(row[0:2]) for row in data])
assert df.shape == (8, 4)
except ImportError as e1:
sys.stderr.write(
'Pandas is apparently not installed, skipping asDataFrame portion of test_csv_table.\n\n'
)
except Exception as ex1:
if filename:
try:
if os.path.isdir(filename):
shutil.rmtree(filename)
else:
os.remove(filename)
except Exception as ex:
print(ex)
raise
def test_RowSetTable():
row_set_json = {
'etag':
'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee',
'headers': [{
'columnType': 'STRING',
'id': '353',
'name': 'name'
}, {
'columnType': 'DOUBLE',
'id': '355',
'name': 'x'
}, {
'columnType': 'DOUBLE',
'id': '3020',
'name': 'y'
}, {
'columnType': 'INTEGER',
'id': '891',
'name': 'n'
}],
'rows': [{
'rowId': 5,
'values': ['foo', '1.23', '2.2', '101'],
'versionNumber': 3
}, {
'rowId': 6,
'values': ['bar', '1.34', '2.4', '101'],
'versionNumber': 3
}, {
'rowId': 7,
'values': ['foo', '1.23', '2.2', '101'],
'versionNumber': 4
}, {
'rowId': 8,
'values': ['qux', '1.23', '2.2', '102'],
'versionNumber': 3
}],
'tableId':
'syn2976298'
}
row_set = RowSet.from_json(row_set_json)
assert row_set.etag == 'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee'
assert row_set.tableId == 'syn2976298'
assert len(row_set.headers) == 4
assert len(row_set.rows) == 4
schema = Schema(id="syn2976298",
name="Bogus Schema",
columns=[353, 355, 3020, 891],
parent="syn1000001")
table = Table(schema, row_set)
assert table.etag == 'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee'
assert table.tableId == 'syn2976298'
assert len(table.headers) == 4
assert len(table.asRowSet().rows) == 4
try:
import pandas as pd
df = table.asDataFrame()
assert df.shape == (4, 4)
assert all(df['name'] == ['foo', 'bar', 'foo', 'qux'])
except ImportError as e1:
sys.stderr.write(
'Pandas is apparently not installed, skipping part of test_RowSetTable.\n\n'
)
def test_schema():
schema = Schema(name='My Table', parent="syn1000001")
assert_false(schema.has_columns())
schema.addColumn(Column(id='1', name='Name', columnType='STRING'))
assert_true(schema.has_columns())
assert_equals(schema.properties.columnIds, ['1'])
schema.removeColumn('1')
assert_false(schema.has_columns())
assert_equals(schema.properties.columnIds, [])
schema = Schema(name='Another Table', parent="syn1000001")
schema.addColumns([
Column(name='Name', columnType='STRING'),
Column(name='Born', columnType='INTEGER'),
Column(name='Hipness', columnType='DOUBLE'),
Column(name='Living', columnType='BOOLEAN')])
assert_true(schema.has_columns())
assert_equals(len(schema.columns_to_store), 4)
assert_in(Column(name='Name', columnType='STRING'), schema.columns_to_store)
assert_in(Column(name='Born', columnType='INTEGER'), schema.columns_to_store)
assert_in(Column(name='Hipness', columnType='DOUBLE'), schema.columns_to_store)
assert_in(Column(name='Living', columnType='BOOLEAN'), schema.columns_to_store)
schema.removeColumn(Column(name='Living', columnType='BOOLEAN'))
assert_true(schema.has_columns())
assert_equals(len(schema.columns_to_store), 3)
assert_not_in(Column(name='Living', columnType='BOOLEAN'), schema.columns_to_store)
assert_in(Column(name='Hipness', columnType='DOUBLE'), schema.columns_to_store)
def test_Schema__max_column_check():
table = Schema(name="someName", parent="idk")
table.addColumns(Column(name="colNum%s" % i, columnType="STRING")
for i in range(synapseclient.table.MAX_NUM_TABLE_COLUMNS + 1))
assert_raises(ValueError, syn.store, table)
def test_schema():
schema = Schema(name='My Table', parent="syn1000001")
assert_false(schema.has_columns())
schema.addColumn(Column(id='1', name='Name', columnType='STRING'))
assert_true(schema.has_columns())
assert_equals(schema.properties.columnIds, ['1'])
schema.removeColumn('1')
assert_false(schema.has_columns())
assert_equals(schema.properties.columnIds, [])
schema = Schema(name='Another Table', parent="syn1000001")
schema.addColumns([
Column(name='Name', columnType='STRING'),
Column(name='Born', columnType='INTEGER'),
Column(name='Hipness', columnType='DOUBLE'),
Column(name='Living', columnType='BOOLEAN')
])
assert_true(schema.has_columns())
assert_equals(len(schema.columns_to_store), 4)
assert_in(Column(name='Name', columnType='STRING'),
schema.columns_to_store)
assert_in(Column(name='Born', columnType='INTEGER'),
schema.columns_to_store)
assert_in(Column(name='Hipness', columnType='DOUBLE'),
schema.columns_to_store)
assert_in(Column(name='Living', columnType='BOOLEAN'),
schema.columns_to_store)
schema.removeColumn(Column(name='Living', columnType='BOOLEAN'))
assert_true(schema.has_columns())
assert_equals(len(schema.columns_to_store), 3)
assert_not_in(Column(name='Living', columnType='BOOLEAN'),
schema.columns_to_store)
assert_in(Column(name='Hipness', columnType='DOUBLE'),
schema.columns_to_store)
