def test_print_memory_use(self, mock_print):
data = test.data_frame("vehicles.csv")
data.print_memory_use()
mock_print.assert_called()
def test_ncol(self):
data = test.data_frame("vehicles.csv")
assert data.ncol == 12
def test_nrow(self):
data = test.data_frame("vehicles.csv")
assert data.nrow == 33442
def test_modify(self):
orig = test.data_frame("vehicles.csv")
data = orig.modify(test=1)
assert data.nrow == orig.nrow
assert data.ncol == orig.ncol + 1
assert np.all(data.test == 1)
def test_modify_function(self):
orig = test.data_frame("vehicles.csv")
data = orig.modify(test=lambda x: x.make)
assert data.nrow == orig.nrow
assert data.ncol == orig.ncol + 1
assert np.all(data.test == data.make)
def test_read_npz(self):
orig = test.data_frame("vehicles.csv")
handle, path = tempfile.mkstemp(".npz")
orig.write_npz(path)
data = DataFrame.read_npz(path)
assert data == orig
def test___setitem__(self):
data = test.data_frame("vehicles.csv")
assert "test" not in data
data["test"] = 1
assert "test" in data
def test_filter_out_given_colname_value_pairs(self):
data = test.data_frame("vehicles.csv")
data = data.filter_out(make="Saab")
assert data.nrow == 33018
assert np.all(data.make != "Saab")
assert np.sum(data.hwy) == 776930
def test_from_json(self):
orig = test.data_frame("downloads.json")
text = orig.to_json()
data = DataFrame.from_json(text)
assert data == orig
def test_deepcopy(self):
orig = test.data_frame("vehicles.csv")
data = orig.copy()
assert data == orig
assert data is not orig
def test_filter_given_colname_value_pairs(self):
data = test.data_frame("vehicles.csv")
data = data.filter(make="Saab")
assert data.nrow == 424
assert np.all(data.make == "Saab")
assert np.sum(data.hwy) == 10672
def test_columns(self):
data = test.data_frame("downloads.csv")
assert data.columns == [data.category, data.date, data.downloads]
def test_colnames_set(self):
data = test.data_frame("downloads.csv")
data.colnames = ["a", "b", "c"]
assert data.colnames == ["a", "b", "c"]
def test_colnames(self):
data = test.data_frame("downloads.csv")
assert data.colnames == ["category", "date", "downloads"]
def test_print_na_counts(self, mock_print):
data = test.data_frame("vehicles.csv")
data.print_na_counts()
mock_print.assert_called()
def test_head(self):
data = test.data_frame("vehicles.csv")
assert data.head(10) == data.slice(list(range(10)))
def test_print_na_counts_none(self, mock_print):
data = test.data_frame("vehicles.csv")
data = data.select("id", "make", "model")
data.print_na_counts()
mock_print.assert_not_called()
def test_map(self):
data = test.data_frame("vehicles.csv")
x = data.map(lambda x, i: x.hwy[i]**2)
y = [x**2 for x in data.hwy]
assert x == y
def test_read_npz_path(self):
orig = test.data_frame("vehicles.csv")
handle, path = tempfile.mkstemp(".npz")
orig.write_npz(path)
DataFrame.read_npz(Path(path))
def test___setattr__(self):
data = test.data_frame("vehicles.csv")
assert "test" not in data
data.test = 1
assert "test" in data