def test_split(self):
data = ListOfDicts({
"x": x,
"y": y
} for x, y in zip(
[1, 2, 2, 3, 3, 3],
[1, 1, 1, 1, 1, 2],
))
rows = data.split("x", "y")
assert rows == [[0], [1, 2], [3, 4], [5]]
def test_read_csv_types(self):
path = str(test.get_data_path("vehicles.csv"))
types = {"hwy": int, "cty": int}
data = ListOfDicts.read_csv(path, types=types)
assert isinstance(data[0].hwy, int)
assert isinstance(data[0].cty, int)
assert isinstance(data[100].hwy, int)
assert isinstance(data[100].cty, int)
def test_read_json_types(self):
path = str(test.get_data_path("downloads.json"))
# datetime.date.fromisoformat requires Python >= 3.7.
date = lambda x: datetime.date(*map(int, x.split("-")))
types = {"date": date, "downloads": int}
data = ListOfDicts.read_json(path, types=types)
assert isinstance(data[0].date, datetime.date)
assert isinstance(data[0].downloads, int)
assert isinstance(data[100].date, datetime.date)
assert isinstance(data[100].downloads, int)
def to_list_of_dicts(self):
"""
Return data frame converted to a :class:`.ListOfDicts`.
>>> data = di.read_csv("data/listings.csv")
>>> data.to_list_of_dicts()
"""
from dataiter import ListOfDicts
data = [{} for i in range(self.nrow)]
for colname in self.colnames:
for i, value in enumerate(self[colname].tolist()):
data[i][colname] = value
return ListOfDicts(data)
def test_write_pickle(self):
orig = test.list_of_dicts("downloads.json")
handle, path = tempfile.mkstemp(".pkl")
orig.write_pickle(path)
data = ListOfDicts.read_pickle(path)
assert data == orig
def read_json(path, *, encoding="utf-8", keys=[], types={}, **kwargs):
return ListOfDicts.read_json(path,
encoding=encoding,
keys=keys,
types=types,
**kwargs)
def test_to_json(self):
orig = test.list_of_dicts("downloads.json")
text = orig.to_json()
data = ListOfDicts.from_json(text)
assert data == orig
def test_write_csv(self):
orig = test.list_of_dicts("vehicles.csv")
handle, path = tempfile.mkstemp(".csv")
orig.write_csv(path)
data = ListOfDicts.read_csv(path)
assert data == orig
def test___init___empty(self):
data = ListOfDicts()
assert len(data) == 0
def test_read_csv_keys(self):
path = str(test.get_data_path("vehicles.csv"))
data = ListOfDicts.read_csv(path, keys=["make", "model"])
assert list(data[0].keys()) == ["make", "model"]
assert list(data[100].keys()) == ["make", "model"]
def test___init__(self):
item = dict(a=1, b=2, c=3)
data = ListOfDicts([item])
assert len(data) == 1
assert data[0] == item
assert data[0] is not item
def test_read_pickle_path(self):
orig = test.list_of_dicts("downloads.json")
handle, path = tempfile.mkstemp(".pkl")
orig.write_pickle(path)
ListOfDicts.read_pickle(Path(path))
def test_read_csv(self):
path = str(test.get_data_path("vehicles.csv"))
data = ListOfDicts.read_csv(path)
assert len(data) == 33442
assert all(len(x) == 12 for x in data)
def test_read_json_path(self):
ListOfDicts.read_csv(test.get_data_path("vehicles.json"))
def test_read_json_keys(self):
path = str(test.get_data_path("downloads.json"))
data = ListOfDicts.read_json(path, keys=["date", "downloads"])
assert list(data[0].keys()) == ["date", "downloads"]
assert list(data[100].keys()) == ["date", "downloads"]
def test_read_json(self):
path = str(test.get_data_path("downloads.json"))
data = ListOfDicts.read_json(path)
assert len(data) == 905
assert all(len(x) == 3 for x in data)
def test_read_csv_path(self):
ListOfDicts.read_csv(test.get_data_path("vehicles.csv"))
