def test_pandas_read_supports_read_csv_kwargs():
with filetext('Alice,1\nBob,2') as fn:
ds = datashape.dshape('var * {name: string, amount: int}')
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds, usecols=['name'])
assert isinstance(df, pd.DataFrame)
assert convert(list, df) == [('Alice',), ('Bob',)]
def test_pandas_read_supports_read_csv_kwargs():
with filetext("Alice,1\nBob,2") as fn:
ds = datashape.dshape("var * {name: string, amount: int}")
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds, usecols=["name"])
assert isinstance(df, pd.DataFrame)
assert convert(list, df) == [("Alice",), ("Bob",)]
def test_pandas_read_supports_missing_integers():
with filetext('Alice,1\nBob,') as fn:
ds = datashape.dshape('var * {name: string, val: ?int32}')
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert list(df.columns) == ['name', 'val']
assert df.dtypes['val'] == 'f4'
def test_pandas_read_supports_datetimes():
with filetext('Alice,2014-01-02\nBob,2014-01-03') as fn:
ds = datashape.dshape('var * {name: string, when: date}')
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert list(df.columns) == ['name', 'when']
assert df.dtypes['when'] == 'M8[ns]'
def test_pandas_read():
with filetext('Alice,1\nBob,2') as fn:
ds = datashape.dshape('var * {name: string, amount: int}')
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert convert(list, df) == [('Alice', 1), ('Bob', 2)]
assert list(df.columns) == ['name', 'amount']
def test_pandas_read_supports_gzip():
with filetext("Alice,1\nBob,2", open=gzip.open, mode="wt", extension=".csv.gz") as fn:
ds = datashape.dshape("var * {name: string, amount: int}")
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert convert(list, df) == [("Alice", 1), ("Bob", 2)]
assert list(df.columns) == ["name", "amount"]
def test_pandas_read_supports_missing_integers():
with filetext("Alice,1\nBob,") as fn:
ds = datashape.dshape("var * {name: string, val: ?int32}")
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert list(df.columns) == ["name", "val"]
assert df.dtypes["val"] == "f4"
def test_pandas_read_supports_datetimes():
with filetext("Alice,2014-01-02\nBob,2014-01-03") as fn:
ds = datashape.dshape("var * {name: string, when: date}")
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert list(df.columns) == ["name", "when"]
assert df.dtypes["when"] == "M8[ns]"
def test_pandas_read():
with filetext("Alice,1\nBob,2") as fn:
ds = datashape.dshape("var * {name: string, amount: int}")
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert convert(list, df) == [("Alice", 1), ("Bob", 2)]
assert list(df.columns) == ["name", "amount"]
def test_unused_datetime_columns():
ds = datashape.dshape('var * {val: string, when: datetime}')
with filetext("val,when\na,2000-01-01\nb,2000-02-02") as fn:
csv = CSV(fn, has_header=True)
assert convert(
list,
csv_to_dataframe(csv, usecols=['val'], squeeze=True,
dshape=ds)) == ['a', 'b']
def test_pandas_read_supports_gzip():
with filetext('Alice,1\nBob,2', open=gzip.open,
mode='wt', extension='.csv.gz') as fn:
ds = datashape.dshape('var * {name: string, amount: int}')
csv = CSV(fn)
df = csv_to_dataframe(csv, dshape=ds)
assert isinstance(df, pd.DataFrame)
assert convert(list, df) == [('Alice', 1), ('Bob', 2)]
assert list(df.columns) == ['name', 'amount']
def test_unused_datetime_columns():
ds = datashape.dshape('var * {val: string, when: datetime}')
with filetext("val,when\na,2000-01-01\nb,2000-02-02") as fn:
csv = CSV(fn, has_header=True)
assert convert(list, csv_to_dataframe(csv, usecols=['val'],
squeeze=True, dshape=ds)) == ['a', 'b']
