def test_rank_apply():
lev1 = tm.rands_array(10, 100)
lev2 = tm.rands_array(10, 130)
lab1 = np.random.randint(0, 100, size=500)
lab2 = np.random.randint(0, 130, size=500)
df = DataFrame(
{
"value": np.random.randn(500),
"key1": lev1.take(lab1),
"key2": lev2.take(lab2),
}
)
result = df.groupby(["key1", "key2"]).value.rank()
expected = [piece.value.rank() for key, piece in df.groupby(["key1", "key2"])]
expected = concat(expected, axis=0)
expected = expected.reindex(result.index)
tm.assert_series_equal(result, expected)
result = df.groupby(["key1", "key2"]).value.rank(pct=True)
expected = [
piece.value.rank(pct=True) for key, piece in df.groupby(["key1", "key2"])
]
expected = concat(expected, axis=0)
expected = expected.reindex(result.index)
tm.assert_series_equal(result, expected)
def test_getitem_negative_out_of_bounds():
s = Series(tm.rands_array(5, 10), index=tm.rands_array(10, 10))
msg = "index -11 is out of bounds for axis 0 with size 10"
with pytest.raises(IndexError, match=msg):
s[-11]
with pytest.raises(IndexError, match=msg):
s[-11] = "foo"
def test_long_strings(setup_path):
# GH6166
df = DataFrame({"a": tm.rands_array(100, size=10)},
index=tm.rands_array(100, size=10))
with ensure_clean_store(setup_path) as store:
store.append("df", df, data_columns=["a"])
result = store.select("df")
tm.assert_frame_equal(df, result)
def test_series_frame_radd_bug(self, fixed_now_ts):
# GH#353
vals = Series(tm.rands_array(5, 10))
result = "foo_" + vals
expected = vals.map(lambda x: "foo_" + x)
tm.assert_series_equal(result, expected)
frame = pd.DataFrame({"vals": vals})
result = "foo_" + frame
expected = pd.DataFrame({"vals": vals.map(lambda x: "foo_" + x)})
tm.assert_frame_equal(result, expected)
ts = tm.makeTimeSeries()
ts.name = "ts"
# really raise this time
fix_now = fixed_now_ts.to_pydatetime()
msg = "|".join([
"unsupported operand type",
# wrong error message, see https://github.com/numpy/numpy/issues/18832
"Concatenation operation",
])
with pytest.raises(TypeError, match=msg):
fix_now + ts
with pytest.raises(TypeError, match=msg):
ts + fix_now
def test_compress_group_combinations(self):
# ~ 40000000 possible unique groups
key1 = tm.rands_array(10, 10000)
key1 = np.tile(key1, 2)
key2 = key1[::-1]
df = DataFrame({"key1": key1, "key2": key2, "value1": np.random.randn(20000)})
df2 = DataFrame(
{"key1": key1[::2], "key2": key2[::2], "value2": np.random.randn(10000)}
)
# just to hit the label compression code path
merge(df, df2, how="outer")
def test_series_frame_radd_bug(self):
# GH#353
vals = pd.Series(tm.rands_array(5, 10))
result = "foo_" + vals
expected = vals.map(lambda x: "foo_" + x)
tm.assert_series_equal(result, expected)
frame = pd.DataFrame({"vals": vals})
result = "foo_" + frame
expected = pd.DataFrame({"vals": vals.map(lambda x: "foo_" + x)})
tm.assert_frame_equal(result, expected)
ts = tm.makeTimeSeries()
ts.name = "ts"
# really raise this time
now = pd.Timestamp.now().to_pydatetime()
with pytest.raises(TypeError):
now + ts
with pytest.raises(TypeError):
ts + now
def test_same_len_hash_collisions(l_exp, l_add):
length = 2**(l_exp + 8) + l_add
s = tm.rands_array(length, 2)
result = hash_array(s, "utf8")
assert not result[0] == result[1]
def test_very_wide_info_repr(self):
df = DataFrame(np.random.randn(10, 20), columns=tm.rands_array(10, 20))
repr(df)
def test_rands_array_2d():
arr = tm.rands_array(7, size=(10, 10))
assert arr.shape == (10, 10)
assert len(arr[1, 1]) == 7
def test_rands_array_1d():
arr = tm.rands_array(5, size=10)
assert arr.shape == (10, )
assert len(arr[0]) == 5