def setup_method(self, method):
# aggregate multiple columns
self.df = DataFrame({
"key1": get_test_data(),
"key2": get_test_data(),
"data1": np.random.randn(N),
"data2": np.random.randn(N),
})
# exclude a couple keys for fun
self.df = self.df[self.df["key2"] > 1]
self.df2 = DataFrame({
"key1":
get_test_data(n=N // 5),
"key2":
get_test_data(ngroups=NGROUPS // 2, n=N // 5),
"value":
np.random.randn(N // 5),
})
index, data = tm.getMixedTypeDict()
self.target = DataFrame(data, index=index)
# Join on string value
self.source = DataFrame({
"MergedA": data["A"],
"MergedD": data["D"]
},
index=data["C"])
def test_map(self, datetime_series):
index, data = tm.getMixedTypeDict()
source = Series(data["B"], index=data["C"])
target = Series(data["C"][:4], index=data["D"][:4])
merged = target.map(source)
for k, v in merged.items():
assert v == source[target[k]]
# input could be a dict
merged = target.map(source.to_dict())
for k, v in merged.items():
assert v == source[target[k]]
# function
result = datetime_series.map(lambda x: x * 2)
tm.assert_series_equal(result, datetime_series * 2)
# GH 10324
a = Series([1, 2, 3, 4])
b = Series(["even", "odd", "even", "odd"], dtype="category")
c = Series(["even", "odd", "even", "odd"])
exp = Series(["odd", "even", "odd", np.nan], dtype="category")
tm.assert_series_equal(a.map(b), exp)
exp = Series(["odd", "even", "odd", np.nan])
tm.assert_series_equal(a.map(c), exp)
a = Series(["a", "b", "c", "d"])
b = Series([1, 2, 3, 4],
index=pd.CategoricalIndex(["b", "c", "d", "e"]))
c = Series([1, 2, 3, 4], index=Index(["b", "c", "d", "e"]))
exp = Series([np.nan, 1, 2, 3])
tm.assert_series_equal(a.map(b), exp)
exp = Series([np.nan, 1, 2, 3])
tm.assert_series_equal(a.map(c), exp)
a = Series(["a", "b", "c", "d"])
b = Series(
["B", "C", "D", "E"],
dtype="category",
index=pd.CategoricalIndex(["b", "c", "d", "e"]),
)
c = Series(["B", "C", "D", "E"], index=Index(["b", "c", "d", "e"]))
exp = Series(
pd.Categorical([np.nan, "B", "C", "D"],
categories=["B", "C", "D", "E"]))
tm.assert_series_equal(a.map(b), exp)
exp = Series([np.nan, "B", "C", "D"])
tm.assert_series_equal(a.map(c), exp)
def test_transpose_float(self, float_frame):
frame = float_frame
dft = frame.T
for idx, series in dft.items():
for col, value in series.items():
if np.isnan(value):
assert np.isnan(frame[col][idx])
else:
assert value == frame[col][idx]
# mixed type
index, data = tm.getMixedTypeDict()
mixed = DataFrame(data, index=index)
mixed_T = mixed.T
for col, s in mixed_T.items():
assert s.dtype == np.object_
