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_join(self):
index, data = common.getMixedTypeDict()
target = self.klass(data, index=index)
# Join on string value
source = self.klass({
'MergedA': data['A'],
'MergedD': data['D']
},
index=data['C'])
merged = target.join(source, on='C')
self.assert_(np.array_equal(merged['MergedA'], target['A']))
self.assert_(np.array_equal(merged['MergedD'], target['D']))
# Test when some are missing
# merge column not p resent
self.assertRaises(Exception, target.join, source, on='E')
# corner cases
# nothing to merge
merged = target.join(source.reindex([]), on='C')
# overlap
source_copy = source.copy()
source_copy['A'] = 0
self.assertRaises(Exception, target.join, source_copy, on='A')
# can't specify how
self.assertRaises(Exception, target.join, source, on='C', how='left')
def setUp(self):
# 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 setUp(self):
# 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'])
self.left = DataFrame({'key': ['a', 'b', 'c', 'd', 'e', 'e', 'a'],
'v1': np.random.randn(7)})
self.right = DataFrame({'v2': np.random.randn(4)},
index=['d', 'b', 'c', 'a'])
def test_join(self):
index, data = common.getMixedTypeDict()
target = self.klass(data, index=index)
# Join on string value
source = self.klass({'MergedA' : data['A'], 'MergedD' : data['D']},
index=data['C'])
merged = target.join(source, on='C')
self.assert_(np.array_equal(merged['MergedA'], target['A']))
self.assert_(np.array_equal(merged['MergedD'], target['D']))
# Test when some are missing
# merge column not p resent
self.assertRaises(Exception, target.join, source, on='E')
# corner cases
# nothing to merge
merged = target.join(source.reindex([]), on='C')
# overlap
source_copy = source.copy()
source_copy['A'] = 0
self.assertRaises(Exception, target.join, source_copy, on='A')
# can't specify how
self.assertRaises(Exception, target.join, source, on='C',
how='left')
def setUp(self):
# 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"])
self.left = DataFrame({"key": ["a", "b", "c", "d", "e", "e", "a"], "v1": np.random.randn(7)})
self.right = DataFrame({"v2": np.random.randn(4)}, index=["d", "b", "c", "a"])
def test_creation_mixed(self):
index, data = tm.getMixedTypeDict()
indexed_frame = DataFrame.from_dict(
data, orient=DataFrame.COLUMNS).set_index(index).build() # noqa
unindexed_frame = DataFrame.from_dict(
data, orient=DataFrame.COLUMNS).build() # noqa
assert self.mixed_frame['foo'].dtype == np.object_
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_map(self):
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 compat.iteritems(merged):
assert v == source[target[k]]
# input could be a dict
merged = target.map(source.to_dict())
for k, v in compat.iteritems(merged):
assert v == source[target[k]]
# function
result = self.ts.map(lambda x: x * 2)
tm.assert_series_equal(result, self.ts * 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_map(self):
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 compat.iteritems(merged):
assert v == source[target[k]]
# input could be a dict
merged = target.map(source.to_dict())
for k, v in compat.iteritems(merged):
assert v == source[target[k]]
# function
result = self.ts.map(lambda x: x * 2)
tm.assert_series_equal(result, self.ts * 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_merge(self):
index, data = common.getMixedTypeDict()
source = Series(data['B'], index=data['C'])
target = Series(data['C'][:4], index=data['D'][:4])
merged = target.merge(source)
for k, v in merged.iteritems():
self.assertEqual(v, source[target[k]])
# input could be a dict
merged = target.merge(source.toDict())
for k, v in merged.iteritems():
self.assertEqual(v, source[target[k]])
def test_merge(self):
index, data = common.getMixedTypeDict()
source = Series(data['B'], index=data['C'])
target = Series(data['C'][:4], index=data['D'][:4])
merged = target.merge(source)
for k, v in merged.iteritems():
self.assertEqual(v, source[target[k]])
# input could be a dict
merged = target.merge(source.toDict())
for k, v in merged.iteritems():
self.assertEqual(v, source[target[k]])
def test_transpose(self):
frame = self.frame
dft = frame.T
for idx, series in dft.iteritems():
for col, value in series.iteritems():
if np.isnan(value):
self.assert_(np.isnan(frame[col][idx]))
else:
self.assertEqual(value, frame[col][idx])
# mixed type
index, data = common.getMixedTypeDict()
mixed = self.klass(data, index=index)
mixed_T = mixed.T
for col, s in mixed_T.iteritems():
self.assert_(s.dtype == np.object_)
def test_transpose(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 = self.klass(data, index=index)
mixed_T = mixed.T
for col, s in mixed_T.items():
assert s.dtype == np.object_
def test_transpose(self, float_frame):
frame = float_frame
dft = frame.T
for idx, series in compat.iteritems(dft):
for col, value in compat.iteritems(series):
if np.isnan(value):
assert np.isnan(frame[col][idx])
else:
assert value == frame[col][idx]
# mixed type
index, data = tm.getMixedTypeDict()
mixed = self.klass(data, index=index)
mixed_T = mixed.T
for col, s in compat.iteritems(mixed_T):
assert s.dtype == np.object_
def test_transpose(self):
frame = self.frame
dft = frame.T
for idx, series in dft.iteritems():
for col, value in series.iteritems():
if np.isnan(value):
self.assert_(np.isnan(frame[col][idx]))
else:
self.assertEqual(value, frame[col][idx])
# mixed type
index, data = common.getMixedTypeDict()
mixed = self.klass(data, index=index)
mixed_T = mixed.T
for col, s in mixed_T.iteritems():
self.assert_(s.dtype == np.object_)
def test_transpose(self):
frame = self.frame
dft = frame.T
for idx, series in compat.iteritems(dft):
for col, value in compat.iteritems(series):
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 compat.iteritems(mixed_T):
assert s.dtype == np.object_
def test_transpose(self):
frame = self.frame
dft = frame.T
for idx, series in compat.iteritems(dft):
for col, value in compat.iteritems(series):
if np.isnan(value):
self.assertTrue(np.isnan(frame[col][idx]))
else:
self.assertEqual(value, frame[col][idx])
# mixed type
index, data = tm.getMixedTypeDict()
mixed = DataFrame(data, index=index)
mixed_T = mixed.T
for col, s in compat.iteritems(mixed_T):
self.assertEqual(s.dtype, np.object_)
def test_map(self):
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.iteritems():
self.assertEqual(v, source[target[k]])
# input could be a dict
merged = target.map(source.to_dict())
for k, v in merged.iteritems():
self.assertEqual(v, source[target[k]])
# function
result = self.ts.map(lambda x: x * 2)
self.assert_(np.array_equal(result, self.ts * 2))
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_constructor_mixed(self):
index, data = common.getMixedTypeDict()
indexed_frame = self.klass(data, index=index)
unindexed_frame = self.klass(data)
def test_constructor_mixed(self):
index, data = common.getMixedTypeDict()
indexed_frame = self.klass(data, index=index)
unindexed_frame = self.klass(data)