def setUp(self):
self.seriesd = common.getSeriesData()
self.tsd = common.getTimeSeriesData()
self.frame = self.klass(self.seriesd)
self.intframe = self.klass(
dict((k, v.astype(int)) for k, v in self.seriesd.iteritems()))
self.tsframe = self.klass(self.tsd)
self.mixed_frame = self.frame.copy()
self.mixed_frame['foo'] = 'bar'
self.ts1 = common.makeTimeSeries()
self.ts2 = common.makeTimeSeries()[5:]
self.ts3 = common.makeTimeSeries()[-5:]
self.ts4 = common.makeTimeSeries()[1:-1]
self.ts_dict = {
'col1': self.ts1,
'col2': self.ts2,
'col3': self.ts3,
'col4': self.ts4,
}
self.empty = self.klass({})
self.unsortable = self.klass(
{
'foo': [1] * 1000,
datetime.today(): [1] * 1000,
'bar': ['bar'] * 1000,
datetime.today() + timedelta(1): ['bar'] * 1000
},
index=np.arange(1000))
def float_frame():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
A B C D
P7GACiRnxd -0.465578 -0.361863 0.886172 -0.053465
qZKh6afn8n -0.466693 -0.373773 0.266873 1.673901
tkp0r6Qble 0.148691 -0.059051 0.174817 1.598433
wP70WOCtv8 0.133045 -0.581994 -0.992240 0.261651
M2AeYQMnCz -1.207959 -0.185775 0.588206 0.563938
QEPzyGDYDo -0.381843 -0.758281 0.502575 -0.565053
r78Jwns6dn -0.653707 0.883127 0.682199 0.206159
... ... ... ... ...
IHEGx9NO0T -0.277360 0.113021 -1.018314 0.196316
lPMj8K27FA -1.313667 -0.604776 -1.305618 -0.863999
qa66YMWQa5 1.110525 0.475310 -0.747865 0.032121
yOa0ATsmcE -0.431457 0.067094 0.096567 -0.264962
65znX3uRNG 1.528446 0.160416 -0.109635 -0.032987
eCOBvKqf3e 0.235281 1.622222 0.781255 0.392871
xSucinXxuV -1.263557 0.252799 -0.552247 0.400426
[30 rows x 4 columns]
"""
return DataFrame(tm.getSeriesData())
def mixed_float_frame():
"""
Fixture for DataFrame of different float types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
A B C D
GI7bbDaEZe -0.237908 -0.246225 -0.468506 0.752993
KGp9mFepzA -1.140809 -0.644046 -1.225586 0.801588
VeVYLAb1l2 -1.154013 -1.677615 0.690430 -0.003731
kmPME4WKhO 0.979578 0.998274 -0.776367 0.897607
CPyopdXTiz 0.048119 -0.257174 0.836426 0.111266
0kJZQndAj0 0.274357 -0.281135 -0.344238 0.834541
tqdwQsaHG8 -0.979716 -0.519897 0.582031 0.144710
... ... ... ... ...
7FhZTWILQj -2.906357 1.261039 -0.780273 -0.537237
4pUDPM4eGq -2.042512 -0.464382 -0.382080 1.132612
B8dUgUzwTi -1.506637 -0.364435 1.087891 0.297653
hErlVYjVv9 1.477453 -0.495515 -0.713867 1.438427
1BKN3o7YLs 0.127535 -0.349812 -0.881836 0.489827
9S4Ekn7zga 1.445518 -2.095149 0.031982 0.373204
xN1dNn6OV6 1.425017 -0.983995 -0.363281 -0.224502
[30 rows x 4 columns]
"""
df = DataFrame(tm.getSeriesData())
df.A = df.A.astype('float32')
df.B = df.B.astype('float32')
df.C = df.C.astype('float16')
df.D = df.D.astype('float64')
return df
def test_convert_r_matrix():
is_na = robj.baseenv.get("is.na")
seriesd = _test.getSeriesData()
frame = pd.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
# Null data
frame["E"] = [np.nan for item in frame["A"]]
r_dataframe = convert_to_r_matrix(frame)
assert np.array_equal(convert_robj(r_dataframe.rownames), frame.index)
assert np.array_equal(convert_robj(r_dataframe.colnames), frame.columns)
assert all(is_na(item) for item in r_dataframe.rx(True, "E"))
for column in frame[["A", "B", "C", "D"]]:
coldata = r_dataframe.rx(True, column)
original_data = frame[column]
assert np.array_equal(convert_robj(coldata),
original_data)
# Pandas bug 1282
frame["F"] = ["text" if item % 2 == 0 else np.nan for item in range(30)]
# FIXME: Ugly, this whole module needs to be ported to nose/unittest
try:
wrong_matrix = convert_to_r_matrix(frame)
except TypeError:
pass
except Exception:
raise
def float_frame2():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['D', 'C', 'B', 'A']
"""
return DataFrame(tm.getSeriesData(), columns=['D', 'C', 'B', 'A'])
def float_string_frame():
"""
Fixture for DataFrame of floats and strings with index of unique strings
Columns are ['A', 'B', 'C', 'D', 'foo'].
A B C D foo
w3orJvq07g -1.594062 -1.084273 -1.252457 0.356460 bar
PeukuVdmz2 0.109855 -0.955086 -0.809485 0.409747 bar
ahp2KvwiM8 -1.533729 -0.142519 -0.154666 1.302623 bar
3WSJ7BUCGd 2.484964 0.213829 0.034778 -2.327831 bar
khdAmufk0U -0.193480 -0.743518 -0.077987 0.153646 bar
LE2DZiFlrE -0.193566 -1.343194 -0.107321 0.959978 bar
HJXSJhVn7b 0.142590 1.257603 -0.659409 -0.223844 bar
... ... ... ... ... ...
9a1Vypttgw -1.316394 1.601354 0.173596 1.213196 bar
h5d1gVFbEy 0.609475 1.106738 -0.155271 0.294630 bar
mK9LsTQG92 1.303613 0.857040 -1.019153 0.369468 bar
oOLksd9gKH 0.558219 -0.134491 -0.289869 -0.951033 bar
9jgoOjKyHg 0.058270 -0.496110 -0.413212 -0.852659 bar
jZLDHclHAO 0.096298 1.267510 0.549206 -0.005235 bar
lR0nxDp1C2 -2.119350 -0.794384 0.544118 0.145849 bar
[30 rows x 5 columns]
"""
df = DataFrame(tm.getSeriesData())
df["foo"] = "bar"
return df
def float_frame_with_na():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
A B C D
ABwBzA0ljw -1.128865 -0.897161 0.046603 0.274997
DJiRzmbyQF 0.728869 0.233502 0.722431 -0.890872
neMgPD5UBF 0.486072 -1.027393 -0.031553 1.449522
0yWA4n8VeX -1.937191 -1.142531 0.805215 -0.462018
3slYUbbqU1 0.153260 1.164691 1.489795 -0.545826
soujjZ0A08 NaN NaN NaN NaN
7W6NLGsjB9 NaN NaN NaN NaN
... ... ... ... ...
uhfeaNkCR1 -0.231210 -0.340472 0.244717 -0.901590
n6p7GYuBIV -0.419052 1.922721 -0.125361 -0.727717
ZhzAeY6p1y 1.234374 -1.425359 -0.827038 -0.633189
uWdPsORyUh 0.046738 -0.980445 -1.102965 0.605503
3DJA6aN590 -0.091018 -1.684734 -1.100900 0.215947
2GBPAzdbMk -2.883405 -1.021071 1.209877 1.633083
sHadBoyVHw -2.223032 -0.326384 0.258931 0.245517
[30 rows x 4 columns]
"""
df = DataFrame(tm.getSeriesData())
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def setUp(self):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = df()
self.df_mixed_floats = DataFrame(
{'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
'C': np.random.randn(8),
'D': np.array(
np.random.randn(8), dtype='float32')})
self.mframe = mframe()
self.three_group = DataFrame(
{'A': ['foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar',
'foo', 'foo', 'foo'],
'B': ['one', 'one', 'one', 'two', 'one', 'one', 'one', 'two',
'two', 'two', 'one'],
'C': ['dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'],
'D': np.random.randn(11),
'E': np.random.randn(11),
'F': np.random.randn(11)})
def int_frame():
"""
Fixture for DataFrame of ints with index of unique strings
Columns are ['A', 'B', 'C', 'D']
A B C D
vpBeWjM651 1 0 1 0
5JyxmrP1En -1 0 0 0
qEDaoD49U2 -1 1 0 0
m66TkTfsFe 0 0 0 0
EHPaNzEUFm -1 0 -1 0
fpRJCevQhi 2 0 0 0
OlQvnmfi3Q 0 0 -2 0
... .. .. .. ..
uB1FPlz4uP 0 0 0 1
EcSe6yNzCU 0 0 -1 0
L50VudaiI8 -1 1 -2 0
y3bpw4nwIp 0 -1 0 0
H0RdLLwrCT 1 1 0 0
rY82K0vMwm 0 0 0 0
1OPIUjnkjk 2 0 0 0
[30 rows x 4 columns]
"""
df = DataFrame({k: v.astype(int) for k, v in tm.getSeriesData().items()})
# force these all to int64 to avoid platform testing issues
return DataFrame({c: s for c, s in df.items()}, dtype=np.int64)
def float_frame():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
A B C D
P7GACiRnxd -0.465578 -0.361863 0.886172 -0.053465
qZKh6afn8n -0.466693 -0.373773 0.266873 1.673901
tkp0r6Qble 0.148691 -0.059051 0.174817 1.598433
wP70WOCtv8 0.133045 -0.581994 -0.992240 0.261651
M2AeYQMnCz -1.207959 -0.185775 0.588206 0.563938
QEPzyGDYDo -0.381843 -0.758281 0.502575 -0.565053
r78Jwns6dn -0.653707 0.883127 0.682199 0.206159
... ... ... ... ...
IHEGx9NO0T -0.277360 0.113021 -1.018314 0.196316
lPMj8K27FA -1.313667 -0.604776 -1.305618 -0.863999
qa66YMWQa5 1.110525 0.475310 -0.747865 0.032121
yOa0ATsmcE -0.431457 0.067094 0.096567 -0.264962
65znX3uRNG 1.528446 0.160416 -0.109635 -0.032987
eCOBvKqf3e 0.235281 1.622222 0.781255 0.392871
xSucinXxuV -1.263557 0.252799 -0.552247 0.400426
[30 rows x 4 columns]
"""
return DataFrame(tm.getSeriesData())
def test_convert_r_matrix(self):
is_na = robj.baseenv.get("is.na")
seriesd = tm.getSeriesData()
frame = pd.DataFrame(seriesd, columns=["D", "C", "B", "A"])
# Null data
frame["E"] = [np.nan for item in frame["A"]]
r_dataframe = com.convert_to_r_matrix(frame)
assert np.array_equal(com.convert_robj(r_dataframe.rownames), frame.index)
assert np.array_equal(com.convert_robj(r_dataframe.colnames), frame.columns)
assert all(is_na(item) for item in r_dataframe.rx(True, "E"))
for column in frame[["A", "B", "C", "D"]]:
coldata = r_dataframe.rx(True, column)
original_data = frame[column]
assert np.array_equal(com.convert_robj(coldata), original_data)
# Pandas bug 1282
frame["F"] = ["text" if item % 2 == 0 else np.nan for item in range(30)]
try:
wrong_matrix = com.convert_to_r_matrix(frame)
except TypeError:
pass
except Exception:
raise
def test_convert_r_matrix():
is_na = robj.baseenv.get("is.na")
seriesd = _test.getSeriesData()
frame = pd.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
#Null data
frame["E"] = [np.nan for item in frame["A"]]
r_dataframe = convert_to_r_matrix(frame)
assert np.array_equal(convert_robj(r_dataframe.rownames), frame.index)
assert np.array_equal(convert_robj(r_dataframe.colnames), frame.columns)
assert all(is_na(item) for item in r_dataframe.rx(True, "E"))
for column in frame[["A", "B", "C", "D"]]:
coldata = r_dataframe.rx(True, column)
original_data = frame[column]
assert np.array_equal(convert_robj(coldata), original_data)
# Pandas bug 1282
frame["F"] = ["text" if item % 2 == 0 else np.nan for item in range(30)]
#FIXME: Ugly, this whole module needs to be ported to nose/unittest
try:
wrong_matrix = convert_to_r_matrix(frame)
except TypeError:
pass
except Exception:
raise
def float_frame_with_na():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
A B C D
ABwBzA0ljw -1.128865 -0.897161 0.046603 0.274997
DJiRzmbyQF 0.728869 0.233502 0.722431 -0.890872
neMgPD5UBF 0.486072 -1.027393 -0.031553 1.449522
0yWA4n8VeX -1.937191 -1.142531 0.805215 -0.462018
3slYUbbqU1 0.153260 1.164691 1.489795 -0.545826
soujjZ0A08 NaN NaN NaN NaN
7W6NLGsjB9 NaN NaN NaN NaN
... ... ... ... ...
uhfeaNkCR1 -0.231210 -0.340472 0.244717 -0.901590
n6p7GYuBIV -0.419052 1.922721 -0.125361 -0.727717
ZhzAeY6p1y 1.234374 -1.425359 -0.827038 -0.633189
uWdPsORyUh 0.046738 -0.980445 -1.102965 0.605503
3DJA6aN590 -0.091018 -1.684734 -1.100900 0.215947
2GBPAzdbMk -2.883405 -1.021071 1.209877 1.633083
sHadBoyVHw -2.223032 -0.326384 0.258931 0.245517
[30 rows x 4 columns]
"""
df = DataFrame(tm.getSeriesData())
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def test_convert_r_dataframe():
is_na = robj.baseenv.get("is.na")
seriesd = _test.getSeriesData()
frame = pd.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
#Null data
frame["E"] = [np.nan for item in frame["A"]]
# Some mixed type data
frame["F"] = ["text" if item % 2 == 0 else np.nan for item in range(30)]
r_dataframe = convert_to_r_dataframe(frame)
assert np.array_equal(convert_robj(r_dataframe.rownames), frame.index)
assert np.array_equal(convert_robj(r_dataframe.colnames), frame.columns)
assert all(is_na(item) for item in r_dataframe.rx2("E"))
for column in frame[["A", "B", "C", "D"]]:
coldata = r_dataframe.rx2(column)
original_data = frame[column]
assert np.array_equal(convert_robj(coldata), original_data)
for column in frame[["D", "E"]]:
for original, converted in zip(frame[column], r_dataframe.rx2(column)):
if pd.isnull(original):
assert is_na(converted)
else:
assert original == converted
def float_frame():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
return DataFrame(tm.getSeriesData())
def bool_frame_with_na():
"""
Fixture for DataFrame of booleans with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
A B C D
zBZxY2IDGd False False False False
IhBWBMWllt False True True True
ctjdvZSR6R True False True True
AVTujptmxb False True False True
G9lrImrSWq False False False True
sFFwdIUfz2 NaN NaN NaN NaN
s15ptEJnRb NaN NaN NaN NaN
... ... ... ... ...
UW41KkDyZ4 True True False False
l9l6XkOdqV True False False False
X2MeZfzDYA False True False False
xWkIKU7vfX False True False True
QOhL6VmpGU False False False True
22PwkRJdat False True False False
kfboQ3VeIK True False True False
[30 rows x 4 columns]
"""
df = DataFrame(tm.getSeriesData()) > 0
df = df.astype(object)
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def int_frame():
"""
Fixture for DataFrame of ints with index of unique strings
Columns are ['A', 'B', 'C', 'D']
A B C D
vpBeWjM651 1 0 1 0
5JyxmrP1En -1 0 0 0
qEDaoD49U2 -1 1 0 0
m66TkTfsFe 0 0 0 0
EHPaNzEUFm -1 0 -1 0
fpRJCevQhi 2 0 0 0
OlQvnmfi3Q 0 0 -2 0
... .. .. .. ..
uB1FPlz4uP 0 0 0 1
EcSe6yNzCU 0 0 -1 0
L50VudaiI8 -1 1 -2 0
y3bpw4nwIp 0 -1 0 0
H0RdLLwrCT 1 1 0 0
rY82K0vMwm 0 0 0 0
1OPIUjnkjk 2 0 0 0
[30 rows x 4 columns]
"""
df = DataFrame({k: v.astype(int) for k, v in tm.getSeriesData().items()})
# force these all to int64 to avoid platform testing issues
return DataFrame({c: s for c, s in df.items()}, dtype=np.int64)
def bool_frame_with_na():
"""
Fixture for DataFrame of booleans with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
A B C D
zBZxY2IDGd False False False False
IhBWBMWllt False True True True
ctjdvZSR6R True False True True
AVTujptmxb False True False True
G9lrImrSWq False False False True
sFFwdIUfz2 NaN NaN NaN NaN
s15ptEJnRb NaN NaN NaN NaN
... ... ... ... ...
UW41KkDyZ4 True True False False
l9l6XkOdqV True False False False
X2MeZfzDYA False True False False
xWkIKU7vfX False True False True
QOhL6VmpGU False False False True
22PwkRJdat False True False False
kfboQ3VeIK True False True False
[30 rows x 4 columns]
"""
df = DataFrame(tm.getSeriesData()) > 0
df = df.astype(object)
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def mixed_int_frame():
"""
Fixture for DataFrame of different int types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
A B C D
mUrCZ67juP 0 1 2 2
rw99ACYaKS 0 1 0 0
7QsEcpaaVU 0 1 1 1
xkrimI2pcE 0 1 0 0
dz01SuzoS8 0 1 255 255
ccQkqOHX75 -1 1 0 0
DN0iXaoDLd 0 1 0 0
... .. .. ... ...
Dfb141wAaQ 1 1 254 254
IPD8eQOVu5 0 1 0 0
CcaKulsCmv 0 1 0 0
rIBa8gu7E5 0 1 0 0
RP6peZmh5o 0 1 1 1
NMb9pipQWQ 0 1 0 0
PqgbJEzjib 0 1 3 3
[30 rows x 4 columns]
"""
df = DataFrame({k: v.astype(int) for k, v in tm.getSeriesData().items()})
df.A = df.A.astype('int32')
df.B = np.ones(len(df.B), dtype='uint64')
df.C = df.C.astype('uint8')
df.D = df.C.astype('int64')
return df
def mixed_int_frame():
"""
Fixture for DataFrame of different int types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
A B C D
mUrCZ67juP 0 1 2 2
rw99ACYaKS 0 1 0 0
7QsEcpaaVU 0 1 1 1
xkrimI2pcE 0 1 0 0
dz01SuzoS8 0 1 255 255
ccQkqOHX75 -1 1 0 0
DN0iXaoDLd 0 1 0 0
... .. .. ... ...
Dfb141wAaQ 1 1 254 254
IPD8eQOVu5 0 1 0 0
CcaKulsCmv 0 1 0 0
rIBa8gu7E5 0 1 0 0
RP6peZmh5o 0 1 1 1
NMb9pipQWQ 0 1 0 0
PqgbJEzjib 0 1 3 3
[30 rows x 4 columns]
"""
df = DataFrame({k: v.astype(int) for k, v in tm.getSeriesData().items()})
df.A = df.A.astype("int32")
df.B = np.ones(len(df.B), dtype="uint64")
df.C = df.C.astype("uint8")
df.D = df.C.astype("int64")
return df
def test_convert_r_dataframe():
is_na = robj.baseenv.get("is.na")
seriesd = _test.getSeriesData()
frame = pd.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
# Null data
frame["E"] = [np.nan for item in frame["A"]]
# Some mixed type data
frame["F"] = ["text" if item % 2 == 0 else np.nan for item in range(30)]
r_dataframe = convert_to_r_dataframe(frame)
assert np.array_equal(convert_robj(r_dataframe.rownames), frame.index)
assert np.array_equal(convert_robj(r_dataframe.colnames), frame.columns)
assert all(is_na(item) for item in r_dataframe.rx2("E"))
for column in frame[["A", "B", "C", "D"]]:
coldata = r_dataframe.rx2(column)
original_data = frame[column]
assert np.array_equal(convert_robj(coldata), original_data)
for column in frame[["D", "E"]]:
for original, converted in zip(frame[column],
r_dataframe.rx2(column)):
if pd.isnull(original):
assert is_na(converted)
else:
assert original == converted
def float_string_frame():
"""
Fixture for DataFrame of floats and strings with index of unique strings
Columns are ['A', 'B', 'C', 'D', 'foo'].
A B C D foo
w3orJvq07g -1.594062 -1.084273 -1.252457 0.356460 bar
PeukuVdmz2 0.109855 -0.955086 -0.809485 0.409747 bar
ahp2KvwiM8 -1.533729 -0.142519 -0.154666 1.302623 bar
3WSJ7BUCGd 2.484964 0.213829 0.034778 -2.327831 bar
khdAmufk0U -0.193480 -0.743518 -0.077987 0.153646 bar
LE2DZiFlrE -0.193566 -1.343194 -0.107321 0.959978 bar
HJXSJhVn7b 0.142590 1.257603 -0.659409 -0.223844 bar
... ... ... ... ... ...
9a1Vypttgw -1.316394 1.601354 0.173596 1.213196 bar
h5d1gVFbEy 0.609475 1.106738 -0.155271 0.294630 bar
mK9LsTQG92 1.303613 0.857040 -1.019153 0.369468 bar
oOLksd9gKH 0.558219 -0.134491 -0.289869 -0.951033 bar
9jgoOjKyHg 0.058270 -0.496110 -0.413212 -0.852659 bar
jZLDHclHAO 0.096298 1.267510 0.549206 -0.005235 bar
lR0nxDp1C2 -2.119350 -0.794384 0.544118 0.145849 bar
[30 rows x 5 columns]
"""
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
return df
def setUp(self):
self.seriesd = common.getSeriesData()
self.tsd = common.getTimeSeriesData()
self.frame = self.klass(self.seriesd)
self.intframe = self.klass(dict((k, v.astype(int))
for k, v in self.seriesd.iteritems()))
self.tsframe = self.klass(self.tsd)
self.mixed_frame = self.frame.copy()
self.mixed_frame['foo'] = 'bar'
self.ts1 = common.makeTimeSeries()
self.ts2 = common.makeTimeSeries()[5:]
self.ts3 = common.makeTimeSeries()[-5:]
self.ts4 = common.makeTimeSeries()[1:-1]
self.ts_dict = {
'col1' : self.ts1,
'col2' : self.ts2,
'col3' : self.ts3,
'col4' : self.ts4,
}
self.empty = self.klass({})
self.unsortable = self.klass(
{'foo' : [1] * 1000,
datetime.today() : [1] * 1000,
'bar' : ['bar'] * 1000,
datetime.today() + timedelta(1) : ['bar'] * 1000},
index=np.arange(1000))
def mixed_float_frame():
"""
Fixture for DataFrame of different float types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
A B C D
GI7bbDaEZe -0.237908 -0.246225 -0.468506 0.752993
KGp9mFepzA -1.140809 -0.644046 -1.225586 0.801588
VeVYLAb1l2 -1.154013 -1.677615 0.690430 -0.003731
kmPME4WKhO 0.979578 0.998274 -0.776367 0.897607
CPyopdXTiz 0.048119 -0.257174 0.836426 0.111266
0kJZQndAj0 0.274357 -0.281135 -0.344238 0.834541
tqdwQsaHG8 -0.979716 -0.519897 0.582031 0.144710
... ... ... ... ...
7FhZTWILQj -2.906357 1.261039 -0.780273 -0.537237
4pUDPM4eGq -2.042512 -0.464382 -0.382080 1.132612
B8dUgUzwTi -1.506637 -0.364435 1.087891 0.297653
hErlVYjVv9 1.477453 -0.495515 -0.713867 1.438427
1BKN3o7YLs 0.127535 -0.349812 -0.881836 0.489827
9S4Ekn7zga 1.445518 -2.095149 0.031982 0.373204
xN1dNn6OV6 1.425017 -0.983995 -0.363281 -0.224502
[30 rows x 4 columns]
"""
df = DataFrame(tm.getSeriesData())
df.A = df.A.astype("float32")
df.B = df.B.astype("float32")
df.C = df.C.astype("float16")
df.D = df.D.astype("float64")
return df
def float_string_frame():
"""
Fixture for DataFrame of floats and strings with index of unique strings
Columns are ['A', 'B', 'C', 'D', 'foo'].
"""
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
return df
def int_frame():
"""
Fixture for DataFrame of ints with index of unique strings
Columns are ['A', 'B', 'C', 'D']
"""
df = DataFrame({k: v.astype(int) for k, v in tm.getSeriesData().items()})
# force these all to int64 to avoid platform testing issues
return DataFrame({c: s for c, s in df.items()}, dtype=np.int64)
def float_string_frame():
"""
Fixture for DataFrame of floats and strings with index of unique strings
Columns are ['A', 'B', 'C', 'D', 'foo'].
"""
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
return df
def int_frame():
"""
Fixture for DataFrame of ints with index of unique strings
Columns are ['A', 'B', 'C', 'D']
"""
df = DataFrame({k: v.astype(int)
for k, v in compat.iteritems(tm.getSeriesData())})
# force these all to int64 to avoid platform testing issues
return DataFrame({c: s for c, s in compat.iteritems(df)}, dtype=np.int64)
def setup_method(self, method):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = DataFrame({
'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
'C':
np.random.randn(8),
'D':
np.random.randn(8)
})
self.df_mixed_floats = DataFrame({
'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
'C':
np.random.randn(8),
'D':
np.array(np.random.randn(8), dtype='float32')
})
index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
['one', 'two', 'three']],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
[0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=['first', 'second'])
self.mframe = DataFrame(np.random.randn(10, 3),
index=index,
columns=['A', 'B', 'C'])
self.three_group = DataFrame({
'A': [
'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar', 'foo',
'foo', 'foo'
],
'B': [
'one', 'one', 'one', 'two', 'one', 'one', 'one', 'two', 'two',
'two', 'one'
],
'C': [
'dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'
],
'D':
np.random.randn(11),
'E':
np.random.randn(11),
'F':
np.random.randn(11)
})
def float_frame_with_na():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
"""
df = DataFrame(tm.getSeriesData())
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def float_frame_with_na():
"""
Fixture for DataFrame of floats with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
"""
df = DataFrame(tm.getSeriesData())
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def mixed_float_frame2():
"""
Fixture for DataFrame of different float types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
df = DataFrame(tm.getSeriesData())
df.D = df.D.astype('float16')
df.C = df.C.astype('float32')
df.B = df.B.astype('float64')
return df
def mixed_float_frame2():
"""
Fixture for DataFrame of different float types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
df = DataFrame(tm.getSeriesData())
df.D = df.D.astype('float32')
df.C = df.C.astype('float32')
df.B = df.B.astype('float16')
df.D = df.D.astype('float64')
return df
def bool_frame_with_na():
"""
Fixture for DataFrame of booleans with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
"""
df = DataFrame(tm.getSeriesData()) > 0
df = df.astype(object)
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def bool_frame_with_na():
"""
Fixture for DataFrame of booleans with index of unique strings
Columns are ['A', 'B', 'C', 'D']; some entries are missing
"""
df = DataFrame(tm.getSeriesData()) > 0
df = df.astype(object)
# set some NAs
df.loc[5:10] = np.nan
df.loc[15:20, -2:] = np.nan
return df
def mixed_int_frame():
"""
Fixture for DataFrame of different int types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
df = DataFrame({k: v.astype(int) for k, v in tm.getSeriesData().items()})
df.A = df.A.astype('int32')
df.B = np.ones(len(df.B), dtype='uint64')
df.C = df.C.astype('uint8')
df.D = df.C.astype('int64')
return df
def mixed_int_frame():
"""
Fixture for DataFrame of different int types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
df = DataFrame({k: v.astype(int)
for k, v in compat.iteritems(tm.getSeriesData())})
df.A = df.A.astype('int32')
df.B = np.ones(len(df.B), dtype='uint64')
df.C = df.C.astype('uint8')
df.D = df.C.astype('int64')
return df
def test_ix_assign_column_mixed(self):
# GH #1142
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
orig = df.loc[:, 'B'].copy()
df.loc[:, 'B'] = df.loc[:, 'B'] + 1
tm.assert_series_equal(df.B, orig + 1)
# GH 3668, mixed frame with series value
df = DataFrame({
'x': np.arange(10),
'y': np.arange(10, 20),
'z': 'bar'
})
expected = df.copy()
for i in range(5):
indexer = i * 2
v = 1000 + i * 200
expected.loc[indexer, 'y'] = v
assert expected.loc[indexer, 'y'] == v
df.loc[df.x % 2 == 0, 'y'] = df.loc[df.x % 2 == 0, 'y'] * 100
tm.assert_frame_equal(df, expected)
# GH 4508, making sure consistency of assignments
df = DataFrame({'a': [1, 2, 3], 'b': [0, 1, 2]})
df.loc[[
0,
2,
], 'b'] = [100, -100]
expected = DataFrame({'a': [1, 2, 3], 'b': [100, 1, -100]})
tm.assert_frame_equal(df, expected)
df = DataFrame({'a': list(range(4))})
df['b'] = np.nan
df.loc[[1, 3], 'b'] = [100, -100]
expected = DataFrame({
'a': [0, 1, 2, 3],
'b': [np.nan, 100, np.nan, -100]
})
tm.assert_frame_equal(df, expected)
# ok, but chained assignments are dangerous
# if we turn off chained assignment it will work
with option_context('chained_assignment', None):
df = DataFrame({'a': list(range(4))})
df['b'] = np.nan
df['b'].loc[[1, 3]] = [100, -100]
tm.assert_frame_equal(df, expected)
def test_convert_r_matrix():
seriesd = _test.getSeriesData()
frame = pn.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
r_dataframe = convert_to_r_matrix(frame)
assert np.array_equal(convert_robj(r_dataframe.rownames), frame.index)
assert np.array_equal(convert_robj(r_dataframe.colnames), frame.columns)
for column in r_dataframe.colnames:
coldata = r_dataframe.rx(True, column)
original_data = frame[column]
assert np.array_equal(convert_robj(coldata), original_data)
def test_rename_inplace():
test_data = pandas.DataFrame(tm.getSeriesData())
modin_df = pd.DataFrame(test_data)
df_equals(
modin_df.rename(columns={"C": "foo"}),
test_data.rename(columns={"C": "foo"}),
)
frame = test_data.copy()
modin_frame = modin_df.copy()
frame.rename(columns={"C": "foo"}, inplace=True)
modin_frame.rename(columns={"C": "foo"}, inplace=True)
df_equals(modin_frame, frame)
def test_frame_operators(self):
seriesd = tm.getSeriesData()
frame = pd.DataFrame(seriesd)
frame2 = pd.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
garbage = np.random.random(4)
colSeries = pd.Series(garbage, index=np.array(frame.columns))
idSum = frame + frame
seriesSum = frame + colSeries
for col, series in idSum.items():
for idx, val in series.items():
origVal = frame[col][idx] * 2
if not np.isnan(val):
assert val == origVal
else:
assert np.isnan(origVal)
for col, series in seriesSum.items():
for idx, val in series.items():
origVal = frame[col][idx] + colSeries[col]
if not np.isnan(val):
assert val == origVal
else:
assert np.isnan(origVal)
added = frame2 + frame2
expected = frame2 * 2
tm.assert_frame_equal(added, expected)
df = pd.DataFrame({'a': ['a', None, 'b']})
tm.assert_frame_equal(df + df,
pd.DataFrame({'a': ['aa', np.nan, 'bb']}))
# Test for issue #10181
for dtype in ('float', 'int64'):
frames = [
pd.DataFrame(dtype=dtype),
pd.DataFrame(columns=['A'], dtype=dtype),
pd.DataFrame(index=[0], dtype=dtype),
]
for df in frames:
assert (df + df).equals(df)
tm.assert_frame_equal(df + df, df)
def test_frame_operators(self):
seriesd = tm.getSeriesData()
frame = pd.DataFrame(seriesd)
frame2 = pd.DataFrame(seriesd, columns=['D', 'C', 'B', 'A'])
garbage = np.random.random(4)
colSeries = pd.Series(garbage, index=np.array(frame.columns))
idSum = frame + frame
seriesSum = frame + colSeries
for col, series in idSum.items():
for idx, val in series.items():
origVal = frame[col][idx] * 2
if not np.isnan(val):
assert val == origVal
else:
assert np.isnan(origVal)
for col, series in seriesSum.items():
for idx, val in series.items():
origVal = frame[col][idx] + colSeries[col]
if not np.isnan(val):
assert val == origVal
else:
assert np.isnan(origVal)
added = frame2 + frame2
expected = frame2 * 2
tm.assert_frame_equal(added, expected)
df = pd.DataFrame({'a': ['a', None, 'b']})
tm.assert_frame_equal(df + df,
pd.DataFrame({'a': ['aa', np.nan, 'bb']}))
# Test for issue #10181
for dtype in ('float', 'int64'):
frames = [
pd.DataFrame(dtype=dtype),
pd.DataFrame(columns=['A'], dtype=dtype),
pd.DataFrame(index=[0], dtype=dtype),
]
for df in frames:
assert (df + df).equals(df)
tm.assert_frame_equal(df + df, df)
def test_ix_assign_column_mixed(self):
# GH #1142
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
orig = df.loc[:, 'B'].copy()
df.loc[:, 'B'] = df.loc[:, 'B'] + 1
tm.assert_series_equal(df.B, orig + 1)
# GH 3668, mixed frame with series value
df = DataFrame({'x': np.arange(10),
'y': np.arange(10, 20),
'z': 'bar'})
expected = df.copy()
for i in range(5):
indexer = i * 2
v = 1000 + i * 200
expected.loc[indexer, 'y'] = v
assert expected.loc[indexer, 'y'] == v
df.loc[df.x % 2 == 0, 'y'] = df.loc[df.x % 2 == 0, 'y'] * 100
tm.assert_frame_equal(df, expected)
# GH 4508, making sure consistency of assignments
df = DataFrame({'a': [1, 2, 3], 'b': [0, 1, 2]})
df.loc[[0, 2, ], 'b'] = [100, -100]
expected = DataFrame({'a': [1, 2, 3], 'b': [100, 1, -100]})
tm.assert_frame_equal(df, expected)
df = DataFrame({'a': list(range(4))})
df['b'] = np.nan
df.loc[[1, 3], 'b'] = [100, -100]
expected = DataFrame({'a': [0, 1, 2, 3],
'b': [np.nan, 100, np.nan, -100]})
tm.assert_frame_equal(df, expected)
# ok, but chained assignments are dangerous
# if we turn off chained assignment it will work
with option_context('chained_assignment', None):
df = DataFrame({'a': list(range(4))})
df['b'] = np.nan
df['b'].loc[[1, 3]] = [100, -100]
tm.assert_frame_equal(df, expected)
def test_astype():
td = pandas.DataFrame(tm.getSeriesData())
modin_df = pd.DataFrame(td.values, index=td.index, columns=td.columns)
expected_df = pandas.DataFrame(td.values,
index=td.index,
columns=td.columns)
modin_df_casted = modin_df.astype(np.int32)
expected_df_casted = expected_df.astype(np.int32)
df_equals(modin_df_casted, expected_df_casted)
modin_df_casted = modin_df.astype(np.float64)
expected_df_casted = expected_df.astype(np.float64)
df_equals(modin_df_casted, expected_df_casted)
modin_df_casted = modin_df.astype(str)
expected_df_casted = expected_df.astype(str)
df_equals(modin_df_casted, expected_df_casted)
modin_df_casted = modin_df.astype("category")
expected_df_casted = expected_df.astype("category")
df_equals(modin_df_casted, expected_df_casted)
dtype_dict = {"A": np.int32, "B": np.int64, "C": str}
modin_df_casted = modin_df.astype(dtype_dict)
expected_df_casted = expected_df.astype(dtype_dict)
df_equals(modin_df_casted, expected_df_casted)
# Ignore lint because this is testing bad input
bad_dtype_dict = {"B": np.int32, "B": np.int64, "B": str} # noqa F601
modin_df_casted = modin_df.astype(bad_dtype_dict)
expected_df_casted = expected_df.astype(bad_dtype_dict)
df_equals(modin_df_casted, expected_df_casted)
modin_df = pd.DataFrame(index=["row1"], columns=["col1"])
modin_df["col1"]["row1"] = 11
modin_df_casted = modin_df.astype(int)
expected_df = pandas.DataFrame(index=["row1"], columns=["col1"])
expected_df["col1"]["row1"] = 11
expected_df_casted = expected_df.astype(int)
df_equals(modin_df_casted, expected_df_casted)
with pytest.raises(KeyError):
modin_df.astype({"not_exists": np.uint8})
def test_rename_axis_inplace():
test_frame = pandas.DataFrame(tm.getSeriesData())
modin_df = pd.DataFrame(test_frame)
result = test_frame.copy()
modin_result = modin_df.copy()
no_return = result.rename_axis("foo", inplace=True)
modin_no_return = modin_result.rename_axis("foo", inplace=True)
assert no_return is modin_no_return
df_equals(modin_result, result)
result = test_frame.copy()
modin_result = modin_df.copy()
no_return = result.rename_axis("bar", axis=1, inplace=True)
modin_no_return = modin_result.rename_axis("bar", axis=1, inplace=True)
assert no_return is modin_no_return
df_equals(modin_result, result)
def setUp(self):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = DataFrame(
{
"A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
"B": ["one", "one", "two", "three", "two", "two", "one", "three"],
"C": np.random.randn(8),
"D": np.random.randn(8),
}
)
self.df_mixed_floats = DataFrame(
{
"A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
"B": ["one", "one", "two", "three", "two", "two", "one", "three"],
"C": np.random.randn(8),
"D": np.array(np.random.randn(8), dtype="float32"),
}
)
index = MultiIndex(
levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=["first", "second"],
)
self.mframe = DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])
self.three_group = DataFrame(
{
"A": ["foo", "foo", "foo", "foo", "bar", "bar", "bar", "bar", "foo", "foo", "foo"],
"B": ["one", "one", "one", "two", "one", "one", "one", "two", "two", "two", "one"],
"C": ["dull", "dull", "shiny", "dull", "dull", "shiny", "shiny", "dull", "shiny", "shiny", "shiny"],
"D": np.random.randn(11),
"E": np.random.randn(11),
"F": np.random.randn(11),
}
)
def test_ix_assign_column_mixed(self):
# GH #1142
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
orig = df.ix[:, 'B'].copy()
df.ix[:, 'B'] = df.ix[:, 'B'] + 1
assert_series_equal(df.B, orig + 1)
# GH 3668, mixed frame with series value
df = DataFrame({'x':range(10), 'y':range(10,20),'z' : 'bar'})
expected = df.copy()
expected.ix[0, 'y'] = 1000
expected.ix[2, 'y'] = 1200
expected.ix[4, 'y'] = 1400
expected.ix[6, 'y'] = 1600
expected.ix[8, 'y'] = 1800
df.ix[df.x % 2 == 0, 'y'] = df.ix[df.x % 2 == 0, 'y'] * 100
assert_frame_equal(df,expected)
def test_ix_assign_column_mixed(self):
# GH #1142
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
orig = df.ix[:, 'B'].copy()
df.ix[:, 'B'] = df.ix[:, 'B'] + 1
assert_series_equal(df.B, orig + 1)
# GH 3668, mixed frame with series value
df = DataFrame({'x':range(10), 'y':range(10,20),'z' : 'bar'})
expected = df.copy()
expected.ix[0, 'y'] = 1000
expected.ix[2, 'y'] = 1200
expected.ix[4, 'y'] = 1400
expected.ix[6, 'y'] = 1600
expected.ix[8, 'y'] = 1800
df.ix[df.x % 2 == 0, 'y'] = df.ix[df.x % 2 == 0, 'y'] * 100
assert_frame_equal(df,expected)
def setup_method(self, method):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = df()
self.df_mixed_floats = DataFrame({
'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
'C':
np.random.randn(8),
'D':
np.array(np.random.randn(8), dtype='float32')
})
self.mframe = mframe()
self.three_group = DataFrame({
'A': [
'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar', 'foo',
'foo', 'foo'
],
'B': [
'one', 'one', 'one', 'two', 'one', 'one', 'one', 'two', 'two',
'two', 'one'
],
'C': [
'dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'
],
'D':
np.random.randn(11),
'E':
np.random.randn(11),
'F':
np.random.randn(11)
})
def test_ix_assign_column_mixed(self):
# GH #1142
df = DataFrame(tm.getSeriesData())
df['foo'] = 'bar'
orig = df.ix[:, 'B'].copy()
df.ix[:, 'B'] = df.ix[:, 'B'] + 1
assert_series_equal(df.B, orig + 1)
# GH 3668, mixed frame with series value
df = DataFrame({'x':lrange(10), 'y':lrange(10,20),'z' : 'bar'})
expected = df.copy()
for i in range(5):
indexer = i*2
v = 1000 + i*200
expected.ix[indexer, 'y'] = v
self.assert_(expected.ix[indexer, 'y'] == v)
df.ix[df.x % 2 == 0, 'y'] = df.ix[df.x % 2 == 0, 'y'] * 100
assert_frame_equal(df,expected)
# GH 4508, making sure consistency of assignments
df = DataFrame({'a':[1,2,3],'b':[0,1,2]})
df.ix[[0,2,],'b'] = [100,-100]
expected = DataFrame({'a' : [1,2,3], 'b' : [100,1,-100] })
assert_frame_equal(df,expected)
df = pd.DataFrame({'a': lrange(4) })
df['b'] = np.nan
df.ix[[1,3],'b'] = [100,-100]
expected = DataFrame({'a' : [0,1,2,3], 'b' : [np.nan,100,np.nan,-100] })
assert_frame_equal(df,expected)
# ok, but chained assignments are dangerous
df = pd.DataFrame({'a': lrange(4) })
df['b'] = np.nan
df['b'].ix[[1,3]] = [100,-100]
assert_frame_equal(df,expected)
def setUp(self):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = DataFrame(
{'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
'C': np.random.randn(8),
'D': np.random.randn(8)})
self.df_mixed_floats = DataFrame(
{'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
'C': np.random.randn(8),
'D': np.array(
np.random.randn(8), dtype='float32')})
index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'], ['one', 'two',
'three']],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
[0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=['first', 'second'])
self.mframe = DataFrame(np.random.randn(10, 3), index=index,
columns=['A', 'B', 'C'])
self.three_group = DataFrame(
{'A': ['foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar',
'foo', 'foo', 'foo'],
'B': ['one', 'one', 'one', 'two', 'one', 'one', 'one', 'two',
'two', 'two', 'one'],
'C': ['dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'],
'D': np.random.randn(11),
'E': np.random.randn(11),
'F': np.random.randn(11)})
def _skip_if_no_xlsxwriter():
try:
import xlsxwriter # NOQA
except ImportError:
raise nose.SkipTest('xlsxwriter not installed, skipping')
def _skip_if_no_excelsuite():
_skip_if_no_xlrd()
_skip_if_no_xlwt()
_skip_if_no_openpyxl()
_seriesd = tm.getSeriesData()
_tsd = tm.getTimeSeriesData()
_frame = DataFrame(_seriesd)[:10]
_frame2 = DataFrame(_seriesd, columns=['D', 'C', 'B', 'A'])[:10]
_tsframe = tm.makeTimeDataFrame()[:5]
_mixed_frame = _frame.copy()
_mixed_frame['foo'] = 'bar'
class SharedItems(object):
def setUp(self):
self.dirpath = tm.get_data_path()
self.csv1 = os.path.join(self.dirpath, 'test1.csv')
self.csv2 = os.path.join(self.dirpath, 'test2.csv')
self.xls1 = os.path.join(self.dirpath, 'test.xls')
self.xlsx1 = os.path.join(self.dirpath, 'test.xlsx')
import os
import sys
import unittest
from textwrap import dedent
from numpy import nan
from numpy.random import randn
import numpy as np
from pandas import DataFrame, Series, Index
import pandas.core.format as fmt
import pandas.util.testing as tm
import pandas
import pandas as pd
_frame = DataFrame(tm.getSeriesData())
def curpath():
pth, _ = os.path.split(os.path.abspath(__file__))
return pth
class TestDataFrameFormatting(unittest.TestCase):
def setUp(self):
self.frame = _frame.copy()
def test_repr_embedded_ndarray(self):
arr = np.empty(10, dtype=[('err', object)])
for i in range(len(arr)):
arr['err'][i] = np.random.randn(i)
import warnings
from numpy import nan
from numpy.random import randn
import numpy as np
from pandas import DataFrame, Series, Index
from pandas.util.py3compat import lzip
import pandas.core.format as fmt
import pandas.util.testing as tm
import pandas
import pandas as pd
from pandas.core.config import (set_option, get_option,
option_context, reset_option)
_frame = DataFrame(tm.getSeriesData())
def curpath():
pth, _ = os.path.split(os.path.abspath(__file__))
return pth
class TestDataFrameFormatting(unittest.TestCase):
_multiprocess_can_split_ = True
def setUp(self):
self.warn_filters = warnings.filters
warnings.filterwarnings('ignore',
category=FutureWarning,
module=".*format")
self.frame = _frame.copy()
def test_invert(self):
_seriesd = tm.getSeriesData()
df = pd.DataFrame(_seriesd)
assert_frame_equal(-(df < 0), ~(df < 0))
def _skip_if_no_xlsxwriter():
try:
import xlsxwriter # NOQA
except ImportError:
raise nose.SkipTest('xlsxwriter not installed, skipping')
def _skip_if_no_excelsuite():
_skip_if_no_xlrd()
_skip_if_no_xlwt()
_skip_if_no_openpyxl()
_seriesd = tm.getSeriesData()
_tsd = tm.getTimeSeriesData()
_frame = DataFrame(_seriesd)[:10]
_frame2 = DataFrame(_seriesd, columns=['D', 'C', 'B', 'A'])[:10]
_tsframe = tm.makeTimeDataFrame()[:5]
_mixed_frame = _frame.copy()
_mixed_frame['foo'] = 'bar'
class SharedItems(object):
def setUp(self):
self.dirpath = tm.get_data_path()
self.csv1 = os.path.join(self.dirpath, 'test1.csv')
self.csv2 = os.path.join(self.dirpath, 'test2.csv')
self.xls1 = os.path.join(self.dirpath, 'test.xls')
self.xlsx1 = os.path.join(self.dirpath, 'test.xlsx')
def setUp(self):
self.frame = DataFrame(tm.getSeriesData())
self.mixed_frame = self.frame.copy()
self.mixed_frame['foo'] = 'bar'
def frame():
return DataFrame(tm.getSeriesData())
def seriesd():
return tm.getSeriesData()
def setUp(self):
self.frame = DataFrame(tm.getSeriesData())
self.mixed_frame = self.frame.copy()
self.mixed_frame['foo'] = 'bar'