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 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 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 mixed_float_frame():
"""
Fixture for DataFrame of different float types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
df = DataFrame(tm.getSeriesData())
df.A = df.A.astype('float16')
df.B = df.B.astype('float32')
df.C = df.C.astype('float64')
return df
def mixed_float_frame():
"""
Fixture for DataFrame of different float types with index of unique strings
Columns are ['A', 'B', 'C', 'D'].
"""
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 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_df_where_with_category(self, kwargs):
# GH 16979
df = DataFrame(np.arange(2 * 3).reshape(2, 3), columns=list("ABC"))
mask = np.array([[True, False, True], [False, True, True]])
# change type to category
df.A = df.A.astype("category")
df.B = df.B.astype("category")
df.C = df.C.astype("category")
result = df.A.where(mask[:, 0], **kwargs)
expected = Series(pd.Categorical([0, np.nan], categories=[0, 3]), name="A")
tm.assert_series_equal(result, expected)
def test_df_where_with_category(self, kwargs):
# GH#16979
df = DataFrame(np.arange(2 * 3).reshape(2, 3), columns=list("ABC"))
mask = np.array([[True, False, False], [False, False, True]])
# change type to category
df.A = df.A.astype("category")
df.B = df.B.astype("category")
df.C = df.C.astype("category")
result = df.where(mask, **kwargs)
A = pd.Categorical([0, np.nan], categories=[0, 3])
B = pd.Categorical([np.nan, np.nan], categories=[1, 4])
C = pd.Categorical([np.nan, 5], categories=[2, 5])
expected = DataFrame({"A": A, "B": B, "C": C})
tm.assert_frame_equal(result, expected)
# Check Series.where while we're here
result = df.A.where(mask[:, 0], **kwargs)
expected = Series(A, name="A")
tm.assert_series_equal(result, expected)
def test_df_where_change_dtype(self):
# GH 16979
df = DataFrame(np.arange(2 * 3).reshape(2, 3), columns=list("ABC"))
mask = np.array([[True, False, False], [False, False, True]])
result = df.where(mask)
expected = DataFrame([[0, np.nan, np.nan], [np.nan, np.nan, 5]],
columns=list("ABC"))
tm.assert_frame_equal(result, expected)
# change type to category
df.A = df.A.astype("category")
df.B = df.B.astype("category")
df.C = df.C.astype("category")
result = df.where(mask)
A = pd.Categorical([0, np.nan], categories=[0, 3])
B = pd.Categorical([np.nan, np.nan], categories=[1, 4])
C = pd.Categorical([np.nan, 5], categories=[2, 5])
expected = DataFrame({"A": A, "B": B, "C": C})
tm.assert_frame_equal(result, expected)
# b 2
# c 2
# dtype: int64
def f(x):
return Series([x.min(), x.max()], index=['min', 'max'])
frame.apply(f)
# result 求每一行的最大、最小值
# A B C
# min 0 1 2
# max 6 7 8
_format = lambda x: '%.2f' % x
frame.applymap(_format)
# result 针对dataframe做出改变
# A B C
# a 0.00 1.00 2.00
# b 3.00 4.00 5.00
# c 6.00 7.00 8.00
frame.A = frame['A'].map(_format)
print(frame)
# result 针对Series
# A B C
# a 0.00 1 2
# b 3.00 4 5
# c 6.00 7 8
# Name: A, dtype: object