340 lines
12 KiB
Python
340 lines
12 KiB
Python
import numpy as np
|
|
import pytest
|
|
|
|
import pandas.util._test_decorators as td
|
|
|
|
from pandas import DataFrame, Series, date_range
|
|
import pandas._testing as tm
|
|
|
|
|
|
class TestDataFrameInterpolate:
|
|
def test_interp_basic(self):
|
|
df = DataFrame(
|
|
{
|
|
"A": [1, 2, np.nan, 4],
|
|
"B": [1, 4, 9, np.nan],
|
|
"C": [1, 2, 3, 5],
|
|
"D": list("abcd"),
|
|
}
|
|
)
|
|
expected = DataFrame(
|
|
{
|
|
"A": [1.0, 2.0, 3.0, 4.0],
|
|
"B": [1.0, 4.0, 9.0, 9.0],
|
|
"C": [1, 2, 3, 5],
|
|
"D": list("abcd"),
|
|
}
|
|
)
|
|
result = df.interpolate()
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.set_index("C").interpolate()
|
|
expected = df.set_index("C")
|
|
expected.loc[3, "A"] = 3
|
|
expected.loc[5, "B"] = 9
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
def test_interp_empty(self):
|
|
# https://github.com/pandas-dev/pandas/issues/35598
|
|
df = DataFrame()
|
|
result = df.interpolate()
|
|
assert result is not df
|
|
expected = df
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
def test_interp_bad_method(self):
|
|
df = DataFrame(
|
|
{
|
|
"A": [1, 2, np.nan, 4],
|
|
"B": [1, 4, 9, np.nan],
|
|
"C": [1, 2, 3, 5],
|
|
"D": list("abcd"),
|
|
}
|
|
)
|
|
msg = (
|
|
r"method must be one of \['linear', 'time', 'index', 'values', "
|
|
r"'nearest', 'zero', 'slinear', 'quadratic', 'cubic', "
|
|
r"'barycentric', 'krogh', 'spline', 'polynomial', "
|
|
r"'from_derivatives', 'piecewise_polynomial', 'pchip', 'akima', "
|
|
r"'cubicspline'\]. Got 'not_a_method' instead."
|
|
)
|
|
with pytest.raises(ValueError, match=msg):
|
|
df.interpolate(method="not_a_method")
|
|
|
|
def test_interp_combo(self):
|
|
df = DataFrame(
|
|
{
|
|
"A": [1.0, 2.0, np.nan, 4.0],
|
|
"B": [1, 4, 9, np.nan],
|
|
"C": [1, 2, 3, 5],
|
|
"D": list("abcd"),
|
|
}
|
|
)
|
|
|
|
result = df["A"].interpolate()
|
|
expected = Series([1.0, 2.0, 3.0, 4.0], name="A")
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
result = df["A"].interpolate(downcast="infer")
|
|
expected = Series([1, 2, 3, 4], name="A")
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
def test_interp_nan_idx(self):
|
|
df = DataFrame({"A": [1, 2, np.nan, 4], "B": [np.nan, 2, 3, 4]})
|
|
df = df.set_index("A")
|
|
msg = (
|
|
"Interpolation with NaNs in the index has not been implemented. "
|
|
"Try filling those NaNs before interpolating."
|
|
)
|
|
with pytest.raises(NotImplementedError, match=msg):
|
|
df.interpolate(method="values")
|
|
|
|
@td.skip_if_no_scipy
|
|
def test_interp_various(self):
|
|
df = DataFrame(
|
|
{"A": [1, 2, np.nan, 4, 5, np.nan, 7], "C": [1, 2, 3, 5, 8, 13, 21]}
|
|
)
|
|
df = df.set_index("C")
|
|
expected = df.copy()
|
|
result = df.interpolate(method="polynomial", order=1)
|
|
|
|
expected.A.loc[3] = 2.66666667
|
|
expected.A.loc[13] = 5.76923076
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(method="cubic")
|
|
# GH #15662.
|
|
expected.A.loc[3] = 2.81547781
|
|
expected.A.loc[13] = 5.52964175
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(method="nearest")
|
|
expected.A.loc[3] = 2
|
|
expected.A.loc[13] = 5
|
|
tm.assert_frame_equal(result, expected, check_dtype=False)
|
|
|
|
result = df.interpolate(method="quadratic")
|
|
expected.A.loc[3] = 2.82150771
|
|
expected.A.loc[13] = 6.12648668
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(method="slinear")
|
|
expected.A.loc[3] = 2.66666667
|
|
expected.A.loc[13] = 5.76923077
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(method="zero")
|
|
expected.A.loc[3] = 2.0
|
|
expected.A.loc[13] = 5
|
|
tm.assert_frame_equal(result, expected, check_dtype=False)
|
|
|
|
@td.skip_if_no_scipy
|
|
def test_interp_alt_scipy(self):
|
|
df = DataFrame(
|
|
{"A": [1, 2, np.nan, 4, 5, np.nan, 7], "C": [1, 2, 3, 5, 8, 13, 21]}
|
|
)
|
|
result = df.interpolate(method="barycentric")
|
|
expected = df.copy()
|
|
expected.loc[2, "A"] = 3
|
|
expected.loc[5, "A"] = 6
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(method="barycentric", downcast="infer")
|
|
tm.assert_frame_equal(result, expected.astype(np.int64))
|
|
|
|
result = df.interpolate(method="krogh")
|
|
expectedk = df.copy()
|
|
expectedk["A"] = expected["A"]
|
|
tm.assert_frame_equal(result, expectedk)
|
|
|
|
result = df.interpolate(method="pchip")
|
|
expected.loc[2, "A"] = 3
|
|
expected.loc[5, "A"] = 6.0
|
|
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
def test_interp_rowwise(self):
|
|
df = DataFrame(
|
|
{
|
|
0: [1, 2, np.nan, 4],
|
|
1: [2, 3, 4, np.nan],
|
|
2: [np.nan, 4, 5, 6],
|
|
3: [4, np.nan, 6, 7],
|
|
4: [1, 2, 3, 4],
|
|
}
|
|
)
|
|
result = df.interpolate(axis=1)
|
|
expected = df.copy()
|
|
expected.loc[3, 1] = 5
|
|
expected.loc[0, 2] = 3
|
|
expected.loc[1, 3] = 3
|
|
expected[4] = expected[4].astype(np.float64)
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(axis=1, method="values")
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.interpolate(axis=0)
|
|
expected = df.interpolate()
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize(
|
|
"axis_name, axis_number",
|
|
[
|
|
pytest.param("rows", 0, id="rows_0"),
|
|
pytest.param("index", 0, id="index_0"),
|
|
pytest.param("columns", 1, id="columns_1"),
|
|
],
|
|
)
|
|
def test_interp_axis_names(self, axis_name, axis_number):
|
|
# GH 29132: test axis names
|
|
data = {0: [0, np.nan, 6], 1: [1, np.nan, 7], 2: [2, 5, 8]}
|
|
|
|
df = DataFrame(data, dtype=np.float64)
|
|
result = df.interpolate(axis=axis_name, method="linear")
|
|
expected = df.interpolate(axis=axis_number, method="linear")
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
def test_rowwise_alt(self):
|
|
df = DataFrame(
|
|
{
|
|
0: [0, 0.5, 1.0, np.nan, 4, 8, np.nan, np.nan, 64],
|
|
1: [1, 2, 3, 4, 3, 2, 1, 0, -1],
|
|
}
|
|
)
|
|
df.interpolate(axis=0)
|
|
# TODO: assert something?
|
|
|
|
@pytest.mark.parametrize(
|
|
"check_scipy", [False, pytest.param(True, marks=td.skip_if_no_scipy)]
|
|
)
|
|
def test_interp_leading_nans(self, check_scipy):
|
|
df = DataFrame(
|
|
{"A": [np.nan, np.nan, 0.5, 0.25, 0], "B": [np.nan, -3, -3.5, np.nan, -4]}
|
|
)
|
|
result = df.interpolate()
|
|
expected = df.copy()
|
|
expected["B"].loc[3] = -3.75
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
if check_scipy:
|
|
result = df.interpolate(method="polynomial", order=1)
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
def test_interp_raise_on_only_mixed(self, axis):
|
|
df = DataFrame(
|
|
{
|
|
"A": [1, 2, np.nan, 4],
|
|
"B": ["a", "b", "c", "d"],
|
|
"C": [np.nan, 2, 5, 7],
|
|
"D": [np.nan, np.nan, 9, 9],
|
|
"E": [1, 2, 3, 4],
|
|
}
|
|
)
|
|
msg = (
|
|
"Cannot interpolate with all object-dtype columns "
|
|
"in the DataFrame. Try setting at least one "
|
|
"column to a numeric dtype."
|
|
)
|
|
with pytest.raises(TypeError, match=msg):
|
|
df.astype("object").interpolate(axis=axis)
|
|
|
|
def test_interp_raise_on_all_object_dtype(self):
|
|
# GH 22985
|
|
df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}, dtype="object")
|
|
msg = (
|
|
"Cannot interpolate with all object-dtype columns "
|
|
"in the DataFrame. Try setting at least one "
|
|
"column to a numeric dtype."
|
|
)
|
|
with pytest.raises(TypeError, match=msg):
|
|
df.interpolate()
|
|
|
|
def test_interp_inplace(self):
|
|
df = DataFrame({"a": [1.0, 2.0, np.nan, 4.0]})
|
|
expected = DataFrame({"a": [1.0, 2.0, 3.0, 4.0]})
|
|
result = df.copy()
|
|
return_value = result["a"].interpolate(inplace=True)
|
|
assert return_value is None
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
result = df.copy()
|
|
return_value = result["a"].interpolate(inplace=True, downcast="infer")
|
|
assert return_value is None
|
|
tm.assert_frame_equal(result, expected.astype("int64"))
|
|
|
|
def test_interp_inplace_row(self):
|
|
# GH 10395
|
|
result = DataFrame(
|
|
{"a": [1.0, 2.0, 3.0, 4.0], "b": [np.nan, 2.0, 3.0, 4.0], "c": [3, 2, 2, 2]}
|
|
)
|
|
expected = result.interpolate(method="linear", axis=1, inplace=False)
|
|
return_value = result.interpolate(method="linear", axis=1, inplace=True)
|
|
assert return_value is None
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
def test_interp_ignore_all_good(self):
|
|
# GH
|
|
df = DataFrame(
|
|
{
|
|
"A": [1, 2, np.nan, 4],
|
|
"B": [1, 2, 3, 4],
|
|
"C": [1.0, 2.0, np.nan, 4.0],
|
|
"D": [1.0, 2.0, 3.0, 4.0],
|
|
}
|
|
)
|
|
expected = DataFrame(
|
|
{
|
|
"A": np.array([1, 2, 3, 4], dtype="float64"),
|
|
"B": np.array([1, 2, 3, 4], dtype="int64"),
|
|
"C": np.array([1.0, 2.0, 3, 4.0], dtype="float64"),
|
|
"D": np.array([1.0, 2.0, 3.0, 4.0], dtype="float64"),
|
|
}
|
|
)
|
|
|
|
result = df.interpolate(downcast=None)
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
# all good
|
|
result = df[["B", "D"]].interpolate(downcast=None)
|
|
tm.assert_frame_equal(result, df[["B", "D"]])
|
|
|
|
def test_interp_time_inplace_axis(self, axis):
|
|
# GH 9687
|
|
periods = 5
|
|
idx = date_range(start="2014-01-01", periods=periods)
|
|
data = np.random.rand(periods, periods)
|
|
data[data < 0.5] = np.nan
|
|
expected = DataFrame(index=idx, columns=idx, data=data)
|
|
|
|
result = expected.interpolate(axis=0, method="time")
|
|
return_value = expected.interpolate(axis=0, method="time", inplace=True)
|
|
assert return_value is None
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize("axis_name, axis_number", [("index", 0), ("columns", 1)])
|
|
def test_interp_string_axis(self, axis_name, axis_number):
|
|
# https://github.com/pandas-dev/pandas/issues/25190
|
|
x = np.linspace(0, 100, 1000)
|
|
y = np.sin(x)
|
|
df = DataFrame(
|
|
data=np.tile(y, (10, 1)), index=np.arange(10), columns=x
|
|
).reindex(columns=x * 1.005)
|
|
result = df.interpolate(method="linear", axis=axis_name)
|
|
expected = df.interpolate(method="linear", axis=axis_number)
|
|
tm.assert_frame_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize("method", ["ffill", "bfill", "pad"])
|
|
def test_interp_fillna_methods(self, axis, method):
|
|
# GH 12918
|
|
df = DataFrame(
|
|
{
|
|
"A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
|
|
"B": [2.0, 4.0, 6.0, np.nan, 8.0, 10.0],
|
|
"C": [3.0, 6.0, 9.0, np.nan, np.nan, 30.0],
|
|
}
|
|
)
|
|
expected = df.fillna(axis=axis, method=method)
|
|
result = df.interpolate(method=method, axis=axis)
|
|
tm.assert_frame_equal(result, expected)
|