def test_interp_limit_direction(self):
# These tests are for issue #9218 -- fill NaNs in both directions.
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
expected = Series([1., 3., np.nan, 7., 9., 11.])
result = s.interpolate(method='linear', limit=2,
limit_direction='backward')
assert_series_equal(result, expected)
expected = Series([1., 3., 5., np.nan, 9., 11.])
result = s.interpolate(method='linear', limit=1,
limit_direction='both')
assert_series_equal(result, expected)
# Check that this works on a longer series of nans.
s = Series([1, 3, np.nan, np.nan, np.nan, 7, 9, np.nan, np.nan, 12,
np.nan])
expected = Series([1., 3., 4., 5., 6., 7., 9., 10., 11., 12., 12.])
result = s.interpolate(method='linear', limit=2,
limit_direction='both')
assert_series_equal(result, expected)
expected = Series([1., 3., 4., np.nan, 6., 7., 9., 10., 11., 12., 12.])
result = s.interpolate(method='linear', limit=1,
limit_direction='both')
assert_series_equal(result, expected)
def test_no_order(self):
_skip_if_no_scipy()
s = Series([0, 1, np.nan, 3])
with tm.assertRaises(ValueError):
s.interpolate(method='polynomial')
with tm.assertRaises(ValueError):
s.interpolate(method='spline')
def test_spline_interpolation(self):
tm._skip_if_no_scipy()
s = Series(np.arange(10) ** 2)
s[np.random.randint(0, 9, 3)] = np.nan
result1 = s.interpolate(method='spline', order=1)
expected1 = s.interpolate(method='spline', order=1)
assert_series_equal(result1, expected1)
def test_interp_all_good(self):
s = Series([1, 2, 3])
result = s.interpolate(method='polynomial', order=1)
assert_series_equal(result, s)
# non-scipy
result = s.interpolate()
assert_series_equal(result, s)
def test_spline_extrapolate(self):
s = Series([1, 2, 3, 4, np.nan, 6, np.nan])
result3 = s.interpolate(method='spline', order=1, ext=3)
expected3 = Series([1., 2., 3., 4., 5., 6., 6.])
assert_series_equal(result3, expected3)
result1 = s.interpolate(method='spline', order=1, ext=0)
expected1 = Series([1., 2., 3., 4., 5., 6., 7.])
assert_series_equal(result1, expected1)
def test_nan_interpolate(self):
s = Series([0, 1, np.nan, 3])
result = s.interpolate()
expected = Series([0, 1, 2, 3])
assert_series_equal(result, expected)
_skip_if_no_scipy()
result = s.interpolate(method='polynomial', order=1)
assert_series_equal(result, expected)
def test_interp_scipy_basic(self):
tm._skip_if_no_scipy()
s = Series([1, 3, np.nan, 12, np.nan, 25])
# slinear
expected = Series([1., 3., 7.5, 12., 18.5, 25.])
result = s.interpolate(method='slinear')
assert_series_equal(result, expected)
result = s.interpolate(method='slinear', donwcast='infer')
assert_series_equal(result, expected)
# nearest
expected = Series([1, 3, 3, 12, 12, 25])
result = s.interpolate(method='nearest')
assert_series_equal(result, expected.astype('float'))
result = s.interpolate(method='nearest', downcast='infer')
assert_series_equal(result, expected)
# zero
expected = Series([1, 3, 3, 12, 12, 25])
result = s.interpolate(method='zero')
assert_series_equal(result, expected.astype('float'))
result = s.interpolate(method='zero', downcast='infer')
assert_series_equal(result, expected)
# quadratic
expected = Series([1, 3., 6.769231, 12., 18.230769, 25.])
result = s.interpolate(method='quadratic')
assert_series_equal(result, expected)
result = s.interpolate(method='quadratic', downcast='infer')
assert_series_equal(result, expected)
# cubic
expected = Series([1., 3., 6.8, 12., 18.2, 25.])
result = s.interpolate(method='cubic')
assert_series_equal(result, expected)
def test_interp_multiIndex(self):
idx = MultiIndex.from_tuples([(0, 'a'), (1, 'b'), (2, 'c')])
s = Series([1, 2, np.nan], index=idx)
expected = s.copy()
expected.loc[2] = 2
result = s.interpolate()
assert_series_equal(result, expected)
tm._skip_if_no_scipy()
with tm.assertRaises(ValueError):
s.interpolate(method='polynomial', order=1)
def test_spline_extrapolate(self):
tm.skip_if_no_package(
'scipy', '0.15',
'setting ext on scipy.interpolate.UnivariateSpline')
s = Series([1, 2, 3, 4, np.nan, 6, np.nan])
result3 = s.interpolate(method='spline', order=1, ext=3)
expected3 = Series([1., 2., 3., 4., 5., 6., 6.])
assert_series_equal(result3, expected3)
result1 = s.interpolate(method='spline', order=1, ext=0)
expected1 = Series([1., 2., 3., 4., 5., 6., 7.])
assert_series_equal(result1, expected1)
def test_interp_limit_forward(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
# Provide 'forward' (the default) explicitly here.
expected = Series([1., 3., 5., 7., np.nan, 11.])
result = s.interpolate(method='linear', limit=2,
limit_direction='forward')
assert_series_equal(result, expected)
result = s.interpolate(method='linear', limit=2,
limit_direction='FORWARD')
assert_series_equal(result, expected)
def test_interpolate_corners(self):
s = Series([np.nan, np.nan])
assert_series_equal(s.interpolate(), s)
s = Series([]).interpolate()
assert_series_equal(s.interpolate(), s)
_skip_if_no_scipy()
s = Series([np.nan, np.nan])
assert_series_equal(s.interpolate(method='polynomial', order=1), s)
s = Series([]).interpolate()
assert_series_equal(s.interpolate(method='polynomial', order=1), s)
def test_interp_limit_to_ends(self):
# These test are for issue #10420 -- flow back to beginning.
s = Series([np.nan, np.nan, 5, 7, 9, np.nan])
expected = Series([5., 5., 5., 7., 9., np.nan])
result = s.interpolate(method='linear', limit=2,
limit_direction='backward')
assert_series_equal(result, expected)
expected = Series([5., 5., 5., 7., 9., 9.])
result = s.interpolate(method='linear', limit=2,
limit_direction='both')
assert_series_equal(result, expected)
def test_interp_timedelta64(self):
# GH 6424
df = Series([1, np.nan, 3],
index=pd.to_timedelta([1, 2, 3]))
result = df.interpolate(method='time')
expected = Series([1., 2., 3.],
index=pd.to_timedelta([1, 2, 3]))
assert_series_equal(result, expected)
# test for non uniform spacing
df = Series([1, np.nan, 3],
index=pd.to_timedelta([1, 2, 4]))
result = df.interpolate(method='time')
expected = Series([1., 1.666667, 3.],
index=pd.to_timedelta([1, 2, 4]))
assert_series_equal(result, expected)
def test_interp_datetime64(self):
tm._skip_if_no_scipy()
df = Series([1, np.nan, 3], index=date_range('1/1/2000', periods=3))
result = df.interpolate(method='nearest')
expected = Series([1., 1., 3.],
index=date_range('1/1/2000', periods=3))
assert_series_equal(result, expected)
def adapt_values(self, data, target_timestamps, merged_timestamps):
timelink = {}
for i in range(0, len(self.timestamp)):
timelink[self.timestamp[i]] = data[i]
length = len(merged_timestamps)
values = np.zeros(length)
values[:] = np.NaN
for i in range(0, length):
timekey = merged_timestamps[i]
if timekey in timelink:
values[i] = timelink[timekey]
s = Series(data=values)
s = s.interpolate()
values = []
for i in range(0, length):
timekey = merged_timestamps[i]
if timekey in target_timestamps:
values.append(s[i])
return values
def test_interp_unlimited(self):
# these test are for issue #16282 default Limit=None is unlimited
s = Series([np.nan, 1., 3., np.nan, np.nan, np.nan, 11., np.nan])
expected = Series([1., 1., 3., 5., 7., 9., 11., 11.])
result = s.interpolate(method='linear',
limit_direction='both')
assert_series_equal(result, expected)
expected = Series([np.nan, 1., 3., 5., 7., 9., 11., 11.])
result = s.interpolate(method='linear',
limit_direction='forward')
assert_series_equal(result, expected)
expected = Series([1., 1., 3., 5., 7., 9., 11., np.nan])
result = s.interpolate(method='linear',
limit_direction='backward')
assert_series_equal(result, expected)
def test_interp_limit(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
expected = Series([1., 3., 5., 7., np.nan, 11.])
result = s.interpolate(method='linear', limit=2)
assert_series_equal(result, expected)
# GH 9217, make sure limit is an int and greater than 0
methods = ['linear', 'time', 'index', 'values', 'nearest', 'zero',
'slinear', 'quadratic', 'cubic', 'barycentric', 'krogh',
'polynomial', 'spline', 'piecewise_polynomial', None,
'from_derivatives', 'pchip', 'akima']
s = pd.Series([1, 2, np.nan, np.nan, 5])
for limit in [-1, 0, 1., 2.]:
for method in methods:
with pytest.raises(ValueError):
s.interpolate(limit=limit, method=method)
def test_interp_limit_before_ends(self):
# These test are for issue #11115 -- limit ends properly.
s = Series([np.nan, np.nan, 5, 7, np.nan, np.nan])
expected = Series([np.nan, np.nan, 5., 7., 7., np.nan])
result = s.interpolate(method='linear', limit=1,
limit_direction='forward')
assert_series_equal(result, expected)
expected = Series([np.nan, 5., 5., 7., np.nan, np.nan])
result = s.interpolate(method='linear', limit=1,
limit_direction='backward')
assert_series_equal(result, expected)
expected = Series([np.nan, 5., 5., 7., 7., np.nan])
result = s.interpolate(method='linear', limit=1,
limit_direction='both')
assert_series_equal(result, expected)
def test_interpolate_index_values(self):
s = Series(np.nan, index=np.sort(np.random.rand(30)))
s[::3] = np.random.randn(10)
vals = s.index.values.astype(float)
result = s.interpolate(method='index')
expected = s.copy()
bad = isnull(expected.values)
good = ~bad
expected = Series(
np.interp(vals[bad], vals[good], s.values[good]), index=s.index[bad])
assert_series_equal(result[bad], expected)
# 'values' is synonymous with 'index' for the method kwarg
other_result = s.interpolate(method='values')
assert_series_equal(other_result, result)
assert_series_equal(other_result[bad], expected)
def interpolate(a, target_size):
length = len(a)
values = np.zeros(target_size)
values[:] = np.NaN
step = target_size / length
for i in range(0, length):
values[i * step] = a[i]
s = Series(data=values)
s = s.interpolate()
return s.values
def test_interp_scipy_basic(self):
tm._skip_if_no_scipy()
s = Series([1, 3, np.nan, 12, np.nan, 25])
# slinear
expected = Series([1., 3., 7.5, 12., 18.5, 25.])
result = s.interpolate(method='slinear')
assert_series_equal(result, expected)
result = s.interpolate(method='slinear', downcast='infer')
assert_series_equal(result, expected)
# nearest
expected = Series([1, 3, 3, 12, 12, 25])
result = s.interpolate(method='nearest')
assert_series_equal(result, expected.astype('float'))
result = s.interpolate(method='nearest', downcast='infer')
assert_series_equal(result, expected)
# zero
expected = Series([1, 3, 3, 12, 12, 25])
result = s.interpolate(method='zero')
assert_series_equal(result, expected.astype('float'))
result = s.interpolate(method='zero', downcast='infer')
assert_series_equal(result, expected)
# quadratic
# GH #15662.
# new cubic and quadratic interpolation algorithms from scipy 0.19.0.
# previously `splmake` was used. See scipy/scipy#6710
if _is_scipy_ge_0190:
expected = Series([1, 3., 6.823529, 12., 18.058824, 25.])
else:
expected = Series([1, 3., 6.769231, 12., 18.230769, 25.])
result = s.interpolate(method='quadratic')
assert_series_equal(result, expected)
result = s.interpolate(method='quadratic', downcast='infer')
assert_series_equal(result, expected)
# cubic
expected = Series([1., 3., 6.8, 12., 18.2, 25.])
result = s.interpolate(method='cubic')
assert_series_equal(result, expected)
def test_interpolate_index_values(self):
s = Series(np.nan, index=np.sort(np.random.rand(30)))
s[::3] = np.random.randn(10)
vals = s.index.values.astype(float)
result = s.interpolate(method='values')
expected = s.copy()
bad = isnull(expected.values)
good = -bad
expected = Series(
np.interp(vals[bad], vals[good], s.values[good]), index=s.index[bad])
assert_series_equal(result[bad], expected)
def test_nan_str_index(self):
s = Series([0, 1, 2, np.nan], index=list('abcd'))
result = s.interpolate()
expected = Series([0., 1., 2., 2.], index=list('abcd'))
assert_series_equal(result, expected)
def test_nan_interpolate(self, kwargs):
s = Series([0, 1, np.nan, 3])
result = s.interpolate(**kwargs)
expected = Series([0.0, 1.0, 2.0, 3.0])
tm.assert_series_equal(result, expected)
def test_interp_quad(self):
_skip_if_no_scipy()
sq = Series([1, 4, np.nan, 16], index=[1, 2, 3, 4])
result = sq.interpolate(method='quadratic')
expected = Series([1, 4, 9, 16], index=[1, 2, 3, 4])
assert_series_equal(result, expected)
def test_nan_irregular_index(self):
s = Series([1, 2, np.nan, 4], index=[1, 3, 5, 9])
result = s.interpolate()
expected = Series([1, 2, 3, 4], index=[1, 3, 5, 9])
assert_series_equal(result, expected)
def test_interpolate_non_ts(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
with tm.assertRaises(ValueError):
s.interpolate(method='time')
def test_interp_quad(self):
sq = Series([1, 4, np.nan, 16], index=[1, 2, 3, 4])
result = sq.interpolate(method="quadratic")
expected = Series([1.0, 4.0, 9.0, 16.0], index=[1, 2, 3, 4])
tm.assert_series_equal(result, expected)
def test_interp_nonmono_raise(self):
tm._skip_if_no_scipy()
s = Series([1, np.nan, 3], index=[0, 2, 1])
with tm.assertRaises(ValueError):
s.interpolate(method='krogh')
def test_interp_nonmono_raise(self):
tm._skip_if_no_scipy()
s = Series([1, np.nan, 3], index=[0, 2, 1])
with pytest.raises(ValueError):
s.interpolate(method='krogh')
def test_spline(self):
tm._skip_if_no_scipy()
s = Series([1, 2, np.nan, 4, 5, np.nan, 7])
result = s.interpolate(method='spline', order=1)
expected = Series([1., 2., 3., 4., 5., 6., 7.])
assert_series_equal(result, expected)
def test_interpolate_corners(self, kwargs):
s = Series([np.nan, np.nan])
tm.assert_series_equal(s.interpolate(**kwargs), s)
s = Series([], dtype=object).interpolate()
tm.assert_series_equal(s.interpolate(**kwargs), s)
def test_spline_smooth(self):
tm._skip_if_no_scipy()
s = Series([1, 2, np.nan, 4, 5.1, np.nan, 7])
assert (s.interpolate(method='spline', order=3, s=0)[5] !=
s.interpolate(method='spline', order=3)[5])
def test_interpolate_non_ts(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
with pytest.raises(ValueError):
s.interpolate(method='time')
def test_nan_irregular_index(self):
s = Series([1, 2, np.nan, 4], index=[1, 3, 5, 9])
result = s.interpolate()
expected = Series([1., 2., 3., 4.], index=[1, 3, 5, 9])
assert_series_equal(result, expected)
def test_interp_nonmono_raise(self):
s = Series([1, np.nan, 3], index=[0, 2, 1])
msg = "krogh interpolation requires that the index be monotonic"
with pytest.raises(ValueError, match=msg):
s.interpolate(method="krogh")
def test_interp_limit(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
expected = Series([1.0, 3.0, 5.0, 7.0, np.nan, 11.0])
result = s.interpolate(method="linear", limit=2)
tm.assert_series_equal(result, expected)
def test_interp_limit(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
expected = Series([1., 3., 5., 7., np.nan, 11.])
result = s.interpolate(method='linear', limit=2)
assert_series_equal(result, expected)
class MySeries:
def __init__(self, *args, **kwargs):
self.x = Series(*args, **kwargs)
self.values = self.x.values
self.index = self.x.index
def rolling_mean(self, *args, **kwargs):
return MySeries(pd.rolling_mean(self.x, *args, **kwargs))
def rolling_count(self, *args, **kwargs):
return MySeries(pd.rolling_count(self.x, *args, **kwargs))
def rolling_sum(self, *args, **kwargs):
return MySeries(pd.rolling_sum(self.x, *args, **kwargs))
def rolling_median(self, *args, **kwargs):
return MySeries(pd.rolling_median(self.x, *args, **kwargs))
def rolling_min(self, *args, **kwargs):
return MySeries(pd.rolling_min(self.x, *args, **kwargs))
def rolling_max(self, *args, **kwargs):
return MySeries(pd.rolling_max(self.x, *args, **kwargs))
def rolling_std(self, *args, **kwargs):
return MySeries(pd.rolling_std(self.x, *args, **kwargs))
def rolling_var(self, *args, **kwargs):
return MySeries(pd.rolling_var(self.x, *args, **kwargs))
def rolling_skew(self, *args, **kwargs):
return MySeries(pd.rolling_skew(self.x, *args, **kwargs))
def rolling_kurtosis(self, *args, **kwargs):
return MySeries(pd.rolling_kurtosis(self.x, *args, **kwargs))
def rolling_window(self, *args, **kwargs):
return MySeries(pd.rolling_window(self.x, *args, **kwargs))
def cumprod(self, *args, **kwargs):
return MySeries(self.x.cumprod(*args, **kwargs))
def cumsum(self, *args, **kwargs):
return MySeries(self.x.cumsum(*args, **kwargs))
def diff(self, *args, **kwargs):
return MySeries(self.x.diff(*args, **kwargs))
def div(self, *args, **kwargs):
return MySeries(self.x.div(*args, **kwargs))
def mul(self, *args, **kwargs):
return MySeries(self.x.mul(*args, **kwargs))
def add(self, *args, **kwargs):
return MySeries(self.x.add(*args, **kwargs))
def dropna(self, *args, **kwargs):
return MySeries(self.x.dropna(*args, **kwargs))
def fillna(self, *args, **kwargs):
return MySeries(self.x.fillna(*args, **kwargs))
def floordiv(self, *args, **kwargs):
return MySeries(self.x.floordiv(*args, **kwargs))
def mod(self, *args, **kwargs):
return MySeries(self.x.mod(*args, **kwargs))
def nlargest(self, *args, **kwargs):
return MySeries(self.x.nlargest(*args, **kwargs))
def nonzero(self, *args, **kwargs):
return MySeries(self.x.nonzero(*args, **kwargs))
def nsmallest(self, *args, **kwargs):
return MySeries(self.x.nsmallest(*args, **kwargs))
def pow(self, *args, **kwargs):
return MySeries(self.x.pow(*args, **kwargs))
def rank(self, *args, **kwargs):
return MySeries(self.x.rank(*args, **kwargs))
def round(self, *args, **kwargs):
return MySeries(self.x.round(*args, **kwargs))
def shift(self, *args, **kwargs):
return MySeries(self.x.shift(*args, **kwargs))
def sub(self, *args, **kwargs):
return MySeries(self.x.sub(*args, **kwargs))
def abs(self, *args, **kwargs):
return MySeries(self.x.abs(*args, **kwargs))
def clip(self, *args, **kwargs):
return MySeries(self.x.clip(*args, **kwargs))
def clip_lower(self, *args, **kwargs):
return MySeries(self.x.clip_lower(*args, **kwargs))
def clip_upper(self, *args, **kwargs):
return MySeries(self.x.clip_upper(*args, **kwargs))
def interpolate(self, *args, **kwargs):
return MySeries(self.x.interpolate(*args, **kwargs))
def resample(self, *args, **kwargs):
return MySeries(self.x.resample(*args, **kwargs))
def replace(self, *args, **kwargs):
return MySeries(self.x.replace(*args, **kwargs))
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pandas import DataFrame, Series
from datetime import datetime
# making TimeSeries with missing values
datestrs = ['6/1/2020','6/3/2020', '6/4/2020', '6/8/2020','6/10/2020']
dates = pd.to_datetime(datestrs)
print(dates)
print("===========")
ts = Series([1, np.nan, np.nan, 8, 10], index = dates)
print(ts)
ts_intp_liner = ts.interpolate()
print(ts_intp_liner)
def test_spline_interpolation(self):
s = Series(np.arange(10)**2)
s[np.random.randint(0, 9, 3)] = np.nan
result1 = s.interpolate(method="spline", order=1)
expected1 = s.interpolate(method="spline", order=1)
tm.assert_series_equal(result1, expected1)
def test_spline_smooth(self):
s = Series([1, 2, np.nan, 4, 5.1, np.nan, 7])
assert (s.interpolate(method="spline", order=3, s=0)[5] !=
s.interpolate(method="spline", order=3)[5])
def test_nan_str_index(self):
s = Series([0, 1, 2, np.nan], index=list("abcd"))
result = s.interpolate()
expected = Series([0.0, 1.0, 2.0, 2.0], index=list("abcd"))
tm.assert_series_equal(result, expected)
def test_spline(self):
s = Series([1, 2, np.nan, 4, 5, np.nan, 7])
result = s.interpolate(method="spline", order=1)
expected = Series([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0])
tm.assert_series_equal(result, expected)
def test_nan_str_index(self):
s = Series([0, 1, 2, np.nan], index=list('abcd'))
result = s.interpolate()
expected = Series([0, 1, 2, 2], index=list('abcd'))
assert_series_equal(result, expected)
def test_interpolate_spline_invalid_order(self, order):
s = Series([0, 1, np.nan, 3])
msg = "order needs to be specified and greater than 0"
with pytest.raises(ValueError, match=msg):
s.interpolate(method="spline", order=order)
def test_interp_limit(self):
s = Series([1, 3, np.nan, np.nan, np.nan, 11])
expected = Series([1., 3., 5., 7., np.nan, 11.])
result = s.interpolate(method='linear', limit=2)
assert_series_equal(result, expected)
def test_no_order(self, method):
# see GH-10633, GH-24014
s = Series([0, 1, np.nan, 3])
msg = "You must specify the order of the spline or polynomial"
with pytest.raises(ValueError, match=msg):
s.interpolate(method=method)
def test_spline(self):
_skip_if_no_scipy()
s = Series([1, 2, np.nan, 4, 5, np.nan, 7])
result = s.interpolate(method='spline', order=1)
expected = Series([1, 2, 3, 4, 5, 6, 7])
assert_series_equal(result, expected)
def test_interp_quad(self):
tm._skip_if_no_scipy()
sq = Series([1, 4, np.nan, 16], index=[1, 2, 3, 4])
result = sq.interpolate(method='quadratic')
expected = Series([1., 4., 9., 16.], index=[1, 2, 3, 4])
assert_series_equal(result, expected)