sktime is a unified framework for machine learning with time series in Python. It provides simple and efficient tools for time series analysis and data mining, with a focus on machine learning. It is accessible to everybody and reusable in various contexts. It is built on NumPy, SciPy, pandas and scikit-learn, among others. The project is open source and commercially usable (BSD license).
Questions tagged [sktime]
52 questions
1
vote
1 answer
How to know from which interval of the input the features used in sktime's TimeSeriesForestClassifier are calculated
I used the sktime library's TimeSeriesForestClassifier class to perform multivariate time series classification.
The code is as follows
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.pipeline import…
pie
- 3,849
- 2
- 11
- 9
1
vote
0 answers
sktime understanding the data format and error message
I am trying to do a classification of time series data and came across sktime which offers many algorithms that can be used to classify time series.
However, I only manage to make RandomIntervalSpectralForest run. All other algorithms give me the…
Blo4d
- 31
- 5
1
vote
0 answers
sktime error cannot import name '_take_along_axis' from 'sklearn.utils.fixes'
I get this error when I try to use an example from sktime documentation.
MWE
from sktime.datasets import load_airline
from sktime.forecasting.model_selection import (
ExpandingWindowSplitter,
ForecastingGridSearchCV,
…
msh855
- 1,493
- 1
- 15
- 36
1
vote
2 answers
ImportError: cannot import name 'ReducedRegressionForecaster' from 'sktime.forecasting.compose'
from sktime.forecasting.compose import ReducedRegressionForecaster
Waheed Waqar
- 13
- 5
1
vote
0 answers
I am running into an error while trying to install latest version of sktime
ERROR: Could not find a version that satisfies the requirement sktime==0.5.2
ERROR: No matching distribution found for sktime==0.5.2
0
votes
0 answers
Error when using sktime model on multiindex hierachical pandas dataframe (pd_multiindex_hier)
I want to use the sktime package for time series classification on a multivariet time series. My time series looks like this:
It is a continious time series dissected into non-overlapping intervals (interval_label) on different sensor node…
pascal_
- 61
- 5
0
votes
1 answer
How to install sktime on Raspberry Pi?
I want to use sktime for time-series classification inference on a Raspberry Pi. I am not able to install it properly with the required dependencies, especially of numpy and numba. When I run pip install sktime it installs correctly and also import…
Sashi
- 79
- 11
0
votes
0 answers
ERROR: Could not build wheels for sktime, which is required to install pyproject.toml-based projects
Encountering this problem when using -
$pip install sktime==0.4.1
More information -
note: This error originates from a subprocess, and is likely not a
problem with pip. ERROR: Failed building wheel for sktime Running
setup.py clean for…
xuanhan
- 1
0
votes
0 answers
sktime forecasting with exogenous variables recursive approach windowsummarizer
Please help understand. I'm reading the documentation sktime WindowSummarizer with exogenous features and y lags example.
documentation.
import pandas as pd
from sktime.transformations.series.summarize import WindowSummarizer
from sktime.datasets…
PineapplePizza
- 87
- 11
0
votes
0 answers
Is nonnegative hierarchical time series reconciliation implemented in sktime?
I am using sktime to perform time series forecasting and hierarchical reconciliation. For the latter I am using the ReconcilerForecaster class with the OLS method (ReconcilerForecaster in sktime).
My question is: is there a way to obtain nonnegative…
0
votes
0 answers
Forecasting with sktime prophet
I am using the timeseries forecast algorithm ´prophet` from sktime.
I have the following train and test set:
X1_train
Saldo
timepoint
2017-01-01 -3574.22
2017-02-01 6351.78
2017-03-01 3297.65
2017-04-01 …
PV8
- 5,799
- 7
- 43
- 87
0
votes
1 answer
How can i convert each element in my panda dataframe from a list to a series? In order to be comapatiable with MiniRocketMultivariateVariable sktime
I have a dataframe. This dataframe holds ts data
Every column is a dimension in my ts data. Every row holds an indidual time series. Ts that i have are not eual in length.
I want each element in my dataframe to be converted to a series instead.…
mohannad rateb
- 72
- 1
- 9
0
votes
0 answers
When performing model selection with ForecastingGridSearchCV in sktime, why do you need to specify a forecaster to instantiate the gridsearch?
In the Pydata 2022 Global sktime tutorial on AutoML there is an example of using sktime.forecasting.model_selection.ForecastingGridSearchCV to select a forecaster:
from sktime.forecasting.theta import ThetaForecaster
from sktime.forecasting.trend…
teejk
- 25
- 4
0
votes
0 answers
Arima gives trend lines instead of expected forecast predictions
Im trying to use ARIMA to do some basic predictions on time-series data.
Sample of data:
year week_of_year ticket_count
2018-01-01 2018 1 174
2018-01-08 2018 2 190
2018-01-15 2018 3 …
DChaps
- 482
- 5
- 12
0
votes
0 answers
sktime is installed but cannot import or use it
I am a data science student and need to use sktime in a Jupyter notebook time series project. I have successfully installed sktime via the terminal on my M1 Macbook Pro, but I can't figure out how to make sktime work. Please help!
I have done many…
Ms.K
- 1
- 1