Questions tagged [time-series]
A Time series is a sequence of data points with values measured at successive times (either in continuous time or at discrete time periods). Time series analysis exploits this natural temporal ordering to extract meaning and trends from the underlying data.
time-series
15,484
questions
0
votes
0
answers
7
views
How to inversely transform time series predictions to add seasonality back in?
I have transformed some data to make it stationary before fitting an ARIMA(1,0,1) model.
I specifically want to manually transform the data to better understand the process.
I can successfully fit a ...
0
votes
0
answers
8
views
Extreme RMSE Validation Score in Time Series Model
I have a dataset consists of hourly data with 4000 rows and 3 numeric columns. It doesn't have clear trend or seasonality. I've shared a graph of stl decomposition together with original lineplot of ...
0
votes
0
answers
6
views
forward-looking versus backward-looking timestamp conventions
I am collecting sensordata in a database. Observations are stored at an hourly or daily resolution, as timestamp - value. I have to deceide to make the timestamps
forward-looking (i.e 01/01/24 02:00 ...
-2
votes
0
answers
11
views
Compare hyperparameters influence on model performance
I want to assess which Hyperparams seem to influence the most my results, if there is any kind of "threshold" value for a given or several hyperparams after which the model does not improve ...
-3
votes
0
answers
22
views
How do I build a Forecasting Model for this kind of data?
I have a dataset where the whole dataset is actually categorical data with timestamp. The other problem is that the timestamp data column has the date as well as time in it, i.e. DD/MM/YYYY HH:MM:SS ...
-1
votes
1
answer
30
views
Time-series correlating suspiciously high
I have two time series from 1986-01-01 to 2024-04-01 following CPI prices of meat and fish and I want to find the correlation between the both of them.
They are huge dataframes so below is a truncated ...
0
votes
0
answers
20
views
Do I need to 'shift' my new target variable in Time Series prediction?
When I have time series data but I don't want to predict the values of the series. Instead, I create a new target variable that gives me the direction (1 to represent an increase and 0 to represent a ...
0
votes
0
answers
20
views
Why we need date tiered compaction and how it is different from size tiered compaction
In size tiered compaction if time series data comes in then each similar sized sstables must be close in time and hence it should work like date tiered compaction right?
Example
Let's consider a ...
1
vote
0
answers
13
views
Payload Too Large
I am using the point cloud version of CnosDB. When I write a pcd file, I get an error: Payload Too Large.
My entire writing steps are as follows:
start a single-mode cluster;
./target/release/cnosdb ...
-1
votes
0
answers
19
views
How to use supervised ML for time series predictions when the feature vector for the target value is known?
I am trying to use an LSTM to predict the consecutive "offset" calibration values for an instrument. These offset values have previously been shown to be well correlated with a pair of ...
0
votes
1
answer
46
views
What is the meaning of: Pandas data cast to numpy dtype of object. Check input data with np.asarray(data) and how can be solved?
I'm trying to model a time series for a stock price with the following code:
import opendatasets as od
import numpy as np
import pandas as pd
import plotly.graph_objects as go
from plotly.subplots ...
0
votes
1
answer
24
views
Difference between the expected input tensor order for LSTM and Conv1d?
I am working with time series data and have noticed a discrepancy in the input tensor order required for LSTM and Conv1d/BatchNorm1d/Dropout1d layers in PyTorch. For example, say I have an input ...
-1
votes
0
answers
12
views
How to save and parse selected features in tsfresh?
My question is, how to convert feature names (column names), resulted by tsfresh extract_features, to format, compatible with ComprehensiveFCParameters. Needs to do not apply select_features every ...
0
votes
0
answers
6
views
Taking account of generator ramp constraints in pypsa optimisation
I would like to know how Pypsa handles the ramp constraints (on load, at start-up and at shutdown) of generators. Is it sufficient to fill in these attributes only or does it require additional codes?
...
1
vote
0
answers
24
views
Optimizing pandas performance on large datasets
I'm working with a large dataset (~10 million rows and 50 columns) in pandas and experiencing significant performance issues during data manipulation and analysis. The operations include filtering, ...