Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [time-series]

Time series are data observed over time (either in continuous time or at discrete time periods).

Overview

Time series are data observed over time (either in continuous time or at discrete time periods).

Time series analysis includes:

  • Trend identification (e.g. autocorrelation)
  • Temporal pattern recognition
  • Spectral analysis / wavelet analysis
  • Forecasting (e.g. regression)
  • Anomaly detection

The salient characteristic of methods of time series analysis (as opposed to more general methods to analyze relationships among data) is accounting for the possibility of serial correlation (also known as temporal correlation) among the data. Positive serial correlation means successive observations in time tend to be close to one another, whereas negative serial correlation means successive observations tend to oscillate between extremes. Time series analysis also differs from analyses of more general stochastic processes by focusing on the inherent direction of time, creating a potential asymmetry between past and future.

1885 questions
12
votes
5 answers

How to merge monthly, daily and weekly data?

Google Trends returns weekly data so I have to find a way to merge them with my daily/monthly data. What I have done so far is to break each serie into daily data, for exemple: from: 2013-03-03 - 2013-03-09 37 to: 2013-03-03 37 2013-03-04…
Lucas Morin
  • 2,196
  • 5
  • 21
  • 42
11
votes
3 answers

Dynamic Time Warping is outdated?

At http://www.speech.zone/exercises/dtw-in-python/ it says Although it's not really used anymore, Dynamic Time Warping (DTW) is a nice introduction to the key concept of Dynamic Programming. I am using DTW for signal processing and are a little…
Make42
  • 752
  • 2
  • 8
  • 18
8
votes
2 answers

DTW (Dynamic Time Warping) requires prior normalization?

I'm trying DTW from mlpy, to check similarity between time series. Should I normalize the series before processing them with DTW? Or is it somewhat tolerant and I can use the series as they are? All time series stored in a Pandas Dataframe, each in…
KcFnMi
  • 343
  • 1
  • 4
  • 8
7
votes
1 answer

Finding unpredictability or uncertainty in a time series

I am interested in finding a statistic that tracks the unpredictability of a time series. For simplicity sake, assume that each value in the time series is either 1 or 0. So for example, the following two time series are entirely predictable TS1: 1…
Rajesh
  • 73
  • 4
4
votes
2 answers

Sales Predictions Over Time

I'd like to model the evolution of the sales of a store. Here are the data I have : Customers are aggregated into monthly cohort depending on the date of the first purchase eg : customers who did their 1st purchase in Jan 2015 are in the cohort 1,…
psql
  • 91
  • 4
4
votes
1 answer

Time series data for Prophet model

I have a time series data that has some missing dates. For example, in the dataset below '2017-08-06' is missing. To enter this data in the Prophet model, do I have to create the data frame with all the missing dates? I know the Prophet model does…
mars
  • 155
  • 4
4
votes
2 answers

How to evaluate time-series model on a longer validation period than the forecast horizon

I'm training ARIMA and Random forest models to forecast on a horizon of 3 days, but need to evaluate models using one full year. What's the proper way to handle the following problems: I've noticed most librairies don't have options to set a…
laurent descaunes
  • 41
  • 1
3
votes
0 answers

How to find a model for a short discrete time-series?

I'm examining the activity of customers over the years which have about one event per year. This results is many short time-series for which I found the distributions (hit/miss over 4 years sorted by probability in the data): 0000 : 0.31834 0001 :…
Gere
  • 355
  • 1
  • 5
3
votes
0 answers

Methods for analyzing multiple time series

My agenda is finding patterns and possible a model that describe my data. My data is comprised of multiple time-series uni-variate sets. data_set = [pd.Series(np.random.normal(size=10), range(10)), pd.Series(np.random.normal(size=10),…
yoav_aaa
  • 993
  • 4
  • 13
3
votes
3 answers

Frequency for a time series

What is meant by frequency of a time series? I am having data observations of energy consumption from 01/05/2016 - 31/05/2017 such that there are 96 values per day. What will be the frequency of the time series in such case?
Manik
  • 429
  • 3
  • 7
  • 15
3
votes
0 answers

Predict event likelihood given time of other events

On a daily basis there is a sequence of events. Each event may or may not occur on a given day. Given the times of the preceding events for the current day I want to be able to say whether there is a high likelihood of an event occurring right…
CoderBrien
  • 131
  • 3
3
votes
1 answer

Euclidean distance between time series in Python

While thinking about similarity between two time series, one can use DTW to approach the issue. There is a Python package for that mlpy. It is also said to compare time series via simple euclidean distance. Is there a Python package to this?
KcFnMi
  • 343
  • 1
  • 4
  • 8
3
votes
1 answer

ARIMAX v. ARX Time Series Modeling

I need to build a time series model with explanatory variables, and ARIMAX seems to be the one that comes up most frequently in practice, based on my survey of related work. I know ARX solves a similar problem, but I'm having trouble wrapping my…
Kyle.
  • 1,483
  • 1
  • 16
  • 32
2
votes
0 answers

How to create Window sequence for TFX timeseries

I am building a TFX pipeline for timeseries with a uci open-source data https://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction. As timeseries training and evaluation requires window sequence of data, i used the…
jaydeemourg
  • 21
  • 1
2
votes
1 answer

time series prediction using arima and non linear trend and too much residuals

I am working on forecasting a financial index, i tried decomposing the time series using : from matplotlib import pyplot from statsmodels.tsa.seasonal import seasonal_decompose result = seasonal_decompose(dataset, model='multiplicative',…
BalticOY
  • 41
  • 3
1
2 3 4 5 6