Comments (9)
@MislavSag You should be good to go now. I was able to get your code running. You'll have to reinstall and restart R to get it going.
from autoquant.
Now it returns:
Error in attr(data, "tsp") <- c(start, end, frequency) :
invalid time series parameters specified
Sample:
data <- structure(list(date = structure(c(885394380, 885394440, 885394500,
885394560, 885394620, 885394680, 885394740, 885394800, 885394860,
885394920, 885394980, 885395040, 885395100, 885395220, 885395280,
885395400, 885395520, 885395640, 885395700, 885395760, 885395820,
885398400, 885457980, 885458040, 885458100, 885458160, 885458220,
885458280, 885458340, 885458400, 885458460, 885458520, 885458580,
885458640, 885458700, 885458760, 885458820, 885458880, 885458940,
885459000, 884779620, 884779680, 884779860, 884780040, 884780160,
884780220, 884780280, 884780340, 884780400, 884780460, 884780520,
884780580, 884780640, 884780700, 884780760, 884780820, 884780880,
884781000, 884781060, 884781240, 884781300, 884781360), class = c("POSIXct",
"POSIXt"), tzone = ""), close = c(96.96875, 96.875, 96.9375,
97.03125, 96.9375, 97, 97.15625, 97.0625, 97.15625, 97.0625,
97.1875, 97.09375, 97.125, 97.125, 97, 97.0625, 97.03125, 97,
96.9375, 96.9375, 97, 96.9375, 96.15625, 96.15625, 96.25, 96.15625,
96.15625, 96.1875, 96.25, 96.40625, 96.375, 96.3125, 96.40625,
96.5, 96.625, 96.59375, 96.5625, 96.53125, 96.46875, 96.4375,
95.1875, 95.1875, 95.25, 95.125, 95.15625, 95.0625, 95.125, 95.1875,
95.09375, 95.09375, 95.09375, 95.21875, 95.125, 95.25, 95.25,
95.25, 95.1875, 95.25, 95.25, 95.25, 95.25, 95.28125)), row.names = c(NA,
-62L), class = c("data.table", "data.frame"))
from autoquant.
@MislavSag Alright... I fixed the issue. Had to wrap a few tryCatch's around a few more of the forecast:: functions. The problem was that if any of those failed it caused the function to fail. Hasn't been an issue till now. Nonetheless, it should be good to go!
from autoquant.
I am still geting the same error after installing the package again.
from autoquant.
@MislavSag I'm not sure how you setup AutoTS to run, but this is working for me.
data <- structure(list(date = structure(c(885394380, 885394440, 885394500,
885394560, 885394620, 885394680, 885394740, 885394800, 885394860,
885394920, 885394980, 885395040, 885395100, 885395220, 885395280,
885395400, 885395520, 885395640, 885395700, 885395760, 885395820,
885398400, 885457980, 885458040, 885458100, 885458160, 885458220,
885458280, 885458340, 885458400, 885458460, 885458520, 885458580,
885458640, 885458700, 885458760, 885458820, 885458880, 885458940,
885459000, 884779620, 884779680, 884779860, 884780040, 884780160,
884780220, 884780280, 884780340, 884780400, 884780460, 884780520,
884780580, 884780640, 884780700, 884780760, 884780820, 884780880,
884781000, 884781060, 884781240, 884781300, 884781360), class = c("POSIXct",
"POSIXt"), tzone = ""), close = c(96.96875, 96.875, 96.9375,
97.03125, 96.9375, 97, 97.15625, 97.0625, 97.15625, 97.0625,
97.1875, 97.09375, 97.125, 97.125, 97, 97.0625, 97.03125, 97,
96.9375, 96.9375, 97, 96.9375, 96.15625, 96.15625, 96.25, 96.15625,
96.15625, 96.1875, 96.25, 96.40625, 96.375, 96.3125, 96.40625,
96.5, 96.625, 96.59375, 96.5625, 96.53125, 96.46875, 96.4375,
95.1875, 95.1875, 95.25, 95.125, 95.15625, 95.0625, 95.125, 95.1875,
95.09375, 95.09375, 95.09375, 95.21875, 95.125, 95.25, 95.25,
95.25, 95.1875, 95.25, 95.25, 95.25, 95.25, 95.28125)), row.names = c(NA,
-62L), class = c("data.table", "data.frame"))
RemixAutoML::AutoTS(
data,
TargetName = "close",
DateName = "date",
FCPeriods = 5,
HoldOutPeriods = 5,
EvaluationMetric = "MAPE",
InnerEval = "AICc",
TimeUnit = "day",
Lags = 2,
SLags = 1,
MaxFourierPairs = 0,
NumCores = 4,
SkipModels = NULL, #c("NNET","TBATS","ETS","TSLM","ARFIMA","DSHW"),
StepWise = TRUE,
TSClean = FALSE,
ModelFreq = TRUE,
PlotPredictionIntervals = TRUE,
PrintUpdates = FALSE)
$Forecast
Date Forecast_ETS ETS_Low80 ETS_Low95 ETS_High80 ETS_High95
1: 1998-01-23 01:50:00 96.43896 96.11721 95.94688 96.76071 96.93104
2: 1998-01-24 01:50:00 96.43896 95.99359 95.75783 96.88433 97.12009
3: 1998-01-25 01:50:00 96.43896 95.89750 95.61086 96.98042 97.26705
4: 1998-01-26 01:50:00 96.43896 95.81605 95.48631 97.06186 97.39161
5: 1998-01-27 01:50:00 96.43896 95.74409 95.37625 97.13382 97.50166
$EvaluationMetrics
ModelName MeanResid MeanPercError MAPE MAE MSE ID
1: ETS -0.10 -0.01127 0.01127 0.1006 0.0135 1
2: ETS_ModelFreq -0.10 -0.01127 0.01127 0.1006 0.0135 2
3: TBATS -0.10 -0.01127 0.01127 0.1006 0.0135 3
4: TBATS_ModelFreq -0.10 -0.01127 0.01127 0.1006 0.0135 4
5: ARIMA -0.11 -0.01133 0.01133 0.1062 0.0146 5
6: ARIMA_ModelFreq -0.11 -0.01133 0.01133 0.1062 0.0146 6
$TimeSeriesModel
ETS(A,N,N)
Call:
forecast::ets(y = dataTSTrain, model = "ZZN", lambda = TRUE,
Call:
biasadj = TRUE, restrict = TRUE, allow.multiplicative.trend = TRUE)
Box-Cox transformation: lambda= 1
Smoothing parameters:
alpha = 0.9571
Initial states:
l = 94.1875
sigma: 0.2511
AIC AICc BIC
88.47561 88.88940 94.85701
$ChampionModel
[1] "ETS"
$TimeSeriesPlot
Warning messages:
1: Removed 5 rows containing missing values (geom_path).
2: Removed 62 rows containing missing values (geom_path).
3: Removed 62 rows containing missing values (geom_path).
4: Removed 62 rows containing missing values (geom_path).
5: Removed 62 rows containing missing values (geom_path).
6: Removed 62 rows containing missing values (geom_path).
from autoquant.
@AdrianAntico , doesn't work with this data:
data <- structure(list(date = structure(c(884779620, 884779680, 884779860,
884780040, 884780160, 884780220, 884780280, 884780340, 884780400,
884780460, 884780520, 884780580, 884780640, 884780700, 884780760,
884780820, 884780880, 884781000, 884781060, 884781240, 884781300,
884781360, 884781420, 884781480, 884781600, 884781660, 884781720,
884781840, 884781900, 884781960, 885394380, 885394440, 885394500,
885394560, 885394620, 885394680, 885394740, 885394800, 885394860,
885394920, 885394980, 885395040, 885395100, 885395220, 885395280,
885395400, 885395520, 885395640, 885395700, 885395760, 885395820,
885398400, 885457980, 885458040, 885458100, 885458160, 885458220,
885458280, 885458340, 885458400, 885458460, 885458520, 885458580,
885458640, 885458700, 885458760, 885458820, 885458880, 885458940,
885459000), class = c("POSIXct", "POSIXt"), tzone = ""), close = c(95.1875,
95.1875, 95.25, 95.125, 95.15625, 95.0625, 95.125, 95.1875, 95.09375,
95.09375, 95.09375, 95.21875, 95.125, 95.25, 95.25, 95.25, 95.1875,
95.25, 95.25, 95.25, 95.25, 95.28125, 95.3125, 95.3125, 95.3125,
95.3125, 95.3125, 95.3125, 95.25, 95.28125, 96.96875, 96.875,
96.9375, 97.03125, 96.9375, 97, 97.15625, 97.0625, 97.15625,
97.0625, 97.1875, 97.09375, 97.125, 97.125, 97, 97.0625, 97.03125,
97, 96.9375, 96.9375, 97, 96.9375, 96.15625, 96.15625, 96.25,
96.15625, 96.15625, 96.1875, 96.25, 96.40625, 96.375, 96.3125,
96.40625, 96.5, 96.625, 96.59375, 96.5625, 96.53125, 96.46875,
96.4375)), row.names = c(NA, -70L), class = c("data.table", "data.frame"
))
It is an irregular 1 minute data, maybe that's the problem?
from autoquant.
@MislavSag I made another change and it should run for the data above that you posted.
from autoquant.
@AdrianAntico , now I get the following error (message):
"Cannot convert your data to a time series object with that TimeUnit"
I can't send you data because it has around 4200 rows. Maybe I can send you via email?
from autoquant.
I would start with sharing the setup of the function... First I need to see if the TimeUnit you supplied is correct and if it is, then I'd need to see if there is anything wrong with the data. If nothing is wrong with the data, then it has to be something about converting the data to a time series object... Feel free to email me though: [email protected]
from autoquant.
Related Issues (20)
- Model Fails to Build AutoBanditSarima HOT 11
- h2o HOT 3
- Some items of .SDcols are not column names HOT 2
- Model was not able to be built HOT 1
- Error in AutoCatBoostRegression HOT 1
- Unable to install RemixAutoML HOT 2
- AutoCatBoostCARMA error. HOT 4
- Confidence level and forecast function HOT 8
- Non-Zero Exit Status HOT 1
- Error catboost.train HOT 2
- Some items of .SDcols are not column names; [Predict.V1] HOT 15
- Error in `[.data.table`(UpdateData., , `:=`(eval(GroupVariables.) HOT 5
- AutoCatBoostCARMA doesn't forecast HOT 9
- unused arguments issue with FakeDataGenerator HOT 3
- AutoXGBoostCARMA Error HOT 11
- [Thanks] Great library HOT 1
- non-zero exit status HOT 1
- AUTO TS HOT 1
- Error when calling ModelInsightsReport: object 'RemixOutput' not found HOT 13
- Installation misprint HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from autoquant.