Name: Time Series Forecasts - Popular Benchmark Datasets
Creator: Kaggle
License: https://opensource.org/licenses/MIT

About this Dataset

Time Series Forecasts - Popular Benchmark Datasets

Collection of popular datasets for time series forecasting.

Traffic: It contains hourly traffic data from 963 San Francisco freeway car lanes for short-term forecasting settings while it contains 862 car lanes for long-term forecasting. It is collected since 01/01/2015 with a sampling interval of every 1 hour.

Electricity: It contains electricity consumption of 370 clients for short-term forecasting while it contains electricity consumption of 321 clients for long-term forecasting. It is collected since 01/01/2011. The data sampling interval is every 15 minutes. (1)

COVID-19: It is about COVID-19 hospitalization in the U.S. state of California (CA) from 01/02/2020 to 31/12/2020 provided by the Johns Hopkins University with the sampling interval of every day.

Exchange: It contains the collection of the daily exchange rates of eight foreign countries including Australia, British, Canada, Switzerland, China, Japan, New Zealand, and Singapore ranging from 1990 to 2016 and the data sampling interval is every 1 day. (2)

Weather: It collects 21 meteorological indicators, such as humidity and air temperature, from the Weather Station of the Max Planck Biogeochemistry Institute in Germany in 2020. The data sampling interval is every 10 minutes. (3)

ETT: It is collected from two different electric transformers labeled with 1 and 2, and each of them contains 2 different resolutions (15 minutes and 1 hour) denoted with m and h. (4)

References

https://archive.ics.uci.edu/dataset/321/electricityloaddiagrams20112014
https://github.com/laiguokun/multivariate-time-series-data
https://www.bgc-jena.mpg.de/wetter/
https://github.com/zhouhaoyi/ETDataset
"Frequency-domain {MLP}s are More Effective Learners in Time Series Forecasting", by Kun Yi and Qi Zhang and Wei Fan and Shoujin Wang and Pengyang Wang and Hui He and Ning An and Defu Lian and Longbing Cao and Zhendong Niu, Thirty-seventh Conference on Neural Information Processing Systems, 2023, https://openreview.net/forum?id=iif9mGCTfy

Tables

Covid

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.covid

66.06 kB
335 rows
56 columns

CREATE TABLE covid (
  "date" VARCHAR,
  "n_1" DOUBLE  -- 1,
  "n_2" DOUBLE  -- 2,
  "n_3" DOUBLE  -- 3,
  "n_4" DOUBLE  -- 4,
  "n_5" DOUBLE  -- 5,
  "n_6" DOUBLE  -- 6,
  "n_7" DOUBLE  -- 7,
  "n_8" DOUBLE  -- 8,
  "n_9" DOUBLE  -- 9,
  "n_10" DOUBLE  -- 10,
  "n_11" DOUBLE  -- 11,
  "n_12" DOUBLE  -- 12,
  "n_13" DOUBLE  -- 13,
  "n_14" DOUBLE  -- 14,
  "n_15" DOUBLE  -- 15,
  "n_16" DOUBLE  -- 16,
  "n_17" DOUBLE  -- 17,
  "n_18" DOUBLE  -- 18,
  "n_19" DOUBLE  -- 19,
  "n_20" DOUBLE  -- 20,
  "n_21" DOUBLE  -- 21,
  "n_22" DOUBLE  -- 22,
  "n_23" DOUBLE  -- 23,
  "n_24" DOUBLE  -- 24,
  "n_25" DOUBLE  -- 25,
  "n_26" DOUBLE  -- 26,
  "n_27" DOUBLE  -- 27,
  "n_28" DOUBLE  -- 28,
  "n_29" DOUBLE  -- 29,
  "n_30" DOUBLE  -- 30,
  "n_31" DOUBLE  -- 31,
  "n_32" DOUBLE  -- 32,
  "n_33" DOUBLE  -- 33,
  "n_34" DOUBLE  -- 34,
  "n_35" DOUBLE  -- 35,
  "n_36" DOUBLE  -- 36,
  "n_37" DOUBLE  -- 37,
  "n_38" DOUBLE  -- 38,
  "n_39" DOUBLE  -- 39,
  "n_40" DOUBLE  -- 40,
  "n_41" DOUBLE  -- 41,
  "n_42" DOUBLE  -- 42,
  "n_43" DOUBLE  -- 43,
  "n_44" DOUBLE  -- 44,
  "n_45" DOUBLE  -- 45,
  "n_46" DOUBLE  -- 46,
  "n_47" DOUBLE  -- 47,
  "n_48" DOUBLE  -- 48,
  "n_49" DOUBLE  -- 49,
  "n_50" DOUBLE  -- 50,
  "n_51" DOUBLE  -- 51,
  "n_52" DOUBLE  -- 52,
  "n_53" DOUBLE  -- 53,
  "n_54" DOUBLE  -- 54,
  "n_55" DOUBLE  -- 55
);

Electricity

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.electricity

13.32 MB
26,304 rows
322 columns

CREATE TABLE electricity (
  "date" TIMESTAMP,
  "n_0" DOUBLE  -- 0,
  "n_1" DOUBLE  -- 1,
  "n_2" DOUBLE  -- 2,
  "n_3" DOUBLE  -- 3,
  "n_4" DOUBLE  -- 4,
  "n_5" DOUBLE  -- 5,
  "n_6" DOUBLE  -- 6,
  "n_7" DOUBLE  -- 7,
  "n_8" DOUBLE  -- 8,
  "n_9" DOUBLE  -- 9,
  "n_10" DOUBLE  -- 10,
  "n_11" DOUBLE  -- 11,
  "n_12" DOUBLE  -- 12,
  "n_13" DOUBLE  -- 13,
  "n_14" DOUBLE  -- 14,
  "n_15" DOUBLE  -- 15,
  "n_16" DOUBLE  -- 16,
  "n_17" DOUBLE  -- 17,
  "n_18" DOUBLE  -- 18,
  "n_19" DOUBLE  -- 19,
  "n_20" DOUBLE  -- 20,
  "n_21" DOUBLE  -- 21,
  "n_22" DOUBLE  -- 22,
  "n_23" DOUBLE  -- 23,
  "n_24" DOUBLE  -- 24,
  "n_25" DOUBLE  -- 25,
  "n_26" DOUBLE  -- 26,
  "n_27" DOUBLE  -- 27,
  "n_28" DOUBLE  -- 28,
  "n_29" DOUBLE  -- 29,
  "n_30" DOUBLE  -- 30,
  "n_31" DOUBLE  -- 31,
  "n_32" DOUBLE  -- 32,
  "n_33" DOUBLE  -- 33,
  "n_34" DOUBLE  -- 34,
  "n_35" DOUBLE  -- 35,
  "n_36" DOUBLE  -- 36,
  "n_37" DOUBLE  -- 37,
  "n_38" DOUBLE  -- 38,
  "n_39" DOUBLE  -- 39,
  "n_40" DOUBLE  -- 40,
  "n_41" DOUBLE  -- 41,
  "n_42" DOUBLE  -- 42,
  "n_43" DOUBLE  -- 43,
  "n_44" DOUBLE  -- 44,
  "n_45" DOUBLE  -- 45,
  "n_46" DOUBLE  -- 46,
  "n_47" DOUBLE  -- 47,
  "n_48" DOUBLE  -- 48,
  "n_49" DOUBLE  -- 49,
  "n_50" DOUBLE  -- 50,
  "n_51" DOUBLE  -- 51,
  "n_52" DOUBLE  -- 52,
  "n_53" DOUBLE  -- 53,
  "n_54" DOUBLE  -- 54,
  "n_55" DOUBLE  -- 55,
  "n_56" DOUBLE  -- 56,
  "n_57" DOUBLE  -- 57,
  "n_58" DOUBLE  -- 58,
  "n_59" DOUBLE  -- 59,
  "n_60" DOUBLE  -- 60,
  "n_61" DOUBLE  -- 61,
  "n_62" DOUBLE  -- 62,
  "n_63" DOUBLE  -- 63,
  "n_64" DOUBLE  -- 64,
  "n_65" DOUBLE  -- 65,
  "n_66" DOUBLE  -- 66,
  "n_67" DOUBLE  -- 67,
  "n_68" DOUBLE  -- 68,
  "n_69" DOUBLE  -- 69,
  "n_70" DOUBLE  -- 70,
  "n_71" DOUBLE  -- 71,
  "n_72" DOUBLE  -- 72,
  "n_73" DOUBLE  -- 73,
  "n_74" DOUBLE  -- 74,
  "n_75" DOUBLE  -- 75,
  "n_76" DOUBLE  -- 76,
  "n_77" DOUBLE  -- 77,
  "n_78" DOUBLE  -- 78,
  "n_79" DOUBLE  -- 79,
  "n_80" DOUBLE  -- 80,
  "n_81" DOUBLE  -- 81,
  "n_82" DOUBLE  -- 82,
  "n_83" DOUBLE  -- 83,
  "n_84" DOUBLE  -- 84,
  "n_85" DOUBLE  -- 85,
  "n_86" DOUBLE  -- 86,
  "n_87" DOUBLE  -- 87,
  "n_88" DOUBLE  -- 88,
  "n_89" DOUBLE  -- 89,
  "n_90" DOUBLE  -- 90,
  "n_91" DOUBLE  -- 91,
  "n_92" DOUBLE  -- 92,
  "n_93" DOUBLE  -- 93,
  "n_94" DOUBLE  -- 94,
  "n_95" DOUBLE  -- 95,
  "n_96" DOUBLE  -- 96,
  "n_97" DOUBLE  -- 97,
  "n_98" DOUBLE  -- 98
);

Etth1

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.etth1

317.52 kB
17,420 rows
8 columns

CREATE TABLE etth1 (
  "date" TIMESTAMP,
  "hufl" DOUBLE,
  "hull" DOUBLE,
  "mufl" DOUBLE,
  "mull" DOUBLE,
  "lufl" DOUBLE,
  "lull" DOUBLE,
  "ot" DOUBLE
);

Ettm1

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.ettm1

1.23 MB
69,680 rows
8 columns

CREATE TABLE ettm1 (
  "date" TIMESTAMP,
  "hufl" DOUBLE,
  "hull" DOUBLE,
  "mufl" DOUBLE,
  "mull" DOUBLE,
  "lufl" DOUBLE,
  "lull" DOUBLE,
  "ot" DOUBLE
);

Exchange Rate

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.exchange_rate

438.59 kB
7,588 rows
9 columns

CREATE TABLE exchange_rate (
  "date" VARCHAR,
  "n_1" DOUBLE  -- 1,
  "n_2" DOUBLE  -- 2,
  "n_3" DOUBLE  -- 3,
  "n_4" DOUBLE  -- 4,
  "n_5" DOUBLE  -- 5,
  "n_6" DOUBLE  -- 6,
  "n_7" DOUBLE  -- 7,
  "n_8" DOUBLE  -- 8
);

Traffic

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.traffic

29.84 MB
17,544 rows
863 columns

CREATE TABLE traffic (
  "date" TIMESTAMP,
  "n_0" DOUBLE  -- 0,
  "n_1" DOUBLE  -- 1,
  "n_2" DOUBLE  -- 2,
  "n_3" DOUBLE  -- 3,
  "n_4" DOUBLE  -- 4,
  "n_5" DOUBLE  -- 5,
  "n_6" DOUBLE  -- 6,
  "n_7" DOUBLE  -- 7,
  "n_8" DOUBLE  -- 8,
  "n_9" DOUBLE  -- 9,
  "n_10" DOUBLE  -- 10,
  "n_11" DOUBLE  -- 11,
  "n_12" DOUBLE  -- 12,
  "n_13" DOUBLE  -- 13,
  "n_14" DOUBLE  -- 14,
  "n_15" DOUBLE  -- 15,
  "n_16" DOUBLE  -- 16,
  "n_17" DOUBLE  -- 17,
  "n_18" DOUBLE  -- 18,
  "n_19" DOUBLE  -- 19,
  "n_20" DOUBLE  -- 20,
  "n_21" DOUBLE  -- 21,
  "n_22" DOUBLE  -- 22,
  "n_23" DOUBLE  -- 23,
  "n_24" DOUBLE  -- 24,
  "n_25" DOUBLE  -- 25,
  "n_26" DOUBLE  -- 26,
  "n_27" DOUBLE  -- 27,
  "n_28" DOUBLE  -- 28,
  "n_29" DOUBLE  -- 29,
  "n_30" DOUBLE  -- 30,
  "n_31" DOUBLE  -- 31,
  "n_32" DOUBLE  -- 32,
  "n_33" DOUBLE  -- 33,
  "n_34" DOUBLE  -- 34,
  "n_35" DOUBLE  -- 35,
  "n_36" DOUBLE  -- 36,
  "n_37" DOUBLE  -- 37,
  "n_38" DOUBLE  -- 38,
  "n_39" DOUBLE  -- 39,
  "n_40" DOUBLE  -- 40,
  "n_41" DOUBLE  -- 41,
  "n_42" DOUBLE  -- 42,
  "n_43" DOUBLE  -- 43,
  "n_44" DOUBLE  -- 44,
  "n_45" DOUBLE  -- 45,
  "n_46" DOUBLE  -- 46,
  "n_47" DOUBLE  -- 47,
  "n_48" DOUBLE  -- 48,
  "n_49" DOUBLE  -- 49,
  "n_50" DOUBLE  -- 50,
  "n_51" DOUBLE  -- 51,
  "n_52" DOUBLE  -- 52,
  "n_53" DOUBLE  -- 53,
  "n_54" DOUBLE  -- 54,
  "n_55" DOUBLE  -- 55,
  "n_56" DOUBLE  -- 56,
  "n_57" DOUBLE  -- 57,
  "n_58" DOUBLE  -- 58,
  "n_59" DOUBLE  -- 59,
  "n_60" DOUBLE  -- 60,
  "n_61" DOUBLE  -- 61,
  "n_62" DOUBLE  -- 62,
  "n_63" DOUBLE  -- 63,
  "n_64" DOUBLE  -- 64,
  "n_65" DOUBLE  -- 65,
  "n_66" DOUBLE  -- 66,
  "n_67" DOUBLE  -- 67,
  "n_68" DOUBLE  -- 68,
  "n_69" DOUBLE  -- 69,
  "n_70" DOUBLE  -- 70,
  "n_71" DOUBLE  -- 71,
  "n_72" DOUBLE  -- 72,
  "n_73" DOUBLE  -- 73,
  "n_74" DOUBLE  -- 74,
  "n_75" DOUBLE  -- 75,
  "n_76" DOUBLE  -- 76,
  "n_77" DOUBLE  -- 77,
  "n_78" DOUBLE  -- 78,
  "n_79" DOUBLE  -- 79,
  "n_80" DOUBLE  -- 80,
  "n_81" DOUBLE  -- 81,
  "n_82" DOUBLE  -- 82,
  "n_83" DOUBLE  -- 83,
  "n_84" DOUBLE  -- 84,
  "n_85" DOUBLE  -- 85,
  "n_86" DOUBLE  -- 86,
  "n_87" DOUBLE  -- 87,
  "n_88" DOUBLE  -- 88,
  "n_89" DOUBLE  -- 89,
  "n_90" DOUBLE  -- 90,
  "n_91" DOUBLE  -- 91,
  "n_92" DOUBLE  -- 92,
  "n_93" DOUBLE  -- 93,
  "n_94" DOUBLE  -- 94,
  "n_95" DOUBLE  -- 95,
  "n_96" DOUBLE  -- 96,
  "n_97" DOUBLE  -- 97,
  "n_98" DOUBLE  -- 98
);

Weather

@kaggle.giochelavaipiatti_time_series_forecasts_popular_benchm_3dd08d81.weather

2.45 MB
52,696 rows
22 columns

CREATE TABLE weather (
  "date" TIMESTAMP,
  "p_mbar" DOUBLE  -- P (mbar),
  "t_degc" DOUBLE  -- T (degC),
  "tpot_k" DOUBLE  -- Tpot (K),
  "tdew_degc" DOUBLE  -- Tdew (degC),
  "rh" DOUBLE  -- Rh (%),
  "vpmax_mbar" DOUBLE  -- VPmax (mbar),
  "vpact_mbar" DOUBLE  -- VPact (mbar),
  "vpdef_mbar" DOUBLE  -- VPdef (mbar),
  "sh_g_kg" DOUBLE  -- Sh (g/kg),
  "h2oc_mmol_mol" DOUBLE  -- H2OC (mmol/mol),
  "rho_g_m_3" DOUBLE  -- Rho (g/m**3),
  "wv_m_s" DOUBLE  -- Wv (m/s),
  "max_wv_m_s" DOUBLE  -- Max. Wv (m/s),
  "wd_deg" DOUBLE  -- Wd (deg),
  "rain_mm" DOUBLE  -- Rain (mm),
  "raining_s" DOUBLE  -- Raining (s),
  "swdr_w_m" DOUBLE  -- SWDR (W/m�),
  "par_mol_m_s" DOUBLE  -- PAR (�mol/m�/s),
  "max_par_mol_m_s" DOUBLE  -- Max. PAR (�mol/m�/s),
  "tlog_degc" DOUBLE  -- Tlog (degC),
  "ot" DOUBLE
);