AcroLearner

FREE
By Samurai | Updated לפני חודש | Artificial Intelligence/Machine Learning
Health Check

N/A

Back to All Tutorials (8)

How to generate AcroLearner Time Series Model

AcroLearner includes a set of RESTful APIs about Time Series Prediction(AR/MA/ARMA/ARIMA). Generally, the following steps is necessary.

  1. First of all, a new Machine Learning Theme is posted with some parameters and its items or not. You will get "trainKey" and “resultKey”.
    "trainKey" is unique only for this theme. “resultKey” is changeable. Actually a different “resultKey” will available when you call the Theme every time.

  2. Then you may individually post or put some items of the theme above.

  3. Once you finish the registration of Machine Learning Theme and its items, you may start a training/learning process to generate a Machine Learning Model using “trainKey”.

  4. Finally, you may post your original data to Machine Learning Model above and get the result of Classification/Prediction using “resultKey”.

##0304. Generate Time Series AR Model
Generate an Autoregressive Prediction Model from the trainText(a numerical dataset) whick inputed in Learning item in advance. In the returned result list, if Coefficient of determination(Score) in last row is close to 1, a satisfying prediction will be available.
https://acrolearner.p.rapidapi.com/AcroLearner/v0_1/CltService/ml/trains/{trainKey}/armodel
http method: get

Request Header parameters:

x-rapidapi-host: acrolearner.p.rapidapi.com
x-rapidapi-key: [your rapidapi-key]

Request Query parameters Example:

learnCount=1000&learnRate=0.000001&interval=400&pOrder=3
learnCount: learning times
learnRate: learning increment rate
interval: the output interval of learning result
pOrder: Autoregressive times for Learning

Request Path parameters:

{trainKey}: XXXXXXXXXX

Response JSON Example:

-Successful case:

{
    "contents": {
        "code": "0000",
        "list": [
            "SN,Weight,Loss,Score,AIC,BIC",
            "1,{1; 1; 1; 1},2488576.9587122356,0.5228415137955127,5500.608495464024,5525.676160148328",
            "401,{0.9941842394; -0.0114451691; -0.0107425851; 0.0312304322},10818.176353840012,0.99792572834269,2879.3774862355035,2904.445150919807",
            "801,{0.990243971; -0.0250207139; -0.0242283347; 0.0583023019},10812.602985684674,0.9979267969774785,2879.12910281222,2904.1967674965235",
            "1000,{0.9882836008; -0.0314655182; -0.0308621047; 0.0713860982},10809.984215093527,0.997927299099226,2879.012350138788,2904.0800148230915",
            "****,{0.9882737495; -0.0314973986; -0.0308953147; 0.0714512148},10809.971302748978,0.9979273015750323,2879.011774397541,2904.0794390818446"
        ],
        "message": "Congratulations on your success!",
        "subject": "generateARModel"
    },
    "errors": null,
    "memo": "",
    "result": true
}

SN: Serial Number
Weight: Weight vector value for Autoregressive calculation.
Loss: difference square between actual value and predicting value.
Score: if the coefficient of determination(Score) in last row is close to 1, a satisfying prediction will be available.
AIC: Akaike’s Information Criterion
BIC: Bayesian Information Criterion

##0305. Generate Time Series MA Model
Generate a Moving Average Regression Prediction Model according to the trainText(a Space-separated numeric string dataset) whick inputed in Learning item in advance.
https://acrolearner.p.rapidapi.com/v0_1/CltService/ml/trains/{trainKey}/mamodel
http method: get

Request Header parameters:

x-rapidapi-host: acrolearner.p.rapidapi.com
x-rapidapi-key: [your rapidapi-key]

Request Path parameters:

{trainKey}: XXXXXXXXXX

Request Query parameters Example:

learnCount=1000&learnRate=0.000001&interval=300&qOrder=3
learnCount: learning times
learnRate: learning increment rate
interval: the output interval of learning result
qOrder: Moving Average Regression times for Learning

Response JSON Example:

Linear Regression Prediction successful case

{
    "contents": {
        "code": "0000",
        "list": [
            "SN,Weight,Loss,Score,AIC,BIC",
            "1,{1; 1; 1; 1},2487222.684538185,0.5395424145610919,5500.346121488055,5525.413786172359",
            "301,{0.9978670227; -0.0195982887; -0.0016041439; 0.0185807283},11203.196447788992,0.9979259610256793,2896.2337104351054,2921.301375119409",
            "601,{0.997637902; -0.0224575919; -0.0016866706; 0.0215239437},11203.053106341313,0.9979259875623692,2896.2275433541204,2921.295208038424",
            "901,{0.9974087857; -0.0228966553; -0.0016973725; 0.02197429},11203.049397398318,0.9979259882490029,2896.2273837805824,2921.295048464886",
            "1000,{0.9973331776; -0.0229333567; -0.0016981143; 0.0220118892},11203.049224539016,0.9979259882810042,2896.227376343484,2921.2950410277876",
            "****,{0.9973324138; -0.0229336236; -0.0016981194; 0.0220121627},11203.049223081296,0.997925988281274,2896.227376280767,2921.2950409650707"
        ],
        "message": "Congratulations on your success!",
        "subject": "generateMAModel"
    },
    "errors": null,
    "memo": "",
    "result": true
}

SN: Serial Number
Weight: Weight vector value for Moving Average Regression calculation.
Loss: difference square between actual value and predicting value.
Score: if the coefficient of determination(Score) in last row is close to 1, a satisfying prediction will be available.
AIC: Akaike’s Information Criterion
BIC: Bayesian Information Criterion

##0306. Generate Autoregressive moving average Prediction Model
Generate an Autoregressive moving average Prediction Model according to the trainText(a Space-separated numeric string dataset) whick inputed in Learning item in advance.
https://acrolearner.p.rapidapi.com/v0_1/CltService/ml/trains/{trainKey}/armamodel
http method: get

Request Header parameters:

Content-Type: application/json
x-rapidapi-host: acrolearner.p.rapidapi.com
x-rapidapi-key: [your rapidapi-key]

Request Path parameters:

{trainKey}: XXXXXXXXXX

Request Query parameters Example:

learnCount=1000&learnRate=0.000001&interval=400&pOrder=3&qOrder=4
learnCount: learning times
learnRate: learning increment rate
interval: the output interval of learning result
pOrder: Autoregressive times for Learning
qOrder: Moving Average Regression times for Learning

Response JSON Example:

{
    "contents": {
        "code": "0000",
        "list": [
            "AR_SN,Weight,Loss,Score,AIC,BIC",
            "1,{1; 1; 1; 1},2474203.259299,0.5104082290728595,5497.816454638019,5522.884119322323",
            "401,{0.9942555257; -0.0204399355; 0.0082958198; 0.0296171122},10394.153377136909,0.9979432199274353,2860.1050813921747,2885.1727460764782",
            "801,{0.9903814943; -0.0455323398; 0.0107955408; 0.0522190701},10388.344013246086,0.9979443694759798,2859.8356129624954,2884.903277646799",
            "1000,{0.9884541648; -0.0576022494; 0.0120254385; 0.0630636595},10385.645405176288,0.9979449034726507,2859.7103862599333,2884.778050944237",
            "****,{0.9884444797; -0.0576622241; 0.0120315961; 0.0631174997},10385.632151036325,0.9979449060953608,2859.7097711321017,2884.777435816405",
            "MA_SN,Weight,Loss,Score,AIC,BIC",
            "1,{1; 1; 1; 1; 1},4371513.609261247,0.13360253230262764,5763.214869865792,5792.445940756533",
            "401,{0.9978443902; 0.0530835081; -0.0000445695; -0.0709790284; 0.0176162459},10435.659888050717,0.997931739413643,2859.112042701139,2888.3431135918795",
            "801,{0.9976004678; 0.0602309392; -0.0002812524; -0.0794334974; 0.0191571988},10434.824816537459,0.9979319049178389,2859.073551079715,2888.304621970455",
            "1000,{0.9974791641; 0.0609172102; -0.0003105423; -0.0801898112; 0.0192564659},10434.813179919185,0.9979319072241194,2859.073014681969,2888.3040855727095",
            "****,{0.9974785546; 0.0609191946; -0.0003106272; -0.0801919579; 0.0192567133},10434.813161992355,0.9979319072276723,2859.0730138556196,2888.30408474636"
        ],
        "message": "Congratulations on your success!",
        "subject": "generateARMAModel"
    },
    "errors": null,
    "memo": "",
    "result": true
}

SN: Serial Number
Weight: Weight vector value for Linear Regression calculation.
Loss: difference between actual value and predicting value.
Score: if Score in last row is close to 1, a satisfying calculation accuracy will be available.
AIC: Akaike’s Information Criterion
BIC: Bayesian Information Criterion

##0307. Generate Autoregressive integrated moving average Prediction Model
Generate an Autoregressive integrated moving average Prediction Model according to the trainText(a Space-separated numeric string dataset) whick inputed in Learning item in advance.
https://acrolearner.p.rapidapi.com/v0_1/CltService/ml/trains/{trainKey}/arimamodel
http method: get

Request Header parameters:

Content-Type: application/json
x-rapidapi-host: acrolearner.p.rapidapi.com
x-rapidapi-key: [your rapidapi-key]

Request Path parameters:

{trainKey}: XXXXXXXXXX

Request Query parameters Example:

learnCount=1000&learnRate=0.000001&interval=400&pOrder=4&dOrder=2&qOrder=3
learnCount: learning times
learnRate: learning increment rate
interval: the output interval of learning result
pOrder: Autoregressive times for Learning
dOrder: Difference floors for Learning
qOrder: Moving Average Regression times for Learning

Response JSON Example:

{
    "contents": {
        "code": "0000",
        "list": [
            "AR_SN,Weight,Loss,Score,AIC,BIC",
            "1,{1; 1; 1; 1; 1},2545.8159579363823,0.996275023283012,2170.0060097157743,2199.1932848432143",
            "401,{1.0001766841; 0.8970572043; 1.0111441033; 1.0629349132; 0.7447483516},2142.9294999604417,0.9968645170643169,2087.6574160299733,2116.8446911574133",
            "801,{1.0003521807; 0.8131985718; 1.0225363156; 1.0827570422; 0.5530211807},1919.7023662258623,0.9971911376407844,2035.0756657409595,2064.2629408683997",
            "1000,{1.000438995; 0.7780328506; 1.0264823637; 1.0821807887; 0.4748781344},1845.6446812884583,0.9972994970652926,2016.2704195534668,2045.457694680907",
            "****,{1.0004394304; 0.777866243; 1.0264984324; 1.0821643979; 0.4745095066},1845.3164365246541,0.9972999773451411,2016.1854005069345,2045.3726756343747",
            "MA_SN,Weight,Loss,Score,AIC,BIC",
            "1,{1; 1; 1; 1},3775.9807647342777,0.9945071935377771,2360.3415211373435,2385.371724721809",
            "401,{1.0017655926; 0.7329383817; 0.7211742479; 0.7515616219},2714.522689674239,0.9960512649028966,2202.250435000328,2227.2806385847935",
            "801,{1.0031206219; 0.5376633522; 0.5101532121; 0.5695317272},2131.4194734438984,0.9968994877392432,2086.414844170939,2111.4450477554046",
            "1000,{1.0036759635; 0.46105072; 0.4251544208; 0.497992258},1948.1098025089805,0.9971661428436609,2043.3390415152385,2068.369245099704",
            "****,{1.0036785833; 0.4606950758; 0.4247563723; 0.497659962},1947.3193918247998,0.9971672926304803,2043.1446564017988,2068.1748599862644"
        ],
        "message": "Congratulations on your success!",
        "subject": "generateARIMAModel"
    },
    "errors": null,
    "memo": "",
    "result": true
}

SN: Serial Number
Weight: Weight vector value for Linear Regression calculation.
Loss: difference between actual value and predicting value.
Score: if Score in last row is close to 1, a satisfying calculation accuracy will be available.
AIC: Akaike’s Information Criterion
BIC: Bayesian Information Criterion