Is it mandatory to supply expected values using SARIMA in python?












0















I went through several examples on the internet discussing time series models. All of them take the dataset, divide it into train and test subsets, then make predictions. On those lines, I have built the SARIMA model and now want to give predictions just by supplying the date. Is it possible? I want to understand if it is necessary to supply expected values for the SARIMA model to predict. I am absolutely new to using this and don't have much knowledge.



I tried running this model supplying 0 as the expected value. The predicted values fell down drastically.



Date         Predicted Values   Actual Val  Real Expected valuesValues  

13-12-2018  11127.43655 100350  100350

14-12-2018  61918.4268  27690   27690

15-12-2018  68056.36533 56250   56250

17-12-2018  58788.21214 27500   27500

18-12-2018  46273.41352 56000   56000

19-12-2018  91364.35307 39500   39500

20-12-2018  35485.45094 16350   16350

21-12-2018  9959.904226 8800    8800

22-12-2018  23623.39142 18200   18200

24-12-2018  7882.683397 11400   11400

25-12-2018  18253.0067  6804    6804

27-12-2018  6054.384028 39750   39750

28-12-2018  29823.65986 36500   36500

30-12-2018  52208.31774 11900   11900

31-12-2018  32834.79271 35460   35460

01-01-2019  33330.47254 0   159800

03-01-2019  18247.63859 0   62110

04-01-2019  674.49602   0   20900

05-01-2019  8413.214224 0   21100

07-01-2019  2443.336355 0   60200

08-01-2019  8453.492621 0   3300

09-01-2019  12263.97753 0   30000

11-01-2019  9781.347563 0   63200

12-01-2019  9030.082098 0   60400

14-01-2019  9764.600961 0   30100

15-01-2019  9003.080852 0   59800

16-01-2019  9198.624997 0   75000

17-01-2019  9237.55489  0   300

18-01-2019  9421.229568 0   

19-01-2019  9508.386223 0   

20-01-2019  8918.123005 0   

21-01-2019  7202.594983 0   

22-01-2019  -1006.512393    0   

23-01-2019  -3449.003746    0   

24-01-2019  11631.88316 0   

25-01-2019  -8201.956656    0   

26-01-2019  269.2584279 0   

27-01-2019  1164.344788 0   

28-01-2019  -1690.742939    0   

29-01-2019  523.1414369 0   

30-01-2019  -800.7755814    0   

31-01-2019  2916.370306 0   

01-02-2019  1054.584057 0   

02-02-2019  -3648.714772    0   

03-02-2019  10658.23127 0   

04-02-2019  7168.453647 0   

05-02-2019  -1923.151   0   

06-02-2019  -433.6187245    0   

07-02-2019  -972.3397832    0   

08-02-2019  -210.005357 0   

09-02-2019  -133.8067359    0   

10-02-2019  -765.2318848    0   

11-02-2019  -469.8792724    0   

12-02-2019  -426.3063272    0   

13-02-2019  -487.2058061    0   

14-02-2019  -383.7439919    0   

15-02-2019  -363.895701 0   

16-02-2019  -670.8445192    0   

17-02-2019  -256.8718444    0   

18-02-2019  -302.5668497    0   

19-02-2019  -2134.088087    0   

20-02-2019  9702.266215 0   

21-02-2019  9386.689598 0   

22-02-2019  9511.400117 0   

23-02-2019  8984.037821 0   

24-02-2019  9274.275375 0   

25-02-2019  9775.821644 0   

26-02-2019  9548.200018 0   

27-02-2019  9102.492507 0   

28-02-2019  9231.856666 0





python







share|improve this question





























    0















    I went through several examples on the internet discussing time series models. All of them take the dataset, divide it into train and test subsets, then make predictions. On those lines, I have built the SARIMA model and now want to give predictions just by supplying the date. Is it possible? I want to understand if it is necessary to supply expected values for the SARIMA model to predict. I am absolutely new to using this and don't have much knowledge.



    I tried running this model supplying 0 as the expected value. The predicted values fell down drastically.



    Date         Predicted Values   Actual Val  Real Expected valuesValues  
    
13-12-2018  11127.43655 100350  100350
    
14-12-2018  61918.4268  27690   27690
    
15-12-2018  68056.36533 56250   56250
    
17-12-2018  58788.21214 27500   27500
    
18-12-2018  46273.41352 56000   56000
    
19-12-2018  91364.35307 39500   39500
    
20-12-2018  35485.45094 16350   16350
    
21-12-2018  9959.904226 8800    8800
    
22-12-2018  23623.39142 18200   18200
    
24-12-2018  7882.683397 11400   11400
    
25-12-2018  18253.0067  6804    6804
    
27-12-2018  6054.384028 39750   39750
    
28-12-2018  29823.65986 36500   36500
    
30-12-2018  52208.31774 11900   11900
    
31-12-2018  32834.79271 35460   35460
    
01-01-2019  33330.47254 0   159800
    
03-01-2019  18247.63859 0   62110
    
04-01-2019  674.49602   0   20900
    
05-01-2019  8413.214224 0   21100
    
07-01-2019  2443.336355 0   60200
    
08-01-2019  8453.492621 0   3300
    
09-01-2019  12263.97753 0   30000
    
11-01-2019  9781.347563 0   63200
    
12-01-2019  9030.082098 0   60400
    
14-01-2019  9764.600961 0   30100
    
15-01-2019  9003.080852 0   59800
    
16-01-2019  9198.624997 0   75000
    
17-01-2019  9237.55489  0   300
    
18-01-2019  9421.229568 0   
    
19-01-2019  9508.386223 0   
    
20-01-2019  8918.123005 0   
    
21-01-2019  7202.594983 0   
    
22-01-2019  -1006.512393    0   
    
23-01-2019  -3449.003746    0   
    
24-01-2019  11631.88316 0   
    
25-01-2019  -8201.956656    0   
    
26-01-2019  269.2584279 0   
    
27-01-2019  1164.344788 0   
    
28-01-2019  -1690.742939    0   
    
29-01-2019  523.1414369 0   
    
30-01-2019  -800.7755814    0   
    
31-01-2019  2916.370306 0   
    
01-02-2019  1054.584057 0   
    
02-02-2019  -3648.714772    0   
    
03-02-2019  10658.23127 0   
    
04-02-2019  7168.453647 0   
    
05-02-2019  -1923.151   0   
    
06-02-2019  -433.6187245    0   
    
07-02-2019  -972.3397832    0   
    
08-02-2019  -210.005357 0   
    
09-02-2019  -133.8067359    0   
    
10-02-2019  -765.2318848    0   
    
11-02-2019  -469.8792724    0   
    
12-02-2019  -426.3063272    0   
    
13-02-2019  -487.2058061    0   
    
14-02-2019  -383.7439919    0   
    
15-02-2019  -363.895701 0   
    
16-02-2019  -670.8445192    0   
    
17-02-2019  -256.8718444    0   
    
18-02-2019  -302.5668497    0   
    
19-02-2019  -2134.088087    0   
    
20-02-2019  9702.266215 0   
    
21-02-2019  9386.689598 0   
    
22-02-2019  9511.400117 0   
    
23-02-2019  8984.037821 0   
    
24-02-2019  9274.275375 0   
    
25-02-2019  9775.821644 0   
    
26-02-2019  9548.200018 0   
    
27-02-2019  9102.492507 0   
    
28-02-2019  9231.856666 0





    python







    share|improve this question



























      0












      0








      0








      I went through several examples on the internet discussing time series models. All of them take the dataset, divide it into train and test subsets, then make predictions. On those lines, I have built the SARIMA model and now want to give predictions just by supplying the date. Is it possible? I want to understand if it is necessary to supply expected values for the SARIMA model to predict. I am absolutely new to using this and don't have much knowledge.



      I tried running this model supplying 0 as the expected value. The predicted values fell down drastically.



      Date         Predicted Values   Actual Val  Real Expected valuesValues  
      
13-12-2018  11127.43655 100350  100350
      
14-12-2018  61918.4268  27690   27690
      
15-12-2018  68056.36533 56250   56250
      
17-12-2018  58788.21214 27500   27500
      
18-12-2018  46273.41352 56000   56000
      
19-12-2018  91364.35307 39500   39500
      
20-12-2018  35485.45094 16350   16350
      
21-12-2018  9959.904226 8800    8800
      
22-12-2018  23623.39142 18200   18200
      
24-12-2018  7882.683397 11400   11400
      
25-12-2018  18253.0067  6804    6804
      
27-12-2018  6054.384028 39750   39750
      
28-12-2018  29823.65986 36500   36500
      
30-12-2018  52208.31774 11900   11900
      
31-12-2018  32834.79271 35460   35460
      
01-01-2019  33330.47254 0   159800
      
03-01-2019  18247.63859 0   62110
      
04-01-2019  674.49602   0   20900
      
05-01-2019  8413.214224 0   21100
      
07-01-2019  2443.336355 0   60200
      
08-01-2019  8453.492621 0   3300
      
09-01-2019  12263.97753 0   30000
      
11-01-2019  9781.347563 0   63200
      
12-01-2019  9030.082098 0   60400
      
14-01-2019  9764.600961 0   30100
      
15-01-2019  9003.080852 0   59800
      
16-01-2019  9198.624997 0   75000
      
17-01-2019  9237.55489  0   300
      
18-01-2019  9421.229568 0   
      
19-01-2019  9508.386223 0   
      
20-01-2019  8918.123005 0   
      
21-01-2019  7202.594983 0   
      
22-01-2019  -1006.512393    0   
      
23-01-2019  -3449.003746    0   
      
24-01-2019  11631.88316 0   
      
25-01-2019  -8201.956656    0   
      
26-01-2019  269.2584279 0   
      
27-01-2019  1164.344788 0   
      
28-01-2019  -1690.742939    0   
      
29-01-2019  523.1414369 0   
      
30-01-2019  -800.7755814    0   
      
31-01-2019  2916.370306 0   
      
01-02-2019  1054.584057 0   
      
02-02-2019  -3648.714772    0   
      
03-02-2019  10658.23127 0   
      
04-02-2019  7168.453647 0   
      
05-02-2019  -1923.151   0   
      
06-02-2019  -433.6187245    0   
      
07-02-2019  -972.3397832    0   
      
08-02-2019  -210.005357 0   
      
09-02-2019  -133.8067359    0   
      
10-02-2019  -765.2318848    0   
      
11-02-2019  -469.8792724    0   
      
12-02-2019  -426.3063272    0   
      
13-02-2019  -487.2058061    0   
      
14-02-2019  -383.7439919    0   
      
15-02-2019  -363.895701 0   
      
16-02-2019  -670.8445192    0   
      
17-02-2019  -256.8718444    0   
      
18-02-2019  -302.5668497    0   
      
19-02-2019  -2134.088087    0   
      
20-02-2019  9702.266215 0   
      
21-02-2019  9386.689598 0   
      
22-02-2019  9511.400117 0   
      
23-02-2019  8984.037821 0   
      
24-02-2019  9274.275375 0   
      
25-02-2019  9775.821644 0   
      
26-02-2019  9548.200018 0   
      
27-02-2019  9102.492507 0   
      
28-02-2019  9231.856666 0





      python







      share|improve this question
















      I went through several examples on the internet discussing time series models. All of them take the dataset, divide it into train and test subsets, then make predictions. On those lines, I have built the SARIMA model and now want to give predictions just by supplying the date. Is it possible? I want to understand if it is necessary to supply expected values for the SARIMA model to predict. I am absolutely new to using this and don't have much knowledge.



      I tried running this model supplying 0 as the expected value. The predicted values fell down drastically.



      Date         Predicted Values   Actual Val  Real Expected valuesValues  
      
13-12-2018  11127.43655 100350  100350
      
14-12-2018  61918.4268  27690   27690
      
15-12-2018  68056.36533 56250   56250
      
17-12-2018  58788.21214 27500   27500
      
18-12-2018  46273.41352 56000   56000
      
19-12-2018  91364.35307 39500   39500
      
20-12-2018  35485.45094 16350   16350
      
21-12-2018  9959.904226 8800    8800
      
22-12-2018  23623.39142 18200   18200
      
24-12-2018  7882.683397 11400   11400
      
25-12-2018  18253.0067  6804    6804
      
27-12-2018  6054.384028 39750   39750
      
28-12-2018  29823.65986 36500   36500
      
30-12-2018  52208.31774 11900   11900
      
31-12-2018  32834.79271 35460   35460
      
01-01-2019  33330.47254 0   159800
      
03-01-2019  18247.63859 0   62110
      
04-01-2019  674.49602   0   20900
      
05-01-2019  8413.214224 0   21100
      
07-01-2019  2443.336355 0   60200
      
08-01-2019  8453.492621 0   3300
      
09-01-2019  12263.97753 0   30000
      
11-01-2019  9781.347563 0   63200
      
12-01-2019  9030.082098 0   60400
      
14-01-2019  9764.600961 0   30100
      
15-01-2019  9003.080852 0   59800
      
16-01-2019  9198.624997 0   75000
      
17-01-2019  9237.55489  0   300
      
18-01-2019  9421.229568 0   
      
19-01-2019  9508.386223 0   
      
20-01-2019  8918.123005 0   
      
21-01-2019  7202.594983 0   
      
22-01-2019  -1006.512393    0   
      
23-01-2019  -3449.003746    0   
      
24-01-2019  11631.88316 0   
      
25-01-2019  -8201.956656    0   
      
26-01-2019  269.2584279 0   
      
27-01-2019  1164.344788 0   
      
28-01-2019  -1690.742939    0   
      
29-01-2019  523.1414369 0   
      
30-01-2019  -800.7755814    0   
      
31-01-2019  2916.370306 0   
      
01-02-2019  1054.584057 0   
      
02-02-2019  -3648.714772    0   
      
03-02-2019  10658.23127 0   
      
04-02-2019  7168.453647 0   
      
05-02-2019  -1923.151   0   
      
06-02-2019  -433.6187245    0   
      
07-02-2019  -972.3397832    0   
      
08-02-2019  -210.005357 0   
      
09-02-2019  -133.8067359    0   
      
10-02-2019  -765.2318848    0   
      
11-02-2019  -469.8792724    0   
      
12-02-2019  -426.3063272    0   
      
13-02-2019  -487.2058061    0   
      
14-02-2019  -383.7439919    0   
      
15-02-2019  -363.895701 0   
      
16-02-2019  -670.8445192    0   
      
17-02-2019  -256.8718444    0   
      
18-02-2019  -302.5668497    0   
      
19-02-2019  -2134.088087    0   
      
20-02-2019  9702.266215 0   
      
21-02-2019  9386.689598 0   
      
22-02-2019  9511.400117 0   
      
23-02-2019  8984.037821 0   
      
24-02-2019  9274.275375 0   
      
25-02-2019  9775.821644 0   
      
26-02-2019  9548.200018 0   
      
27-02-2019  9102.492507 0   
      
28-02-2019  9231.856666 0





      python




      python






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited 3 hours ago









      TrebuchetMS

      2,3771622




      2,3771622










      asked 3 hours ago









      Pallavi GroverPallavi Grover

      374




      374
























          0






          active

          oldest

          votes











          Your Answer






          StackExchange.ifUsing("editor", function () {
          StackExchange.using("externalEditor", function () {
          StackExchange.using("snippets", function () {
          StackExchange.snippets.init();
          });
          });
          }, "code-snippets");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "1"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54249350%2fis-it-mandatory-to-supply-expected-values-using-sarima-in-python%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes
















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Stack Overflow!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid …



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f54249350%2fis-it-mandatory-to-supply-expected-values-using-sarima-in-python%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          -

          Popular posts from this blog

          Callistus III

          Image
          Callistus III Res apud Vicidata repertae: Nativitas : 8 Ianuarii 1379 ; Canals Obitus : 15 Augusti 1458 ; Roma Patria : Corona Aragoniae Nomen nativum : Alonso de Borja i Llançol Pontificatus 1455 - 1458 Praecessor : Nicolaus V Successor : Pius II Insignia heraldica Callistus III (natus Alphonsus de Borgia Hispanice Alonso de Borja y Borja , Italiane Alfonso Borgia , die 31 Decembris 1378 Saetabis Augustae in Hispania apud Valentiam - obiit die 6 Augusti 1458), papa catholicus episcopus Romanus a die 8 Aprilis 1455 erat. Vita | Alphonsus de Borgia studuit iuri canonico Ilerdae. Postea iuris consultus antipapae Benedicti XIII et regis Alphonsi V Aragoniae fit. Anno 1444 episcopus Valentiae factus est. Anno 1444 a papa Eugenio IV Cardinalis Sanctae Romanae Ecclesiae creatus est. Bibliographia | Friedrich Wilhelm Bautz, "CALIXT III., Papst" in Biographisch-Bibliographisches Kirchenlexikon  vol. 1 (Hammonae, 1975; reimpr. 1990. ISBN 3-88...
          Read more

          Plistias Cous

          Plistias Cous (Graece Πλειστίας ), qui saeculo IV a.C.n. exeunte floruit, insulae Coi incola, fuit anno 306 a.C.n. pro Demetrio Poliorceta dux classium. Ille enim navigator principalis fuit classis omnis; ille una cum Hegesippo Halicarnassensi in proelio iuxta Salaminem Cypri commisso praefuit alae dextrae. Fontes | Diodorus Siculus, Bibliotheca historica 20.50.4 Bibliographia | "Prosopography of Antigonos's Friends and Subordinates" in Richard A. Billows, Antigonos the One-Eyed and the Creation of the Hellenistic State (Berkeley: University of California Press, 1990) no. 98, p. 425 H. Hauben, Het vlootbevelhebberschap in de vroege Diadochen tijd (Bruxellis, 1975) pp. 78, 117-119 T. Lenschau, "Pleistias" in Paulys Real-Enzyklopädie der classischen Altertumswissenschaft edd. G. Wissowa et alii (Stuttgart, 1893-1972 ~ ~) This page is only for reference, If you need detailed information, please check here
          Read more

          Index Sanctorum

          Index Sanctorum Sanctus, -i n. Religio Christiana . Sancti | Index A B C D E F G H I L M N O P Q R S T U V X Z Vide etiam — Nexus externi Index hic non iuxta normas Ecclesiae Catholicae Romanae est factus, cum plurimos tenet qui a ecclesia non agnoscuntur. A | Abundius episcopus Adalbertus (episcopus Pragensis) Aegidius abbas Agapetus I Agapitus Praenestinus Agatha Catanensis Agatho Agnes de Bohemia Agnes Romana Albertus Hurtado Albertus Magnus Alexander I Aloisius Gonzaga Aloisius Orione Alphonsus a Ligorio Ambrosius Anastasius I (papa) Andreas (apostolus) Anicetus (papa) Anscharius (archiepiscopus Hamburgensis-Bremensis) Anterus Antonius Patavinus Antonius abbas Antoninus Natolii de Pactis Athanasius Alexandrinus Augustinus Augustinus Cantuariensis Avitus B | Bartholomaeus (apostolus) Basilius (beatus) Basilius Magnus Basilius Ostrogiensis Beda Benedictus de Nursia Benedictus II Bernadetta Lapurdensis Bernardus ...
          Read more