From 5c5f61089844ceabf460b2450d9fa7e3d1bc3bff Mon Sep 17 00:00:00 2001 From: Ivikhostrup Date: Tue, 17 May 2022 10:17:01 +0200 Subject: [PATCH 1/7] data loading intro --- master.tex | 1 + sections/data-loading.tex | 10 ++++++++++ 2 files changed, 11 insertions(+) create mode 100644 sections/data-loading.tex diff --git a/master.tex b/master.tex index 3b21a2e..dd5bfd7 100644 --- a/master.tex +++ b/master.tex @@ -54,6 +54,7 @@ \section{Preliminaries} \section{Transformer model for time series forecasting by embedding temporal data as vectors} % Methodology +\input{sections/data-loading.tex} \input{sections/transformers.tex} \input{sections/methodology.tex} diff --git a/sections/data-loading.tex b/sections/data-loading.tex new file mode 100644 index 0000000..c26b30c --- /dev/null +++ b/sections/data-loading.tex @@ -0,0 +1,10 @@ +As the purpose of the project is to create a system in which a user should be able to see the weather forecast for specific area, or more specifically the temperature forcast, we have developed a system that leverages several models to do the temparature forecasting. +The goal is to allow the user to interact with the system in such a way that the user can see the accuracy of the different models. +The user will be able to select a region for which they want to predict the temperature. The results will be shown both as a graph that will display the predicted value versus the actual value as well as the specific set of temperatures of that region for a given time period into the future. This is similar to what one may see on regular weather forecasts. + +In order to achieve this we have constructed a pipeline that preprocesses the data, trains our models, and the resulting models are then used to do the forecasting which is displayed on a web application. +Figure xx shows the architecture of the pipeline in broad terms. +Note that since the transformer model is the best performing model, which is shown in section (experiment afsnit), this is the model that we chosen to include and describe as part of the pipeline. Regardless of this fact, the other models are used into the pipeline in a similar fashion. + +\subsection{Data loading and preprocessing} +In order to load the data we have done the following... \ No newline at end of file From 001cd201e47ad5e77d14adc3365c311222b78dc1 Mon Sep 17 00:00:00 2001 From: Ivikhostrup <56341364+Ivikhostrup@users.noreply.github.com> Date: Tue, 17 May 2022 11:40:33 +0200 Subject: [PATCH 2/7] Update sections/data-loading.tex Co-authored-by: Pattrigue <57709490+Pattrigue@users.noreply.github.com> --- sections/data-loading.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/data-loading.tex b/sections/data-loading.tex index c26b30c..5fd4bea 100644 --- a/sections/data-loading.tex +++ b/sections/data-loading.tex @@ -1,4 +1,4 @@ -As the purpose of the project is to create a system in which a user should be able to see the weather forecast for specific area, or more specifically the temperature forcast, we have developed a system that leverages several models to do the temparature forecasting. +As the purpose of the project is to create a system in which a user should be able to see the weather forecast for a specific area, or more precisely, the temperature forecast, we have developed a system that leverages several models to perform the temperature forecasting. The goal is to allow the user to interact with the system in such a way that the user can see the accuracy of the different models. The user will be able to select a region for which they want to predict the temperature. The results will be shown both as a graph that will display the predicted value versus the actual value as well as the specific set of temperatures of that region for a given time period into the future. This is similar to what one may see on regular weather forecasts. From 600b729910c9ba63fbc68035b7f846456d150c8e Mon Sep 17 00:00:00 2001 From: Ivikhostrup <56341364+Ivikhostrup@users.noreply.github.com> Date: Tue, 17 May 2022 11:40:47 +0200 Subject: [PATCH 3/7] Update sections/data-loading.tex Co-authored-by: Pattrigue <57709490+Pattrigue@users.noreply.github.com> --- sections/data-loading.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/data-loading.tex b/sections/data-loading.tex index 5fd4bea..7ed2b82 100644 --- a/sections/data-loading.tex +++ b/sections/data-loading.tex @@ -1,6 +1,6 @@ As the purpose of the project is to create a system in which a user should be able to see the weather forecast for a specific area, or more precisely, the temperature forecast, we have developed a system that leverages several models to perform the temperature forecasting. The goal is to allow the user to interact with the system in such a way that the user can see the accuracy of the different models. -The user will be able to select a region for which they want to predict the temperature. The results will be shown both as a graph that will display the predicted value versus the actual value as well as the specific set of temperatures of that region for a given time period into the future. This is similar to what one may see on regular weather forecasts. +The user is able to select a region for which they want to predict the temperature. The results are shown both as a graph that displays the predicted value versus the actual value, as well as the specific set of temperatures of that region for a given time period into the future. This is similar to what one may see on regular weather forecasts. In order to achieve this we have constructed a pipeline that preprocesses the data, trains our models, and the resulting models are then used to do the forecasting which is displayed on a web application. Figure xx shows the architecture of the pipeline in broad terms. From cb12032a50df033b6d7a8526bbc0c4389917472f Mon Sep 17 00:00:00 2001 From: Ivikhostrup <56341364+Ivikhostrup@users.noreply.github.com> Date: Tue, 17 May 2022 11:40:57 +0200 Subject: [PATCH 4/7] Update sections/data-loading.tex Co-authored-by: Pattrigue <57709490+Pattrigue@users.noreply.github.com> --- sections/data-loading.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/data-loading.tex b/sections/data-loading.tex index 7ed2b82..9b87a80 100644 --- a/sections/data-loading.tex +++ b/sections/data-loading.tex @@ -2,7 +2,7 @@ The goal is to allow the user to interact with the system in such a way that the user can see the accuracy of the different models. The user is able to select a region for which they want to predict the temperature. The results are shown both as a graph that displays the predicted value versus the actual value, as well as the specific set of temperatures of that region for a given time period into the future. This is similar to what one may see on regular weather forecasts. -In order to achieve this we have constructed a pipeline that preprocesses the data, trains our models, and the resulting models are then used to do the forecasting which is displayed on a web application. +In order to achieve, this we have constructed a pipeline that preprocesses the data, trains our models, and the resulting models are then used to perform the forecasting displayed on a web application. Figure xx shows the architecture of the pipeline in broad terms. Note that since the transformer model is the best performing model, which is shown in section (experiment afsnit), this is the model that we chosen to include and describe as part of the pipeline. Regardless of this fact, the other models are used into the pipeline in a similar fashion. From 88e43531bb515a96e75109d7de67a2232fc08462 Mon Sep 17 00:00:00 2001 From: Ivikhostrup <56341364+Ivikhostrup@users.noreply.github.com> Date: Tue, 17 May 2022 11:41:05 +0200 Subject: [PATCH 5/7] Update sections/data-loading.tex Co-authored-by: Pattrigue <57709490+Pattrigue@users.noreply.github.com> --- sections/data-loading.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/data-loading.tex b/sections/data-loading.tex index 9b87a80..3ca33ec 100644 --- a/sections/data-loading.tex +++ b/sections/data-loading.tex @@ -3,7 +3,7 @@ The user is able to select a region for which they want to predict the temperature. The results are shown both as a graph that displays the predicted value versus the actual value, as well as the specific set of temperatures of that region for a given time period into the future. This is similar to what one may see on regular weather forecasts. In order to achieve, this we have constructed a pipeline that preprocesses the data, trains our models, and the resulting models are then used to perform the forecasting displayed on a web application. -Figure xx shows the architecture of the pipeline in broad terms. +Figure xx shows an overview of the architecture of the pipeline. Note that since the transformer model is the best performing model, which is shown in section (experiment afsnit), this is the model that we chosen to include and describe as part of the pipeline. Regardless of this fact, the other models are used into the pipeline in a similar fashion. \subsection{Data loading and preprocessing} From 50a4fcc35dbe503964515e3b430a6c3eb974c63e Mon Sep 17 00:00:00 2001 From: Ivikhostrup <56341364+Ivikhostrup@users.noreply.github.com> Date: Tue, 17 May 2022 11:41:14 +0200 Subject: [PATCH 6/7] Update sections/data-loading.tex Co-authored-by: Pattrigue <57709490+Pattrigue@users.noreply.github.com> --- sections/data-loading.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/data-loading.tex b/sections/data-loading.tex index 3ca33ec..9f4f37a 100644 --- a/sections/data-loading.tex +++ b/sections/data-loading.tex @@ -4,7 +4,7 @@ In order to achieve, this we have constructed a pipeline that preprocesses the data, trains our models, and the resulting models are then used to perform the forecasting displayed on a web application. Figure xx shows an overview of the architecture of the pipeline. -Note that since the transformer model is the best performing model, which is shown in section (experiment afsnit), this is the model that we chosen to include and describe as part of the pipeline. Regardless of this fact, the other models are used into the pipeline in a similar fashion. +Note that since the transformer model is the best performing model, which is shown in section (experiment afsnit), this is the model that we chose to include and describe as part of the pipeline. Regardless of this fact, the other models are used in the pipeline in a similar fashion. \subsection{Data loading and preprocessing} In order to load the data we have done the following... \ No newline at end of file From 7470fcf4f33ee90a4cf7b045d745a7f0a5ea5e6a Mon Sep 17 00:00:00 2001 From: Ivikhostrup <56341364+Ivikhostrup@users.noreply.github.com> Date: Tue, 17 May 2022 11:41:21 +0200 Subject: [PATCH 7/7] Update sections/data-loading.tex Co-authored-by: Pattrigue <57709490+Pattrigue@users.noreply.github.com> --- sections/data-loading.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/data-loading.tex b/sections/data-loading.tex index 9f4f37a..4a2052f 100644 --- a/sections/data-loading.tex +++ b/sections/data-loading.tex @@ -7,4 +7,4 @@ Note that since the transformer model is the best performing model, which is shown in section (experiment afsnit), this is the model that we chose to include and describe as part of the pipeline. Regardless of this fact, the other models are used in the pipeline in a similar fashion. \subsection{Data loading and preprocessing} -In order to load the data we have done the following... \ No newline at end of file +In order to load the data, we have done the following... \ No newline at end of file