{"id":16509637,"url":"https://github.com/jeugregg/coronavirusmodel","last_synced_at":"2026-06-24T22:31:23.092Z","repository":{"id":37669148,"uuid":"243444649","full_name":"jeugregg/coronavirusModel","owner":"jeugregg","description":"Coronavirus Visualization \u0026 Modeling","archived":false,"fork":false,"pushed_at":"2023-05-23T04:19:09.000Z","size":255112,"stargazers_count":1,"open_issues_count":16,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-06T06:19:48.779Z","etag":null,"topics":["coronavirus","covid-19","data-visualization"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jeugregg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-02-27T06:09:49.000Z","updated_at":"2021-12-29T06:34:15.000Z","dependencies_parsed_at":"2025-04-04T18:55:43.202Z","dependency_job_id":null,"html_url":"https://github.com/jeugregg/coronavirusModel","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jeugregg/coronavirusModel","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeugregg%2FcoronavirusModel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeugregg%2FcoronavirusModel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeugregg%2FcoronavirusModel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeugregg%2FcoronavirusModel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jeugregg","download_url":"https://codeload.github.com/jeugregg/coronavirusModel/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeugregg%2FcoronavirusModel/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34752465,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-24T02:00:07.484Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["coronavirus","covid-19","data-visualization"],"created_at":"2024-10-11T15:51:27.762Z","updated_at":"2026-06-24T22:31:23.067Z","avatar_url":"https://github.com/jeugregg.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Coronavirus Visualization \u0026 Modeling  \n\nThis project is about COVID-19 evolution.  \n\nI have developed 3 main python projects.  \n\n**1) A very complete notebook [coronavirus-visualization-modeling.ipynb](https://github.com/jeugregg/coronavirusModel/blob/master/coronavirus-visualization-modeling.ipynb) shows the evolution of COVID-19 virus all over the world.**  \n\nPublished version is available on kaggle : https://www.kaggle.com/jeugregg/coronavirus-visualization-modeling  \n\nIt also focuses on South Korea and France areas.  \n\nAnimated Maps are Available at Region-level for South Korea, France, USA, China.  \nAlso, more globally, at country-level for all other countries in the World.  \n \nAlso, this notebook scraps data from French and Korean Health official websites.  \nIf you discover the code, you can see how.  \nKorean \u0026 French data are updated daily.   \n\nThe world data source is https://github.com/CSSEGISandData/COVID-19 provided by JHU CSSE  \n\nSouth Korea areas data are retrieved with scrapy from KCDC Press Release articles at https://www.cdc.go.kr/board/board.es?mid=a30402000000\u0026bid=0030.  \n\n**2) App Dashboard with evolution prediction by Deep Learning: [app.py](https://github.com/jeugregg/coronavirusModel/blob/master/app.py)**  \n\nThis app is online here : http://app-covid-visu.coolplace.fr/  \n\nI added a simple LSTM Deep Learning Tensorflow model to estimate the actual total number of confirmed cases  in France.  \n\nIt is developed in [Plotly Dash](https://plotly.com/dash/)  \n\nYou can see the model development notebook [ModelCovidTimeSeries.ipynb](https://github.com/jeugregg/coronavirusModel/blob/master/ModelCovidTimeSeries.ipynb)  \n\nThe model estimates the number of daily confirmed cases in France for next days by time-series forecast.  \nFor that, it takes a period of 14 days to estimate the next 7 days.  \nBecause of lack of data, it has been trained with only few past periods and validated on only very few periods!  \n\nInput Features are daily data for:  \n- Min/Max Temperatures\n- Min/Max Humidities\n- Confirmed cases\n- Test cases\n- Day of the week\n- Mean Age of Tested cases\n- Mean Age of Confirmed cases\n\nThe predictions are under-estimated because the evolution is big during last days.  \nThe model will learn from this current changing period in few weeks, so predictions must be better.  \nIf new data is available, the model is predicting daily confirmed cases for next days.  \n\nThe model is hosted on AWS EC2 Cluster (t2.micro).  \n\nBecause memory needed to do prediction is too high for t2.micro instance, I use AWS Lambda API call only for this purpose.  \nI have implemented it thanks to [serverless framework](https://www.serverless.com/).  \n\nBut, the tensorflow model have to be converted in Tensorflow LITE to respect storage limit for AWS lambda function. [conversion](https://github.com/jeugregg/coronavirusModel/blob/master/ModelCovidTimeSeries-convert-publish-KR.ipynb)  \nFor the conversion, LSTM neural network needs special format.  \nHave a look at this [tutorial](https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/experimental_new_converter/Keras_LSTM_fusion_Codelab.ipynb).  \n\nAnd Tensorflow lite library is pre-compiled before packaging it in lambda function.  \nIf you are interested, look at this [very good tutorial](https://github.com/edeltech/tensorflow-lite-on-aws-lambda).  \n\n\nDATA Sources :  \n- Tested / Confirmed cases: https://www.data.gouv.fr/fr/datasets/donnees-relatives-aux-resultats-des-tests-virologiques-covid-19\n- Meteo France : https://public.opendatasoft.com/explore/dataset/donnees-synop-essentielles-omm\n- Tested / Confirmed cases KR: https://www.data.go.kr/tcs/dss/selectApiDataDetailView.do?publicDataPk=15043376\n- Confirmed cases by age KR: https://www.data.go.kr/tcs/dss/selectApiDataDetailView.do?publicDataPk=15043377\n- Confirmed cases by area KR: https://www.data.go.kr/tcs/dss/selectApiDataDetailView.do?publicDataPk=15043378\n- Meteo South Korea (Seoul, Deagu, Busan): https://www.visualcrossing.com/weather-data\n- Geoson Map South Korea: https://github.com/southkorea/southkorea-maps \n\n**3) Deep Learning for read Table in HTML : [readTableWithBERT.ipynb](https://github.com/jeugregg/coronavirusModel/blob/master/readTableWithBERT.ipynb)**  \nAdditional file : [read Table into HTML BERT model resume training.ipynb](https://github.com/jeugregg/coronavirusModel/blob/master/read%20Table%20into%20HTML%20BERT%20model%20resume%20training.ipynb)  \nI stop this project because I just tried transfert learning from a BERT style model : distilbert and I had bad results.  \n\nI prefer adapting scrapy classical method every times table format changed (KCDC table COVID-19 reports).  \n\nI used this github to train the model : [simpletransformers](https://github.com/ThilinaRajapakse/simpletransformers)  \n\nI think it is not the good model to do that.  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjeugregg%2Fcoronavirusmodel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjeugregg%2Fcoronavirusmodel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjeugregg%2Fcoronavirusmodel/lists"}