Compare time series predictions of COVID-19 deaths

Оценки: 23
от партнера
Coursera Project Network
В этом Проект с консультациями вы:

Preprocess time series data for various machine learning models

Visualize time series data

Compare the time series predictions of 4 machine learning models

Clock2 hours
IntermediateУчащийся среднего уровня
CloudЗагрузка не требуется
VideoВидео на разделенном экране
Comment DotsАнглийский
LaptopТолько для ПК

In this 2-hour long project-based course, you will learn how to preprocess time series data, visualize time series data and compare the time series predictions of 4 machine learning models.You will create time series analysis models in the python programming language to predict the daily deaths due to SARS-CoV-19, or COVID-19. You will create and train the following models: SARIMAX, Prophet, neural networks and XGBOOST. You will visualize data using the matplotlib library, and extract features from a time series data set, perform data splitting and normalization. To successfully complete this project, learners should have prior Python programming experience, a basic understanding of machine learning, and a familiarity of the Pandas library. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Навыки, которые вы получите

  • Time Series Forecasting
  • Machine Learning
  • Feature Engineering
  • Python Programming
  • Time Series Models

Будете учиться пошагово

На видео, которое откроется рядом с рабочей областью, преподаватель объяснит эти шаги:

  1. Preprocess the data using pandas to be ready for machine learning, and visualize the data using matplotlib

  2. Create a SARIMAX model, optimize the model hyperparameters, use the model for forecasting future COVID-19 deaths and visualize the results

  3. Create a prophet model and use the model for forecasting future COVID-19 deaths and visualize the results

  4. Create a function that extracts features for training the XGBOOST and a feedforward neural network models

  5. Split time series feature dataset into training and test datasets and perform data normalization

  6. Train an XGBOOST model and a feedforward neural network model, and finally compare the predictions of all the models covered in the project

Как устроены проекты с консультациями

Ваше рабочее пространство — это облачный рабочий стол в браузере. Ничего не нужно загружать.

На разделенном экране видео преподаватель предоставляет пошаговые



Посмотреть все отзывы

Часто задаваемые вопросы

Часто задаваемые вопросы

Остались вопросы? Посетите Центр поддержки учащихся.