Posted on Categories:Time Series, 数据科学代写, 时间序列, 统计代写, 统计代考

# 统计代写|时间序列分析代写Time-Series Analysis代考|STAT360 DATA DESCRIPTION

avatest™

## avatest™帮您通过考试

avatest™的各个学科专家已帮了学生顺利通过达上千场考试。我们保证您快速准时完成各时长和类型的考试，包括in class、take home、online、proctor。写手整理各样的资源来或按照您学校的资料教您，创造模拟试题，提供所有的问题例子，以保证您在真实考试中取得的通过率是85%以上。如果您有即将到来的每周、季考、期中或期末考试，我们都能帮助您！

•最快12小时交付

•200+ 英语母语导师

•70分以下全额退款

## 统计代写|时间序列分析代写Time-Series Analysis代考|DATA DESCRIPTION

The data set used in this paper has been taken from covid-tracker source (COVID19 India Org Data Operations Group, 2020). The data set is tallied with the official government data source and is highly reliable. However, the escalation and fall in cases depends upon many factors. For example, person-to-person spreads were subsequently increased due to recent freedom of movement in metropolitan cities. The line plots in Figure 8.4 are based on the daily figures of confirmed and recovered cases in the entire Indian subcontinent, starting from the first reported case on February 3, 2020 to the tally as on October 20, 2020. For the training and evaluation of the forecasting models, the data has been split into training (from March 14, 2020 to October 20, 2020) and testing (from October 21, 2020 to November 4, 2020) sets. From Figure 8.4, it is evident that the virus spread exponentially in the months leading up to September 2020, upon which it hit a certain peak and a steep downfall is visible. On November 4,2020 , the recorded cases were $8,363,329$, recovered cases were $7,710,463$ and deaths were 123,765 . However, the number of cases is expected to increase in the coming days due to the complete relaxation of lockdown norms and extensive inter-state movement due to the upcoming festival.

## 统计代写|时间序列分析代写Time-Series Analysis代考|SeVERITY ANALYSIS

Figure 8.6 gives the severity analysis of the confirmed cases in all states and union territories of India. The geographical map is color-coded to show the comparative distribution of cases from the most severely affected to the least affected state. The five worst-affected states-Maharashtra with $19.6 \%$, Karnataka with $9.69 \%$, Kerala with 5.99\%, Andhra Pradesh with $9.60 \%$ and Tamil Nadu with $8.55 \%$ of total Indian cases-are on the highly affected zone of the spectrum of the heat map. These five states are together responsible for a majority of total cases reported in the entire nation. In contrast, states like Himachal Pradesh and the northeastern states of Sikkim, Meghalaya, Tripura, etc., have a negligible share of COVID-19 cases and are among the least-affected regions.

For the experiments, we used the Jupyter notebook environment with Python version 3.7. The computational specifications include an Intel Core i5 eighth generation processor with 8 GB RAM and a 64-bit Windows 10 operating system. Since none of the experiments involved graphical processing units (GPUs) for training deep learning models, the details for the same have been omitted. The data processing and model design is done with the help of open-source libraries like Numpy (Oliphant, 2006), Pandas (McKinney, 2010), Scikit-Learn (Pedregosa et al., 2011) and PyTorch (Paszke et al., 2017). All the deep learning models (RNN, LSTM, GRU) are manually designed using functions and classes of the PyTorch framework, and the machine learning models (SVR, PR, VAR) are implemented using the Scikit-Learn and StatsModel libraries.

Except for $\mathrm{PR}$, all the other forecasting models are trained on a univariate data set with the end goal of predicting daily confirmed cases for the next 15 days. All predictive models are trained and evaluated on the data of the ten states individually and their predictions, are compared based on the following performance metrics:
$$M A E=\frac{1}{n} * \sum_{k=1}^n\left|Y_k-\hat{Y}_k\right|$$

$$\begin{gathered} \text { RMSLE }=\sqrt{\frac{1}{2} \sum_{k=1}^n\left(\log Y_k-\log \hat{Y}k\right)^2} \ \text { MAPE }=\frac{100}{n} * \sum{k=1}^n\left|\frac{Y_k-\hat{Y}_k}{Y_k}\right| \ E V=1-\frac{\operatorname{Var}(Y-\hat{Y})}{\operatorname{Var}(Y)} \end{gathered}$$
where $Y$ is the actual value, $\hat{Y}$ the predicted value and $n$ denotes the total number of instances.

## 统计代写|时间序列分析代写Time-Series Analysis代考|SeVERITY ANALYSIS

$$\begin{gathered} M A E=\frac{1}{n} * \sum_{k=1}^n\left|Y_k-\hat{Y}k\right| \ \operatorname{RMSLE}=\sqrt{\frac{1}{2} \sum{k=1}^n\left(\log Y_k-\log \hat{Y} k\right)^2} \mathrm{MAPE}=\frac{100}{n} * \sum k=1^n\left|\frac{Y_k-\hat{Y}_k}{Y_k}\right| E V=1-\frac{\operatorname{Var}(Y-\hat{Y})}{\operatorname{Var}(Y)} \end{gathered}$$

## MATLAB代写

MATLAB 是一种用于技术计算的高性能语言。它将计算、可视化和编程集成在一个易于使用的环境中，其中问题和解决方案以熟悉的数学符号表示。典型用途包括：数学和计算算法开发建模、仿真和原型制作数据分析、探索和可视化科学和工程图形应用程序开发，包括图形用户界面构建MATLAB 是一个交互式系统，其基本数据元素是一个不需要维度的数组。这使您可以解决许多技术计算问题，尤其是那些具有矩阵和向量公式的问题，而只需用 C 或 Fortran 等标量非交互式语言编写程序所需的时间的一小部分。MATLAB 名称代表矩阵实验室。MATLAB 最初的编写目的是提供对由 LINPACK 和 EISPACK 项目开发的矩阵软件的轻松访问，这两个项目共同代表了矩阵计算软件的最新技术。MATLAB 经过多年的发展，得到了许多用户的投入。在大学环境中，它是数学、工程和科学入门和高级课程的标准教学工具。在工业领域，MATLAB 是高效研究、开发和分析的首选工具。MATLAB 具有一系列称为工具箱的特定于应用程序的解决方案。对于大多数 MATLAB 用户来说非常重要，工具箱允许您学习应用专业技术。工具箱是 MATLAB 函数（M 文件）的综合集合，可扩展 MATLAB 环境以解决特定类别的问题。可用工具箱的领域包括信号处理、控制系统、神经网络、模糊逻辑、小波、仿真等。