A report is needed with detailed observations, inferences, and results is need in a word document along with .ipynb file.

Case study: US daily Covid 19 data
Case study: US daily Covid 19 data
The out
eak of COVID-19 has impacted people worldwide in various ways. It has had
significant effects on economies, individuals, and societies. As countries encounter the
challenges posed by the pandemic, it is critical to comprehend the spread of the virus and how it
can be managed. In this case study, we will evaluate COVID-19 data in the United States and use
time series forecasting models to anticipate future trends in hospitalizations due to the virus.
Our dataset includes observations of daily hospitalizations in the US resulting from COVID-19
from March 2020 to December 2020. The dataset has two columns, "Date" and "Hospitalized,"
with 265 rows. The "Hospitalized" column shows the daily count of hospitalizations due to
COVID-19, while the "Date" column displays the co
esponding date.
Our dataset has four columns, "Date," "Positive," "Hospitalized," and "Death." The "Date" column
shows the date the data was collected, while the other three columns represent the counts of
positive cases, hospitalized patients, and deaths on that date.
We will begin by examining the data frame's metrics, such as the presence of missing values,
total data points, mean, median, and so on. According to the summary statistics, the dataset
has three columns named "Positive," "Hospitalized," and "Death." There are 265 rows of data,
with no missing values in any of the three columns. The mean, standard deviation, minimum,
maximum, and quartile values are also given for each column. The "Positive" column has an
average of around 4.78 million, with a standard deviation of roughly 3.72 million, indicating that
the values in this column are quite spread out. Similarly, the "Hospitalized" column has an
average of around 44,522 and a standard deviation of around 19,060. The "Death" column has
an average of around 139,419 and a standard deviation of roughly 73,570.
To commence the analysis of your dataset, we can ca
y out some fundamental exploratory
data analysis. Here are a few suggestions:
Examine for absent values: It is crucial to ensure that the dataset is comprehensive and does
not hold any absent values. We can employ the pandas li
ary of Python to check for absent
values in your dataset.
Visualize the patterns in the data: You can generate visualizations to gain a bette
understanding of how the frequencies of affirmative cases, hospitalizations, and fatalities have
altered over time. For instance, you can generate line charts to demonstrate how the
frequencies have transformed over time.
Calculate synopsis statistics: You can calculate synopsis statistics to get a better perception of
the distribution of the frequencies. For instance, you can calculate the mean, standard deviation,
minimum, and maximum frequencies for each column.
We transmute your data into time series data by establishing the "Date" column as the index of
the data frame. To accomplish this in pandas, you can utilize the read_csv() function with the
parse_dates parameter set to True to guarantee that the "Date" column is acknowledged as a
date and then establish the index of the data frame to the "Date" column using the set_index()
function.
We will ca
y out a bivariate analysis on 'hospitalized' and the remaining features. Bivariate
analysis is a statistical analysis that comprises the analysis of two variables (in this instance,
'hospitalized' and the other features) to conclude the empirical relationship between...