Great Deal! Get Instant $10 FREE in Account on First Order + 10% Cashback on Every Order Order Now

Data Science 311 Final Project Catchy and Descriptive Project Title Group n Member One, Member2, ..., Memberk Here is a template to use for your final project report. As a rule, avoid vague...

1 answer below »
Data Science 311 Final Project
Catchy and Descriptive Project Title
Group n
Member One, Member2, ..., Memberk
Here is a template to use for your final project report. As a rule, avoid vague statements,
include exact numbers, include and reference figures and tables, and also reference supporting
files with code to reproduce results.
All supporting code and materials must be included in the final submission for your project.
Supporting notebooks should not include commented out code and all code should run without
producing any e
ors. The notebooks should be run and saved in the executed state to confirm
the absence of e
ors.
1 Project Overview
At least one paragraph describing project goals, motivation, and plan.
2 Datasets
In this section include:
1. Reason for selecting the dataset.
2. Source of data. Who originally collected the data and why. Be precise here including
the url where data is located as well as any special instructions or considerations when
acquiring the data, e.g. (long download time, accounts needed, requirement to sign an
agreement).
3. Explanation of data contents, e.g. relevant CSV fields and what they mean, missing
values, and other data quirks.
3 Data curation
In this section discuss any steps you took to clean, process, merge or otherwise curate you
espective datasets. Make sure to reference the relevant sections of your notebook used to fo
initial data processing.
4 Exploratory Data Analysis
This section will include the statement of data analysis questions, approaches to analyses,
and resulting findings. There should be prose and reference to a relevant figure for each data
analysis question. At the beginning of this section include some high level sentences discussing
motivation and approach.
1
4.1 Question 1
• Data analysis question
• Figure
• Findings
4.2 Question 2
• Data analysis question
• Figure
• Findings
4.3 Question N
• Data analysis question
• Figure
• Findings
4.4 Conclusions
Discuss overall conclusions from exploratory data analysis.
5 Machine Learning
5.1 Approach
5.1.1 Machine learning problem
Inputs and outputs x and y
Loss function
Metrics Discuss the metrics you will use to assess the ML portion of the project.
5.1.2 Models
Baselines Describe the baseline/s you will use to compare the performance of your machine
learning model.
Prospective algorithms Here describe your main approach to the ML problem. Be precise
here citing the li
aries you will use as well as the modeling approach.
2
5.1.3 Data splits
Explain your method for splitting the data. Be exact here citing the total number of data
points in train/validation/test splits and any special considerations such as removal of outlie
data points or balancing splits on some categorical features.
5.2 Results and analysis
Describe the outcome of your machine learning approach. This should include discussion of
esults according to your loss function on training, validation, and test sets with an accompa-
nying figure and/or table. Some discussion on model behavior beyond reporting of metrics is
needed here.
5.3 Concluding remarks
Make some general statements about the findings of the project, issues involved, and interest-
ing next steps for future research and analysis.
3
    Project Overview
    Datasets
    Data curation
    Exploratory Data Analysis
    Question 1
    Question 2
    Question N
    Conclusions
    Machine Learning
    Approach
    Machine learning problem
    Models
    Data splits
    Results and analysis
    Concluding remarks
Answered Same Day Nov 29, 2022

Solution

Amar Kumar answered on Nov 30 2022
41 Votes
1. Project Overview
A machine learning based approach for natural calamity analysis
2. Datasets
Selected below since directly impacted by natural calamities
a. # High/Low Tide Data
. # hourly Tide Data
c. # king County Storm Data
d. # earthquake Data
3. Data curation
Data custodians gather information from several sources, combine it into a single form, and then manage, authenticate, archive, maintain, retrieve, and portray it.
a. Long before datasets are made available, the process of selecting datasets for machine learning begins. Here is what we recommend:
. Describe the purpose of AI.
Determine the dataset you'll need to address the issue.
c. Keep a note of your presumptions as you choose the data.
d. Try to gather a variety of useful data from both internal and external sources.
e. Create a dataset that is challenging for your rivals to replicate.
Using a model that has already been trained on huge datasets might be a smart move if your dataset is tiny. You may adjust it using the minimal dataset you have.
4. Exploratory Data Analysis
You may start creating the training...
SOLUTION.PDF

Answer To This Question Is Available To Download

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here