# Unit 21 Homework: Charity Funding Predictor ## Background The nonprofit founda

Published by

Aug 12, 2022


Struggling with a similar assignment? Don’t know where to start? Don’t have time to work on this? Get a high-quality paper written for you from scratch – PLAGIARISM FREE, guaranteed to get you a good grade. To get started, please click on the Submit Your Instructions at the bottom of the page.

# Unit 21 Homework: Charity Funding Predictor
## Background
The nonprofit foundation Alphabet Soup wants a tool that can help it select the applicants for funding with the best chance of success in their ventures. With your knowledge of machine learning and neural networks, you’ll use the features in the provided dataset to create a binary classifier that can predict whether applicants will be successful if funded by Alphabet Soup.
From Alphabet Soup’s business team, you have received a CSV containing more than 34,000 organizations that have received funding from Alphabet Soup over the years. Within this dataset are a number of columns that capture metadata about each organization, such as:
* **EIN** and **NAME**—Identification columns
* **APPLICATION_TYPE**—Alphabet Soup application type
* **AFFILIATION**—Affiliated sector of industry
* **CLASSIFICATION**—Government organization classification
* **USE_CASE**—Use case for funding
* **ORGANIZATION**—Organization type
* **STATUS**—Active status
* **INCOME_AMT**—Income classification
* **SPECIAL_CONSIDERATIONS**—Special consideration for application
* **ASK_AMT**—Funding amount requested
* **IS_SUCCESSFUL**—Was the money used effectively
## Instructions
### Step 1: Preprocess the Data
Using your knowledge of Pandas and scikit-learn’s `StandardScaler()`, you’ll need to preprocess the dataset. This step prepares you for Step 2, where you’ll compile, train, and evaluate the neural network model.
Using the information we have provided in the starter code, follow the instructions to complete the preprocessing steps.
1. Read in the charity_data.csv to a Pandas DataFrame, and be sure to identify the following in your dataset:
* What variable(s) are the target(s) for your model?
* What variable(s) are the feature(s) for your model?
2. Drop the `EIN` and `NAME` columns.
3. Determine the number of unique values for each column.
4. For columns that have more than 10 unique values, determine the number of data points for each unique value.
5. Use the number of data points for each unique value to pick a cutoff point to bin “rare” categorical variables together in a new value, `Other`, and then check if the binning was successful.
6. Use `pd.get_dummies()` to encode categorical variables.
### Step 2: Compile, Train, and Evaluate the Model
Using your knowledge of TensorFlow, you’ll design a neural network, or deep learning model, to create a binary classification model that can predict if an Alphabet Soup–funded organization will be successful based on the features in the dataset. You’ll need to think about how many inputs there are before determining the number of neurons and layers in your model. Once you’ve completed that step, you’ll compile, train, and evaluate your binary classification model to calculate the model’s loss and accuracy.
1. Continue using the Jupyter Notebook in which you performed the preprocessing steps from Step 1.
2. Create a neural network model by assigning the number of input features and nodes for each layer using TensorFlow and Keras.
3. Create the first hidden layer and choose an appropriate activation function.
4. If necessary, add a second hidden layer with an appropriate activation function.
5. Create an output layer with an appropriate activation function.
6. Check the structure of the model.
7. Compile and train the model.
8. Create a callback that saves the model’s weights every five epochs.
9. Evaluate the model using the test data to determine the loss and accuracy.
10. Save and export your results to an HDF5 file. Name the file `AlphabetSoupCharity.h5`.
### Step 3: Optimize the Model
Using your knowledge of TensorFlow, optimize your model to achieve a target predictive accuracy higher than 75%.
Using any or all of the following methods to optimize your model:
* Adjust the input data to ensure that no variables or outliers are causing confusion in the model, such as:
* Dropping more or fewer columns.
* Creating more bins for rare occurrences in columns.
* Increasing or decreasing the number of values for each bin.
* Add more neurons to a hidden layer.
* Add more hidden layers.
* Use different activation functions for the hidden layers.
* Add or reduce the number of epochs to the training regimen.
**Note**: If you make at least three attempts at optimizing your model, you will not lose points if your model does not achieve target performance.
1. Create a new Jupyter Notebook file and name it `AlphabetSoupCharity_Optimzation.ipynb`.
2. Import your dependencies and read in the `charity_data.csv` to a Pandas DataFrame.
3. Preprocess the dataset like you did in Step 1, Be sure to adjust for any modifications that came out of optimizing the model.
4. Design a neural network model, and be sure to adjust for modifications that will optimize the model to achieve higher than 75% accuracy.
5. Save and export your results to an HDF5 file. Name the file `AlphabetSoupCharity_Optimization.h5`.
### Step 4: Write a Report on the Neural Network Model
For this part of the assignment, you’ll write a report on the performance of the deep learning model you created for AlphabetSoup.
The report should contain the following:
1. **Overview** of the analysis: Explain the purpose of this analysis.
2. **Results**: Using bulleted lists and images to support your answers, address the following questions.
* Data Preprocessing
* What variable(s) are the target(s) for your model?
* What variable(s) are the features for your model?
* What variable(s) should be removed from the input data because they are neither targets nor features?
* Compiling, Training, and Evaluating the Model
* How many neurons, layers, and activation functions did you select for your neural network model, and why?
* Were you able to achieve the target model performance?
* What steps did you take in your attempts to increase model performance?
3. **Summary**: Summarize the overall results of the deep learning model. Include a recommendation for how a different model could solve this classification problem, and then explain your recommendation.
– – –
## Rubric


Need Writing Help? Our writing specialists are here 24/7, every day of the year, ready to support you! Instantly chat with an online tutor below or click here to submit your paper instructions to the writing team.

More than just an assignment.

Explore Now →

Who is this homework service for?

* If you are having a really hard class and want to get through it, then this is for you.

* If you have a medical emergency or someone close to you has a medical emergency and you don’t think you’ll be able to turn your assignment on time, this is definitely a service you could use.

* You can use us if you are having a tough Professor who won’t give you the grades you deserve.

* If you have a tight work schedule and you are getting points deducted for not submitting assignments on time.

* English might not be your first language and you feel like you are being left behind in class because of it.

* If you have a large project coming up and don’t think you have enough time to get it done well, definitely reach out to us.


Super stoked you are checking us out! We would like to help you with your assignment. We just need a few things from you:

* The full assignment instructions as they appear on your school account.

* If a Rubric is present, make sure to attach it.

* Any relevant weekly readings or learning resources.

* Include any special announcements or emails you might have gotten from your Professor regarding your assignment.

* Any templates or additional files required to complete the assignment.

If your assignment is somewhat complex and you need to explain it, please don’t hesitate to reach out to me via live chat. 



Frequently asked questions

How soon can I get my paper done?

It depends with your deadline. If you need your paper completed in 3 hours, we will deliver it in that time. All you need to do is indicate your deadline in our custom order page here. Alternatively, if you are sending us your instructions via email, please be sure to indicate your deadline.

Will it be completely original? I don't want to be caught in a case of Academic Integrity Violation.

We are as paranoid as you are. Maybe even more! And we understand that the greatest sin you can commit in your academic journey is plagiarizing your academic work. To that end, we have made sure that we check and double-check our papers using high quality plagiarism detection tools such as SafeAssign and Turnitin before submitting the paper to you.

Who is my writer? Is he/she a native English Speaker?

All our writers are native English Speakers. That is not to say that ESL writers are not good, we just prefer hiring native writers because we want the very best people working on your paper. This might mean paying a little bit more for your paper as opposed to when you pay a foreign company whose writers are non-native English Speakers.

What if I need revisions? Will your charge additional for this?

Of course not! If you do happen to require a revision on your paper, our team will handle it for you free of charge. Matter of fact, we won’t rest till you are happy with your paper. So, ask for as many revisions as you need, it’s completely FREE!

Will you give me my money back if I don't like my paper?

We have very few instances where we delivered a paper that a client didn’t fall in love with. But if it so happens that you don’t like your paper for any reason whatsoever, we’ll refund your money back no questions asked.

I have more assignments after this, can you help me with those too?

Of course! And what’s even better is that we can reserve a writer permanently to work on your entire class. This comes in handy for projects which build up on each other and where you need just one writer, one writing style.

I got my order information wrong, can I change that?

Yes you can. Just reach out to our support team via email (support@essaynook.com) or live chat here and they’ll help you change the instructions.

Can I place an order via email instead of going through the order page?

Yes you can. Email Anna at anna@essaynook.com, she’s in charge of our sales team. Alternatively, you can talk to our Live Chat team here and request to speak to Anna.

Trusted by Thousands of Students

Delivering quality assignments since 2007

%d bloggers like this: