Create a machine learning model which predicts the crop yield using the random forest algorithm. Link to the dataset:

Factors such as temperature, humidity and precipitation must be added to the dataset (The data for the temperature, humidity, precipitation should be taken by using a weather API such as openweathermap for each district). Season A is from september to march. Season B is from April to august. (IDE-Pycharm language-python)

In this assignment, we build a simple ANN model for a dataset and we explore some methods to optimize model parameters.

Dependencies

Python > 2.7
Scikit Learn package
Pandas toolkit (If it is needed) Numpy toolkit (If it is needed)

Dataset

This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. The objective of the dataset is to diagnostically predict whether a patient has diabetes, based on certain diagnostic measurements included in the dataset. Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are females at least 21 years old of Pima Indian heritage.

Note: You do not need to download the data. Two subsets of data for training and test is created and posted for downloading. The original data set also is included for your further testing and experimenting.

The list of the fields in order of columns in the data file is:
PregnanciesNumber of times pregnant
GlucosePlasma glucose concentration 2 hours in an oral glucose tolerance test BloodPressureDiastolic blood pressure (mm Hg)
SkinThicknessTriceps skin fold thickness (mm)
Insulin2-Hour serum insulin (mu U/ml)
BMIBody mass index (weight in kg/(height in m)^2)
DiabetesPedigreeFunctionDiabetes pedigree function
Age (years)
OutcomeClass variable (0 No Diabetes or 1 Diabetes) 268 of 768 are 1, the others are 0.

ANNprojectdescription
– Loading the required libraries and modules
To finish this assignment, you may use any module that you think is necessary. These modules includes:
1- Pandas
2- Numpy
3- Matplotlib
4- Sklearn

– Reading the data and performing basic data checks

1- Use describe() method of the dataframe (e.g df.describe()) to output the data dimensions and fields basic stats.

– Creating the train and test datasets

1. 1- Splityourdataintotrain,testand,validation.

2. 2- Splityourdatabasedontheratiooftrain=0.75,validation=0.15and,test=0.10

3. 3- Printoutthetotalnumberofrowsandthenumberofrowsallocatedforeach

   category above.
   Note1: There are many ways you can achieve splitting dataset.
   You can use any method as long as you have a balanced ratio of classes in each category.

4. 4- Useyourtestdatasetonlyforfinaltesting.Youshouldnotusetestdatasetfor adjusting parameters.

– Building your model

1. 1- Useneural_networkclassifiertobuildyournetwork.

2. 2- Thereareafewparametersneedstobeadjustedinthismodel:

   a. Hidden_layer_sizes b. Activation
   c. Solver
   d. Batch_size

   e. Learning_rate
   f. Learning_rate_init

3. 3- Mostofparametersabovehavedefaultvalues.Youmayrunyournetworkon default values to get an idea about your network

4. 4- Youmayadjustparametersbasedwhatwetalkedintheclassetc

– Network metric and plots

1. 1- To evaluate your network, calculate confusion matrix. For that you may use confusion_matrix function from sklearn.metrics library.
   How do you interpret precision and recall?

2. 2- Plot error plot for each iteration (epoch) for both validate and train.
   Based on your parameter setting you may see an overfitting problem. Try to spot it if that’s happened.

3. 3- Once you finish your parameter tunning, run your model on your test data set and create a plot for your test the same as previous step

Whatareyourdeliverables?

a. A Jupyter document containing your model and experiment results.

Do you want me to send you the whole 24 questions was on the test and tell you which topics they said we got it wrong?  I can try to put it here.  If not I can email it to you.

Here is the 24 questions with my answers.

2/20/2022

Question 1 of 24

You have a Speech service resource.

You need to develop an application that creates real-time captions for audio.

What should you include in the code?

Select only one answer.

1. SpeakerRecognizer

2. KeywordRecognizer

3. SpeechRecognizer

4. SpeechSynthesizer

My Answer is "3. SpeechRecognizer"

Question 2 of 24

You have an application that performs Speech to Text services for users by using the Speech SDK.

You need to add the ability to perform Text to Speech in the application.

Besides the text, which other values should you include in your queries?

Select only one answer.

1. the pronunciation

2. the voice

3. keyword

4. the phrase list

My answer was 1. The Pronunciation

Question 3 of 24

You are building a text to speech solution.

You need to ensure that your solution supports different name pronunciations.

What Speech Synthesis Markup Language (SSML) element should you use?

Select only one answer.

1. phoneme

2. mstts:express-as

3.break

4. lang

My answer was 1. Phoneme

Question 4 of 24

You develop an application by using the Speech SDK. The application translates the English language version of podcasts into French and German.

You need to create the code to provide the English version of the podcast for translation.

Which two objects should you add to the code?

Select all answers that apply.

1.  TranslationRecognizer

2. SpeechRecognizer

3. SpeechSynthesizer

4. AutoDetect SourceLanguageConfig

5. SpeechTranslationConfig

My answer is 2. SpeechRecognizer

                      3. SpeechSynthesizer

Question 5 of 24

You have a Azure Video Analyzer for Media service that provides a search interface for video content.

You need to extract what is said in the videos so that it can be translated into other languages.

What should you extract?

Select only one answer.

1. labels

2. brands

3. transcripts

4. keywords

The answer is 3. Transcripts

Question 6 of 24

You build an application that uses Language Understanding.

You need to ensure that the application support speech inputs by using the Speech service.

What should you configure for Language Understanding?

Select only one answer.

1.  Enable the Speech priming setting during model publishing.

2. Add additional utterances to the intents in the model before publishing.

3. Set the endpoint URL parameter verbose to true.

4. Enable the Normalize punctuation setting on the application.

Answer: 1.  Enable the Speech priming setting during model publishing.

Question 7 of 24

You plan to use a Language Understanding container for an application that you previously exported.

Which two values from the underlying Language Understanding resource should you retrieve before you can containerize the application?

Select all answers that apply.

1.  the subscription key

2. the endpoint URI

3. the prediction key

4. the resource location

My Answer: 2. the endpoint URI

4. the resource location

Question 8 of 24

You make a Text Analytics API call.

You call the following URL.

You send the following body.

{

  "documents": [

    {

      "id": "1",

      "countryHint":"US",

      "text": "We analyzed text to see what would happen"

    },

    {

      "id": "2",

      "countryHint":"UK",

      "text": "We analysed text to see what would happen"

    },

  ]

}

You receive the following response.

{

  "statistics": {

    "documentsCount": 2,

    "validDocumentsCount": 1,

    "erroneousDocumentsCount": 1,

    "transactionsCount": 1

  },

  "documents": [{

    "id": "1",

    "detectedLanguages": [{

      "name": "English",

      "iso6391Name": "en",

      "score": 1.0

    }],

    "statistics": {

      "charactersCount": 41,

      "transactionsCount": 1

    }

  }],

  "errors": [{

    "id": "2",

    "message": "Country hint is not valid. Please specify an ISO 3166-1 alpha-2 two letter country code."

  }]

}

Which three of the following statements correctly describe the code?

Select all answers that apply.

1.  The text fragment that has ID 1 is identified as English.

2. US is a valid value for countryHint.

3. The document that has countryHint=UK does not generate a billable transaction.

4. UK is a valid value for name.

5. The document that has countryHint=US does not generate a billable transaction.

My answer: 1. The text fragment that has ID 1 is identified as English.

2.  US is a valid value for countryHint.

3. The document that has countryHint=UK does not generate a billable transaction.

Question 9 of 24

You plan to use Text Analytics to detect the language of reviews.

You need to route the reviews that are multi-lingual to a human translator.

Which field in the JSON response should you use to filter records?

Select only one answer.

1. score

2. errors

3. statistics

4. name

My answer: 3. statistics

Question 10 of 24

You develop a product review feature for an international e-commerce application.

When reviews are received by the application, the application posts the reviews to an Azure Cosmos DB database.

You need to develop an Azure Function that uses the Text Analytics API to notify a team when a negative review is posted. The notification must be sent as quickly as possible.

Which two components should you use in the function to identify a negative review?

Select all answers that apply.

1. the Sentiment endpoint

2. an Azure Cosmos DB trigger

3. a schedule triggert

4. he Key Phrase endpoint

5.the Detect Language endpoint

6.an Azure Cosmos DB output

My answer: 1. the Sentiment endpoint

6.an Azure Cosmos DB output

Question 11 of 24

You make a Text Analytics API call.

You call the following URL.

You send the following body.

{

  "documents": [

    {

      "language": "en",

      "id": "1",

      "text": "Our tour guide took us up the Space Needle during our trip to Seattle last week."

    }

  ]

}

You receive the following response body.

{

  "statistics": {

    "documentsCount": 1,

    "validDocumentsCount": 1,

    "erroneousDocumentsCount": 0,

    "transactionsCount": 1

  },

  "documents": [{

    "id": "1",

    "score": 0.5,

    "statistics": {

      "charactersCount": 80,

      "transactionsCount": 1

    }

  }],

  "errors": []

}

The text fragment that has ID 1 contains 80 alphanumeric characters.

Select Yes if the statement is true. Otherwise, select No.

Select only one answer.

1. Yes

2. No

My answer is Yes

Question 12 of 24

You are designing a chatbot for a restaurant.

You plan to include a series of questions that will be required to complete a reservation.

What type of dialog should you use?

Select only one answer.

1. Waterfall

2. Prompt

3. QnA Maker

4. Action

My answer was Prompt ( I know you said Qna Maker)

Question 13 of 24

You are building a chatbot by using the Microsoft Bot Framework Composer.

The chatbot will include a dialog that will be used to enter prices of products.

Users will perform an action for the products.

The products and prices will resemble the following:

• Butter 1.99
• Bread 1.01
• Salt 3.50

Which type of recognizer should you use?

Select only one answer.

1. Regex

2. None

3. LUIS

My answer was 3. LUIS

Question 14 of 24

You are building a chatbot that uses the Bot Framework Composer.

You need to collect user contact information.

What should you use to validate the user phone numbers?

Select only one answer.

1. Language Generator

2. Recognizer

3. Trigger

4. Dialog

My answer is 2. Recognizer

Question 15 of 24

You are building a chatbot by using the Microsoft Bot Framework Composer.

You need to test the bot.

What two tools could you use?

Select all answers that apply.

1. Bot Framework CLI

2. Bot Framework Composer

3. Bot Framework SDK

4. Bot Framework Emulator

My answer is

3. Bot Framework SDK

4. Bot Framework Emulator

Question 16 of 24

You are building an Azure Cognitive Search solution.

What should you use to increase the amount of concurrent query requests that can be handled by the solution?

Select only one answer.

1. Replicas

2. Partitions

3. Indexes

4. Pricing tier

My answers 4. Pricing Tier

Question 17 of 24

You have 20,000 PDF documents that must be indexed by using Azure Cognitive Search.

You need to recommend a storage solution for the PDFs.

What should you recommend?

Select only one answer.

1. Azure Storage

2. Microsoft SQL Server

3. Azure Cosmos DB

4. Amazon AWS S3

My answer is s1. Azure Storage

Question 18 of 24

You are building an Azure Cognitive Search solution.

You are defining an index for blog posts.

Searches must query the description field and return the descriptions in search results.

What field options should you select for the description field?

Select only one answer.

1. Retrievable and Searchable

2. Filterable and Searchable

3. Retrievable and Sortable

4. Facetable and Sortable

My answer is 2. Filterable and Searchable

Question 19 of 24

You are building an Azure Cognitive Search solution.

You plan to build an API for a custom skillset.

What data format should you use for the API to accept and return?

Select only one answer.

1. JSON

2. XML

3. YAML

4. HTML

My answer is 1. JSON

Question 20 of 24

You plan to build an Azure Cognitive Search solution that will search images and PDF documents.

Users of the solution will search for text, captions, key phrases, identified objects, or named entities.

Each day, you will need to index and enrich 5,000 images and 10,000 PDFs.

Which type of resource should you create for the planned solution?

Select only one answer.

1. Computer Vision

2. Text Analytics

3. Azure Machine Learning

4.Azure Cognitive Services

My Answer is 1. Computer Vision

Question 21 of 24

You have an Azure Cognitive Search solution.

You need to extract text from PDFs during indexing.

Which skill should you use?

Select only one answer.

1. key phrase extraction

2. content moderation

3. sentiment

4. optical character recognition (OCR)

My Answer is :. optical character recognition (OCR)

Question 22 of 24

You have an Azure Cognitive Search solution.

You have a custom skillset that receives a complex set of fields in a response.

What should you use to simplify and restructure the fields?

Select only one answer.

1. A shaper skill

2. An object projection

3. An indexer

4. A data source

My answer is A. A shaper skill

Question 23 of 24

You have an enrichment pipeline that uses Azure Cognitive Search.

The pipeline ingests Azure Cosmos DB data and identifies key phrases.

The application that generates the data must be able to retrieve key phrases and confidence by querying an API.

What should you use to persist the data?

Select only one answer.

1. a table store

2. a file storea

3.an object store

The correct answer is 3. an Object store

Question 24 of 24

You have an enrichment pipeline in Azure Cognitive Services.

The enrichment pipeline has a custom skill that calls an API.

You need to ensure that all responses from the API are structured consistently.

Which skill should you add to the skillset?

Select only one answer.

1. Merge

2. Shaper

3. ConditionalText

4. Split

My answer is 2. Shaper

I would appreciate if you can help me to get this over.  I need 65% to pass and i only got 45%.

Here is what parts I am wrong.