Topic 2, Case Study
Overview
You are a data scientist for Fabrikam Residences, a company specializing in quality private and commercial property in the United States. Fabrikam Residences is considering expanding into Europe and has asked you to investigate prices for private residences in major European cities. You use Azure Machine Learning Studio to measure the median value of properties. You produce a regression model to predict property prices by using the Linear Regression and Bayesian Linear Regression modules.
Datasets
There are two datasets in CSV format that contain property details for two cities, London and Paris, with the following columns:

The two datasets have been added to Azure Machine Learning Studio as separate datasets and included as the starting point of the experiment.
Dataset issues
The AccessibilityToHighway column in both datasets contains missing values. The missing data must be replaced with new data so that it is modeled conditionally using the other variables in the data before filling in the missing values.
Columns in each dataset contain missing and null values. The dataset also contains many outliers. The Age column has a high proportion of outliers. You need to remove the rows that have outliers in the Age column. The MedianValue and AvgRoomsinHouse columns both hold data in numeric format. You need to select a feature selection algorithm to analyze the relationship between the two columns in more detail.
Model fit
The model shows signs of overfitting. You need to produce a more refined regression model that reduces the overfitting.
Experiment Requirements
You must set up the experiment to cross-validate the Linear Regression and Bayesian Linear Regression modules to evaluate performance.
In each case, the predictor of the dataset is the column named MedianValue. An initial investigation showed that the datasets are identical in structure apart from the MedianValue column. The smaller Paris dataset contains the MedianValue in text format, whereas the larger London dataset contains the MedianValue in numerical format. You must ensure that the datatype of the MedianValue column of the Paris dataset matches the structure of the London dataset.
You must prioritize the columns of data for predicting the outcome. You must use non-parameters statistics to measure the relationships.
You must use a feature selection algorithm to analyze the relationship between the MedianValue and AvgRoomsinHouse columns.
Model training
Given a trained model and a test dataset, you need to compute the permutation feature importance scores of feature variables. You need to set up the Permutation Feature Importance module to select the correct metric to investigate the model's accuracy and replicate the findings.
You want to configure hyperparameters in the model learning process to speed the learning phase by using hyperparameters. In addition, this configuration should cancel the lowest performing runs at each evaluation interval, thereby directing effort and resources towards models that are more likely to be successful.
You are concerned that the model might not efficiently use compute resources in hyperparameter tuning. You also are concerned that the model might prevent an increase in the overall tuning time. Therefore, you need to implement an early stopping criterion on models that provides savings without terminating promising jobs.
Testing
You must produce multiple partitions of a dataset based on sampling using the Partition and Sample module in Azure Machine Learning Studio. You must create three equal partitions for cross-validation. You must also configure the cross-validation process so that the rows in the test and training datasets are divided evenly by properties that are near each city's main river. The data that identifies that a property is near a river is held in the column named NextToRiver. You want to complete this task before the data goes through the sampling process.
When you train a Linear Regression module using a property dataset that shows data for property prices for a large city, you need to determine the best features to use in a model. You can choose standard metrics provided to measure performance before and after the feature importance process completes. You must ensure that the distribution of the features across multiple training models is consistent.
Data visualization
You need to provide the test results to the Fabrikam Residences team. You create data visualizations to aid in presenting the results.
You must produce a Receiver Operating Characteristic (ROC) curve to conduct a diagnostic test evaluation of the model. You need to select appropriate methods for producing the ROC curve in Azure Machine Learning Studio to compare the Two-Class Decision Forest and the Two-Class Decision Jungle modules with one another.

Explanation
Explanation:
Use the SMOTE module in Azure Machine Learning Studio (classic) to increase the number of underepresented cases in a dataset used for machine learning. SMOTE is a better way of increasing the number of rare cases than simply duplicating existing cases.
You connect the SMOTE module to a dataset that is imbalanced. There are many reasons why a dataset might be imbalanced: the category you are targeting might be very rare in the population, or the data might simply be difficult to collect. Typically, you use SMOTE when the class you want to analyze is under-represented.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/smote Prepare data for modeling Testlet 1 Case study Overview You are a data scientist in a company that provides data science for professional sporting events. Models will use global and local market data to meet the following business goals:
* Understand sentiment of mobile device users at sporting events based on audio from crowd reactions.
* Assess a user's tendency to respond to an advertisement.
* Customize styles of ads served on mobile devices.
* Use video to detect penalty events
Current environment
* Media used for penalty event detection will be provided by consumer devices. Media may include images and videos captured during the sporting event and shared using social media. The images and videos will have varying sizes and formats.
* The data available for model building comprises of seven years of sporting event media. The sporting event media includes; recorded video transcripts or radio commentary, and logs from related social media feeds captured during the sporting events.
* Crowd sentiment will include audio recordings submitted by event attendees in both mono and stereo formats.
Penalty detection and sentiment
* Data scientists must build an intelligent solution by using multiple machine learning models for penalty event detection.
* Data scientists must build notebooks in a local environment using automatic feature engineering and model building in machine learning pipelines.
* Notebooks must be deployed to retrain by using Spark instances with dynamic worker allocation.
* Notebooks must execute with the same code on new Spark instances to recode only the source of the data.
* Global penalty detection models must be trained by using dynamic runtime graph computation during training.
* Local penalty detection models must be written by using BrainScript.
* Experiments for local crowd sentiment models must combine local penalty detection data.
* Crowd sentiment models must identify known sounds such as cheers and known catch phrases. Individual crowd sentiment models will detect similar sounds.
* All shared features for local models are continuous variables.
* Shared features must use double precision. Subsequent layers must have aggregate running mean and standard deviation metrics available.
Advertisements
During the initial weeks in production, the following was observed:
* Ad response rated declined.
* Drops were not consistent across ad styles.
* The distribution of features across training and production data are not consistent Analysis shows that, of the 100 numeric features on user location and behavior, the 47 features that come from location sources are being used as raw features. A suggested experiment to remedy the bias and variance issue is to engineer 10 linearly uncorrelated features.
* Initial data discovery shows a wide range of densities of target states in training data used for crowd sentiment models.
* All penalty detection models show inference phases using a Stochastic Gradient Descent (SGD) are running too slow.
* Audio samples show that the length of a catch phrase varies between 25%-47% depending on region
* The performance of the global penalty detection models shows lower variance but higher bias when comparing training and validation sets. Before implementing any feature changes, you must confirm the bias and variance using all training and validation cases.
* Ad response models must be trained at the beginning of each event and applied during the sporting event.
* Market segmentation models must optimize for similar ad response history.
* Sampling must guarantee mutual and collective exclusively between local and global segmentation models that share the same features.
* Local market segmentation models will be applied before determining a user's propensity to respond to an advertisement.
* Ad response models must support non-linear boundaries of features.
* The ad propensity model uses a cut threshold is 0.45 and retrains occur if weighted Kappa deviated from
0.1 +/- 5%.
* The ad propensity model uses cost factors shown in the following diagram:

* The ad propensity model uses proposed cost factors shown in the following diagram:

* Performance curves of current and proposed cost factor scenarios are shown in the following diagram:

Explanation

Box 1: AksCompute
Example:
aks_target = AksCompute(ws,"myaks")
# If deploying to a cluster configured for dev/test, ensure that it was created with enough
# cores and memory to handle this deployment configuration. Note that memory is also used by
# things such as dependencies and AML components.
deployment_config = AksWebservice.deploy_configuration(cpu_cores = 1, memory_gb = 1) service = Model.deploy(ws, "myservice", [model], inference_config, deployment_config, aks_target) Box 2: AksWebservice Box 3: token_auth_enabled=Yes Whether or not token auth is enabled for the Webservice.
Note: A Service principal defined in Azure Active Directory (Azure AD) can act as a principal on which authentication and authorization policies can be enforced in Azure Databricks.
The Azure Active Directory Authentication Library (ADAL) can be used to programmatically get an Azure AD access token for a user.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/how-to-deploy-azure-kubernetes-service
https://docs.microsoft.com/en-us/azure/databricks/dev-tools/api/latest/aad/service-prin-aad-token

Explanation
Example:
# Get the training dataset
diabetes_ds = ws.datasets.get("Diabetes Dataset")
# Create an estimator that uses the remote compute
hyper_estimator = SKLearn(source_directory=experiment_folder,
inputs=[diabetes_ds.as_named_input('diabetes')], # Pass the dataset as an input compute_target = cpu_cluster, conda_packages=['pandas','ipykernel','matplotlib'], pip_packages=['azureml-sdk','argparse','pyarrow'], entry_script='diabetes_training.py') Reference:
https://notebooks.azure.com/GraemeMalcolm/projects/azureml-primers/html/04%20-%20Optimizing%20Model

A Deep Learning Virtual Machine is a pre-configured environment for deep learning using GPU instances.
References:
https://azuremarketplace.microsoft.com/en-au/marketplace/apps/microsoft-ads.dsvm-deep-learning