🌍 All Study Guides📊 Dashboard📰 Blog💡 About
Coursera Microsoft Azure Data Scientist Associate (DP-100) • STUDY MODE

Quiz: Full Practice Exam

QUESTION 1 OF 124

Your task is to predict if a person suffers from a disease by setting up a binary classification model. Your solution needs to be able to detect the classification errors that may appear. 

A
True negatives
B
False positives
C
False negatives
D
True positivesCorrect Answer
QUESTION 2 OF 124

As a senior data scientist, you need to evaluate a binary classification machine learning model.

A
Violin plot
B
Receiver Operating Characteristic (ROC) curveCorrect Answer
C
Gradient descent
D
Scatter plot
QUESTION 3 OF 124

You have a dataset that can be used for multiclass classification tasks. The dataset provided contains a normalized numerical feature set with 20,000 data points and 300 features. For training purposes, you need 75 percent of the data points and for testing purposes you need 25 percent. 

A
Box1: PCA(n_components=10);
B
Box2: model;
C
Box3: transform(x_test)
D
Box2: pca; 
E
Box1: PCA(n_components=150); 
F
Box3: x_test
G
Box1: PCA(n_components=10000);
H
Box2: pca;
I
Box3: X_train
QUESTION 4 OF 124

What is the result for multiplying a list by 3?

A
The new list created has the length 3 times the original length with the sequence repeated 3 times.Correct Answer
B
The new list created has the length 3 times the original length with the sequence repeated 3 times and also all the elements are also multiplied by 3.
C
The new list remains the same size, but the elements are multiplied by 3.
QUESTION 5 OF 124

Python is commonly known to ensure extensive functionality with powerful and statistical numerical libraries. What are the utilities of TensorFlow? 

A
Analyzing and manipulating data
B
Providing attractive data visualizations
C
Supplying machine learning and deep learning capabilitiesCorrect Answer
D
Offering simple and effective predictive data analysis
QUESTION 6 OF 124

Choose from the list below the evaluation model that is described as a relative metric where the higher the value is, the better will be the fit of the model.

A
Root Mean Square Error (RMSE)
B
Coefficient of Determination (known as R-squared or R2)Correct Answer
C
Mean Square Error (MSE)
QUESTION 7 OF 124

Choose from the list below the evaluation metric that provides you with an absolute metric in the same unit as the label.

A
Coefficient of Determination (known as R-squared or R2)
B
Mean Square Error (MSE)
C
Root Mean Square Error (RMSE)Correct Answer
QUESTION 8 OF 124

You are able to associate the K-Means clustering algorithm with the following machine learning type:

A
Reinforcement learning
B
Unsupervised machine learningCorrect Answer
C
Supervised machine learning
QUESTION 9 OF 124

Your deep neural network is in the process of training. You decided to set 30 epochs to the training process configuration. 

A
The entire training dataset is passed through the network 30 timesCorrect Answer
B
The training data is split into 30 subsets, and each subset is passed through the network
C
The first 30 rows of data are used to train the model, and the remaining rows are used to validate it
QUESTION 10 OF 124

Which of the layer types described below is a principal one that retrieves important features in images and works by putting a filter to images?

A
Pooling layer
B
Flattening layer
C
Convolutional layerCorrect Answer
QUESTION 11 OF 124

You want to set up a new Azure subscription. The subscription doesn’t contain any resources. 

A
Run Python code that uses the Azure ML SDK library and calls the Workspace.get method with name, subscription_id, and resource_group parameters.
B
Navigate to Azure Machine Learning studio and create a workspace.
C
Use an Azure Resource Management template that includes a Microsoft.MachineLearningServices/ workspaces resource and its dependencies.Correct Answer
D
Use the Azure Command Line Interface (CLI) with the Azure Machine Learning extension to call the az group create function with –name and –location parameters, and then the az ml workspace create function, specifying Cw and Cg parameters for the workspace name and resource group .Correct Answer
E
Run Python code that uses the Azure ML SDK library and calls the Workspace.create method with name, subscription_id, resource_group, and location parameters.Correct Answer
QUESTION 12 OF 124

You decide to use GPU-based training to develop a deep learning model on Azure Machine Learning service that is able to recognize image.

A
Field Programmable Gate Array
B
Azure Kubernetes ServiceCorrect Answer
C
Machine Learning Compute
D
Azure Container Instance
QUESTION 13 OF 124

You decide to use Azure Machine Learning designer for your real-time service endpoint. You can make use of only one Azure Machine Learning service compute resource. 

A
the existing Machine Learning Compute resource
B
Azure Databricks
C
a new Machine Learning Compute resource
D
HDInsight
E
Azure Kubernetes ServicesCorrect Answer
QUESTION 14 OF 124

In order to define a pipeline with multiple steps, you decide to use the Azure Machine Learning Python SDK. You notice that some steps of the pipeline do not run. Instead of running the steps, the pipeline uses a cached output from a previous run. Your task is to make sure that the pipeline runs every step, even when the parameters and contents of the source directory are the same with the ones from the previous run. 

A
Restart the compute cluster where the pipeline experiment is configured to run.
B
Set the outputs property of each step in the pipeline to True.
C
Use a PipelineData object that references a datastore other than the default datastore.
D
Set the regenerate_outputs property of the pipeline to True.Correct Answer
E
Set the allow_reuse property of each step in the pipeline to False.Correct Answer
QUESTION 15 OF 124

Yes or No?

A
YesCorrect Answer
B
No
QUESTION 16 OF 124

If you want to install the Azure Machine Learning SDK for Python, what are the most suitable package managers and CLI commands?

A
pip install azureml-sdkCorrect Answer
B
npm install azureml-sdk
C
yarn install azureml-sdk
D
nuget azureml-sdk
QUESTION 17 OF 124

If you want to use the from_delimited_files method of the Dataset.Tabular class to configure and register a tabular dataset, what are the most appropriate Python commands?

A
from azureml.core import Dataset
B
blob_ds = ws.get_default_datastore()
C
csv_paths = [(blob_ds, ‘data/files/current_data.csv’),
D
(blob_ds, ‘data/files/archive/*.csv’)]
E
tab_ds = Dataset.Tabular.from_delimited_files()
F
tab_ds = tab_ds.register(workspace=ws, name=’csv_table’)
G
(blob_ds, ‘data/files/archive/csv’)]
H
tab_ds = Dataset.Tabular.from_delimited_files(path=csv_paths)
I
blob_ds = ws.change_default_datastore()
J
(blob_ds, ‘data/files/archive/*.csv’)]tab_ds = Dataset.Tabular.from_delimited_files(path=csv_paths)
QUESTION 18 OF 124

If you want to visualize the environments that you registered in your workspace, what are the most appropriate SDK commands that you should choose?

A
from azureml.core import Environment
B
env_names = Environment.list(workspace=ws)
C
for env_name of env_names:
D
print(‘Name:’,env_name)
E
env_names = Environment_list(workspace=ws)
F
for env_name in env_names:
G
for each env_name in env_names:
QUESTION 19 OF 124

What object needs to be defined if your task is to create a schedule for your pipeline?

A
ScheduleConfig
B
ScheduleTimer
C
ScheduleSync
D
ScheduleRecurrenceCorrect Answer
QUESTION 20 OF 124

Choose from the options below the one that explains how are values for hyperparameters selected by random sampling.

A
From a mix of discrete and continuous valuesCorrect Answer
B
It tries every possible combination of parameters in the search space
C
It tries to select parameter combinations that will result in improved performance from the previous selection
QUESTION 21 OF 124

What Python code should you write if your goal is to extract the primary metric for a regression task?

A
from azureml.train.automl.utilities import catch_primary_metrics
B
catch_primary_metrics(‘regression’)
C
from azureml.train.automl.utilities import pull_primary_metrics
D
pull_primary_metrics(‘regression’)
E
from azureml.train.automl.utilities import get_primary_metricsCorrect Answer
F
get_primary_metrics(‘regression’)
G
from azureml.train.automl.utilities import feed_primary_metrics
H
feed_primary_metrics(‘regression’)
QUESTION 22 OF 124

Your task is to enable the creation of an explanation in the experiment script. What packages should you install in the run environment in order to achieve this goal?

A
azureml-blackbox
B
azureml-explainer
C
azureml-contrib-interpretCorrect Answer
D
azureml-interpretCorrect Answer
QUESTION 23 OF 124

If you want to minimize disparity in combined true positive rate and false_positive_rate across sensitive feature groups, what is the most suitable parity constraint that you should choose to use with any of the mitigation algorithms?

A
True positive rate parity
B
Error rate parity
C
Equalized oddsCorrect Answer
D
False-positive rate parity
QUESTION 24 OF 124

You decided to preprocess and filter down only the relevant columns for your AirBnB housing dataframe.

A
airbnbDF.createTempView(“airbnbDF”)
B
spark.udf.register(sql_udf = firstInitialFunction)
C
airbnbDF.createOrReplaceTempView(“airbnbDF”)
D
spark.udf.register(“sql_udf”, firstInitialFunction)
E
airbnbDF.createAndReplaceTempView(“airbnbDF”)
F
spark.udf.register(sql_udf.firstInitialFunction)
G
airbnbDF.replaceTempView(“airbnbDF”)Correct Answer
QUESTION 25 OF 124

In order to track the runs of a Linear Regression model of your AirBnB dataset, you decide to use MLflow. 

A
predDF = pipelineModel.evaluate(testDF)Correct Answer
B
regressionEvaluator = RegressionEvaluator(labelCol=”price”, predictionCol=”prediction”)
C
rmse = regressionEvaluator.setMetricName(“rmse”).evaluate(predDF)
D
r2 = regressionEvaluator.setMetricName(“r2”).evaluate(predDF)
E
predDF = pipelineModel.estimate(testDF)
F
predDF = pipelineModel.transform(testDF)
G
regression = RegressionEvaluator(labelCol=”price”, predictionCol=”prediction”)
QUESTION 26 OF 124

You decided to use Azure Machine Learning to create machine learning models. You want to use multiple compute contexts to train and score models. 

A
Inference cluster
B
Compute cluster
C
Attached computeCorrect Answer
QUESTION 27 OF 124

For your experiment in Azure Machine Learning you decide to run the following code:

A
files = run.get_properties()
B
files = run.get_details_with_logs()
C
files = run.get_fine_names()Correct Answer
D
files = run.get_metrics()
QUESTION 28 OF 124

Which of the options listed below is able to show if you have missing values in the dataset when you want to find out the number of observations in the data set in the process of explanatory data analysis?

A
Standard deviation
B
CountCorrect Answer
C
Mean
QUESTION 29 OF 124

You are able to use the the MlflowClient object as the pathway in order to query previous runs in a programmatic manner. 

A
from mlflow.pipelines import MlflowClientCorrect Answer
B
client = MlflowClient(
C
list.experiments()
D
from mlflow.tracking import MlflowClient
E
client = MlflowClient()
F
client.list_experiments()
G
list.client_experiments()
QUESTION 30 OF 124

In you want to explore the hyperparameters on a model while knowing that every algorithm uses a different hyperparameter for tuning, what is the most appropriate method you should choose?

A
showParams()
B
getParams()
C
exploreParams()
D
explainParams()Correct Answer
QUESTION 31 OF 124

True or False?

A
True
B
FalseCorrect Answer
QUESTION 32 OF 124

Your task is to store in the Azure ML workspace a model for whose training you ran an experiment. You want to do this so that other experiments and services can be applied to the model.

A
Save the model as a file in a compute instanceCorrect Answer
B
Save the experiment script as a notebook
C
Save the model as a file in a Key Vault instance
D
Register the model in the workspace
QUESTION 33 OF 124

Your hyperparameter tuning needs to have a search space defined. The values of the batch_size hyperparameter can be 128, 256, or 512 and the normal distribution values for the learning_rate hyperparameter can have a mean of 10 and a standard deviation of 3.

A
from azureml.train.hyperdrive import choice, normalCorrect Answer
B
param_space = {
C
 ‘–batch_size’: choice(128, 256, 512),
D
 ‘–learning_rate’: normal(10, 3)
E
 }
F
from azureml.train.hyperdrive import choice, uniform
G
 ‘–learning_rate’: uniform(10, 3)
H
 ‘–learning_rate’: qnormal(10, 3)
I
 ‘–learning_rate’: lognormal(10, 3)
QUESTION 34 OF 124

You decided to use Parquet files and Petastorm to train a distributed neural network by using Horovod.

A
from pyspark.ml.feature import VectorAssembler
B
vecAssembler = VectorAssembler(inputCols=cal_housing.feature_names, outputCol=”features”)
C
vecTrainDF = vecAssembler.transform(trainDF).call(“features”, “label”)
D
display(vecTrainDF)
E
vecTrainDF = vecAssembler.transform(trainDF).hook(“features”, “label”)
F
from pyspark.ml.feature import VectorAssembleCorrect Answer
G
vecTrainDF = vecAssembler.transform(trainDF).select(“features”, “label”)
H
vecAssembler = VectorAssembler(inputCols=cal_housing.feature_names, outputCol=”labels “)
QUESTION 35 OF 124

You are evaluating a completed binary classification machine learning model.

A
Box plot
B
A violin plot
C
Binary classification confusion matrixCorrect Answer
D
Gradient descent
QUESTION 36 OF 124

In order to foretell the price for a student’s craftwork, you have to rely on the following variables: the student’s length of education, degree type, and craft form. You decide to set up a linear regression model that you will have to evaluate. Solution: Apply the following metrics: Relative Squared Error, Coefficient of Determination, Accuracy, Precision, Recall, F1 score, and AUC:

A
Yes
B
NoCorrect Answer
QUESTION 37 OF 124

What is the result for multiplying a NumPy array by 3?

A
The new array will be 3 times longer, with the sequence repeated 3 times and also all the elements are multiplied by 3.
B
Array stays the same size, but each element is multiplied by 3.Correct Answer
C
The new array will be 3 times longer, with the sequence repeated 3 times.
QUESTION 38 OF 124

How should the following sentence be completed?One example of the machine learning […] type models is the Support Vector Machine algorithm.

A
Classification
B
RegressionCorrect Answer
C
Clustering
QUESTION 39 OF 124

If you multiply by 2 a list and a NumPy array, what result would you get?

A
Multiplying an NumPy array by 2 creates a new array 2 times the length with the original sequence repeated 2 times.
B
Multiplying a list by 2 performs an element-wise calculation on the list, which sees the list stay the same size, but each element has been multiplied by 2.
C
Multiplying a list by 2 creates a new list 2 times the length with the original sequence repeated 2 times.Correct Answer
D
Multiplying a NumPy array by 2 performs an element-wise calculation on the array, which sees the array stay the same size, but each element has been multiplied by 2.Correct Answer
QUESTION 40 OF 124

For training a classification model that is able to predict based on 8 numeric features where in the classes is belonging an observation, you configured a deep neural network. 

A
The network layer should contain four hidden layers
B
The input layer should contain four nodes
C
The output layer should contain four nodesCorrect Answer
QUESTION 41 OF 124

The company that you work for decides to expand the use of machine learning. The company decides not to set up another compute environment in Azure. At the moment, you have at your disposal the compute environments below.

A
1 mlc_cluster, 2 nb_server
B
1 mlc_cluster, 2 aks_clusterCorrect Answer
C
1 nb_server, 2 mlc_cluster
D
1 nb_server, 2 aks_cluster
QUESTION 42 OF 124

. In order to do a multi-class classification using an unbalanced training dataset, you have to apply C-Support Vector classification. You use the following Python code for the C-Support Vector classification:

A
class_weight=balanced: Automatically adjust weights inversely proportional to class frequencies in the input data
B
 C parameter: Size of the kernel cache
C
class_weight=balanced: Automatically select the performance metrics for the classification 
D
 C parameter: Penalty parameter
E
 C parameter: Degree of polynomial kernel function
F
class_weight=balanced: Automatically adjust weights directly proportional to class frequencies in the input data
QUESTION 43 OF 124

If you want to extract a dataset after its registration, what are the most suitable methods you should choose from the Dataset class?

A
find_by_name
B
find_by_id
C
get_by_nameCorrect Answer
D
get_by_idCorrect Answer
QUESTION 44 OF 124

If you want to set up a parallel run step, which of the SDK commands below should you choose?

A
parallelrun_step = ParallelRunStep(
B
 name=’batch-score’,
C
parallel_run_config=parallel.run.config,
D
 inputs=[batch_data_set.as_named_input(‘batch_data’)],
E
 output=output_dir,
F
 arguments=[]
G
 allow_reuse=True
H
 parallel_run_config=parallel_run_config,
I
 arguments=[],
J
parallelrun.step = ParallelRunStep(
K
 parallel.run.config=parallel_run_config,
L
output=output_dir,
QUESTION 45 OF 124

You are able to update web services already deployed and to enable the Application Insight with the use of Azure ML SDK. 

A
service = ws.webservices[‘my-svc’]
B
service.modify (enable_app_insights=True)
C
service.new (enable_app_insights=True)
D
service = ws.webservices(‘my-svc’)
E
service.create(enable_app_insights=True)
F
service.update(enable_app_insights=True)
QUESTION 46 OF 124

The DataFrame you are currently working on contains data regarding the daily sales of ice cream. In order to compare the avg_temp and units_sold columns you decided to use the corr method which returned a result of 0.95. 

A
On the day with the maximum units_sold value, the avg_temp value was 0.95
B
Days with high avg_temp values tend to coincide with days that have high units_sold valuesCorrect Answer
C
The units_sold value is, on average, 95% of the avg_temp value
QUESTION 47 OF 124

Which of the following methods are the ACI services and AKS services default authentication ones?

A
Disabled for AKS services
B
Token-based for AKS services.
C
Token-based for ACI services
D
Key-based for AKS servicesCorrect Answer
E
Disabled for ACI servicesCorrect Answer
QUESTION 48 OF 124

If your goal is to use a configuration file in order to ensure connection to your Azure ML workspace, what Python command would be the most appropriate?

A
from azureml.core import Workspace
B
ws = from.config_Workspace()
C
ws = Workspace.from_config()
D
ws = Workspace.from.config
QUESTION 49 OF 124

Your company is asking you to analyze a dataset that contains historical data obtained from a local car-sharing company. For this task, you decide to develop a regression model and you want to be able to foretell what price a trip will be. For the correct evaluation of the regression model, you have to use performance metrics. 

A
An F1 score that is low
B
An R-Squared value close to 0
C
A Root Mean Square Error value that is lowCorrect Answer
D
An R-Squared value close to 1Correct Answer
QUESTION 50 OF 124

Your task is to create and evaluate a model. One of the metrics shows an absolute metric in the same unit as the label. 

A
Coefficient of Determination (known as R-squared or R2)
B
Mean Square Error (MSE)
C
Root Mean Square Error (RMSE)Correct Answer
QUESTION 51 OF 124

When you use the Support Vector Machine algorithm, what type of machine learning model is possible to train?

A
Regression
B
Clustering
C
ClassificationCorrect Answer
QUESTION 52 OF 124

In order to create clusters, Hierarchical clustering uses two methods. 

A
Aggregational
B
Distinctive
C
AgglomerativeCorrect Answer
D
DivisiveCorrect Answer
QUESTION 53 OF 124

What is the effect that you obtain if you increase the Learning Rate parameter for the deep neural network that you are creating?

A
More hidden layers are added to the network
B
Larger adjustments are made to weight values during backpropagationCorrect Answer
C
More records are included in each batch passed through the network
QUESTION 54 OF 124

Your task is to set up an Azure Machine Learning workspace. You decide to use a laptop computer to create a local Python environment. 

A
Login
B
Region
C
Key
D
Resource_groupCorrect Answer
E
Subscription_idCorrect Answer
QUESTION 55 OF 124

You are using an Azure Machine Learning service for your data science project. In order to deploy the project, you have to choose a compute target. For this scenario, which of the following Azure services is the most suitable?

A
Azure Databricks
B
Azure Data Lake Analytics
C
Apache Spark for HDInsight
D
Azure Container InstancesCorrect Answer
QUESTION 56 OF 124

You want to use your registered model in a batch inference pipeline. 

A
process_count_per_node= “6”
B
node_count= “6”
C
mini_batch_size= “6”Correct Answer
D
error_threshold= “6”
QUESTION 57 OF 124

After installing the Azure Machine Learning Python SDK, you decide to use it to configure on your subscription a workspace entitled “aml-workspace”.

A
azureml.core import Workspace
B
 ws = Workspace.create(name=’aml-workspace’, 
C
 subscription_id=’123456-abc-123…’,
D
 resource_group=’aml-resources’,
E
 create_resource_group=False,
F
 location=’eastus’
G
 )
H
from azureml.core import WorkspaceCorrect Answer
I
 create_resource_group=True,
QUESTION 58 OF 124

What Python command should you choose in order to view the models previously registered in the Azure ML studio by using the Model object?

A
from azureml.core import Model
B
for model in Model.list(ws):
C
print(model.name, ‘version:’, model.version)
D
for model in List.Model(ws):
E
for model in Model.object(ws):
F
get(model.name, ‘version:’, model.version)
QUESTION 59 OF 124

What SDK commands should you choose if you want to extract a certain version of a data set?

A
img_ds = Dataset.get_by_name(workspace=ws, name=’img_files’, version_2)
B
img_ds = Dataset.get_by_name(workspace=ws, name=’img_files’, version(2))
C
img_ds = Dataset.get_by_name(workspace=ws, name=’img_files’, version=2)Correct Answer
D
img_ds = Dataset.get_by_name(workspace=ws, name=’img_files’, version=’2’)
QUESTION 60 OF 124

Your task is to deploy your service on an AKS cluster that is set up as a compute target.

A
from azureml.core.webservice import ComputeTarget, AksWebservice
B
cluster_name = ‘aks-cluster’
C
compute_config = AksCompute.provisioning_configuration(location=’eastus’)
D
production_cluster = ComputeTarget.create(ws, cluster_name, compute_config)
E
production_cluster.wait_for_completion(show_output=True)
F
from azureml.core.compute import ComputeTarget, AksComputeCorrect Answer
G
production_cluster = ComputeTarget.deploy (ws, cluster_name, compute_config)
H
from azureml.core.webservice import ComputeTarget, AksCompute
QUESTION 61 OF 124

If you want to extract the parallel_run_step.txt file from the output of the step after the pipeline run has ended, what code should you choose?

A
df = pd.read_csv(result_file, delimiter=”:”, header=None)
B
df.columns = [“File”, “Prediction”]
C
print(df)
D
prediction_run = next(pipeline_run.get_children())
E
prediction_output = prediction_run.get_output_data(‘inferences’)
F
prediction_output.download(local_path=’results’)
G
for root, dirs, files in os.walk(‘results’):Correct Answer
H
 for file in files:
I
 if file.endswith(‘parallel_run_step.txt’):
J
 result_file = os.path.join(root,file)
QUESTION 62 OF 124

What code should you write for an instance of a MimicExplainer if you have a model entitled loan_model?

A
from interpret.ext.blackbox import MimicExplainer
B
from interpret.ext.glassbox import DecisionTreeExplainableModel
C
mim_explainer = MimicExplainer(model=loan_model,
D
 initialization_examples=X_test,
E
 explainable_model = DecisionTree,
F
 classes=[‘loan_amount’,’income’,’age’,’marital_status’], 
G
 features=[‘reject’, ‘approve’])
H
 explainable_model = DecisionTreeExplainableModel,
I
 features=[‘loan_amount’,’income’,’age’,’marital_status’], 
J
 classes=[‘reject’, ‘approve’])
QUESTION 63 OF 124

What code should you write for a PFIExplainer if you have a model entitled loan_model?

A
from interpret.ext.blackbox import PFIExplainer
B
pfi_explainer = PFIExplainer(model = loan_model,
C
      initialization_examples=X_test,
D
 classes=[‘loan_amount’,’income’,’age’,’marital_status’],
E
 features=[‘reject’, ‘approve’])
F
 features=[‘loan_amount’,’income’,’age’,’marital_status’],
G
 classes=[‘reject’, ‘approve’])
H
      explainable_model= DecisionTreeExplainableModel,
I
features=[‘loan_amount’,’income’,’age’,’marital_status’],
J
from interpret.ext.blackbox 
QUESTION 64 OF 124

Choose from the list below all the options that show how are also entitled the qualitative variables.

A
Continuous
B
Numerical
C
DiscreteCorrect Answer
D
CategoricalCorrect Answer
QUESTION 65 OF 124

Which of the non-exhaustive cross validation techniques listed below enables you to assign data points in a random way to the training set and the test set?

A
K-fold cross-validation
B
Repeated random sub-sampling validation
C
Holdout cross-validationCorrect Answer
QUESTION 66 OF 124

If you want to list the generated files after your experiment run is completed, what is the most suitable object run you should choose?

A
download_files
B
download_file
C
get_file_namesCorrect Answer
D
list_file_names
QUESTION 67 OF 124

You can enable the Application Insights when configuring the service deployment at the moment you want to deploy a new real-time service. 

A
dep_config = AciWebservice.deploy_configuration(cpu_cores = 1,
B
 memory_gb = 1,
C
 app_insights(True))
D
 appinsights=True)
E
 enable_app_insights=True)
F
 app_insights=True)
QUESTION 68 OF 124

You intend to use the Hyperdrive feature of Azure Machine Learning to determine the optimal hyperparameter values when training a model.

A
A choice expression for learning_rate
B
A normal expression for batch_size
C
A choice expression for batch_sizeCorrect Answer
D
A uniform expression for learning_rateCorrect Answer
QUESTION 69 OF 124

You have a set of CSV files that contain sales records. Your CSV files follow an identical data schema. 

A
Create a new tabular dataset that references the datastore and explicitly specifies each ‘sales/mm-yyyy/sales.csv’ file every month. Register the dataset with the name sales_dataset_MM-YYYY each month with appropriate MM and YYYY values for the month and year. Use the appropriate month-specific dataset for experiments.
B
Create a tabular dataset that references the datastore and specifies the path ‘sales/*/sales.csv’, register the dataset with the name sales_dataset and a tag named month indicating the month and year it was registered, and use this dataset for all experiments.
C
Create a tabular dataset that references the datastore and explicitly specifies each ‘sales/mm-yyyy/sales.csv’ file. Register the dataset with the name sales_dataset each month as a new version and with a tag named month indicating the month and year it was registered. Use this dataset for all experiments, identifying the version to be used based on the month tag as necessary.Correct Answer
D
Create a tabular dataset that references the datastore and explicitly specifies each ‘sales/mm-yyyy/sales.csv’ file every month. Register the dataset with the name sales_dataset each month, replacing the existing dataset and specifying a tag named month indicating the month and year it was registered. Use this dataset for all experiments.
QUESTION 70 OF 124

Your company uses a set of labeled photographs for the multi-class image classification deep learning model that is creating. 

A
Increase the VM size of nodes in the compute cluster where the web service is deployed.
B
Increase the node count of the compute cluster where the web service is deployed.Correct Answer
C
Create a new compute cluster by using larger VM sizes for the nodes, redeploy the web service to that cluster, and update the DNS registration for the service endpoint to point to the new cluster.
D
Increase the minimum node count of the compute cluster where the web service is deployed.
QUESTION 71 OF 124

You decided to use the from_files method of the Dataset.File class to configure a file dataset. 

A
from azureml.core import Dataset
B
file_ds = Dataset.File.from_files(path=(blob_ds, ‘data/files/images/*.jpg’))
C
file_ds = file_ds.register(workspace=ws, name=’img_files’)
D
blob_ds = ws.get_default_datastore()
E
file_ds = Dataset.File.from_files(path=(blob_ds, ‘data/files/images’))
QUESTION 72 OF 124

You can combine the Bayesian sampling with an early-termination policy and you can use it only with these three parameter expressions: choice, uniform and quniform.

A
FalseCorrect Answer
B
True
QUESTION 73 OF 124

What code should you write using SDK if your goal is to extract the best run and its model?

A
best_run, fitted_model = automl.run.get_output()
B
best_run_metrics = best_run.get_metrics()
C
for metric_name in best_run_metrics:
D
 metric = best_run_metrics[metric_name]
E
 print(metric_name, metric)
F
best_run, fitted_model = automl_run.get_output()Correct Answer
G
best_run_metrics = best_run_get_metrics(1)
H
best_run, fitted_model = automl_run.get_input()
I
print(metric_name, metric)
QUESTION 74 OF 124

Your task is to train a binary classification model in order for it to be able to target the correct subjects in a marketing campaign. 

A
Remove the ethnicity feature from the training dataset.
B
Evaluate each trained model with a validation dataset, and use the model with the highest accuracy score. An accurate model is inherently fair.
C
Compare disparity between selection rates and performance metrics across ethnicities.Correct Answer
QUESTION 75 OF 124

You decided to use Python code interactively in your Conda environment. You have all the required Azure Machine Learning SDK and MLflow packages in the environment. 

A
#1 mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri()), #2 mlflow.get_run(‘mlflow-experiment), #3 mlflow.start_run(), #4 mlflow.log_metric
B
#1 mlflow.tracking.client = ws, #2 mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri()), #3 mlflow.active_run(), #4 mlflow.log_metric
C
#1 mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri()), #2 mlflow.get_run(‘mlflow-experiment), #3 mlflow.start_run(), #4 run.log()Correct Answer
D
#1 mlflow.set_tracking_uri(ws.get_mlflow_tracking_uri()), #2 mlflow.set_experiment(‘mlflow-experiment), #3 mlflow.start_run(), #4 mlflow.log_metric
QUESTION 76 OF 124

You want to deploy in your Azure Container Instance a deep learning model. 

A
from azureml.core.webservice import requests, predictions = service.run(input_json)
B
from azureml.core.webservice import Webservice, predictions = service.deserialize(ws, input_json)
C
from azureml.core.webservice import LocalWebservice, predictions = service.run(input_json)
D
from azureml.core.webservice import Webservice, predictions = service.run(input_json)Correct Answer
QUESTION 77 OF 124

One of the categorical variables of your AirBnB dataset is room type. 

A
from pyspark.ml.feature import OneHotEncoder
B
encoder = OneHotEncoder(inputCols=[“room_type_index”], outputCols=[“encoded_room_type”])
C
encoderModel = encoder.fit(indexedDF)
D
encodedDF = encoderModel.transform(indexedDF)
E
display(encodedDF)
F
encodedDF = encoderModel.fit (indexedDF)
G
encodedDF = encoderModel(indexedDF)
H
encodedDF = encoderModel_transform()
I
display(encodedDF) 
QUESTION 78 OF 124

You decided to use Azure Machine Learning and your goal is to train a Diabetes Model and build a container image for it.

A
aks_target = ComputeTarget.create(workspace = workspace, 
B
name = aks_cluster_name, 
C
provisioning_configuration = prov_config)
D
name = aks_cluster_name,)
E
aks_target = ComputeTarget.deploy(workspace = workspace,Correct Answer
F
 provisioning_configuration = prov_config)
G
aks_target = ComputeTarget.workspace = workspace 
H
 (name = aks_cluster_name, 
QUESTION 79 OF 124

You decide to use a two-class logistic regression model for a binary classification. If you have to evaluate the results for imbalance issues, what would be the best evaluation metric for the model?

A
Mean Absolute Error
B
Relative Squared Error
C
AUC CurveCorrect Answer
D
Relative Absolute Error
QUESTION 80 OF 124

Your task is to create and evaluate a model. You decide to use a specific metric that provides you a direct proportionality with how well the model fits. 

A
Root Mean Square Error (RMSE)
B
Mean Square Error (MSE)
C
Coefficient of Determination (known as R-squared or R2)Correct Answer
QUESTION 81 OF 124

Four possible prediction outcomes are able to provide you with the Precision and Recall metrics. 

A
False Negative
B
True Negative
C
True Positive
D
False PositiveCorrect Answer
QUESTION 82 OF 124

In order to register a datastore in a Machine Learning services workspace, one of your coworkers decides to use the code below:

A
DataStore, ws, demo_datastoreCorrect Answer
B
Run, ws, demo_datastore
C
Run, experiment, demo_datastore
D
Experiment, run, demo_account
QUESTION 83 OF 124

You decide to register and train a model in your Azure Machine Learning workspace. 

A
main()
B
score(mini_batch)
C
batch()
D
run(mini_batch)Correct Answer
E
init()Correct Answer
QUESTION 84 OF 124

You decide to deploy a real-time inference service for a trained model. 

A
View the log files generated by the experiment used to train the model.
B
View the explanations for the registered model in Azure ML studio.
C
Create an ML Flow tracking URI that references the endpoint, and view the data logged by ML Flow.
D
Enable Azure Application Insights for the service endpoint and view logged data in the Azure portal.Correct Answer
QUESTION 85 OF 124

After installing the Azure Machine Learning CLI extension, you decide to use it to set up an ML workspace in your existing resource group. 

A
az ml ws create -w ‘aml-workspace’ -g ‘aml-resources’
B
az ml workspace create -w ‘aml-workspace’ -g ‘aml-resources’Correct Answer
C
new az ml workspace create -w ‘aml-workspace’ -g ‘aml-resources’
D
az ml new workspace create -w ‘aml-workspace’ -g ‘aml-resources’
QUESTION 86 OF 124

Your task is to use the SDK in order to define a compute configuration for a managed compute target. 

A
compute_config = AmlCompute_provisioning_configuration(vm_size=’STANDARD_DS11_V2′,
B
 min_nodes=0, max_nodes=4,
C
 vm_priority=’dedicated’)
D
compute_config = AmlCompute.provisioning_configuration(vm_size=’STANDARD_DS11_V2′,Correct Answer
E
min_nodes=0, max_nodes=4,
F
 min_nodes=0, max_nodes=0,
G
compute_config = AmlCompute.provisioning.configuration(vm_size=’STANDARD_DS11_V2′,
QUESTION 87 OF 124

What Python code should you write if your goal is to implement a median stopping policy?

A
from azureml.train.hyperdrive import MedianStoppinPolicy
B
early_termination_policy = MedianStoppingPolicy(slack_amount = 0.2,
C
             evaluation_interval=1,
D
             delay_evaluation=5)
E
from azureml.train.hyperdrive import MedianStoppingPolicy
F
early_termination_policy = MedianStoppingPolicy(truncation_percentage=10,
G
          evaluation_interval=1,
H
          delay_evaluation=5)
I
early_termination_policy = MedianStoppingPolicy(evaluation_interval=1,
J
 delay_evaluation=5)
QUESTION 88 OF 124

Your task is to back fill a dataset monitor for the previous 5 months based on changes made in data on a monthly basis.

A
import datetime as dt
B
backfill = monitor.backfill( dt.datetime.now(), dt.timedelta(months=5), dt.datetime.now())
C
backfill = monitor_backfill( dt.datetime.now(), dt.timedelta(months=5), dt.datetime.now())
D
backfill = monitor_backfill( dt.datetime.now() – dt.timedelta(months=5), dt.datetime.now())
E
backfill = monitor.backfill( dt.datetime.now() – dt.timedelta(months=5), dt.datetime.now())
QUESTION 89 OF 124

You decided to use the AirBnB Housing dataset and the Linear Regression algorithm for which you want to tune the Hyperparameters. 

A
from pyspark.ml.tuning import ParamGridBuilder
B
paramGrid = (ParamGridBuilder(lr)
C
.addGrid(lr.maxIter, [1, 10, 100])
D
.addGrid(lr.fitIntercept, [True, False])
E
.addGrid(lr.standardization, [True, False])
F
.run()
G
)
H
paramGrid = (ParamGridBuilder()
I
.build()
J
.search()
K
.create()
QUESTION 90 OF 124

Choose from the list below the cross-validation technique that belongs to the exhaustive type.

A
K-fold cross-validation
B
Holdout cross-validation
C
Leave-p-out cross-validationCorrect Answer
D
Leave-one-out cross-validationCorrect Answer
QUESTION 91 OF 124

You usually take the following steps when you use HorovodRunner in order to develop a distributed training program:

A
hr = HorovodRunner(tf)
B
def train():
C
 import tensorflow as np
D
 hvd.init(2)
E
hr.run(train)
F
hr = HorovodRunner()
G
 import tensorflow as tf
H
 hvd.init(np)
I
hr = HorovodRunner(np=2)Correct Answer
J
 hvd.init()
K
hr = HorovodRunner(np)
L
import tensorflow as tf
M
hvd.init()
QUESTION 92 OF 124

You create a machine learning model by using the Azure Machine Learning designer. You publish the model as a real-time service on an Azure Kubernetes Service (AKS) inference compute cluster. You make no change to the deployed endpoint configuration. 

A
The run ID of the inference pipeline experiment for the endpoint
B
The name of the inference pipeline for the endpoint
C
The name of the AKS cluster where the endpoint is hosted
D
The URL of the endpointCorrect Answer
E
The key for the endpointCorrect Answer
QUESTION 93 OF 124

In order to foretell the price for a student’s craftwork, you have to rely on the following variables:

A
Yes 
B
NoCorrect Answer
QUESTION 94 OF 124

You have a Pandas DataFrame entitled df_sales that contains the sales data from each day. You DataFrame contains these columns: year, month, day_of_month, sales_total. Which of the following codes should you choose if your goal is to return the average sales_total value?

A
mean(df_sales[‘sales_total’])
B
df_sales[‘sales_total’].avg()
C
df_sales[‘sales_total’].mean()Correct Answer
QUESTION 95 OF 124

If you use the sklearn.metrics classification report for evaluating how your model performs, what result do you get from the F1-Score metric?

A
How many instances of this class are there in the test dataset
B
Out of all of the instances of this class in the test dataset, how many did the model identify
C
Of the predictions the model made for this class, what proportion were correct
D
An average metric that takes both precision and recall into account.Correct Answer
QUESTION 96 OF 124

In order to train your K-Means clustering model that enables grouping observations into four clusters, you decide to use scikit-learn library. Considering this scenario, what method should you choose to create the K-Means object?

A
model = Kmeans(n_init=4)
B
model = KMeans(n_clusters=4)Correct Answer
C
model = Kmeans(max_iter=4)
QUESTION 97 OF 124

The layer described below is used to reduce the number of feature values that are extracted from images, while still retaining the key differentiating features.

A
Convolutional layer
B
Pooling layerCorrect Answer
C
Flattening layer
QUESTION 98 OF 124

You are in the process of training a machine learning model. Your model has to be configured for testing as a real-time inference service. For the service you have to ensure low CPU utilization and less than 48 MB of RAM. While keeping cost and administrative overhead to a minimum, you have to make sure that the compute target for the deployed service is initialized in an automatic manner.

A
attached Azure Databricks cluster
B
Azure Kubernetes Service (AKS) inference cluster
C
Azure Container Instance (ACI)Correct Answer
D
Azure Machine Learning compute cluster
QUESTION 99 OF 124

You want to create a pipeline for which you defined three steps entitled as step1, step2, and step3.

A
train_pipeline = Pipeline(workspace = ws, steps = [step1,step2,step3])
B
experiment = Experiment(workspace = ws, name = ‘training-pipeline’)
C
pipeline_run = experiment_submit(train_pipeline)
D
experiment = Experiment(workspace = ws)
E
pipeline_run = experiment.submit(train_pipeline)
F
train_pipeline = Pipeline(workspace = ws, steps = [step1;step2;step3])
QUESTION 100 OF 124

You want to evaluate a Python NumPy array that has six data points with the following definition: data = [10, 20, 30, 40, 50, 60]

A
K-means, 6, array
B
K-fold, 3, array
C
K-fold, 3, dataCorrect Answer
D
CrossValidation, 3, data
QUESTION 101 OF 124

Choose from the list below the supervised learning problem type that usually outputs quantitative values.

A
Classification
B
RegressionCorrect Answer
C
Clustering
QUESTION 102 OF 124

Choose from the descriptions below the one that explains what does a negative correlation of -1 mean in terms of correlations.

A
For each unit increase in one variable, the same increase is seen in the other
B
There is no association between the variables
C
For each unit increase in one variable, the same decrease is seen in the otherCorrect Answer
QUESTION 103 OF 124

Your task is to extract from the experiments list the last run. 

A
runs = client.search_runs(experiment_id, order_by=[“attributes.start_time desc”], max_results=1)
B
runs[0].data.metricsCorrect Answer
C
runs = client.search_runs(experiment_id, order_by=[“attributes.start_time”], max_results=1)
D
runs = client.search_runs(experiment_id, order_by=[“attributes.start_time asce”], max_results=1)
E
runs = client.search_runs(experiment_id, order_by=[“attributes.start_time desc”], max_results=3)
QUESTION 104 OF 124

You published a parametrized pipeline and you now want to be able to pass parameter values in the JSON payload for the REST interface.

A
response = requests_post(rest_endpoint,
B
 json={“ExperimentName”: “run_training_pipeline”,
C
 “ParameterAssignments”: {“reg_rate”: 0.1}})
D
response = requests.post(rest_endpoint,Correct Answer
E
 headers=auth_header,
F
 json=auth_header,
G
 headers={“ExperimentName”: “run_training_pipeline”,
H
 headers()
QUESTION 105 OF 124

You are creating a model to predict the price of a student’s artwork depending on the following variables: the student’s length of education, degree type, and art form. 

A
No
B
YesCorrect Answer
QUESTION 106 OF 124

Your NumPy array has the shape (2,35). Considering this, what information can you get about the elements?

A
The array contains 2 elements with the values of 2 and 35.
B
The array contains 35 elements, all with the value 2.
C
The array is two dimensional, consisting of two arrays with 35 elements each.Correct Answer
QUESTION 107 OF 124

You decided to use the LinearRegression class from the scikit-learn library to create your model object. 

A
Call the score() method of the model object, specifying the training feature and test feature arrays
B
Call the predict() method of the model object, specifying the training feature and label arrays
C
Call the fit() method of the model object, specifying the training feature and label arraysCorrect Answer
QUESTION 108 OF 124

Which are two appropriate ways to approach a problem when using multiclass classification?

A
Rest minus One
B
One and Rest
C
One vs RestCorrect Answer
D
One vs OneCorrect Answer
QUESTION 109 OF 124

Your task is to train a model entitled finance-data for the financial department, by using data in an Azure Storage blob container. 

A
register_azure_blob_container, overwrite = True
B
register_azure_blob_container, create_if_not_exists = FalseCorrect Answer
C
register_azure_data_lake, create_if_not_exists = False
D
register_azure_data_lake, overwrite = False
QUESTION 110 OF 124

You decide to use the code below for the deployment of a model as an Azure Machine Learning real-time web service:

A
service.get_logs()Correct Answer
B
service.update_deployment_state()
C
service.serialize()
D
service.state
QUESTION 111 OF 124

In order to train models, you decide to use an Azure Machine Learning compute resource. You set up the compute resource in the following manner: – Minimum nodes: 1 – Maximum nodes: 5. You have to decrease the minimum number of nodes and to increase the maximum number of nodes to the following values: – Minimum nodes: 0 – Maximum nodes: 8

A
Use the Azure Machine Learning designer.
B
Run the refresh_state() method of the BatchCompute class in the Python SDK.
C
Run the update method of the AmlCompute class in the Python SDK.Correct Answer
D
Use the Azure portal.Correct Answer
E
Use the Azure Machine Learning studio.Correct Answer
QUESTION 112 OF 124

You discover a median value for a number of variables in your AirBnB Housing dataset, variables like the number of rooms, per capita crime and economic status of residents. 

A
from pyspark.ml.regression import LinearRegression
B
lr = LinearRegression(featuresCol=”rm”, labelCol=”medv”)
C
lrModel = lr_fit(bostonFeaturizedDF)
D
from pyspark.ml import LinearRegression
E
lr = LinearRegression(featuresCol=”rm “, labelCol=”medv”)
F
from pyspark import LinearRegression
G
lr = LinearRegression(featuresCol=”features”, labelCol=”medv”)
H
lrModel = lr.fit(bostonFeaturizedDF)
QUESTION 113 OF 124

You are using remote compute in Azure Machine Learning to run a training experiment. 

A
#1 import mlflow, #2 mlflow.start_run(), #3 logger.info(‘ ..’), #4 mlflow.end_run()
B
#1 from azureml.core import Run, #2 run = Run.get_context(), #3 logger.info(‘ ..’), #4 run.complete()
C
#1 import mlflow, #2 mlflow.start_run(), #3 mlflow.log_metric(‘ ..’), #4 mlflow.end_run()Correct Answer
D
#1 import logging, #2 mlflow.start_run(), #3 mlflow.log_metric(‘ ..’), #4 run.complete()
QUESTION 114 OF 124

Your task is to extract local feature importance from a TabularExplainer.

A
local.tab_explanation = tab_explainer_explain_local(X_test[0:5])
B
local_tab_features = local_tab_explanation.get_ranked_local_names()
C
local_tab_importance = local_tab_explanation.get_ranked_local_values()
D
local_tab_explanation = tab_explainer.explain_local(X_test[0:5])
E
local_tab_features = local_tab_explanation.get_feature_local_names()
F
local_tab_features = local_tab_explanation.get_feature_importance_dict ()
QUESTION 115 OF 124

If you want to string together all the different possible hyperparameters that you need for testing, what is the most suitable PySpark class method you should choose?

A
ParamGridBuilder()Correct Answer
B
ParamBuilder()
C
ParamGridSearch()
D
ParamSearch()
QUESTION 116 OF 124

Your task is to clean up the deployments and terminate the “dev” ACI webservice by making use of the Azure ML SDK after your work with Azure Machine Learning has ended. 

A
dev_webservice.remove()
B
dev_webservice.terminate()
C
dev_webservice.flush()
D
dev_webservice.delete()Correct Answer
QUESTION 117 OF 124

As a data scientist, you are asked to build a deep convolutional neural network (CNN) in order to classify images. Your CNN model seems to present some overfitting signs. Your goal is to minimize overfitting and to give an optimal fit to the model. 

A
Reduce the amount of training data 
B
Add an additional dense layer with 64 input units
C
Add an additional dense layer with 512 input units
D
Add L1/L2 regularizationCorrect Answer
E
Use training data augmentationCorrect Answer
QUESTION 118 OF 124

You have the role of lead data scientist in a project that keeps record of birds’ health and migration. You decide to use a set of labeled bird photographs collected by experts for your multi-class image classification deep learning model. 

A
Register the Azure blob storage containing the bird photographs as a datastore in Azure Machine Learning service.Correct Answer
B
Copy the bird photographs to the blob datastore that was created with your Azure Machine Learning service workspace.
C
Create an Azure Data Lake store and move the bird photographs to the store.
D
Create and register a dataset by using TabularDataset class that references the Azure blob storage containing bird photographs.
E
Create an Azure Cosmos DB database and attach the Azure Blob containing bird photographs storage to the database. 
QUESTION 119 OF 124

Your task is to ensure that your data drift monitor, that you scheduled to run daily, is able to send an alert when the drift magnitude surpasses 0.2. What code should you write in Python to achieve this?

A
alert_email = AlertConfiguration(‘data_scientists@contoso.com’)
B
monitor = DataDriftDetector.create_from_datasets(ws, ‘dataset-drift-detector’, 
C
baseline_data_set, target_data_set,
D
compute_target=cpu_cluster,
E
frequency=’Day’, latency=2,
F
drift_threshold=.2,
G
alert_configuration=alert_email)
H
 baseline_data_set, target_data_set,
I
 compute_target=cpu_cluster,
J
 frequency=’Week’, latency=2,
K
 drift_threshold=.2,
L
 alert_configuration=alert_email)
M
drift_threshold=.4)
QUESTION 120 OF 124

In order to find all the runs for a specific experiment, you can use also the search_runs method. 

A
experiment = run.experiment_id
B
runs_df = mlflow.search_runs(experiment_id)
C
display(runs_df)
D
experiment_id = run.info.experiment_id
E
experiment_id = info.experiment_id
F
experiment_id = run.experiment_idCorrect Answer
QUESTION 121 OF 124

What are the most appropriate SDK commands you should choose if you want to publish the pipeline that you created?

A
published.pipeline = pipeline_publish(name=’training_pipeline’,
B
 description=’Model training pipeline’,
C
 version=’1.0′)
D
published.pipeline = pipeline.publish(name=’training_pipeline’,
E
description=’Model training pipeline’,
F
published_pipeline = pipeline.publish(name=’training_pipeline’,Correct Answer
G
publishedpipeline = pipeline_publish(name=’training_pipeline’,
QUESTION 122 OF 124

Your task is to reduce the size of the feature maps that a convolutional layer generates when you create a convolutional neural network. What action should you take in this case?

A
Increase the number of filters in the convolutional layer
B
Add a pooling layer after the convolutional layerCorrect Answer
C
Reduce the size of the filter kernel used in the convolutional layer
QUESTION 123 OF 124

You’re using the Azure Machine Learning Python SDK to define a pipeline to train a model.

A
Create a ScheduleRecurrence object with a Frequency of auto. Use the object to create a schedule for the pipeline
B
Set the regenerate_outputs property of the pipeline to True
C
Create a PipelineParameter with a default value that references the location where the training data is stored
D
Create a Schedule for the pipeline. Specify the datastore in the datastore property, and the folder containing the training data in the path_on_datastore propertyCorrect Answer
QUESTION 124 OF 124

If you want to minimize disparity in the selection rate across sensitive feature groups, what is the most suitable parity constraint that you should choose to use with any of the mitigation algorithms?

A
Equalized odds
B
Bounded group loss
C
Demographic parityCorrect Answer
D
Error rate parity

Ready to test your recall?

Your task is to predict if a person suffers from a disease by setting up a binary classification model. Your solution needs to be able to detect the classification errors that may appear. 

A
True negatives
B
False positives
C
False negatives
D
True positives

How confident are you in this answer?