Microsoft DP-100 Online Practice Questions and Exam Preparation

Microsoft DP-100 Online Questions & Answers

• Question 131:

  HOTSPOT

  A coworker registers a datastore in a Machine Learning services workspace by using the following code:

  

  You need to write code to access the datastore from a notebook.

  How should you complete the code segment? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  Box 1: DataStore

  To get a specific datastore registered in the current workspace, use the get() static method on the Datastore class: # Get a named datastore from the current workspace datastore = Datastore.get(ws, datastore_name='your datastore name')

  Box 2: ws

  Box 3: demo_datastore

  https://docs.microsoft.com/en-us/azure/machine-learning/how-to-access-data

• Question 132:

  You are profiling mltabte data assets by using Azure Machine Learning studio. You need to detect columns with odd or missing values.

  Which statistic should you analyze?

  A. Profile
  B. Std deviation
  C. Error count
  D. Type
  C. Error count

• Question 133:

  HOTSPOT

  You are using the Azure Machine Learning Service to automate hyperparameter exploration of your neural network classification model.

  You must define the hyperparameter space to automatically tune hyperparameters using random sampling according to following requirements:

  1. The learning rate must be selected from a normal distribution with a mean value of 10 and a standard deviation of 3.

  2. Batch size must be 16, 32 and 64.

  3. Keep probability must be a value selected from a uniform distribution between the range of 0.05 and 0.1.

  You need to use the param_sampling method of the Python API for the Azure Machine Learning Service.

  How should you complete the code segment? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  In random sampling, hyperparameter values are randomly selected from the defined search space. Random sampling allows the search space to include both discrete and continuous hyperparameters.

  Example:

  from azureml.train.hyperdrive import RandomParameterSampling

  param_sampling = RandomParameterSampling( {

  "learning_rate": normal(10, 3),

  "keep_probability": uniform(0.05, 0.1),

  "batch_size": choice(16, 32, 64)

  } Reference:

  https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-tune-hyperparameters

• Question 134:

  You use Azure Machine Learning Designer to load the following datasets into an experiment:

  Dataset1

  

  Dataset2

  

  You use Azure Machine Learning Designer to load the following datasets into an experiment:

  You need to create a dataset that has the same columns and header row as the input datasets and contains all rows from both input datasets.

  Solution: Use the Join Data component.

  Does the solution meet the goal?

  A. Yes
  B. No
  B. No

• Question 135:

  You use Azure Machine Learning Studio to build a machine learning experiment.

  You need to divide data into two distinct datasets.

  Which module should you use?

  A. Assign Data to Clusters
  B. Load Trained Model
  C. Partition and Sample
  D. Tune Model-Hyperparameters
  C. Partition and Sample

  ---

  Explanation

  Partition and Sample with the Stratified split option outputs multiple datasets, partitioned using the rules you specified.

  References:

  https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/partition-and-sample

• Question 136:

  DRAG DROP

  You previously deployed a model that was trained using a tabular dataset named training-dataset, which is based on a folder of CSV files.

  Over time, you have collected the features and predicted labels generated by the model in a folder containing a CSV file for each month. You have created two tabular datasets based on the folder containing the inference data: one named predictions-dataset with a schema that matches the training data exactly, including the predicted label; and another named features-dataset with a schema containing all of the feature columns and a timestamp column based on the filename, which includes the day, month, and year.

  You need to create a data drift monitor to identify any changing trends in the feature data since the model was trained. To accomplish this, you must define the required datasets for the data drift monitor.

  Which datasets should you use to configure the data drift monitor? To answer, drag the appropriate datasets to the correct data drift monitor options. Each source may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.

  NOTE: Each correct selection is worth one point.

  Select and Place:

  

  

  ---

  Box 1: training-dataset

  Baseline dataset - usually the training dataset for a model.

  Box 2: predictions-dataset

  Target dataset - usually model input data - is compared over time to your baseline dataset. This comparison means that your target dataset must have a timestamp column specified.

  The monitor will compare the baseline and target datasets.

  https://docs.microsoft.com/en-us/azure/machine-learning/how-to-monitor-datasets

• Question 137:

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

  You must use Hyperdrive to try combinations of the following hyperparameter values. You must not apply an early termination policy.

  1. learning_rate: any value between 0.001 and 0.1

  2. batch_size: 16, 32, or 64

  You need to configure the sampling method for the Hyperdrive experiment.

  Which two sampling methods can you use? Each correct answer is a complete solution.

  NOTE: Each correct selection is worth one point.

  A. No sampling
  B. Grid sampling
  C. Bayesian sampling
  D. Random sampling
  C. Bayesian sampling
  D. Random sampling

  ---

  Explanation

  C: Bayesian sampling is based on the Bayesian optimization algorithm and makes intelligent choices on the hyperparameter values to sample next. It picks the sample based on how the previous samples performed, such that the new sample improves the reported primary metric. Bayesian sampling does not support any early termination policy

  Example:

  from azureml.train.hyperdrive import BayesianParameterSampling from azureml.train.hyperdrive import uniform, choice

  param_sampling = BayesianParameterSampling( {

  "learning_rate": uniform(0.05, 0.1),

  "batch_size": choice(16, 32, 64, 128)

  }

  ) D: In random sampling, hyperparameter values are randomly selected from the defined search space. Random sampling allows the search space to include both discrete and continuous hyperparameters.

  Incorrect Answers:

  B: Grid sampling can be used if your hyperparameter space can be defined as a choice among discrete values and if you have sufficient budget to exhaustively search over all values in the defined search space. Additionally, one can use automated early termination of poorly performing runs, which reduces wastage of resources.

  Example, the following space has a total of six samples: from azureml.train.hyperdrive import GridParameterSampling from azureml.train.hyperdrive import choice

  param_sampling = GridParameterSampling( {

  "num_hidden_layers": choice(1, 2, 3),

  "batch_size": choice(16, 32)

  }

  ) Reference:

  https://docs.microsoft.com/en-us/azure/machine-learning/how-to-tune-hyperparameters

• Question 138:

  HOTSPOT

  You load data from a notebook in an Azure Machine Learning workspace into a pandas dataframe named df. The data contains 10,000 patient records. Each record includes the Age property for the corresponding patient.

  You must identify the mean age value from the differentially private data generated by SmartNoise SDK.

  You need to complete the Python code that will generate the mean age value from the differentially private data.

  Which code segments should you use? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  Explanation:

  Box 1: Analysis()

  Box 2: epsilon

  Note: Differential Privacy

  Differential Privacy is a technique for add statistical noise to the data. A parameter named epsilon governs the differential privacy algorithm. It is like the hyper-parameter of a machine learning algorithm and the difference between original and de-identified data is inversely proportional to the value of epsilon. Higher the value epsilon, your de-identified data is more similar to the original one.

  We won't go into the mathematics of differential privacy, since it's quite complex. Instead, we will look at its python package implementation. The python package is smart noise. For detailed code implementation, refer to this link: SmartNoise.

  Now, let's walk through a piece of code. We will use the toy data, i.e. diabetes dataset. But first things first. Let us install the Smart Noise package.

  !pip install opendp-smartnoise

  Next, load diabetes data into a dataframe.

  Next, let's use the smart noise 'Analysis' and get the differentially private mean of the 'Age' column using the dp_mean method in the diabetes dataframe.

  import opendp.smartnoise.core as sn lst_cols = list(df_diabetes.columns) #get all columns

  age_range = [0.0, 120.0] #set the age range samples = len(df_diabetes) #numver of samples

  with sn.Analysis() as analysis: data = sn.Dataset(path=file_path, column_names=lst_cols) age_dt = sn.to_float(data['Age'])

  #Calculate differential privacy age_mean = sn.dp_mean(data = age_dt, privacy_usage = {'epsilon': .50}, data_lower = age_range[0], data_upper = age_range[1], data_rows = samples )

  analysis.release() Reference:

  https://www.data4v.com/a-look-at-differential-privacy/

• Question 139:

  Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.

  After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

  You create a model to forecast weather conditions based on historical data.

  You need to create a pipeline that runs a processing script to load data from a datastore and pass the processed data to a machine learning model training script.

  Solution: Run the following code:

  

  Does the solution meet the goal?

  A. Yes
  B. No
  A. Yes

  ---

  Explanation

  The two steps are present: process_step and train_step

  The training data input is not setup correctly.

  Note:

  Data used in pipeline can be produced by one step and consumed in another step by providing a PipelineData object as an output of one step and an input of one or more subsequent steps.

  PipelineData objects are also used when constructing Pipelines to describe step dependencies. To specify that a step requires the output of another step as input, use a PipelineData object in the constructor of both steps.

  For example, the pipeline train step depends on the process_step_output output of the pipeline process step:

  from azureml.pipeline.core import Pipeline, PipelineData from azureml.pipeline.steps import PythonScriptStep datastore = ws.get_default_datastore()

  process_step_output = PipelineData("processed_data", datastore=datastore) process_step = PythonScriptStep(script_name="process.py", arguments=["--data_for_train", process_step_output], outputs=[process_step_output], compute_target=aml_compute, source_directory=process_directory) train_step = PythonScriptStep(script_name="train.py", arguments=["--data_for_train", process_step_output], inputs=[process_step_output], compute_target=aml_compute, source_directory=train_directory) pipeline = Pipeline(workspace=ws, steps=[process_step, train_step])

  https://docs.microsoft.com/en-us/python/api/azureml-pipeline-core/azureml.pipeline.core.pipelinedata?view=azure-ml-py

• Question 140:

  Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.

  After you answer a question in this section, you will not be able to return to it. As a result, these questions will not appear in the review screen.

  You have an Azure Machine Learning workspace.

  You plan to tune model hyperparameters by using a sweep job.

  You need to find a sampling method that supports early termination of low-performance jobs and continuous hyperparameters.

  Solution: Use the grid sampling method over the hyperparameter space.

  Does the solution meet the goal?

  A. Yes
  B. No
  B. No