You have your dataset extracted in a csv file and now you want to generate accurate machine learning predictions.

Can you do this using Amazon SageMaker Canvas and without writing any code?

--
SageMaker is a fully managed service to prepare data and build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows.

--
Tutorial Summary:
- Demonstrates using Amazon SageMaker Canvas for machine learning predictions without writing code.
- Starts by selecting input values: 50 for age, 35 for BMI, and affirming "Smoker" to expect a high insurance cost.
- Guides through preparing a dataset in Excel: creates input and output columns with random numbers and saves it as "my_data.csv."
- Uploads the file to an S3 bucket in the SageMaker Canvas tab.
- Creates a dataset by selecting "S3" as the data source, choosing the uploaded file, and creating the dataset.
- Builds a predictive model by defining the target column and using "quick build" to automatically create the model.
- Tests the model's accuracy by providing different input values and checking if it predicts the correct output values.
- Introduces a new dataset (insurance.csv) with columns defining insurance variables.
- Creates a new model based on this insurance dataset to predict yearly insurance costs based on defined variables.
- Shows how being a smoker significantly impacts yearly insurance costs in the model.
- Tests the model by inputting values and expecting a high insurance cost for a smoker.
- Concludes by advising to log out to avoid incurring Canvas charges and ends with a humorous question.

--
P.S. Why did the data scientist bring Amazon SageMaker to the comedy club? Because they wanted to train their model to recognize a good "punch" line!

свернуть