
Navigate the Dataiku data science studio designer studio UI, exploring the landing page, projects, design node, and credentials. Build flows, datasets, recipes, notebooks, and automation to develop pipelines across zones.
You can quickly download the dummy csv files used in this session from resources to your local machine and source them in dataiku or use your own files
Import raw data from cloud storage into Dataiku DSS Designer by configuring zones, selecting S3 datasets, previewing CSV files, and computing metadata before moving to a flow.
The presentation used in this session is attached in resources
Implement risk ranges from FICO scores, define loyalty by days active, apply targeted risk, then clean data and prepare a dataset with a primary key using regex.
Sort data by risk range, demographics, and targeted reward using the sort recipe, then filter for immunity booster kit records to reveal counts by risk and demographic group.
Explore the stack recipe in Dataiku Data Science Studio, learning to union two datasets with similar schemas, address incompatibilities through preparation and column renaming, and verify results.
Explore the split recipe to divide cleaned data into train and test datasets using a random ratio, enabling model training and evaluation with CSV Metastore outputs.
Explore the python code recipe introduction in Dataiku DSS Designer, learning how core recipes auto-generate input/output code, convert datasets to dataframes, apply pandas and numpy operations, and write back.
Learn how to use Python code recipes in the DSS designer to create columns with constant and random values, import libraries, delete and rename columns, and validate data flow.
Create charts and dashboards in data iq data science studio, from vertical bars to line charts with date handling. Build interactive dashboards using tiles, filters, and presentation mode.
Explore statistics cards in Dataiku DSS designer series, using univariate and bivariate analysis, automatic card suggestions, and visual insights from demographics, risk, and rewards.
More than half of the time in any BI and Data science project is spent on cleaning the raw data and preparing it for analysis ready. In this Dataiku DSS Designer series, we are learning this part of data project in an efficient way.
This is a complete practical hands-on based course, Structured logically
This course is for absolute beginners, At the end of this course you will be:
Able to access the Dataiku's free cloud train instance
Able to navigate through the launch pad and understand the environment details
Able to successfully source the data from local and cloud storages
Confidently apply various visual recipes on the sourced data
Understanding the code recipe and using it in pipeline
Visualize the data by applying charts,graphs and other visual statistics
Use Dataiku in your Professional Day Job-For Extract transform and load
In just one weekend you will go from absolute beginner to being able to integrate data from multiple sources, perform data preparation and cleansing to raw data sets and more.
Requirements
No prior coding experience required
Basic knowledge of any programming or querying language or cloud would be extra beneficial. But not absolutely neccessary
Curiosity to explore the data.