DATA-101 Data science and MLOps
SQL and data analysis for business roles
Your data sits in a database, an ERP or twenty spreadsheets, and Monday's question is waiting for an answer in figures. In two days, the participant queries a database in SQL, cleans and aggregates with Python, and delivers a dashboard that refreshes itself. It is also the groundwork before machine learning.
Objectives
- Write an SQL query with filters, joins and aggregations that answers a given business question, and check its result against a known case.
- Load, clean and aggregate a dataset with pandas (missing values, duplicates, date formats, merging sources).
- Check the quality of a dataset and document the anomalies found in a one-page report.
- Compute and interpret descriptive statistics (mean, median, standard deviation, correlation) while avoiding the usual pitfalls.
- Build a three-indicator dashboard in Power BI, connected to the source, and share it with their department.
Audience
Business analysts, management controllers, research officers, reporting managers, accountants and managers who want to move beyond the spreadsheet; future participants of DATA-201.
Prerequisites
Comfortable with a spreadsheet up to pivot tables and lookup formulas. No programming. One laptop per participant; a training database and an online notebook environment provided by Yolea, with nothing to install; Power BI Desktop installed before the first day (a Windows machine is required for this workshop, an online alternative is offered otherwise); for remote delivery, a stable connection of at least 5 Mbit/s, microphone and camera. A real export from the participant is accepted if it is anonymised.
Programme
- Querying a database
- Data preparation in Python
- Quality control
- Descriptive statistics
- Building dashboards
Format
In-company or open enrolment. 14 hours, 2 consecutive days of 7 hours; remotely, 4 sessions of 3 hours 30 minutes over two weeks. On site, live remote or hybrid; 8 to 12 participants. 30% input, 70% guided workshops, built around one running dataset (multi-site sales with stock discrepancies) followed from the raw query to the dashboard.
Assessment
Beforehand, a placement questionnaire. During the course, check quizzes and a practical challenge (answer five business questions on an imposed dataset; queries and dashboard assessed against a grid). At the end, a same-day feedback survey and a named certificate of course completion. Three weeks later, a follow-up check-in.
Ask for this course
A person answers you and sends you a quote.
Related courses
- Data science and MLOpsApplied machine learningThree days to go from a table of data to a model that predicts, honestly evaluated and explained to a decision-maker.DATA-2013 days
- Data science and MLOpsAnomaly detection and forecasting on operational dataA breakdown, a fraud or a stock-out leaves traces in the data before it becomes costly.DATA-2022 days
- Data science and MLOpsApplied statistical modellingRegressions, tests, confidence intervals and critical reading of results, on company data.DATA-2032 days