bp Data Science Foundational Bootcamp
Issued by
bp
Earners have completed a hands-on, intensive online training of foundational Data Science practices. They have learned the fundamentals of programming using Python and obtained skills that lead to uncovering greater insights and promote data-driven decision making. They have gained the knowledge needed to move beyond the limitations of traditional spreadsheets, making it possible to work with large datasets and streamline, improve and automate workflows used in real-world data applications.
- Type Learning
- Level Foundational
- Time Days
- Cost Free
Skills
Earning Criteria
-
The earner completed at least 7 out of 10 core mini-projects. A completed mini-project means scoring at least a 90% on each question of the mini-project.
-
Two of the mini-projects focus on Python fundamentals. The earner demonstrated ability to write Python code to work with fundamental data structures such as lists (including appending to lists, modifying and sorting lists, list slicing, indexing etc.), work with dictionaries (dictionary lookup, adding keys, finding the key associated with largest value and more), work with sets, write for and while loops as well as compose list and dictionary comprehensions.
-
In the mini-project focused on Python functions and string manipulation, earner has written custom functions that included working with various fundamental data structures and Python string processing. Tasks completed required understanding function scope, input arguments, the return statement and function calling.
-
The regular expressions mini project required the earner to build and use regular expressions using Python’s regular expressions library. The earner constructed a regular expression that given a telephone number (given in a variety of formats) extracted sub parts of the phone number if the phone number was valid. They wrote a Python function that accepts a list of strings and returns a list of tuples that contain the relevant parts of each phone number for all strings of the input list.
-
In the NumPy mini-project, the earner demonstrated the use of basic NumPy functions and manipulations to compute various statistics on the Iris data set. They used indexing, filtering with conditional indexing, aggregation functions such as sum, mean and median, and made use of NumPy broadcasting.
-
Four of the core mini-projects tested the earner’s data wrangling skills using Python’s pandas library. The introductory pandas mini-project required the earner to load a CSV file into pandas, set a given column as the index of the data frame and use indexing and filtering to select different columns and rows in order to answer a variety of data wrangling questions.
-
Two more advanced pandas mini-projects tested the earner’s ability to combine multiple data frames, use grouping and aggregating pandas operations as well as apply custom functions. In the timeseries pandas mini-project the earner operated with timeseries sales data, resampled the original data and computed various statistics.
-
In the SQL mini-project, the earner worked with a SQL database containing two tables, one containing customer information and the other included information about advertisements that were served to the customers on websites they have visited, and whether or not a customer clicked on the advertisement or not. The earner wrote and executed queries against this database to understand customer properties and estimate the ad 'click-through rate’.