Open workspace
Tools 0.1The video for this lesson is on its way.

Everything else is ready: study the parts, the key terms and the quiz below.

  1. Part 11The Python language, and the libraries built on it
  2. Part 22pandas, matplotlib, NumPy and scikit-learn, on one file
Tools 0.1Overview2 parts

Why These Tools

Say what this track is for, what the four libraries are, and in what order we take them.

Loading your progress…Next: 1.1 Why NumPy

In this lesson2 parts

  1. 01The Python language, and the libraries built on it
  2. 02pandas, matplotlib, NumPy and scikit-learn, on one file

Quiz 5 questions

Answer each one in your head, or on paper, before you check it. Getting one wrong here is how the lesson sticks.

  1. 01

    The raw file loads as (2921, 11) and the cleaned table is (2919, 11). Two rows left. Name both reasons.

  2. 02

    raw.loc[1, "revenue"] returns '1,275.86' — with quotation marks around it. Why can a model not use that column as it stands, and which of the four libraries fixes it?

  3. 03

    Thirty eight point seven percent of shop-days sell out. A model that always answers "no sellout" scores 0.614 on the test set. Where does that number come from, and why is it the number to beat rather than zero?

  4. 04

    X.shape is (2919, 4) and X.dtype is float64. The table it came from has eleven columns and holds dates and weather words. What happened to the other seven columns, and why does the array have one dtype when the table did not?

  5. 05

    The chart this video saved reads back as (250, 400, 4), and three of them stacked is (3, 250, 400, 4). What does each of those four numbers count, and what is the same object called once a deep learning library holds it?

Builds on

This lesson stands on its own. These go deeper into what it uses.

  • Python Modules 1–4