Week 14 - Machine Learning - (Supervised Learning) Visualizing Data for Regression for automobile prices from Principles of M.L. Python by Microsoft Learning

Liaw Bei Le · June 24, 2021

Learning   Python   Machine Learning   Matplotlib   Seaborn   Pandas
  • Visualizing Data for Regression
  • Exploratory data analysis
  • Matplotlib, Pandas plotting & Seaborn
  • Different chart types:
    • Single axis view of data:
      • Univariate plot types
        • Bar charts
        • Histograms
        • Kernel density estimation (kde) plots
        • Combining histograms and kdes
      • 2-dimensional plot types
        • Scatter plots
        • Dealing with Overplotting
          • transparency
          • Countour plots or 2d density plots
          • Hexbin plots
        • For categorical (non-numeric) variables:
          • Box plots
          • Violin plots
      • Using Aesthetics
        • Marker shape, size and colour
    • Multi-axis views of data
      • Pair-wise scatter plots or scatter plot matrices
      • Conditioned plots, facetted plots or small multiple plots use group-by operations

These are my notes taken from Microsoft Learning’s Principles of Machine Learning in Python - Module 2.

What I learnt:

Visualizing Data for Regression

Method: Visualize and explore data (exploratory data analysis) by summarizing data & developing multiple views of data using multiple chart types.

Goal: To explore a dataset about automobile pricing to determine which features may be useful in predicting automobile prices.

  • to understand the relationships between the data columns.
  • to identify features that may be useful for predicting labels

I have reviewed and went through Visualizing Data for Regression for automobile prices in this link.

Twitter, Facebook