search

BreakoutMentors / Data-Science-and-Machine-Learning

Breakout Mentors deep dive lessons and resources on data science and machine learning. All materials are made easily accessible through Google Colab notebooks. Learn more about ML @ Breakout Mentors by visiting the website link below.
https://breakoutmentors.com/machine-learning-and-artificial-intelligence-academy/
MIT License
4 stars 4 forks source link

Enhance our in-house data visualization material #41

Open krmiddlebrook opened 1 year ago

krmiddlebrook commented 1 year ago

Why

Students lose interest when we use the Kaggle resources to teach them the basics of data visualization

Engineering Spec

Create/enhance our data visualization material. The material should highlight various types of plots and charts to effectively communicate insights from data. It should use matplotlib and seaborn for static plots and plotly for interactive plots. The material should be topical, interactive, and beginner friendly. Use the synthetic dataset we generated for middle and high school students to develop challenges. The challenges need to encourage students to experiment, customize the visualizations, and interpret the results to gain a better understanding of the data.

krmiddlebrook commented 1 year ago

Here is an example of tasks you might include in the data visualization material. Assuming a synthetic student performance dataset is available, here are several data visualization tasks that students can practice using the student performance dataset. Here are a few examples:

  1. Line Plot:

    • Visualize the trend of scores over time for a specific subject (e.g., Math, English, Art).
    • Plot the average score for each subject over time.

  2. Bar Chart:

    • Create a bar chart to compare the average scores across different subjects.
    • Generate a bar chart showing the top-performing students in each subject.

  3. Histogram:

    • Create a histogram to visualize the distribution of scores for a specific subject.
    • Plot histograms for multiple subjects to compare their score distributions.

  4. Scatter Plot:

    • Visualize the relationship between scores in different subjects (e.g., Math vs. English).
    • Create a scatter plot to explore the relationship between scores and exam dates.

  5. Box Plot:

    • Generate a box plot to compare the score distributions across different subjects.
    • Create a box plot to identify any outliers in the scores for each subject.

  6. Heatmap:

    • Create a heatmap to visualize the correlation between scores in different subjects.
    • Generate a heatmap to explore any patterns or trends in scores across different exam dates.

These tasks will help students practice using various types of plots and charts to effectively communicate insights from the data. They can use popular data visualization libraries like Matplotlib or Seaborn in Python to create static visualizations and plotly for interactive ones. Encourage them to experiment, customize the visualizations, and interpret the results to gain a better understanding of the data.