PES-intro-data-analysis-guest-lecture

A brief intro to data analysis for PES students

Installation of Jupyter with anaconda

If you install Jupyter through anaconda, you will by default get a lot of the scientific packages associated with Anaconda like pandas and matplotlib and there will not be a requirement to install them separately.

Installation Instructions

Topics Covered

1. What is data analysis? (Open to students)

2. What is the end goal of data analysis?

• Use answers to questions posed about the data to create change in business, government, education, etc.

3. Steps involved in data analysis:

• Choose the population of interest
• Sample from this population
• Analyze the sample
• Draw inferences about the population based on the sample(Inference)

4. Packages:

• Pandas(Helps with data analysis of data in tabular like format)
• matplotlib(plotting)

5. File formats

• What is CSV
• What do the rows and columns represent?

6. Frame questions about the data (Open to students)

• Number of people with different types of education levels
• Relationship between education and salary
• Relationship between age and salary

7. Types of data:

• Qualitative/Categorical
• Quantitative

8. Plots & Measures for each data type:

• Qualitative: bar graph
• Quantitative measures:
  1. Mean vs median
  2. Quartiles
• Quantitative: histogram, box plot

9. Relationship between variables

• Quantitative vs Quantitative: scatter-plot
• Quantitative vs Categorical: Side-by-side box plots

10. New data structures introduced

• dataframe
• series