Lesson 11: Module 6 Hands-on Projects

In this final project for Module 6, you will act as a Data Scientist at a major firm. Your job is to take a raw dataset, clean it, summarize it, and visualize the findings into a report.

---

Project 1: The Stock Pulse (Finance Focus)

Objective: Analyze 5 years of stock price data to find the best time to buy.

• Data: Download a CSV of any stock (AAPL, TSLA, BTC) from Yahoo Finance.
• Tasks:
  1. Calculate the Daily Returns (Percentage change from day to day).
  2. Use a Rolling Window to find the 50-day moving average.
  3. Create a Line Chart with both the price and the moving average.
  4. Highlight days where the price dropped by more than 5% using a Scatter plot.

Project 2: Climate Watch (Science Focus)

Objective: Identify if your city is actually getting hotter.

• Data: Get weather data from NOAA or any weather API.
• Tasks:
  1. Group the data by Year.
  2. Calculate the Max Temp and Min Temp per year.
  3. Create a Seaborn Bar Plot showing the average temperature trend over time.
  4. Identify the 5 hottest years on record using sort_values().

Project 3: The Personal Habit Tracker (Life Focus)

Objective: Find out if your sleep affects your productivity.

• Data: Create a CSV with your own data for the last 30 days (Date, Sleep_Hours, Cups_of_Coffee, Productivity_Score).
• Tasks:
  1. Create a Seaborn Heatmap to see the correlation between Coffee and Productivity.
  2. Create a Violin Plot of Productivity partitioned by Sleep Hours (e.g., < 6 hrs, 6-8 hrs, > 8 hrs).
  3. Clean any days where you forgot to record data.

---

Module 6 Recap: Exercises and Quiz

Exercise 1: The Filter Expert

Take a NumPy array of 100 random numbers. Use a Boolean Mask to replace every number greater than 50 with the value 999.

Exercise 2: The Multi-aggregator

Take a Pandas DataFrame of Sales data. Group by Region and Product_Type. Calculate the sum of Sales and the mean of Price in one line using .agg().

---

Module 6 Quiz

1. Which library is the foundation for almost all numerical computing in Python? A) Pandas B) Seaborn C) NumPy D) Matplotlib

2. In a 2D NumPy array, what does axis=1 refer to? A) Columns B) Rows C) The whole array D) The labels

3. What is the main structural difference between a Series and a DataFrame in Pandas? A) Series is faster B) DataFrame is for strings only C) Series is 1D, DataFrame is 2D D) There is no difference

4. Which visualization is best for showing a trend over time? A) Bar Chart B) Heatmap C) Scatter Plot D) Line Chart

5. What is the purpose of the hue parameter in Seaborn? A) To change the font size B) To color data based on a category C) To highlight the highest value D) To remove outliers

---

Quiz Answers

1. C | 2. B | 3. C | 4. D | 5. B

---

Conclusion

You have officially entered the world of Data Science. You can now take a raw file and turn it into a clear, visual story.

But wait... we've used our brains to find patterns. Can we teach a Computer to find these patterns for us? In Module 7: Introduction to AI and Machine Learning, we’ll take our Data Science skills and use them to build Predictive Models!