Solutions Python week 3

3.1

# Part 1: For loop – print numbers divisible by 3 or 5

numbers_divisible = []  # we will store the numbers divisible by 3 or 5 here

for n in range(1, 51):  # numbers from 1 to 50
    if (n % 3 == 0) or (n % 5 == 0):
        print(n)
        numbers_divisible.append(n)  # remember this number for later

# Part 2: While loop – cumulative sum of these numbers until it exceeds 200

cumulative_sum = 0
i = 0  # index for the list

while i < len(numbers_divisible) and cumulative_sum <= 200:
    cumulative_sum = cumulative_sum + numbers_divisible[i]
    i = i + 1  # move to the next number

3.2

import pandas as pd

# using the following dataframe
data = {
    "Region": ["A", "B", "A", "C", "B", "C", "A"],
    "EnergyUsage": [10, 20, 30, 40, 50, 60, 70],
    "Sustainable": [True, False, True, False, True, False, True]
}

df = pd.DataFrame(data)
print("Full DataFrame:")
print(df)

# --- Part 1: For loop – print rows with Sustainable == True and EnergyUsage > 20 

print("Rows where Sustainable is True and EnergyUsage > 20:")

# We loop over the row indices: 0, 1, 2, ...
for i in range(len(df)):
    row = df.iloc[i]  # get the i-th row
    if (row["Sustainable"] == True) and (row["EnergyUsage"] > 20):
        print(row)


# --- Part 2: While loop – cumulative EnergyUsage for Sustainable rows

cumulative_energy = 0
i = 0
contributing_indices = []  # we will store the row indices that contribute

# We continue while i is inside the dataframe AND cumulative_energy <= 50
while i < len(df) and cumulative_energy <= 50:
    row = df.iloc[i]
    if row["Sustainable"] == True:
        cumulative_energy = cumulative_energy + row["EnergyUsage"]
        contributing_indices.append(i)
    i = i + 1

print("Cumulative EnergyUsage from sustainable rows (stopped when > 50):")
print(cumulative_energy)

print("Rows that contributed to this cumulative EnergyUsage:")
print(df.iloc[contributing_indices])

3.3: Guess the secret number

import random

# Randomly select a secret number between 1 and 20
secret_number = random.randint(1, 20)

attempts = 0          # how many guesses the user has made
max_attempts = 5      # maximum number of allowed guesses

print("I have chosen a number between 1 and 20. Can you guess it?")

# Use a while loop to allow the user to guess
while attempts < max_attempts:
    guess = int(input("Enter your guess: "))
    attempts = attempts + 1

    if guess > secret_number:
        print("Too high!")
    elif guess < secret_number:
        print("Too low!")
    else:
        print("Correct!")
        print("You guessed it in", attempts, "attempt(s).")
        break  # stop the loop if the guess is correct

# This runs if the loop ends without a correct guess
if attempts == max_attempts and guess != secret_number:
    print("Game Over!")
    print("The secret number was:", secret_number)

3.4 Working with real data

# This was not part of the exercise, but to ensure you can run the script we create some data here to ensure it will always work.
data = {
    "Country": ["Netherlands", "Belgium", "France", "Germany", "Spain", "USA", "China", "Sweden"],
    "Continent": ["Europe", "Europe", "Europe", "Europe", "Europe", "North America", "Asia", "Europe"],
    "renewable_energy": [50, 30, 40, np.nan, 25, 80, 100, 60],   # some values, one missing (Germany)
    "total_energy":     [120, 100, 150, 200, np.nan, 300, 500, 90]  # some values, one missing (Spain)
}

# transform into a pandas dataframe for the functions to work
df = pd.DataFrame(data)


# ---------------------------------------------------------
# 2. Inspect the data
# ---------------------------------------------------------

print("First 10 rows of the dataset:")
print(df.head(10))

print("Column types:")
print(df.dtypes)

print("Summary statistics (describe):")
print(df.describe())

# ---------------------------------------------------------
# 3. Subset the data to European countries
# ---------------------------------------------------------

EU_data = df[df["Continent"] == "Europe"].copy()
print("Data for European countries (EU_data):")
print(EU_data)

# ---------------------------------------------------------
# 4. Compute renewable energy percentage
#     renewable_percentage = (renewable_energy / total_energy) * 100
# ---------------------------------------------------------

EU_data["renewable_percentage"] = (EU_data["renewable_energy"] / EU_data["total_energy"]) * 100
print("EU_data with renewable_percentage:")
print(EU_data)

# ---------------------------------------------------------
# 5. Classify countries by renewable_percentage
#    > 50%  -> "High Renewable"
#    20–50% -> "Medium Renewable"
#    else   -> "Low Renewable"
# ---------------------------------------------------------

def classify_renewable(pct):
    if pct > 50:
        return "High Renewable"
    elif pct >= 20 and pct <= 50:
        return "Medium Renewable"
    else:
        return "Low Renewable"

EU_data["renewable_category"] = EU_data["renewable_percentage"].apply(classify_renewable)
print("EU_data with renewable_category:")
print(EU_data)

# ---------------------------------------------------------
# 6. Using if/else to check for missing values
#    in renewable_energy or total_energy
# ---------------------------------------------------------

missing_mask = EU_data["renewable_energy"].isna() | EU_data["total_energy"].isna()
n_missing = missing_mask.sum()

if n_missing > 0:
    print("There are", n_missing, "rows with missing values in renewable_energy or total_energy.")
else:
    print("There are no missing values in renewable_energy or total_energy.")

# Optional: show the incomplete rows
if n_missing > 0:
    print("Rows with missing values:")
    print(EU_data[missing_mask])

# ---------------------------------------------------------
# 7. Group and summarize data
#    Group by renewable_category and compute the average
#    renewable_percentage for each category
# ---------------------------------------------------------

summary = (
    EU_data
    .groupby("renewable_category")["renewable_percentage"]
    .mean()
    .reset_index()
)

print("Average renewable_percentage by renewable_category:")
print(summary)