Solutions Python week 2

Exercises part 1

if emissions < 2:
    print("Low Emissions.")
elif emissions >= 2 and emissions < 6:
    print("Moderate Emissions.")
elif emissions >= 6 and emissions < 15:
    print("High Emissions.")
else:
    print("Very High Emissions.")

Ecercises part 2

import numpy as np
import pandas as pd

# 1. Create a 10 by 10 matrix filled with 1s
matrix_10x10 = np.ones((10, 10))
print("10x10 matrix filled with 1s:")
print(matrix_10x10)

# 2. Multiply each element of this matrix by 5
matrix_10x10_times_5 = matrix_10x10 * 5
print("10x10 matrix multiplied by 5:")
print(matrix_10x10_times_5)

# 3. Compute the sum of all elements in this matrix
sum_elements = np.sum(matrix_10x10_times_5)
print("Sum of all elements in the 10x10 matrix multiplied by 5:")
print(sum_elements)

# 4. Create a 3 by 3 matrix filled with random values (like runif() in R)
matrix_3x3_random = np.random.rand(3, 3)
print("3x3 matrix filled with random values:")
print(matrix_3x3_random)

# 5. Create a dataframe with 3 columns: ID, Country, Value
data = {
    "ID": [1, 2, 3],
    "Country": ["NL", "BE", "FR"],
    "Value": [1340.90, 142.23, 821.42]
}

df = pd.DataFrame(data)
print("DataFrame with ID, Country, Value:")
print(df)

# 6. Multiply the first column of the 3x3 matrix with the Value column of the dataframe
first_column_matrix = matrix_3x3_random[:, 0]  # first column of the random matrix
result_multiplication = first_column_matrix * df["Value"]

print("First column of 3x3 matrix:")
print(first_column_matrix)

print("Result of multiplying first column of matrix with Value column of DataFrame:")
print(result_multiplication)

Exercise part 4 & 5

import pandas as pd

# 4.1
# We can join the datasets with a left join since they all have the same countries

all_data = EU_countries_water_pollution.merge(
    EU_countries_GDP,
    on="Country",
    how="left"
)

all_data = all_data.merge(
    EU_countries_population_pollution,
    on="Country",
    how="left"
)

# 4.2
# Compute the GDP per capita
all_data["GDP_per_capita"] = all_data["GDP_USD_Billions"] / all_data["Population"]
print(all_data)

# On average, what percentage of water bodies are in poor condition in Europe?
mean_poor_condition = all_data["Water_Bodies_in_Poor_Condition_Percentage"].mean()
print(mean_poor_condition)
# Example output might be: 49.07407

# Create a dataset with countries that have a Mean_pollution higher than 15,
# call this dataset EU_higher_than_fifteen

EU_higher_than_fifteen = all_data[all_data["Mean_pollution"] > 15]
print(EU_higher_than_fifteen)

Exercise part 6

import pandas as pd
import os

# 1. Create a DataFrame with 4 columns
data = {
    "ID": [1, 2, 3],
    "Country": ["NL", "BE", "FR"],
    "Value": [10.5, 20.3, 30.7],
    "Category": ["A", "B", "C"]
}

df = pd.DataFrame(data)

print("DataFrame:")
print(df)

# 2. Export the DataFrame to an .xlsx file
df.to_excel("toy_data.xlsx", index=False)

# 3. Export the same DataFrame to a .pkl file
df.to_pickle("toy_data.pkl")