CO2 Emissions Evaluation and Bicycle Market Analysis Python

# Import the pandas and numpy packages (pandas as pd and numpy as np)
# We use "Aliasing" to redefine python libraries with another variable to make it easier to use again.
import pandas as pd
import numpy as np

# we Load the data by using 'read_csv' pandas function
cars = pd.read_csv('data/co2_emissions_canada.csv')

# create numpy arrays
cars_makes = cars['Make'].to_numpy()
cars_models = cars['Model'].to_numpy()
cars_classes = cars['Vehicle Class'].to_numpy()
cars_engine_sizes = cars['Engine Size(L)'].to_numpy()
cars_cylinders = cars['Cylinders'].to_numpy()
cars_transmissions = cars['Transmission'].to_numpy()
cars_fuel_types = cars['Fuel Type'].to_numpy()
cars_fuel_consumption = cars['Fuel Consumption Comb (L/100 km)'].to_numpy()
cars_co2_emissions = cars['CO2 Emissions(g/km)'].to_numpy()

# Preview the dataframe
cars

# Look at the first ten items in the CO2 emissions array
cars_co2_emissions[:10]

# >>>> 1)
# To calculate the median of engine size in liters, we use the function 'median()'
cars['Engine Size(L)'].median()

# >>>> 2)
# In Pandas, to calculate the average of values, we use the function 'mean()'

# Calculate the average fuel consumption for regular gasoline
avg_reg_gas = cars.loc[cars['Fuel Type'] == 'X', 'Fuel Consumption Comb (L/100 km)'].mean()

# Calculate the average fuel consumption for premium gasoline
avg_prem_gas = cars.loc[cars['Fuel Type'] == 'Z', 'Fuel Consumption Comb (L/100 km)'].mean()

# Calculate the average fuel consumption for ethanol
avg_ethanol = cars.loc[cars['Fuel Type'] == 'E', 'Fuel Consumption Comb (L/100 km)'].mean()

# Calculate the average fuel consumption for diesel
avg_diesel = cars.loc[cars['Fuel Type'] == 'D', 'Fuel Consumption Comb (L/100 km)'].mean()

# Print the results
print('Average fuel consumption for regular gasoline: {:.2f} L/100 km'.format(avg_reg_gas))
print('Average fuel consumption for premium gasoline: {:.2f} L/100 km'.format(avg_prem_gas))
print('Average fuel consumption for ethanol: {:.2f} L/100 km'.format(avg_ethanol))
print('Average fuel consumption for diesel: {:.2f} L/100 km'.format(avg_diesel))

# >>>> 3)

# To calculate the relationship between fuel consumption and carbon dioxide emissions,
# we use the function 'corr()', which takes a parameter inside
corr = cars['Fuel Consumption Comb (L/100 km)'].corr(cars['CO2 Emissions(g/km)']).round(2)
corr

# >>>> 4)

# Calculate the mean CO2 emissions for SUV - SMALL vehicles
suv_co2 = cars.loc[cars['Vehicle Class'] == 'SUV - SMALL', 'CO2 Emissions(g/km)'].mean()
print('SUV - SMALL :', suv_co2.round(2))

# Calculate the mean CO2 emissions for MID-SIZE vehicles
midsize_co2 = cars.loc[cars['Vehicle Class'] == 'MID-SIZE', 'CO2 Emissions(g/km)'].mean()
print('MID-SIZE :', midsize_co2.round(2))

print('After looking at the two results together, I see that \'MID-SIZE\' is the lower average value')

# >>>> 5)

# Calculate the mean CO2 emissions for all vehicles using the function 'mean()'
all_co2 = cars['CO2 Emissions(g/km)'].mean()
print(all_co2.round(2))

# Calculate the mean CO2 emissions for vehicles with condition of 'engine size <= 2.0' using 'mean()' function
small_engine_co2 = cars.loc[cars['Engine Size(L)'] <= 2.0, 'CO2 Emissions(g/km)'].mean()
print(small_engine_co2.round(2))

# >>>> 6)
# We also have a question mark about a number of things that remain opaque in our dataset,
# like the relationship between engine size and fuel consumption or CO2 emissions.
# In the following statements, we will try to answer these questions through the code.

# Calculate the correlation between engine size and fuel consumption
corr_fc = cars['Engine Size(L)'].corr(cars['Fuel Consumption Comb (L/100 km)'])

# Calculate the correlation between engine size and CO2 emissions
corr_co2 = cars['Engine Size(L)'].corr(cars['CO2 Emissions(g/km)'])

# Print the results
print('Correlation between engine size and fuel consumption: {:.2f}'.format(corr_fc))
print('Correlation between engine size and CO2 emissions: {:.2f}'.format(corr_co2))