import pandas as pd # Assuming you have a DataFrame named 'pwt_data' with the relevant columns # Capital per Capita pwt_data['Capital_per_Capita'] = pwt_data['Capital_Stock'] / pwt_data['Population'] # Capital per Worker pwt_data['Capital_per_Worker'] = pwt_data['Capital_Stock'] / pwt_data['Number_of_Persons_Engaged'] # Capital per Effective Worker pwt_data['Capital_per_Effective_Worker'] = pwt_data['Capital_Stock'] / (pwt_data['Number_of_Persons_Engaged'] * pwt_data['Average_Annual_Hours_Worked_per_Person_Engaged']) # Capital per Unit of Effective Labor pwt_data['Capital_per_Unit_of_Effective_Labor'] = pwt_data['Capital_Stock'] / (pwt_data['Human_Capital_Index'] * pwt_data['Average_Annual_Hours_Worked_per_Person_Engaged']) # GDP per Capita pwt_data['GDP_per_Capita'] = pwt_data['GDP_at_Constant_2017_National_Prices'] / pwt_data['Population'] # GDP per Worker pwt_data['GDP_per_Worker'] = pwt_data['GDP_at_Constant_2017_National_Prices'] / pwt_data['Number_of_Persons_Engaged'] # GDP per Human Capital pwt_data['GDP_per_Human_Capital'] = pwt_data['GDP_at_Constant_2017_National_Prices'] / pwt_data['Human_Capital_Index'] # GDP per Unit of Effective Labor pwt_data['GDP_per_Unit_of_Effective_Labor'] = pwt_data['GDP_at_Constant_2017_National_Prices'] / (pwt_data['Human_Capital_Index'] * pwt_data['Average_Annual_Hours_Worked_per_Person_Engaged']) # Display the updated DataFrame print(pwt_data)

import matplotlib.pyplot as plt # Assuming you have a DataFrame named 'pwt_data' with the relevant columns # Define the years of interest years_of_interest = [1950, 1970, 1990, 2010, pwt_data['Year'].max()] # Loop through the years and create scatter plots for year in years_of_interest: # Filter data for the specific year data_for_year = pwt_data[pwt_data['Year'] == year] # Scatter plot plt.figure(figsize=(10, 6)) plt.scatter(data_for_year['GDP_at_Constant_2017_National_Prices'], data_for_year['Capital_Stock'], alpha=0.7) plt.title(f'Relation between GDP and Capital ({year})') plt.xlabel('GDP at Constant 2017 National Prices') plt.ylabel('Capital Stock') plt.grid(True) # Save the plot file_path = f'./graphs/scatter_plot_gdp_vs_capital_{year}.png' plt.savefig(file_path) print(f'Plot saved as PNG: {file_path}') # Show the plot (optional) plt.show()

import matplotlib.pyplot as plt import seaborn as sns # Assuming you have a DataFrame named 'pwt_data' with the relevant columns # and columns like 'Income_Group' and 'Region' that represent income groups and regions # List of measures measures = [ 'GDP', 'Capital_per_Capita', 'Capital_per_Worker', 'Capital_per_Effective_Worker', 'Capital_per_Unit_of_Effective_Labor' ] # Loop through measures for measure in measures: # Separate figures for each income group plt.figure(figsize=(12, 8)) sns.set_palette("husl") for income_group in pwt_data['Income_Group'].unique(): data_income_group = pwt_data[pwt_data['Income_Group'] == income_group] plt.plot(data_income_group['Year'], data_income_group[measure], label=income_group) plt.title(f'Evolution of {measure} by Income Group') plt.xlabel('Year') plt.ylabel(measure) plt.legend() plt.grid(True) # Save the plot file_path = f'./graphs/line_plot_{measure}_by_income_group.png' plt.savefig(file_path) print(f'Plot saved as PNG: {file_path}') # Show the plot (optional) plt.show() # Separate figures for each region plt.figure(figsize=(12, 8)) sns.set_palette("husl") for region in pwt_data['Region'].unique(): data_region = pwt_data[pwt_data['Region'] == region] plt.plot(data_region['Year'], data_region[measure], label=region) plt.title(f'Evolution of {measure} by Region') plt.xlabel('Year') plt.ylabel(measure) plt.legend() plt.grid(True) # Save the plot file_path = f'./graphs/line_plot_{measure}_by_region.png' plt.savefig(file_path) print(f'Plot saved as PNG: {file_path}') # Show the plot (optional) plt.show()

import seaborn as sns import matplotlib.pyplot as plt # Assuming you have a DataFrame named 'pwt_data' with relevant columns # Select the variables for which you want to plot the KDEs variables = ['Log_Income_Per_Capita', 'Log_Capital_Per_Worker'] # Extract the years you want to include in the plots selected_years = list(range(1950, pwt_data['Year'].max() + 1, 10)) selected_years.append(pwt_data['Year'].max()) # Filter data for the selected years selected_data = pwt_data[pwt_data['Year'].isin(selected_years)] # Loop through variables and create KDE plots for variable in variables: # Separate figures for each variable plt.figure(figsize=(12, 8)) sns.set_palette("husl") # Loop through years and create subplots for year in selected_years: data_for_year = selected_data[selected_data['Year'] == year] sns.kdeplot(data=data_for_year, x=variable, label=str(year), fill=False) plt.title(f'Distribution of {variable} Every 10 Years') plt.xlabel(variable) plt.ylabel('Density') plt.legend() plt.grid(True) # Save the plot file_path = f'./graphs/kde_plot_{variable}_every_10_years.png' plt.savefig(file_path) print(f'Plot saved as PNG: {file_path}') # Show the plot (optional) plt.show()