myprojects-hg-reborn

Fork

import pandas as pd
import matplotlib.pyplot as plt

# Define the Herfindahl-Hirschman Index (HHI) function
def hhi_index(x):
    y = x / x.sum()
    res = (y**2).sum()
    return res

# Load the dataset
df = pd.read_csv("../../input/scb_data_for_figures-19-02-2024.tar.gz", compression='gzip')

# Clean column names (convert to lowercase and replace spaces with underscores)
df.columns = df.columns.str.lower().str.replace(' ', '_')

# Group by 'expenditure_year' and 'member_state_2_letter_codes' and summarize
df_hhi = (df.groupby(['expenditure_year', 'member_state_2_letter_codes'])
            .agg(exp_eur_bn=('aid_element_eur_bn', 'sum'),
                 ms_gdp_eur_bn=('gdp_eur_bn', 'first'))
            .reset_index())

# Group by 'expenditure_year', calculate shares, and then calculate HHI
df_hhi = (df_hhi.groupby('expenditure_year')
            .apply(lambda x: pd.Series({
                'hhi_aid': hhi_index(x['exp_eur_bn'] / x['exp_eur_bn'].sum()) * 1e4,
                'hhi_gdp': hhi_index(x['ms_gdp_eur_bn'] / x['ms_gdp_eur_bn'].sum()) * 1e4
            }))
            .reset_index())


# Plot hhi_aid against expenditure_year (First Plot)
plt.figure(figsize=(10, 6))
## plt.plot(df_hhi['hhi_aid'], df_hhi['expenditure_year'], 'g-', label='HHI Aid vs Year (reversed)')  # Green line for reverse plot
plt.plot(df_hhi['expenditure_year'], df_hhi['hhi_aid'], 'b-', label='Year vs HHI Aid')  # Blue line for standard plot

plt.plot(df_hhi['expenditure_year'], df_hhi['hhi_gdp'], 'b-', label='Year vs HHIGDP')  # Blue line for standard plot


# Add labels and title
plt.xlabel('Expenditure Year')
plt.ylabel('HHI Aid')
plt.title('HHI Aid Over Time')

# Display the legend and plot
plt.legend()
plt.show()