In [3]:
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib.colors import LinearSegmentedColormap
# Define a grayscale colormap
grayscale = LinearSegmentedColormap.from_list(
'Grayscale', ['#f0f0f0', '#d0d0d0', '#b0b0b0', '#808080', '#000000']
)
# Load the data
df = pd.read_excel('/content/drive/MyDrive/Tadeo/MiTesis/Articulos/SupplementaryMaterial/Supplement_ExcelData_03092024.xlsx', sheet_name='Merge1')
# Total Fertility Rate (TFR)
df['tasa_fecundidad_global'] = (
(df['Maternidad 15 a 19 años'] / df['Afiliadas 15 a 19 años']) +
(df['Maternidad 20 a 24 años'] / df['Afiliadas 20 a 24 años']) +
(df['Maternidad 25 a 29 años'] / df['Afiliadas 25 a 29 años']) +
(df['Maternidad 30 a 34 años'] / df['Afiliadas 30 a 34 años']) +
(df['Maternidad 35 a 39 años'] / df['Afiliadas 35 a 39 años']) +
(df['Maternidad 40 a 44 años'] / df['Afiliadas 40 a 44 años']) +
(df['Maternidad 45 a 49 años'] / df['Afiliadas 45 a 49 años'])
) * 5
# Infant Fertility Rate (10-14 years)
df['tasa_fertilidad_infantil'] = (df['Maternidad infantil'] / df['Afiliadas 10 a 14 años']) * 1000
# Adolescent Fertility Rate (15-19 years)
df['tasa_fertilidad_adolescente'] = (df['Maternidad 15 a 19 años'] / df['Afiliadas 15 a 19 años']) * 1000
# Early Fertility Rate (<19 years)
df['tasa_fertilidad_Precoz'] = (
(df['Maternidad infantil'] + df['Maternidad 15 a 19 años']) /
(df['Afiliadas 10 a 14 años'] + df['Afiliadas 15 a 19 años']) * 1000
)
# Function to plot heatmaps
def plot_heatmap(data, title, cbar_label):
plt.figure(figsize=(14, 10))
sns.heatmap(
data,
annot=True,
cmap=grayscale,
fmt='.2f',
linewidths=0.5,
linecolor='black',
cbar_kws={'label': cbar_label}
)
plt.title(title, fontsize=16)
plt.ylabel('Department', fontsize=12)
plt.xlabel('Year', fontsize=12)
plt.xticks(rotation=45, ha='right')
plt.yticks(rotation=0)
plt.tight_layout()
plt.show()
#======================= Infant Fertility ============================================================
# Create heatmap for infant fertility rate
pivot_table_infantil = df.pivot_table(
values='tasa_fertilidad_infantil',
index='Departamento',
columns='Año',
aggfunc='mean'
)
# Add a total row for average infant fertility rate across the period
total_row_infantil = pd.DataFrame(pivot_table_infantil.mean(axis=0)).T
total_row_infantil.index = ['Total']
pivot_table_infantil = pd.concat([total_row_infantil, pivot_table_infantil])
# Sort by the average infant fertility rate in the period, highest to lowest
sorted_departments_infantil = pivot_table_infantil.iloc[1:].mean(axis=1).sort_values(ascending=False).index
pivot_table_infantil = pivot_table_infantil.loc[['Total'] + list(sorted_departments_infantil)]
# Draw heatmap for infant fertility rate
plot_heatmap(pivot_table_infantil, 'Infant Fertility Rate', '1,000 women (10-14 years)')
#======================= Adolescent Fertility =======================================================
# Create heatmap for adolescent fertility rate
pivot_table_adolescente = df.pivot_table(
values='tasa_fertilidad_adolescente',
index='Departamento',
columns='Año',
aggfunc='mean'
)
# Add a total row for average adolescent fertility rate across the period
total_row_adolescente = pd.DataFrame(pivot_table_adolescente.mean(axis=0)).T
total_row_adolescente.index = ['Total']
pivot_table_adolescente = pd.concat([total_row_adolescente, pivot_table_adolescente])
# Sort by the average adolescent fertility rate in the period, highest to lowest
sorted_departments_adolescente = pivot_table_adolescente.iloc[1:].mean(axis=1).sort_values(ascending=False).index
pivot_table_adolescente = pivot_table_adolescente.loc[['Total'] + list(sorted_departments_adolescente)]
# Draw heatmap for adolescent fertility rate
plot_heatmap(pivot_table_adolescente, 'Adolescent Fertility Rate', '1,000 women (15-19 years)')
#======================= Early Fertility =============================================================
# Create heatmap for early fertility rate (infant + adolescent)
pivot_table_precoz = df.pivot_table(
values='tasa_fertilidad_Precoz',
index='Departamento',
columns='Año',
aggfunc='mean'
)
# Add a total row for average early fertility rate across the period
total_row_precoz = pd.DataFrame(pivot_table_precoz.mean(axis=0)).T
total_row_precoz.index = ['Total']
pivot_table_precoz = pd.concat([total_row_precoz, pivot_table_precoz])
# Sort by the average early fertility rate in the period, highest to lowest
sorted_departments_precoz = pivot_table_precoz.iloc[1:].mean(axis=1).sort_values(ascending=False).index
pivot_table_precoz = pivot_table_precoz.loc[['Total'] + list(sorted_departments_precoz)]
# Draw heatmap for early fertility rate
plot_heatmap(pivot_table_precoz, 'Early Fertility Rate', '1,000 women (10-19 years)')
#======================= Total Fertility =============================================================
# Create heatmap for total fertility rate (TFR)
pivot_table_general = df.pivot_table(
values='tasa_fecundidad_global',
index='Departamento',
columns='Año',
aggfunc='mean'
)
# Add a total row for average total fertility rate across the period
total_row_general = pd.DataFrame(pivot_table_general.mean(axis=0)).T
total_row_general.index = ['Total']
pivot_table_general = pd.concat([total_row_general, pivot_table_general])
# Sort by the average total fertility rate in the period, highest to lowest
sorted_departments_general = pivot_table_general.iloc[1:].mean(axis=1).sort_values(ascending=False).index
pivot_table_general = pivot_table_general.loc[['Total'] + list(sorted_departments_general)]
# Draw heatmap for total fertility rate
plot_heatmap(pivot_table_general, 'Total Fertility Rate', 'Births per woman during fertility period (15-49 years)')
