Visualization Example

import pandas as pd
import plotly.express as px

# Assume 'resultados' is available from batch processing
df = pd.DataFrame(resultados)
print(f"TOTAL STUDENTS ANALYZED: {len(df)}")

if not df.empty:
    # CHART 1: Talent Map (University > Profile)
    if 'universidad' in df.columns and 'tipo_perfil' in df.columns:
        fig1 = px.sunburst(
            df, 
            path=['universidad', 'tipo_perfil'],
            title="Youth Talent Distribution (University > Specialty)",
            color='universidad',
            color_discrete_sequence=px.colors.qualitative.Bold
        )
        fig1.show()
else:
    print("No data extracted. Make sure batch processing ran successfully.")

if 'ciclo_actual' in df.columns:
    # Sort by current cycle
    df_sorted = df.sort_values(by='ciclo_actual')

    fig2 = px.bar(
        df_sorted, 
        x='nombre', 
        y='ciclo_actual',
        color='tipo_perfil',
        title="Academic Ranking: Students by Cycle and Profile",
        text='ciclo_actual',
        labels={
            'ciclo_actual': 'Academic Cycle', 
            'nombre': 'Student'
        }
    )

    fig2.update_traces(textposition='outside')
    fig2.update_layout(xaxis_tickangle=-45)
    fig2.show()

print("\n📊 INTERNSHIP DATABASE:")

cols_a_mostrar = [
    'nombre', 
    'universidad', 
    'ciclo_actual', 
    'tipo_perfil', 
    'stack_principal', 
    'potencial_contratacion'
]

# Only show columns that exist
cols_finales = [c for c in cols_a_mostrar if c in df.columns]

# Display the DataFrame
from IPython.display import display
display(df[cols_finales])

import pandas as pd
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.graph_objects as go

# Load data
df = pd.DataFrame(resultados)
print(f"TOTAL STUDENTS ANALYZED: {len(df)}")

if not df.empty:
    # Create figure with subplots
    from plotly.subplots import make_subplots
    
    # Chart 1: Sunburst - University distribution
    if 'universidad' in df.columns and 'tipo_perfil' in df.columns:
        fig1 = px.sunburst(
            df, 
            path=['universidad', 'tipo_perfil'],
            title="Youth Talent Distribution (University > Specialty)",
            color='universidad',
            color_discrete_sequence=px.colors.qualitative.Bold
        )
        fig1.show()
    
    # Chart 2: Bar - Academic ranking
    if 'ciclo_actual' in df.columns:
        df_sorted = df.sort_values(by='ciclo_actual')
        
        fig2 = px.bar(
            df_sorted, 
            x='nombre', 
            y='ciclo_actual',
            color='tipo_perfil',
            title="Academic Ranking: Students by Cycle and Profile",
            text='ciclo_actual',
            labels={'ciclo_actual': 'Academic Cycle', 'nombre': 'Student'}
        )
        
        fig2.update_traces(textposition='outside')
        fig2.update_layout(xaxis_tickangle=-45)
        fig2.show()
    
    # Display final table
    print("\n📊 INTERNSHIP DATABASE:")
    cols_a_mostrar = [
        'nombre', 'universidad', 'ciclo_actual', 
        'tipo_perfil', 'stack_principal', 'potencial_contratacion'
    ]
    cols_finales = [c for c in cols_a_mostrar if c in df.columns]
    display(df[cols_finales])
else:
    print("No data extracted. Ensure batch processing ran without errors.")

# Extract and count all technologies
from collections import Counter

all_tech = []
for stack in df['stack_principal']:
    if isinstance(stack, list):
        all_tech.extend(stack)

tech_counts = Counter(all_tech)
tech_df = pd.DataFrame(tech_counts.most_common(10), 
                       columns=['Technology', 'Count'])

fig3 = px.bar(
    tech_df,
    x='Technology',
    y='Count',
    title="Top 10 Technologies Across All Candidates",
    color='Count',
    color_continuous_scale='Viridis'
)
fig3.show()

profile_counts = df['tipo_perfil'].value_counts()

fig4 = px.pie(
    values=profile_counts.values,
    names=profile_counts.index,
    title="Distribution of Profile Types",
    hole=0.3  # Creates a donut chart
)
fig4.show()