[WIP] Add advanced descriptive analysis for statistical study

[Copilot]

Thanks for asking me to work on this. I will get started on it and keep this PR's description up to date as I form a plan and make progress.

Original prompt

✅ ANÁLISIS ESTADÍSTICO COMPLETO - FASE 1
Perfecto. Comenzamos análisis estadístico riguroso.

📊 PARTE 1: ANÁLISIS DESCRIPTIVO AVANZADO
python
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import warnings
warnings.filterwarnings('ignore')

Cargar datos (si no están ya cargados)

try:
df = pd.read_csv('cicy_data_analysis.csv')
except:
# Si no existe, usar datos generados
print("⚠️ Usando datos de ejemplo. Si tienes datos reales, cárgalos.")
np.random.seed(42)
n_samples = 500
df = pd.DataFrame({
'h11': np.random.randint(1, 25, n_samples),
'h21': np.random.randint(1, 100, n_samples)
})
df['N'] = df['h11'] + df['h21']
df['chi'] = 2 * (df['h11'] - df['h21'])

Calcular métricas de complejidad estimadas

df['log_N'] = np.log(df['N'])
df['sqrt_N'] = np.sqrt(df['N'])
df['ratio_h'] = df['h11'] / np.maximum(df['h21'], 1)

Métrica de complejidad proxy (mejorada)

def improved_complexity_estimate(row):
"""Métrica de complejidad mejorada basada en literatura"""
N = row['N']
h11, h21 = row['h11'], row['h21']

# Factores basados en literatura:
# 1. N contribuye logarítmicamente
# 2. Asimetría h11/h21 añade complejidad
# 3. Valor absoluto de χ indica topología no trivial
log_term = np.log(N + 1)
asym_term = np.abs(np.log((h11 + 1) / (h21 + 1)))
chi_term = np.log(np.abs(row['chi']) + 1)

return 2.0 * log_term + 1.5 * asym_term + 0.5 * chi_term

df['complexity'] = df.apply(improved_complexity_estimate, axis=1)

print("📋 DATOS PREPARADOS:")
print(f"Muestras: {len(df)}")
print(f"Variables: {df.columns.tolist()}")
print("\n" + "="*60)
🔍 PARTE 2: ANÁLISIS DE DISTRIBUCIÓN
python

Configuración de visualización

plt.style.use('seaborn-v0_8-darkgrid')
fig = plt.figure(figsize=(16, 12))

1. Distribución de N

ax1 = plt.subplot(3, 3, 1)
ax1.hist(df['N'], bins=30, density=True, alpha=0.7, color='steelblue', edgecolor='black')
ax1.axvline(df['N'].mean(), color='red', linestyle='--', label=f'Media: {df["N"].mean():.1f}')
ax1.axvline(df['N'].median(), color='green', linestyle='--', label=f'Mediana: {df["N"].median():.1f}')
ax1.set_xlabel('N = h¹¹ + h²¹')
ax1.set_ylabel('Densidad')
ax1.set_title('Distribución de N')
ax1.legend()
ax1.grid(True, alpha=0.3)

2. Distribución de complejidad

ax2 = plt.subplot(3, 3, 2)
ax2.hist(df['complexity'], bins=30, density=True, alpha=0.7, color='darkorange', edgecolor='black')
ax2.axvline(df['complexity'].mean(), color='red', linestyle='--',
label=f'Media: {df["complexity"].mean():.2f}')
ax2.set_xlabel('Complejidad estimada')
ax2.set_ylabel('Densidad')
ax2.set_title('Distribución de Complejidad')
ax2.legend()
ax2.grid(True, alpha=0.3)

3. Q-Q plot de complejidad (normalidad)

ax3 = plt.subplot(3, 3, 3)
stats.probplot(df['complexity'], dist="norm", plot=ax3)
ax3.set_title('Q-Q Plot: Complejidad vs Normal')
ax3.grid(True, alpha=0.3)

4. Scatter N vs Complejidad

ax4 = plt.subplot(3, 3, 4)
scatter = ax4.scatter(df['N'], df['complexity'], c=df['ratio_h'],
cmap='viridis', alpha=0.6, s=30)
ax4.set_xlabel('N')
ax4.set_ylabel('Complejidad')
ax4.set_title('N vs Complejidad (color: h¹¹/h²¹)')
plt.colorbar(scatter, ax=ax4, label='h¹¹/h²¹')
ax4.grid(True, alpha=0.3)

5. Scatter log(N) vs Complejidad

ax5 = plt.subplot(3, 3, 5)
ax5.scatter(df['log_N'], df['complexity'], alpha=0.6, s=30, color='purple')
ax5.set_xlabel('log(N)')
ax5.set_ylabel('Complejidad')
ax5.set_title('log(N) vs Complejidad')
ax5.grid(True, alpha=0.3)

6. Boxplot por cuartiles de N

ax6 = plt.subplot(3, 3, 6)
n_quartiles = pd.qcut(df['N'], q=4, labels=['Q1', 'Q2', 'Q3', 'Q4'])
box_data = [df.loc[n_quartiles == q, 'complexity'] for q in ['Q1', 'Q2', 'Q3', 'Q4']]
bp = ax6.boxplot(box_data, labels=['Q1', 'Q2', 'Q3', 'Q4'])
ax6.set_xlabel('Cuartiles de N')
ax6.set_ylabel('Complejidad')
ax6.set_title('Distribución de Complejidad por Cuartiles de N')
ax6.grid(True, alpha=0.3)

7. Heatmap de correlaciones

ax7 = plt.subplot(3, 3, 7)
corr_vars = ['N', 'log_N', 'h11', 'h21', 'ratio_h', 'complexity']
corr_matrix = df[corr_vars].corr()
im = ax7.imshow(corr_matrix, cmap='coolwarm', vmin=-1, vmax=1)
ax7.set_xticks(range(len(corr_vars)))
ax7.set_yticks(range(len(corr_vars)))
ax7.set_xticklabels(corr_vars, rotation=45, ha='right')
ax7.set_yticklabels(corr_vars)
ax7.set_title('Matriz de Correlaciones')

Añadir valores

for i in range(len(corr_vars)):
for j in range(len(corr_vars)):
text = ax7.text(j, i, f'{corr_matrix.iloc[i, j]:.2f}',
ha="center", va="center", color="black", fontsize=9)

8. Regresión lineal N vs Complejidad

ax8 = plt.subplot(3, 3, 8)
z = np.polyfit(df['N'], df['complexity'], 1)
p = np.poly1d(z)
ax8.scatter(df['N'], df['complexity'], alpha=0.5, s=20)
ax8.plot(df['N'], p(df['N']), "r--",
label=f'y = {z[0]:.3f}x + {z[1]:.3f}\nR² = {np.corrcoef(df["N"], df["complexity"])[0,1]**2:.3f}')
ax...

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[vercel]

Deployment failed with the following error:

If `rewrites`, `redirects`, `headers`, `cleanUrls` or `trailingSlash` are used, then `routes` cannot be present.

Learn More: https://vercel.link/mix-routing-props

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[Copilot]

Copilot wasn't able to review any files in this pull request.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
p-np	Ready	Preview, Comment	Jan 24, 2026 9:03pm