Exploratory Data Analysis

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np

# Load the dataset
df = pd.read_excel('excel26deenero.xlsx')

# Display basic information
print(df.info())
print(df.head())

# Get top 5 videos by likes
top_5_likes = df[['Texto del reel', 'Likes', 'Comentarios', 'Visualizaciones']].sort_values(
    by='Likes', ascending=False
).head(5)

print("Top 5 videos con más Likes:")
print(top_5_likes)

# Aggregate metrics by category
data = df.groupby('Categoria').agg({
    'Likes': 'sum',
    'Comentarios': 'sum',
    'Visualizaciones': 'sum'
}).reset_index()

print(data)

# Create stacked bar chart
fig, ax = plt.subplots(figsize=(12, 6))

bottom = np.zeros(len(data))
for column in ['Likes', 'Comentarios', 'Visualizaciones']:
    ax.bar(data['Categoria'], data[column], bottom=bottom, label=column)
    bottom += data[column]

ax.set_title('Engagement por Categoría', fontsize=16)
ax.set_xlabel('Categoría', fontsize=12)
ax.set_ylabel('Cantidad', fontsize=12)
ax.legend(title='Tipo de Engagement')
ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha='right')

plt.tight_layout()
plt.show()

import plotly.express as px

# Create interactive scatter plot
fig = px.scatter(
    df, 
    x='Likes', 
    y='Comentarios', 
    size='Visualizaciones',
    color='Categoria',
    hover_data=['Titulo'],
    title='Relación entre Likes y Comentarios',
    labels={'Likes': 'Likes', 'Comentarios': 'Comentarios'}
)

fig.show()