ComercioYA Sales Analysis

PROYECTO/
├── main.py                        # Main EDA script
├── app.py                         # Streamlit dashboard
├── comercio_ya.ipynb              # Jupyter notebook with analysis
├── ecommerce_sales_data-2.csv     # Sales dataset
├── requirements.txt               # Python dependencies
├── figures/                       # Exported visualizations
│   ├── sales_by_category.png
│   ├── monthly_revenue.png
│   └── customer_segments.png
├── figures_notebook/              # Notebook visualizations
└── informes/                      # Final reports
    └── informe_final_eda.pdf

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

# Load data
df = pd.read_csv('ecommerce_sales_data-2.csv')

# Basic info
print(f"Dataset shape: {df.shape}")
print(f"\nColumns: {df.columns.tolist()}")
print(f"\nData types:\n{df.dtypes}")
print(f"\nMissing values:\n{df.isnull().sum()}")

# First rows
print(df.head())

# Descriptive statistics
print("\n=== Numerical Variables ===")
print(df.describe())

print("\n=== Categorical Variables ===")
for col in df.select_dtypes(include='object').columns:
    print(f"\n{col}: {df[col].nunique()} unique values")
    print(df[col].value_counts().head())

# Sales by category
sales_by_category = df.groupby('category')['sales'].sum().sort_values(ascending=False)

plt.figure(figsize=(10, 6))
sales_by_category.plot(kind='bar', color='steelblue')
plt.title('Total Sales by Category', fontsize=16)
plt.xlabel('Category')
plt.ylabel('Sales ($)')
plt.xticks(rotation=45)
plt.tight_layout()
plt.savefig('figures/sales_by_category.png')
plt.show()

# Convert dates
df['order_date'] = pd.to_datetime(df['order_date'])
df['year_month'] = df['order_date'].dt.to_period('M')

# Monthly revenue
monthly_revenue = df.groupby('year_month')['sales'].sum()

plt.figure(figsize=(14, 6))
monthly_revenue.plot(kind='line', marker='o', color='green')
plt.title('Monthly Revenue Trend', fontsize=16)
plt.xlabel('Month')
plt.ylabel('Revenue ($)')
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.savefig('figures/monthly_revenue.png')
plt.show()

# Customer segments
segment_analysis = df.groupby('segment').agg({
    'sales': 'sum',
    'profit': 'sum',
    'order_id': 'count',
    'customer_id': 'nunique'
}).rename(columns={'order_id': 'total_orders', 'customer_id': 'unique_customers'})

print("\n=== Customer Segment Analysis ===")
print(segment_analysis)

# Visualization
fig, axes = plt.subplots(1, 2, figsize=(14, 6))

# Sales by segment
segment_analysis['sales'].plot(kind='pie', ax=axes[0], autopct='%1.1f%%')
axes[0].set_title('Sales Distribution by Segment')
axes[0].set_ylabel('')

# Orders by segment
segment_analysis['total_orders'].plot(kind='bar', ax=axes[1], color='coral')
axes[1].set_title('Total Orders by Segment')
axes[1].set_xlabel('Segment')
axes[1].set_ylabel('Orders')
axes[1].tick_params(axis='x', rotation=45)

plt.tight_layout()
plt.savefig('figures/customer_segments.png')
plt.show()

# Top 10 products by sales
top_products = df.groupby('product_name')['sales'].sum().sort_values(ascending=False).head(10)

plt.figure(figsize=(12, 6))
top_products.plot(kind='barh', color='purple')
plt.title('Top 10 Products by Sales', fontsize=16)
plt.xlabel('Sales ($)')
plt.ylabel('Product')
plt.tight_layout()
plt.savefig('figures/top_products.png')
plt.show()

# Sales by region
region_sales = df.groupby('region').agg({
    'sales': 'sum',
    'profit': 'sum',
    'order_id': 'count'
}).sort_values('sales', ascending=False)

print("\n=== Sales by Region ===")
print(region_sales)

# Visualization
fig, ax = plt.subplots(figsize=(10, 6))
region_sales['sales'].plot(kind='bar', ax=ax, color='teal')
ax.set_title('Sales by Region', fontsize=16)
ax.set_xlabel('Region')
ax.set_ylabel('Sales ($)')
ax.tick_params(axis='x', rotation=45)
plt.tight_layout()
plt.savefig('figures/sales_by_region.png')
plt.show()

# Discount bins
df['discount_bin'] = pd.cut(df['discount'], 
                            bins=[-0.01, 0, 0.1, 0.2, 0.3, 1],
                            labels=['No Discount', '1-10%', '11-20%', '21-30%', '30%+'])

# Average profit by discount level
discount_impact = df.groupby('discount_bin').agg({
    'profit': 'mean',
    'sales': 'mean',
    'order_id': 'count'
})

print("\n=== Discount Impact on Profit ===")
print(discount_impact)

# Visualization
fig, ax = plt.subplots(figsize=(10, 6))
discount_impact['profit'].plot(kind='bar', ax=ax, color='orange')
ax.set_title('Average Profit by Discount Level', fontsize=16)
ax.set_xlabel('Discount Range')
ax.set_ylabel('Average Profit ($)')
ax.tick_params(axis='x', rotation=45)
plt.tight_layout()
plt.savefig('figures/discount_impact.png')
plt.show()

import streamlit as st
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go

st.set_page_config(page_title='ComercioYA Dashboard', layout='wide')

st.title('ComercioYA Sales Analytics Dashboard')

# Load data
@st.cache_data
def load_data():
    df = pd.read_csv('ecommerce_sales_data-2.csv')
    df['order_date'] = pd.to_datetime(df['order_date'])
    return df

df = load_data()

# Sidebar filters
st.sidebar.header('Filters')
date_range = st.sidebar.date_input(
    'Date Range',
    value=(df['order_date'].min(), df['order_date'].max())
)
categories = st.sidebar.multiselect(
    'Categories',
    options=df['category'].unique(),
    default=df['category'].unique()
)

# Filter data
filtered_df = df[
    (df['order_date'] >= pd.to_datetime(date_range[0])) &
    (df['order_date'] <= pd.to_datetime(date_range[1])) &
    (df['category'].isin(categories))
]

# KPIs
col1, col2, col3, col4 = st.columns(4)
with col1:
    st.metric('Total Sales', f"${filtered_df['sales'].sum():,.2f}")
with col2:
    st.metric('Total Profit', f"${filtered_df['profit'].sum():,.2f}")
with col3:
    st.metric('Avg Order Value', f"${filtered_df['sales'].mean():,.2f}")
with col4:
    st.metric('Total Orders', f"{len(filtered_df):,}")

# Charts
col1, col2 = st.columns(2)

with col1:
    st.subheader('Sales by Category')
    fig = px.pie(filtered_df, values='sales', names='category')
    st.plotly_chart(fig, use_container_width=True)

with col2:
    st.subheader('Sales by Segment')
    segment_data = filtered_df.groupby('segment')['sales'].sum().reset_index()
    fig = px.bar(segment_data, x='segment', y='sales')
    st.plotly_chart(fig, use_container_width=True)

# Time series
st.subheader('Sales Trend Over Time')
time_data = filtered_df.groupby(filtered_df['order_date'].dt.to_period('M'))['sales'].sum()
time_data.index = time_data.index.to_timestamp()
fig = px.line(time_data, title='Monthly Sales')
st.plotly_chart(fig, use_container_width=True)

# Data table
st.subheader('Detailed Data')
st.dataframe(filtered_df)

streamlit run app.py
# Opens at http://localhost:8501

pip install -r requirements.txt

pandas
numpy
matplotlib
seaborn
plotly
streamlit

python main.py

cd PROYECTO/
streamlit run app.py

jupyter notebook comercio_ya.ipynb