Stacked Area Graph

# === IMPORTS ===
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go

# === USER-EDITABLE PARAMETERS ===
# Change: Customize data generation
np.random.seed(42)  # Change: Set to None for truly random data each run, or different int for reproducible variations
NUM_MONTHS = 24  # Change: Number of months (2 years = 24)
START_DATE = '2022-01-01'  # Change: Start date for time series
CATEGORIES = ['Electronics', 'Clothing', 'Home & Garden', 'Books']  # Change: Product category names
BASE_REVENUES = [400000, 300000, 200000, 100000]  # Change: Base monthly revenue ($) for each category
ANNUAL_GROWTH_RATES = [0.15, 0.08, 0.10, 0.03]  # Change: Annual growth rates for each category
NOISE_STD = 0.08  # Change: Standard deviation for monthly noise (as fraction of base)

# Seasonal peaks (multipliers) - Change: Adjust months and factors for peaks
SEASONAL_PEAKS = {
    'Clothing': {'months': [11, 12], 'factor': 1.5},
    'Home & Garden': {'months': [6, 7, 8], 'factor': 1.3},
    'Books': {'months': [11, 12], 'factor': 1.4},
    'Electronics': {'months': [], 'factor': 1.0}
}
BF_EXTRA_MONTHS = [11]  # Change: Months for Black Friday/Cyber Monday extra boost (25%)
BF_EXTRA_FACTOR = 1.25  # Change: Extra multiplier for BF/CM

# Visual styling - Change: Hex codes only for all colors
COLOR_DISCRETE_MAP = {
    'Electronics': '#4B9CD3',    # Change: Soft blue
    'Clothing': '#66C2A5',       # Change: Teal green
    'Home & Garden': '#8DD3C7',  # Change: Light green
    'Books': '#A6CEE3'           # Change: Light blue
}
TOTAL_LINE_COLOR = '#000000'  # Change: Total line color (black)
ANNOTATION_COLOR = '#FF0000'  # Change: Annotation arrow color (red)

# Plot styling
TITLE_FONT_SIZE = 18  # Change: Title font size
LABEL_FONT_SIZE = 14  # Change: Axis labels and legend font size
LINE_WIDTH = 4  # Change: Total line width
AREA_OPACITY = 0.85  # Change: Stacked area transparency (0.0-1.0)
SHOW_GRID = True  # Change: Toggle subtle gridlines
Y_SUFFIX = 'K'  # Change: Y-axis suffix (e.g., 'K' for thousands)
DATE_COLUMN = 'month'  # Change: Name of the date column used for x-axis

# === DATA GENERATION ===
# Create dates and month numbers
dates = pd.date_range(start=START_DATE, periods=NUM_MONTHS, freq='MS')
month_of_year = dates.month
df = pd.DataFrame({DATE_COLUMN: dates})

# Compute growth factors (monthly compounding)
growth_factors = {}
for i, cat in enumerate(CATEGORIES):
    r_annual = 1 + ANNUAL_GROWTH_RATES[i]
    r_monthly = r_annual ** (1 / 12)
    growth = np.cumprod(np.full(NUM_MONTHS, r_monthly))
    growth_factors[cat] = growth

# Seasonal and BF factors
seasonal = pd.DataFrame(1.0, index=df.index, columns=CATEGORIES)
bf_extra = pd.Series(1.0, index=df.index)
bf_extra[month_of_year.isin(BF_EXTRA_MONTHS)] = BF_EXTRA_FACTOR

for cat in CATEGORIES:
    peak_months = SEASONAL_PEAKS[cat]['months']
    factor = SEASONAL_PEAKS[cat]['factor']
    seasonal.loc[month_of_year.isin(peak_months), cat] = factor

# Generate revenues with growth, seasonal, BF, and noise
noise = np.random.normal(1, NOISE_STD, NUM_MONTHS)
for i, cat in enumerate(CATEGORIES):
    df[cat] = (BASE_REVENUES[i] * growth_factors[cat] * 
               seasonal[cat] * bf_extra * noise)

df['Total'] = df[CATEGORIES].sum(axis=1)

# Scale to thousands for plotting
df_plot = df.copy()
df_plot[CATEGORIES + ['Total']] /= 1000

# Ensure date column always exists for plotting/annotations
if DATE_COLUMN not in df_plot.columns:
    df_plot[DATE_COLUMN] = dates[:len(df_plot)]

df_plot[DATE_COLUMN] = pd.to_datetime(df_plot[DATE_COLUMN], errors='coerce')

# Order categories by average revenue (descending) for legend/stacking
avgs = df_plot[CATEGORIES].mean().sort_values(ascending=False)
y_order = avgs.index.tolist()

# Compute insights for title and prints
avg_total_22 = df_plot['Total'].iloc[:12].mean()
avg_total_23 = df_plot['Total'].iloc[12:].mean()
growth_pct = ((avg_total_23 - avg_total_22) / avg_total_22) * 100
insight_title = f'Monthly Revenue Grew {growth_pct:.0f}% from 2022 (${avg_total_22:.0f}{Y_SUFFIX}) to 2023 (${avg_total_23:.0f}{Y_SUFFIX}) by Category'

# Print key statistics
print("=== KEY INSIGHTS ===")
print(f"Average monthly total revenue:")
print(f"  2022: ${avg_total_22:.0f}{Y_SUFFIX}")
print(f"  2023: ${avg_total_23:.0f}{Y_SUFFIX}")
print(f"  Growth: +{growth_pct:.1f}%")
print("\nAverage monthly revenue by category:")
for cat in y_order:
    print(f"  {cat}: ${df_plot[cat].mean():.0f}{Y_SUFFIX}")
peak_idx_for_print = int(df_plot['Total'].idxmax())
peak_date_for_print = df_plot[DATE_COLUMN].iloc[peak_idx_for_print]
if pd.isna(peak_date_for_print):
    peak_date_label = f"Month {peak_idx_for_print + 1}"
else:
    peak_date_label = peak_date_for_print.strftime('%b %Y')
print(f"\nPeak month: {peak_date_label} (${df_plot['Total'].max():.0f}{Y_SUFFIX})")

# === CREATE PLOT ===
# Stacked area chart
fig = px.area(df_plot, x=DATE_COLUMN, y=y_order, color_discrete_map=COLOR_DISCRETE_MAP)

# Add total revenue line overlay
fig.add_trace(go.Scatter(
    x=df_plot[DATE_COLUMN],
    y=df_plot['Total'],
    mode='lines',
    name='Total Revenue',
    line=dict(color=TOTAL_LINE_COLOR, width=LINE_WIDTH, dash='dash'),
    hovertemplate='<b>Total</b>: $%{y:,.0f}' + Y_SUFFIX + '<extra></extra>'
))

# Adjust area opacity for soft look
fig.update_traces(opacity=AREA_OPACITY, stackgroup='revenue')

# Black Friday/Cyber Monday annotation (latest Nov peak)
bf_months = df_plot[DATE_COLUMN][month_of_year == 11]
if len(bf_months) > 0:
    latest_bf_idx = df_plot[DATE_COLUMN][month_of_year == 11].index[-1]
    peak_x = df_plot[DATE_COLUMN].iloc[latest_bf_idx]
    peak_y = df_plot['Total'].iloc[latest_bf_idx]
    fig.add_annotation(
        x=peak_x, y=peak_y * 1.02,
        text='Black Friday /<br>Cyber Monday Peak',
        showarrow=True,
        arrowhead=2, arrowsize=1, arrowwidth=2, arrowcolor=ANNOTATION_COLOR,
        ax=0, ay=-40,
        bgcolor='rgba(255,255,255,1)', bordercolor=ANNOTATION_COLOR, borderwidth=1,
        font=dict(size=LABEL_FONT_SIZE)
    )

# === FINALIZE LAYOUT ===
fig.update_layout(
    title=dict(text=insight_title, x=0.5, font_size=TITLE_FONT_SIZE),
    xaxis_title='Month',
    yaxis_title=f'Revenue ({Y_SUFFIX}$)',
    margin=dict(t=130, b=90, l=90, r=100),
    font=dict(size=LABEL_FONT_SIZE),
    legend=dict(
        x=0.02, y=0.85,
        xanchor='left', yanchor='top',
        bgcolor='rgba(255,255,255,0.8)',
        bordercolor='rgba(128,128,128,0.3)', borderwidth=1
    ),
    xaxis=dict(
        showgrid=SHOW_GRID,
        gridcolor='rgba(128,128,128,0.3)', gridwidth=1,
        tickformat='%b<br>%y', tickangle=-45
    ),
    yaxis=dict(
        tickprefix='$', ticksuffix=Y_SUFFIX,
        showgrid=SHOW_GRID,
        gridcolor='rgba(128,128,128,0.3)', gridwidth=1
    ),
    hovermode='x unified'
)

fig.show()
# END-OF-CODE

Revenue Statistics by Category (Year-over-Year):
Electronics          : 2022=$4432K, 2023=$5123K, Growth=+15.6%
Clothing             : 2022=$3542K, 2023=$3732K, Growth=+5.4%
Home & Garden        : 2022=$2389K, 2023=$2561K, Growth=+7.2%
Books                : 2022=$1205K, 2023=$1284K, Growth=+6.6%

Total 2-Year Revenue: $24471K
Monthly Average: $1019K