Data Storytelling and Communication

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

# BAD: Too much clutter
fig, axes = plt.subplots(1, 2, figsize=(14, 5))

np.random.seed(42)
categories = ['Q1', 'Q2', 'Q3', 'Q4', 'Q1', 'Q2', 'Q3', 'Q4']
years = ['2023']*4 + ['2024']*4
values = [45, 52, 48, 61, 49, 58, 55, 72]
colors = ['#ff6b6b', '#4ecdc4', '#45b7d1', '#96ceb4',
          '#ff6b6b', '#4ecdc4', '#45b7d1', '#96ceb4']

axes[0].bar(categories, values, color=colors, edgecolor='black',
            linewidth=2, hatch='//')
axes[0].set_title('Quarterly Performance (BAD)', fontsize=14, fontweight='bold', color='darkblue')
axes[0].grid(True, linestyle='--', alpha=0.7)
axes[0].set_facecolor('#f0f0f0')

# After: Clean
df = pd.DataFrame({
    'Quarter': ['Q1', 'Q2', 'Q3', 'Q4'] * 2,
    'Year': ['2023']*4 + ['2024']*4,
    'Revenue': [45, 52, 48, 61, 49, 58, 55, 72]
})

for year, group in df.groupby('Year'):
    marker = 'o' if year == '2024' else 's'
    linestyle = '-' if year == '2024' else '--'
    axes[1].plot(group['Quarter'], group['Revenue'],
                 marker=marker, linewidth=2.5, markersize=8,
                 label=year, linestyle=linestyle)

axes[1].set_title('Revenue by Quarter', fontsize=14, fontweight='bold')
axes[1].set_ylabel('Revenue ($K)', fontsize=12)
axes[1].legend(title='Year', frameon=True)
axes[1].spines['top'].set_visible(False)
axes[1].spines['right'].set_visible(False)
axes[1].grid(axis='y', alpha=0.3)

plt.tight_layout()
plt.show()

# Color-blind friendly palettes
COLORBLIND_PALETTE = ['#0072B2', '#E69F00', '#009E73',
                       '#F0E442', '#56B4E9', '#D55E00', '#CC79A7']

def create_accessible_chart(df, x, y, hue=None):
    fig, ax = plt.subplots(figsize=(10, 6))
    if hue:
        for i, (name, group) in enumerate(df.groupby(hue)):
            color = COLORBLIND_PALETTE[i % len(COLORBLIND_PALETTE)]
            ax.scatter(group[x], group[y], label=name, color=color,
                      s=100, edgecolors='white', linewidth=0.5)
    ax.spines['top'].set_visible(False)
    ax.spines['right'].set_visible(False)
    ax.set_xlabel(x.replace('_', ' ').title(), fontsize=12)
    ax.set_ylabel(y.replace('_', ' ').title(), fontsize=12)
    return fig, ax

def create_analysis_email(
    finding: str,
    recommendation: str,
    evidence: list[str],
    metrics: dict,
    next_steps: list[str]
) -> str:
    email = f"""Hi Team,

**Key Finding:**
{finding}

**Recommendation:**
{recommendation}

**Supporting Evidence:**
"""
    for i, e in enumerate(evidence, 1):
        email += f"{i}. {e}\n"

    email += "\n**Key Metrics:**\n"
    for metric, value in metrics.items():
        email += f"- {metric}: {value}\n"

    email += "\n**Next Steps:**\n"
    for step in next_steps:
        email += f"- [ ] {step}\n"

    email += "\nHappy to discuss further."
    return email

# Example
email = create_analysis_email(
    finding="Mobile conversion rate dropped 23% after the latest app update.",
    recommendation="Roll back the checkout flow changes in the next release.",
    evidence=[
        "Conversion dropped from 4.2% to 3.2% within 48 hours",
        "User session recordings show confusion at the new payment screen",
        "Mobile revenue is down $45K week-over-week"
    ],
    metrics={
        "Mobile Conversion Rate": "3.2% (was 4.2%)",
        "Revenue Impact": "-$45K/week",
        "Affected Users": "~12,000/day"
    },
    next_steps=[
        "Schedule emergency rollback for tonight",
        "Prepare A/B test for alternative checkout flow",
        "Post-mortem scheduled for Friday"
    ]
)
print(email)

presentation_checklist = {
    "Before": [
        "Test all links and code demos",
        "Prepare backup screenshots",
        "Know your audience (technical vs business)",
        "Prepare for tough questions",
        "Have one-page summary ready"
    ],
    "During": [
        "Start with the answer, not the journey",
        "Use concrete numbers, not vague claims",
        "Pause after key points",
        "Watch for confused faces",
        "Stay within time limit"
    ],
    "After": [
        "Send follow-up with key slides",
        "Include actionable next steps",
        "Provide data/code for technical audience",
        "Schedule follow-up if needed"
    ]
}

# BAD: Technical explanation
"""
Our XGBoost model achieved an AUC-ROC of 0.847 on the test set,
with a precision-recall tradeoff at threshold 0.35, and the SHAP
values indicate feature importance is dominated by recency_score..."
"""

# GOOD: Business language
def executive_summary():
    return """
    What we built:
    A system that predicts which customers are about to leave.

    How well it works:
    Out of 100 customers we flag, 73 actually leave (73% precision).
    We catch 81% of all customers who leave (81% recall).

    Business impact:
    If we intervene with our top 1,000 at-risk customers:
    - Expected saves: ~250 customers
    - Revenue retained: ~$1.2M annually
    - Cost of intervention: ~$50K (discounts + outreach)
    - Net benefit: ~$1.15M

    Recommendation:
    Pilot the retention program with the top 500 customers next month.
    """

def product_recommendation_deck():
    slides = [
        {
            "title": "The Opportunity",
            "content": "Users who complete onboarding within 24 hours have 3x higher LTV",
            "visual": "bar_chart: onboarding_speed_vs_ltv"
        },
        {
            "title": "Current State",
            "content": "Only 34% of users complete onboarding within 24 hours",
            "visual": "funnel_chart: onboarding_completion"
        },
        {
            "title": "Root Cause",
            "content": "Step 3 (payment setup) causes 62% of drop-offs",
            "visual": "waterfall_chart: dropoff_by_step"
        },
        {
            "title": "Our Recommendation",
            "content": "Move payment setup to post-trial, after users experience value",
            "visual": "before_after: conversion_comparison"
        },
        {
            "title": "Expected Impact",
            "content": "+18% onboarding completion -> +$3.2M annual revenue",
            "visual": "projection_chart: revenue_impact"
        }
    ]
    return slides