Build a Data Analytics Portfolio With Zero Job Experience

Retail:     Which categories drive repeat purchases?
            Which weekdays have the highest order values?
Banking:    Which customer segments use digital payments most?
Healthcare: Which time slots have the most missed appointments?
Education:  Which factors relate to higher course completion?

Rule: one main question + two follow-up questions per project.

import pandas as pd

df = pd.read_csv("orders.csv")      # your downloaded public dataset
print("rows, columns:", df.shape)
print("columns:", list(df.columns))
print("date range:", df["order_date"].min(), "to", df["order_date"].max())
print("missing values per column:")
print(df.isna().sum().sort_values(ascending=False).head())
# Good portfolio data: answers your question, a little messy, not huge.

import pandas as pd

raw = pd.DataFrame({
    "order_id": [1, 2, 2, 3, 4],
    "city": ["Delhi", "delhi ", "delhi ", "Mumbai", None],
    "order_date": ["2026-10-01", "2026-10-02", "2026-10-02", "2026-10-03", "2026-10-04"],
    "amount": ["500", "750", "750", "1,200", "300"],
})
log = []
df = raw.drop_duplicates().copy(); log.append(f"removed {len(raw) - len(df)} duplicate rows")
df["city"] = df["city"].str.strip().str.title().fillna("Unknown"); log.append("standardised city, missing -> Unknown")
df["order_date"] = pd.to_datetime(df["order_date"])
df["amount"] = df["amount"].str.replace(",", "").astype(float)
print(df)
print("\n".join(log))

-- Repeat customers by city
WITH orders_per_customer AS (
  SELECT customer_id, city, COUNT(*) AS orders
  FROM orders
  GROUP BY customer_id, city
)
SELECT city,
       COUNT(*) AS customers,
       SUM(CASE WHEN orders >= 2 THEN 1 ELSE 0 END) AS repeat_customers,
       ROUND(100.0 * SUM(CASE WHEN orders >= 2 THEN 1 ELSE 0 END) / COUNT(*), 1)
         AS repeat_pct
FROM orders_per_customer
GROUP BY city
ORDER BY repeat_pct DESC;

# Missed Appointments Analysis

**Question:** Which time slots have the most missed appointments?

**Finding:** Early morning and late evening slots show the highest
miss rates in this dataset.

**Evidence:** Miss rate by slot (chart), checked across 6 months.

**Recommendation:** Send reminders the evening before for these
slots and test the effect for one month.

**Limitations:** Public dataset from one region; no reason codes.

import pandas as pd
import matplotlib.pyplot as plt

slots = pd.DataFrame({
    "slot": ["8-10", "10-12", "12-2", "2-4", "4-6", "6-8"],
    "miss_rate": [0.22, 0.12, 0.10, 0.11, 0.14, 0.20],
})
ax = slots.plot.bar(x="slot", y="miss_rate", legend=False)
ax.set_title("Missed appointments by time slot")
ax.set_ylabel("Miss rate")
plt.tight_layout()
plt.savefig("miss_rate_by_slot.png", dpi=150)
print("saved chart")

Project 1 (Excel + SQL):
  Sales or orders analysis with pivot tables and SQL queries
Project 2 (Power BI or Tableau):
  Interactive dashboard answering one business question
Project 3 (Python or SQL deep-dive):
  Cleaning-heavy project with a documented log

Together they cover the tools most analyst listings mention.

Weeks 1-2  Project 1: question, cleaning, SQL, pivot tables
Weeks 3-4  Project 2: dashboard and write-up
Weeks 5-6  Project 3: cleaning-heavy analysis
Week 7     Portfolio page, README polish, resume links
Week 8     Ask two people to review; fix what confuses them

[ ] Each project starts with a business question
[ ] Data source and licence stated
[ ] Cleaning log included
[ ] 3-5 clear visuals per dashboard
[ ] Recommendation and limitations written
[ ] Links work from resume and LinkedIn
[ ] One portfolio page lists all projects