Data Analyst Terms Explained for Absolute Beginners

import pandas as pd

orders = pd.DataFrame({
    "order_id": [101, 102, 102, 103, 104],
    "city": ["Delhi", "Noida", "Noida", None, "Pune"],
    "amount": ["450", "1200", "1200", "300", "95000"],
})

print(orders.dtypes)                     # data types (amount is text!)
orders["amount"] = orders["amount"].astype(int)
print(orders.isna().sum())               # nulls per column
print(orders.duplicated().sum())         # duplicate rows
orders = orders.drop_duplicates()
print(orders[orders["amount"] > 10000]) # possible outlier to check

Cleaning terms in Excel

Data type:   Format Cells -> Number / Date / Text
             =ISNUMBER(C2) checks a value is really a number
Null:        =COUNTBLANK(B2:B500) counts empty cells
Duplicate:   Data -> Remove Duplicates
             =COUNTIF($A$2:$A$500, A2)>1 flags repeats
Outlier:     Sort descending, or use conditional formatting
             to highlight values far above the rest
Trim spaces: =TRIM(B2)

-- Filter: only paid orders
-- Group by + aggregate: total and count per city
SELECT
  city,
  COUNT(*)    AS orders,
  SUM(amount) AS total_sales,
  AVG(amount) AS average_order
FROM orders
WHERE status = 'PAID'
GROUP BY city
ORDER BY total_sales DESC;

-- Join: bring customer names into the orders table
SELECT o.order_id, c.customer_name, o.amount
FROM orders o
INNER JOIN customers c
  ON c.customer_id = o.customer_id;

-- LEFT JOIN keeps all orders, even if the customer is missing
SELECT o.order_id, c.customer_name
FROM orders o
LEFT JOIN customers c
  ON c.customer_id = o.customer_id
WHERE c.customer_id IS NULL;   -- orders with no matching customer

import statistics as st

# Daily orders at a small shop, with one bulk-order day
orders = [12, 15, 11, 14, 13, 16, 120]

print("mean:", round(st.mean(orders), 1))     # pulled up by 120
print("median:", st.median(orders))          # the typical day
print("mode-free spread (stdev):", round(st.stdev(orders), 1))
# For skewed data, report the median as the 'typical' value.

import pandas as pd

sales = pd.Series(
    [100, 110, 95, 130],
    index=["2025-10", "2025-11", "2026-09", "2026-10"],
)

# Year-over-year: compare Oct 2026 with Oct 2025
yoy = (sales["2026-10"] - sales["2025-10"]) / sales["2025-10"] * 100
print(f"YoY growth: {yoy:.1f}%")   # 30.0%

# Month-over-month: compare Oct 2026 with Sep 2026
mom = (sales["2026-10"] - sales["2026-09"]) / sales["2026-09"] * 100
print(f"MoM growth: {mom:.1f}%")   # 36.8%

Term: ____________________
My simple definition (one line):
__________________________________
Example from a real table:
__________________________________
Where I used it (SQL / Excel / Python / BI):
__________________________________
Common mistake to avoid:
__________________________________

Data:       dataset, row, column, data type, schema
Cleaning:   null, duplicate, outlier, trim, standardise
SQL:        SELECT, WHERE, GROUP BY, JOIN, HAVING
Excel:      pivot table, XLOOKUP, conditional formatting
Statistics: mean, median, mode, range, standard deviation
Reporting:  KPI, dashboard, trend, YoY, MoM
Process:    ETL, data source, refresh

Can you explain these in one sentence each?

[ ] Difference between INNER JOIN and LEFT JOIN
[ ] When to use median instead of mean
[ ] What a KPI is, with one example
[ ] What ETL stands for and does
[ ] Difference between WHERE and HAVING
[ ] What a pivot table summarises

Explain them aloud to a friend - if they understand,
you understand.