Data + Keyword's

For Data + version 2 test

SPSS

Easy to use ,

Similar to spreadsheet

software for statistical analysis and data management.

SAS

Harder then SPSS

More Advanced,

For massive data

A software suite used for advanced analytics, business intelligence, data management, and predictive analytics.

Data Warehouse

Holds clean structured data for a database like SQL

Has multiple system .

Unites data

Used for a data Management

Centralized repository that allows for the storage, management, and analysis of large volumes of data from different sources, enabling business intelligence and reporting.

Data Lakehouse

A management system that combines the features of a data lake and a data warehouse, allowing for storage and analysis of both structured and unstructured data.

Managed Hybrid

This layer allows you to run fast SQL queries on your structured data and enforce security rules, while keeping your unstructured data accessible for AI and machine learning tasks in the same system.

Data lake

Stores all data bad

Massive dumping ground. It easily stores structured tables (CSV, Parquet) alongside unstructured files (PDFs, images, audio, logs).

lacks built-in management, which can turn it into an unorganized "data swamp."

Data Mart

A small section of Data Warehouse for a specific part of the business

Data Silo

Is like a Data Mart, but a bad

Not able to share info

SAP

Enterprise software

Master dada Management

Epicor

Weak version of SAP

EZ to use

Tableau

Data visualization software

Makes graphs

Turns complex raw data into interactive, easy-to-read charts, graphs, and dashboards

Elastic

software that helps you store, search, and analyze large amounts of data quickly

Outer Join

= Left and right join

adds every Oder and shows nulls from both sides

Inner Join

Only shares matching Data

Sub Query

Nested query

Just a query within a query.

Fast 2 at once

WHERE department_id IN (SELECT id FROM departments WHERE location = 'NYC');

Appending

Adding new table to the bottom of a table.

Adding table like join table

Index

Fast

book mark for SQL

Parameter

Flexible fill in the blank

Start Date =_________

Delta Load

=Update

Loading only the new or changed data since the last update, instead of reloading the entire dataset.

Full Load (Monday): Load all 10,000 customer records.

Delta Load (Tuesday): Load only the 50 new customers added today.

ETL

Source data load

(Transform data before loading it into the target system.

Slower then ETL

ELT

Extract → Load → Transform

Faster and loads new source data

Denormalization

process of combining tables (adding redundant data) to make queries faster, at the cost of extra storage.

Normalized Data

Data organized into separate tables to reduce redundancy and save storage space.

MongoDB Compass

is the official graphical user interface (GUI) tool for MongoDB. It allows you to visually explore, query, edit, and manage your MongoDB data without using the command line

DBeaver

free, multi-platform GUI tool for managing and querying SQL and NoSQL databases.

Type	Examples
SQL	MySQL, PostgreSQL, SQL Server, Oracle, SQLite
NoSQL	MongoDB, Cassandra, Redis
Cloud	Amazon Redshift, Google BigQuery, Snowflake

Toad

Used for oracle

database management and development tool used primarily for Oracle and SQL databases

Aggregate

Summary of data EX= AVG,SUM,COUNT

combines rows into a single summary value.

Duplicate Data

Mistake

Unwanted records that appear more than once in a dataset, causing inaccurate analysis, wasted storage, and reporting errors.

Redundant data

Intended to be there

The same information stored in multiple places. It is bad for storage and consistency but good for query speed

Parsing

To take a piece of data out

Augment

To fill in data if there is not enough or to make data from existing data

T-test

A statistical test that compares the averages (means) of two groups to determine if the difference between them is real (statistically significant) or just due to random chance.

uses numbers only

Type 1

Rejecting a true null hypothesis. Concluding there is an effect when there is none.

Type 2

Failing to reject a false null hypothesis. Concluding there is no effect when there actually is one.

P-Value

The probability that the observed results occurred by random chance, assuming there is no real effect

P-Value	Meaning
Low (≤ 0.05)	Results are statistically significant. The effect is likely real.
High (> 0.05)	Results are not significant. The effect could be due to random chance.

Chi-square

Compare groups

= low, med, high uses those vaules

Chi-Square Goodness of Fit

Compares observed data to expected distribution (one variable)

Chi-Square Test of Independence

Checks if two categorical variables are related (two variables)

Minitab

Quality control

process improvement

Key - value

Fast lookup

A data model where each piece of data is stored as a unique key paired with its corresponding value

= Non Relational

Choropleth Map

map that uses colors or shading patterns to represent data values across predefined geographic areas

Heat Map:

A data visualization that uses red/ grey color intensity to show magnitude, density, or concentration across a continuous space without fixed boundaries.

Matrix

Is a Pivot table

Card

One value displayed = KPI

Line graph

Trend over time 2 max variables

Scatter Plot

Relationship and patterns = 2 max

Bubble chart

Compares 3-4 variables .

Use when comparing size/importance

Binning

Groups ex [1-10] [11-20] [21-30] age group is fixed

Clustering

Similar to binning, but is for grouping data points based on similarity

Ex=Customer based on purchasing behavior

Exploding

Expanding a single value into multiple rows or columns

Ex= 101 "apple,orange,banana"

101	apple
101	orange
101	banana

Similar to parsing but for multiple rows

Ungroups

Z-Score

A statistical measure that tells you how many standard deviations a data point is from the mean (average). It shows whether a value is typical or unusual for a dataset.

Where ‘Clause’

What WHERE can do

• Filter rows using column values and expressions (>, <, =, BETWEEN, LIKE, IS NULL).

• Use logical operators: AND, OR, NOT.

• Use subqueries (IN, EXISTS).

• Use arithmetic or function calls on columns (price * qty > 100).

What WHERE can't do

• Cannot use aggregate functions (SUM, COUNT, AVG, MAX, MIN). Use HAVING for that.

• Cannot filter results of GROUP BY or window functions directly.

• Cannot use a SELECT column alias defined in the same SELECT list.

Accuracy

Data is correct and reflects reality

Completeness

no missing values

Consistency

data is the same across systems

Validity

data follows required formats and rules

Timeliness

data is current and available when needed

Atomicity

Ensures that a transaction is treated as a single, indivisible unit — either all operations in the transaction are completed successfully, or none are.

Consistency acid term

Ensures that a transaction brings the database from one valid state to another, maintaining all defined rules, constraints, and triggers. Data must be valid before and after the transaction.

Isolation Acid

Ensures that concurrent execution of transactions leaves the database in the same state as if they were executed sequentially. Transactions do not interfere with each other.

Durability acid

Ensures that once a transaction is committed, it remains permanent, even in the event of a system crash or power failure. The data is safely stored.

Power BI business intelligence (BI)

The technologies, processes, and tools used to collect, store, and analyze business data to support decision-making. BI tools (Tableau, Power BI, Looker) are built specifically to perform analytics

Graph Store (Graph Database)

A NoSQL database that stores data as nodes (entities) and edges (relationships), optimized for traversing connections instantly.

Parametric Data

numerical information that fits a specific distribution pattern, typically a normal bell-shaped curve, and uses continuous measurements

Non-Parametric Data:

information that does not follow a set bell-curve pattern or normal distribution. Instead of using raw numbers, averages, and strict rules, these methods look at data ranks, counts, or categories. They work well for skewed numbers, small sample