Scribd
Upload
6 views19 pages

Data Analyst Notes

The document provides an overview of Data Analytics, detailing its definition, types, and importance for organizations in making data-driven decisions. It outlines the skills required to become a Data Analyst, the Data Analytics Lifecycle, and the use of tools like Excel and SQL for data analysis. Additionally, it discusses the four types of data analytics—Descriptive, Diagnostic, Predictive, and Prescriptive—and their applications in real-world scenarios.

Uploaded by

wafaek693
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
6 views19 pages

Data Analyst Notes

The document provides an overview of Data Analytics, detailing its definition, types, and importance for organizations in making data-driven decisions. It outlines the skills required to become a Data Analyst, the Data Analytics Lifecycle, and the use of tools like Excel and SQL for data analysis. Additionally, it discusses the four types of data analytics—Descriptive, Diagnostic, Predictive, and Prescriptive—and their applications in real-world scenarios.

Uploaded by

wafaek693
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
COUT UU ear ee eee ANALYST COMPLETE NOTES = (Data Analyst) < Ov = Excel SQL Statistics Visualization Data Analysis =| BEGINNER To ADVANCED | < SWIPE TO_NEXT —> < ee > Qa_insights better careers = @qa_insights if What is Data Analytics? @ What is Data Analytics? Data Analytics is the process of ee oY cling, tig waieng od > és =H Y-@ interpreting data to find pattems, + — alll e trends and insights that help Collect Clean. Analyze Generate Better organizations make better Data Data Data Insights Decisions decisions. Turn Data into Actionable Insights @ Data vs Information @ Types of Data © Structured Data = anized in rows Data Taformation Leper . int . ing ful * Semi-Structured Data: Not in fixed format Raws, unprocessed facts | * Processed and meaningful ackure (GS0N, XML, Lg) of ns come peewee * Unstricured Data + No fixed format * Hard to understand | * Easy to understand (Text, Images, Videos) : sa * Quolitative Data : Descriptive data + Example: 25, 70,40 | * Exomple eae sed pee © * Quantitative Data : Numerical data {ol (Sales, Revenue, Age) @ Why Companies Use Analytics? © Real-World Examples © Inpro business, performance FS to recommend products and increase sales it Banking : Detect fraud, assess loan risk GF Understand customers beter Ee TFET E-Commerce : Analyze customer behavior Zi Identify trends and patterns ‘and improve customer experience Zi Make data-driven decisions Healthcare : Predict disease risk, optimize GZ Reduce costs and increase efficiency boar] treatment and manage patient data. TF Forecast future outcomes gd Macketing + Understand campaign performance Sass} and target the right audience. Gop besistcs + Optimize delivery routes, reduce delays and control costs. D Gain competitive advantage ~Q* Taterview Tip Dots Selene ibs navel Remember: A good Data Analyst not only analyzes, data but also tells a story behind the data ond helps the business make smarter decisions The veal value comes when we convert Data > Insights > Action! @qa-insights | Quality Insights, Better Careers! @qa_insights Data Analyst Roadmap Your step-by-step guide to become a successful Data Analyst! © Skills Required @® Learning Path (Step-by-Step) 7 Aralyica Thiking & Probl Sebing @ @ ® ® SQL Quang & Dalabse Kenedge iS 4 SA ae Sr Excel & Dale. Maipulation a CladBin Analysis EE” ; Excl, Baie Gueies, Jens, ing : SOON | EE RE, % Daa Cain & Vesging Dipl, Oars Ini ¥ Data Vanalzalion &Dasnrding 1 in fr Dada Pala Oe estate dint Denes Kani Res Phen mae Y Conran & Selig per eee Se ee ¥ Allention to Detail (Poser BI/Tableau) ——Aralysis. Forecasting, Real-warld Prajects, Sepets Case Suber @® Tools Overview HBeede reo eee ~w | SQL Python Power BI Tableau MysaL. Supyter CSV/Files Data ei Querying, Pandas, Mun?y, | Dashboards, Vinulization, Database | Interactive Data, Sources, ct as, | Drinker, | Baa nna, | Qapets, | Datars’ | Monnet | teak | Mnr/Eapets ars Frm | Dita Exrecin | Adawatin” {Duin Modding | Surfing | Sglen |‘ Aongie eae @ Career Progression ey i a Remenber i Grout — Practice consistently | oan : i 8 Leaing & ee 5 Bi ao res | A ag | ua eee ee | Le Pata Senin | Dale Ant pies ree es - | Data Analyst | Analyst | Data Analyst + Keep inping & stay wos! gy | bai) Fo te eo © Salary Roadmap (Approximate in INR) at es Tip Rae ag Sinton) \ Fresher Ob ger_| Hor Dt ah ia ane [3-6 UPA | | v Shang Fndanerale i SOL & Ered | Early Career: 1 = 3 years | Data Analyst 6 = 40 LPA | ode sith ren abate | Tad Caw | 8 Sgn Som Bia ag 16 A | | 7 Bald dated a te | Experienced 5 = B years | Lend Date Analyst afLzSVURA | cna eee tac ' Expert erage | aeaer areal Bs ee SORIA 6 Tals us what | Explains why something ! Predicts what is likely Recommends the best happened in the past. | happened | to happen in the future. | actions 4o achieve the desired outcome. Focus: Historical data : Focus: Finding the root Focus: Future outcomes | Focus: Decision support summarization | cause or reason using data & models | tization Key Question | Key Question Key Question: * Kaj uns What happened? Why did it happen? | What is likely to What should we-do? i happen? Business Examples for Each Type Type Business Example How it Helps Descriptive | + Sales dashboard showing tatal | [2] Helps teams understand performance Analytics revenue, orders, profit te ea and track KPIS. Diagnostic ‘© Identify why sales dropped in May | [2] Helps find root causes and fix Analytics & % low marketing spend, the real problem. high competitor discount). Predictive + Predict next month’s sales using | [7] Helps plan inventory, budgeting Analytics historical data and ML models. and resource allocation. Prescriptive | * Recommend best pricing strategy | [71 Helps choose the best action and Analytics cor best marketing channel to improve ROL, maximize profit, 7 Q Interview Tip All four types work together in a Interviewer may ask: Data Anolytics Lifecycle “Explain the difference between Descriptive, =) Ga (GS Predictive and Prescriptive Analytics” Tip: Always relate with real business Ci ‘examples ard the key question each From understanding the past > to optimizing the future et ec © @qa-insights | Quality Insights, Better Careers! @qa-insights 4 Data Analytics Lifecycle The Data. Analytics Lifecycle is a step-by-step process that turns raw data into meaningful insights and drives better business decisions. Lifecyele Flow Define the problem clearly Understand the goal, scope and success metrics Ye 2) + Use insights to * Collect relevart data Pe ae From sources like cisions, optimize Databases, APIS, performance and Files (CSV, Excel), veasure impact. Web, Logs, Forms, Data -> Insights Se eee Insights ~> Tnmpact + Present. insights Visualization + Handle missing values, Weng arts, ete and LW aed ates, pee ee ball nw @ and validate data ee a Re quality. fablea, Excel, Looker, etc.). terancuat Forgery ears} ap ees “QS Best Practices Good data + Right analysis © Understand the business first + Clear insights © Ensure data, quolity early = Better decisions & Document ossumptions & metrics EZ Use the right tools for the job. © Tell the story behind the data. Tgnoring the business problem Caliecting unnecessary data Poor data. cleaning Wrong visualization choice No clear action from insights xX XX { The Ufecytle ie NOT aluays strictly Gren. : B inprint Teter oe se G58-8-9-9-9 Note based on new Findings or data changes. ac a @qainsights | Quality Insights, Better Career sights Excel for Data Analysis Excel is a powerful tool for data cleaning, analysis and visualization These features are widely used by every Data Analyst. Tables ! Sortin Filteri ‘9 | Organize data in a structured | Arrange data in Ascending (A->2) Filter data to view only table using Ctrl + T. | or Descending (Z-+A) order. records that meet. criteria. TD | Back | Cotgoy | Saw eee =. aS a 102 | Phone | Elctreries | 25000] | [Ret [5200 | ty satue | Zobm | 6100 ee 303 | Chair | Furniture | 8500 | | | Am | 4300 | (High te Low) | Rovi_| 5200 i, 104 [Table | Future [12000] | [Jom [e100 | ——— | Aw | 9300 wath ad ges \ [Neka_[ 3800 Neka_ | 3900 5 rie + Easy to manage large data i Di Use Data > Filter * Auto expand formulas & charts FA_Use Duta -» Sort for quick sorting or Ctl + Shift +L @® Conditional. Formatting © Pivot Tables © Charts Highlight cells based on conditions Summarize, analyze and explore Visualize data to find trends ving rl, data from large datasets ord -eighs esl Example: Highlight Sales > 20000 | EE (eg | came Céurm Ghat Une Gur Pest [Sales] o> Rats | [Ch date | [Pred | Region gE Bom | |e Eat [Wat [a] aver Phone | 18000 2 © a Entity Employee Relationship Altribate Connection Relationship (Wang Employees wer in Ove Department) 1000 oO Trteriew Tip ‘Alongs design tables with Primary Kay } | Know the diference bebeen Saat en eet Trinny Kay ad Forage Koy. a dy Beira be do ER ding Not using Primary Key Using duplicate values in Primary Key Forgetting Forsign Key relationships ‘Allowing NULL in Primary Key @qa—insights | Quality Insights, Better Careers! SQL Queries SQL (Structured Query Language) is used to retrieve and manipulate data from databases using different powerful queries @ SELECT Selects columns from a. table. SELECT column, column2 FROM tablename; Example: SELECT Name, Salary FROM Employes; Returns Nome and Salary of al employes. @ Group By Groups rows that have same values and performs aggregate Function. @ WHERE Filters rows based on a condition SELECT + FROM Employees WHERE Salary > 50000; Example Returns employees whose salary ie greater than 50000, © HAVING Filters groups based on an aggregate condition (wed with GROUP BY). @ orver BY Sorts results in ascending or descending order. SELECT Name, Salary FROM Employees ORDER BY Salary DESC; Example: Displays employees sorted by salary highest to lowest, © umit Limits the number of records returned SELECT Dapertment, COUNT(#) AS Total FROM Employees GROUP BY Department: Example: ‘Shows the rmber of enploees nea depi el @ bistinct Removes duplicate values from the resi ‘SELECT DISTINCT Department FROM Engle Example: Rebs « et of urigue departments ‘SELECT Departent,AVG(Salary) AS Alay FROM Employes GROUP BY Depertnent HAVING AUG(Salary) > 60000; Example Shows departments where average salary it greater than 60000. 7 SELECT: Choose columns WHERE: Filter rows ORDER BY: Sort results GROUP BY: Group rows HAVING: Fiker groups LIMIT: Limit number of rows DISTINCT: Remove duplicates aungegg SELECT * FROM Employees ORDER BY Salary DESC LIMIT 5; Example Retume top 5 highest oid employees Query Reslls (Examples) X Forgetting GROUP BY with aggregate X_ Missing DISTINCT on all clams Toot each query step by step Wate clan, simple ues i {Et Us Smee rr, HATING fr gg | N J Example Table: Employees | SELECT Rn, Sky WHERE Sly > 6010 OROER BY SaliryDESE™ GROUP BY Dine NANG MS > 40 Sep] [eset] samy) | tne cnet) cm ‘com + [ee [we [somo || [Mee [Soy] [ome [my] [Rem [suey] [emt] a) [Dpeteoe | ageing 2 [pm | Fem | oseo |) [Ret | somo] [anim [10000] [neon | somo] [we | 2 | [| ato 9 [ie [ar | Fs Pee] Cree [eee] [ase [ne] reece [| [ren | + [nine [we | seo |} SS me [osooo} [at 2 5 [tere[ 17 | sooo |! [Crees som Comet, Mitabis (7 Be Remember cel Coed Exel =a X Using WERE ih agyage fictine |} hp a fad orteesaees @qa—insights | Quality Insights, Better Careers! @qo—insights 8 SQL Joins SQL JOINs are used to combine rows from two or more tables based on a related column between them. eleceereser ee Table: Departments (D) Ie 2 ¥ eae ay EnpiD | EnpNare | DeptiD ae ee ae { E:DeplDD = DDepADD tar Ren a ws HR Legend 102 [Ans 2 2 Fiance rg ae _ Sn cae TD From Employees (E) oy Tc Nike! a 5 ak From Departments (D) @ INNER JOIN > @ LEFT JOIN air a o Rete Dy snatching rows from left table (E) Gj from both tables. L and matched rows from right table (D = EnplD | Enya [ DepiNane is 2) EnpiD [ Enpane | Depitane ree oe eee wor | Rai | HR Poorer: ~ FROM Employees E 402 Bow Finance INNER JIN Departments D | [102 | Aru | Fnaee | | LePT SOR Deptinents D sf = On Edd = Bw: | Tos [sam [or] [en Eby = poyao, | | M2 Sef @ RIGHT JOIN @ FULL JOIN x Returns all rows Returns all rows: Z from right table (D) then there is a match ‘and matched rows in either left (E) or from left table (E). right (D) table, TDD 401 Select * SELECT © FROM Employees E 302_| Anu | Finance FROM Employes : RIGHT JOIN Departments D | [308 | asin | TT FULL JOIN Departments D 103 [ohn 7 (ON [Link] = [Link]; 40% [Neha [ROLL ON [Link] = [Link]; HOLL [NULL | Marting Wout | NULL | Markating © cross JOIN Returns the Carteson produc 2 [Al Conbintins Each vow of et table ie Use INNER JOIN when you need only matching data combined with every ru Engi Enphane | DepBlone Use LEFT/RIGHT JOIN te include womatched roe oF right tale o1_| ten [ mR from on 5 ‘or | ter | Fane Une FULL TOIN te inca al rows from bth table. ‘SELECT, asia ae CROSS JOIN shouldbe used eareflly (can return | te FROM Emplages el very loge ret et) GROSS JOIN Departments; & Interview Tip Understand the difference betueen types of JOINS tnd be able to predict the catput quickly! X Forging the JOIN condition (lads te CROSS JOIN). Ange speity JOIN condition sing ON dase Use tal lass (E,D) for bar readily Aud SELECT * in production gure Eas th join es Sor bata prorane X- Using INNER JOIN when LEFT JOIN reared, X_ Not handling NULL vlan cuter jo Ne Saing ores coke @ga—insights | Quality Insights, Better Careers! @qainsights Advanced SQ ie Advanced SQL helps us write efficient, reusable and powerful queries to salve complex business problems. @® Subquer OW ly etal ed eat aoery. Undo Fier data or Ween akties SELECT Enplone, Salry FROM Employes © UNION © Combines reds of tn oF ere SELECT qui, Gamers deletn by det) UNIDN UNION ALL SELECT Enghane FROM Engage 2023 | [Rogerd | Dales usc oa SELECT Ena FRO Enlos2028; | [pew ac] Heo @® Views tal al ated SELECT gry 5 Dot mt lr dl Ue Cove: CRERTE VIE w= ighfamers AS SELECT Empl, Enplane, Salary FROM Employes WHERE Stary > 60000; YY ‘Smliy compos ques YY Tnpr secrity Y Reb Dat abstraction @ Best Practices Oo Bhs Fee a ed Sc og a & & Z Interview Tip Pcie writing cml grits ae Oe ese arti Tae lange aed in tert! Ue CTE fr bat eda Fe gor ery da A @qo—insights | WETH Highfarare AS ( Quality Insights, Better Careers! @® CTE (Common Table Expression) Pr “+ Temporary named recall cot, Improves reodabiily and can be reused in the main query, CTE Flow (CTE Defwiton| SELECT EmpID, EmpName, Salary ‘ans Frat) FROM Employees WHERE Salary » (SELECT. NG(Salanyd ae a WHERE Story > 60000 > Main Query Example Outpt: Enphone [Salary Sa ursiiehees ees TE) ‘nw | 65000 ein | Toon @ Window Functions @ CASE WHEN fear ee ete aera + Used for conditional loge in SELECT, WHERE + te the orvert row sth collapsing rove er ORDER BY cancer, er ale ay Fhe sample Ont AIK OVER (EER BF Sarg DESC) AS Rank| RANK a FROM Employes: YY aNSE_RANK WHEN Salary >= 60000 THEN ‘High’ Ton [| 70000_| High oe Y rouse |e sry > 0000 TN nein] [Tig] e000 | eh ae v smo ova | ELSE Lm eke | 85000 | Ped Engle [Sarg [Park] ¥ 60 o¥eR) | B10 AS Slaten = Tim | 70000 | 4 = : FFM Employes, toe | 5000-2 Wow fuaine | fot] s0000 | 8 exp a rove | ae ond odd caldobed | helps in erecting ‘te | 58000 I eresiealtereeests © Indeves “+ Improves qutry performance by Serccaater iets cael B 1 == Remove duplicates (keep Fret) DELETE FROM employees WHERE EmpID NOT IN ( SELECT. MINCEmpID) FROM employees @® Date Validation oinastig loin heertoneret ane flows business re. + Validate ranger, date types, formats cod relationship. Valation Grek Eas Data Type Check | Pye il brome Range Check | Age bees 0 end 20 Formal Check | Enel mash fe wl Uniguenes Chek | Enel shed be wigs Referens Check | DepttD mast wit in ‘operant tate SQL Example SELECT * FROM enplogece WHERE Age NOT BETWEEN 0 AND 120 (OR Email NOT LIKE "KOR.X" Undarttand your data bare casing Keep « backap oF orignal dat, Dera ll nrg sips [Retest fob repeal, Waidate oer lering 66586 @qa—insights | ter Racaon = df drop duplicate subset Nom © Formatting Pig sed oasen clasts rnb chandletagaes aati ta Moat ott Example: a + Proper eave (UPPER/LOWER,Tile) Stndandan dla format “DepD'D Remove special chanactars + Consistent number formate SQL Example SELECT UPPERCTRDMNane}) AS Nae, TO_CHAR(JinDate, “YYYY-M-DD") AS JD REPLACECEmall, "", 7) AS Ena FROM enloees Clann data ia eri for sccurate analyse nd reale inighs. Aaoys describe our clearing approach, arsumptions and Iesinss igeck in iar a Data Cleanin Data Cleaning is the process of fixing or removing incorrect, incomplete, irrelevant or inconsistent data to improve data quality and reliability ® Outliers Pode fleeces tt oy bance, = Die aera Deletion ung TOR Method Median MS ee t i 1 aes a \ ter tel tn eig Ge 3 eee. Oram | ‘siar oo tu teats J Treatment 2S ewes Ad aa es “shee 1. Ren SE nes © Null Handling Spas depress ning: earls dota in doabans Handle proparly in queries ond ana Woe to Handle NULLS: + Use WHERE. TS MULL / 1S NOT NULL + Use COALESCEQ), TSNULLO, TFNULL() Replace NULLA wth defeat vans «lade NULL in eaeltios SQL. Example: ‘SELECT CCOALESCE(Phone, ‘Net Provded’) AS Phone, TSNULLGlary, 0) AS Salary FROM enplyeee WHERE’ Dep IS NOT NUL; Dilting data without veriPcaion Nt handing NULLs properly dorcel aad eee Trconsstent Formatting Not vdating date oer clearing Quality Insights, Better Careers! @qa—insights 12 Python for Data Analysis Puthon is one of the most popular programming languages for Data Analysis due to its simplicity, powerful libraries and strong community @® Why Python? Fang te barn od rad Rik cnn for Date Analise 8 AL Open source and free Lage comunity ager Mert sith ol mje 5 (Window, Mac, Lins) Gea iteration ith SQL, Excl, APIs, et Sacre @® Pandas Pendaa i a pari Urary for dla main eilzaeih i tees shel Ste reed te 1 Dan ding 8 betermatin Resi abseil eats 1 Mans ining data iy ® NumPy NamPy (Mmarzal Python) ia the fundlion rary ete cal ooton tT ay Fate: SN eeeieel oes thereat + Fast mathemati operations Fon fr Una. dar tn, Enangle 3D Array > npert anpy oe oo aoe = sprry(l’s 2, 3, 4D) meret eragl2, 4, 6, 8D, ® Tupyter Notebook a yaar eats ge Pe sons / me Pee Sue a upyten Reece Pe Saat Spek eee eee D> af info) Rangelndex: 3 entrias, O ts 2 Deta clams (ttal 4 columns) Estep Example Cal a ipo pads ap ak a ea Fim] [FPR Pe] || Trt rs Sales": (800, 790, 600]) re head D> dE = pl DataFrana(data) ‘ou_| 700 oat >> dead) 2 | sim | co eee ©® DatoFrames (Pandas) © Basic Workflow in Python for Data Analy: 1 Daafone is 2-Sinma ald date srctre = Sates © srrinee (REET | ee one Grandin ret ii ep st FT areal, deat 7 pale ie ans Binine (See |} 0] Red | 25 | Hyd | 500 + df. describe) r = —— Rows [1 [fou | 27 | Bl | WO] + akshope (J) 2 conn rope [ote ne | “Ea [ake [20 [id [600 | + at eines ener spent Pa type 2 hate et soo SI GG) rete te Nene, Age, City, Sales We lee oo mer cnt Uae mearingfl variable naman Be ready fo eli: bees Inte at pe, ara, ered Beem, © Ve yu hr nn wt od wiles epee els a Waldo data st er sep Vistse te ndarstnd bt eke 5. Vale 6 dew igs [Br | pigaaae X Frnt haa ming wan. |b Rey X Naty aa ye + Pena | 2 gg en vind tin | > Ph fa eaien eet Pore i % Nt dence the vw \ Saikt-tern @qainsights | Quality Insights, Better Careers! @qa—insights 13 Data Visualization Good visualizations turn data into insights. Choose the right chart to tell the right story! © Bar Chart Nalbctrrese ere eee + Vertal o Horie brs ha oD Category When to use + Great for comparing quankiies between different. groupe Examples: Sales by Product, @® Line Chart eeafimatr sine Canal ofc tons als 100 one. Bi Bs, Te Rb Month When to use: + deal for showing trends, patterns and changes over tine Examples: Monthly Revenue, Website Uses i Regln Traffic Or Te. ® Histogram © Scatter Plot © Show dation Feri + Show ralatlonship babwaen rare data, th mere erable, Dalat groped te bie + Helps identity coralation, ‘0 10 x 0 r oo En Me jn MEE » » LAZIa ae on mo oe en mad aaa ee ‘Nbetisog Spend ($4) When to use: When to use: ae Use to understand the Frequency Aistristion of mameric data. + Use to find coralation, clusters, or patterns between voriables, @ Pie Chart + Show part-to-uhole relationship + Tetal must be 100%. When to use + Use hen you have feu catagories (5 er less) te show proportions Examples: Market Share, Budget Distribution © Heatmap 1+ Show patterns in data using celor intensity. + Great for large datasets a & Ten Feb Mar Apr May. Sin when to use + Use to visualize density, intensity or Frequancy in «madris: = Examples: Age Ditton, dail a eg Seah, | ede id a tates Tae Serer Ditrbtin Hight we Wei Sale by Day & How a SERIE) (hat age anc unt See || es 2 ig Pat my ei Tie hart [Toe Ste | Trond [ Ravn Ow Te || | Avid 3D charts and anracesery | | % Wrong chart for the wrong date Feat | Cag —| pets | “Ra Se ‘ed X Ming bl, aso wis, apa hater Paeaee Pigame ||| v Mae ealiadseae eis cep ree Nee Scaler Plat | Numeric we Numeric | Relationship | Salas ow Ad Spend jae Tain [etree Raney tool | | Yar snl dr 2% NA Neiiing In Ree nein tv @qa—insights | Quality Insights, Better Careers! @qa—insights 14 Power BI - End to End Workflow Power BI helps us connect, transform and visualize data to build interactive dashboards and meaningful reports ® Import Data @® Power Query (Data Transformation) Data Model. & Relationships + Comet to mate data sorsa__| © Clay shige and traf data. before + Dota model is the foundation of lide Exal, C5V, SQL, Wb, APT, lending te te Rover BE mel ower BI rr Dalabees, ShersPeint, te + Stage: Remove Columns, Change Type, + Graal ralalionhips between tables Far Rows, Spit Columas, Merge, Append, ating hays. Fl Misting, Unpvet, Group By, ee Enample Data Mode (Star Schema) & & Tow Oy Ee iar 1 Ex SQL CSV eb Tse Tefen Ml Gln Vow se oo ors ch, Ned 8868 oe tee Other APL Felder More | Example St = Dababoows edt ction ee Te D [um] Tae | DD a Power BL Desktip “> Get Data -> = — Chote Saea Led camer ena Sept te ee | 1-6 5 ete Pang Ga ne) 13 Py tay PC: Foon Ka @® DAX (Data Analysis. Expressions) © Dashboard Creation DIO is « femal lnguge ated fo ete clio, 1 Bald nteractive ond sigh dashbourds wing rears ond Ps uals, cre and iar > O(a cinna bl craaiatp Drag felde to vanle format and bls Dated Lee Common Vile ce Te a es Y itl a ERAGE) | here of aw sae rm Y fig cut CUNT) | Cont oe ip ser al paar CmSnATED [rae ta] | MATE coos FIER) Files « tale Nearer o Ss fe aL fates i} Dont Chart | Table aise Stier aapets DATESYTDO) | 1D etn | | sap vate Ss « S orl 0 attri] | toon i> sow, | | MPR | SEE | [le | AD | |v sete ia abet om Mp Seater Pat _|_KPL ore Power BI Key Componente Se i pag le Weta a ede le mars peony cee Optnie dal mde env dpe, soe tle), Fe Pees EL tpt 3 lager: Dela Source > Power Query —> ala Model > Report (Vials) Be ready to explain cach leer! X Landing wan dae X Crating eames on exratta X Ung tos mary val in single ge XN dang tna oa, X Tgoring ab ype i Putra Get Date > Comet Poser Quy > Taran Date Moist’ > Relate DAX Cala Raper iw > Vali Pibuth > Shore SA888 J! @aa—insights | Quality Insights, Better Careers! @qa—insights 15 Tableau - From Data to Stories Tableau helps us connect, visualize and share dota through interactive dashboards and. stories. sights © Tableau Interface ® Worksheets ® Dashboards Teac nerfice ts wer endl A verah te baie baling | Combine mapa wershets in 0 calesla arefied Ble fr any vinlzaton Sal feesk ts at = Key Ares: mee Ta as We Pad Soy Rape Ry dea Roane ptialeuau ane omeae pele Bieyafe wid ISO Peer e Ih4 hla eit parca ecard + Fiters > Lint data to hat + Responsive ond interactive on salad SPR 5 elie aca penta oa ow sazom | $aask | 2356 | sn Sales by Cater Sale by Regn SF 9: aRGERE r ft i E ® Storytelling (Stories) © Filters ®© Best Practices a Protech your dala Ue « sd shew Firs bly go Sous othe ight date. F Kenpit single end freed ee mening tiles & labels Use conn eslrs od too many charts Highlight hay insights (KP, Tens) Optinize performance (Aggregation, Exdrocts, Fiters) Design for your audience “yes of Fer: + Conta Fier = Aly fst Diente ilar = Fer by fal ‘Mesa Fil ~ Fler by eatin Tag N Fler = Show bp N ols Feat Date Fier = Dyan dale range Benfte ita partes Sera aa J + a test, age, sortations z © Grek ir probe 2 Stary Flow Example: Rams ia Fler Example (Reson & ipl how gen wil Id « desk From data te insights Aly pare aa Nt ein Flere > Ovrlanded et x eee, X Per tle / no contest od pro, Whales “> Ours YY Detheardt > Conkne & Detar YS > Comme nes Cenedh => Prepare > Vein > Dashboard > Share > Daciine La Hae pe Nit valdiing date bre alin @ga—insights | Quality Insights, Better Careers! @qa—insights 16 KPIs & Business Metrics KPIs (Key Performance Indicators) help Data Analysts measure performance, track progress and drive data-driven decisions. @® Revenue ® Profit ® Growth Rote ©® Customer Retention Rate Tal income gueratd From |The emt aft afar sabecing | Manse the rela of irene Pacaniage of ctoers ho ear ease ieee aetea | aneaT at cesta eee ested uls eceCaN [Reema] [Ferma] [Fema] [Formals] pA: Hn (Cantons End = New Catone) eos ae ‘ators Start 100 Price = $100, Quankty = 1,200 Revenue = $120,000 Ee an > Pewut = $20,000 Cates $800 a ae uioogne = 20 —> Profit = $40,000 a - End = 850 femeunes —> Retention Rate = 65% é j Tn Fab Par By Pay Son © Churn Rate © Conversion Rote @ ROT (Return on Investment) sea age gee cet 8 Ole case eel ae ese neyo atc are en ce leet [aie] (Ferma: Caan REI ROT (1) = (Wat Pht / Intent Cat) = 100 (Cement Vatere) = 100) Investment = $50,000, Net Profit = $12,500 > ROL = 25% Example Start = 1,000, Lest = 150 > Churn Rate = 15% 15% Caters Chared Ror = 25% Para ees) Define clear Farmala & dale sour “Tack rupley & conta Compare. ith targets & benchmarks Vesalte KPa in dathboard Faaltomet Soca anil epprtaitin 2. rks ‘lig oan sth Drcinate gale ‘Supperk data-driven cisions Tngrore rely & prolly Tracking toe many KPIs Using song or inconitrk dat Tyving contd tranda Focusing ely on vastly mcbrics No taking action on insights (ERB tp ce ee ee atin i coda rtaareae) sit re al ach Pd hae chal a ap? | 468658 XXX @qa—insights | Quality Insights, Better Careers! sights @ ® @ © ay End-to-End Data Analyst Project ‘A complete Data Analytics project follows a structured workflow from understanding the problem to driving business deci d QP © a © Undated ses. performance ba produc and regi, + Terily top & btion eee talerree © Raconmand. ait te inprve rover, + Delabcee (Sab, myst) || ¢ Minow dps (of @aloligl lS |-la Se! sau Problem Cale Clan sat Python Tris Reconmedlina Statement Data Date Analgis ——Abalysa—(Viualzabion) & ations © Problem Statement @ Collec. Data )(® clean Data ® SOL Analysis Dafa tha bunts poton, | | Galbr dla fn va ef ciara etd | [Unsafe eet thet ed seine ac, ||| aren sh a mare tt | | ed vr meng we Example: | Gaample rate Example Query SECT regi, shan) AS tase CUMING ei) 18 ates WARE rede BETWEEN “mnt 0 Parpare: Tep performing regions ay tte les ed torr cr © Python Analysis netomat eee Tapert ped as phrase en’) pada = gry gg) reeviany eee eee | | + 69V/ Gd Fi Fe date type || = art Standards formas + Mae Scoping Wade date + Tinkeprly danas Bare Hee || (eis) epee | 2 [wu | > [2 | zo © Dashboard (Visualization) | @ Insights ] Greate interactive dashboards to | | Intel the date to coer | communica sgh ay Rdg. Toa Engle Ing: ee + ast rogion a the | + Lester Sto Beate | «Tahal enhgery drat the most reves > Encl Dachboarde eS | ae aay || eee | oem] | | * Se rae eo ee) Sam] oe [som [aes ||| eve Pap Agee fer I eect oe Mi ty Saget ym ||] oe | @ = ae EA ||| | ) [® Recommendations & Actions: alee [cies as Pemaececaea Seis eae eee es ie aaa, ania ieee eared v v v Dela -> Tight > Action > Busine. Impact Pf Dated he Renn Flow ths werfow fr any Dla Ant prj -—[ eater — Wilda den bre eral ee ils lenis epee Use version cos (GO) Aidomatereplive tase Saari tied Comma ite clay 1 3. 5 66666856 @qa—insights | Quality Insights, Better Careers! Mor adelisrealelpniae eae angie racy Katp &dea, cocion and imped deinen! ——— Protlem > 2. Agpronch Toole Used > 4. Insights Tapect @ga—insights 48 Interview Preparation & Cheat Sheet ‘Ace your Data Analyst interviews with the right. know practical skills and strong portfolio! A. What dows Dale Anil da? || Y Write simple, sean end otinied || Y Master formas: VLOOKUP, ¥ Lear Pandas for date 2. hak the dificence bates ure LOOKUP, INDEX MATCH, eniplaton SL and Ena? Maser SELECT, WHERE, GROUP BY, || SUMS, ‘COUNTIES. Prin NanPy for mamaria Explain the SQL JOON type HAVING, ORDER BY. > Wl normalization? Hao do yo handle iting alae? Wat othe diffrence betwen snd Wada Ft snd tenafenaion Use Pk Tle & Pot Chats] | operation Y Prati JOINS, Subqrite, CTEs Use Matt & Staborn for awn Prine Galy for slang _ | WHERE and HAVING? FU mules | Ye ith re-use Been finale rt eateries Hos de you ede Ye goth? © Top Interview Questions | (@) SQL Tips @® Excel Tips @® Python Tips Use condition formalin if eaten ada Inco ekdeairons th oa fe aii, ommend cde LIMIT and ORDER BY ha is «pny hy og bg prataplernlge Pala eaterenye Poa 4 Rap i ty mies || Ue Sr ae Exton rd , = pr Paci witht datas || | | FROM —» wneRe -» crour By || { ; oleae + HAVING —> SELECT > | ¢ ll dearly ORDER BY + LIMIT L 3 © Dashboard Tips © Portfolio Tips | (@ Resume Tips Pid gletraptce te ||P un, Mots Peemrese Olas fee eas o Wan 2 tty We ba Fea ee || peace Tomei ghee Cremel a Nica aoage eae trap ae Show pl tana, eppah, Pen, Pe BY, Tec Ui eaten i, Cape nd gi te Bo parameters ¥ Build dashboards (Poser BI / Tablas Mention tod and techoolagies. Pye 9 het pepsin Naiael pa aoes Soatiieia Ya te ROME ath ay wie] | Y te mtr en nen, vw Raag Rept stoped |] pad vn ded Gb ote] | Y Map hd gep eS po opt &- @ || d )-(B)-\O #7) at © apa This Ey Bow Fel, Pot, Raden nf, Por BL Tian, 3-5 Endod GN, Cae Sadi, rape, Naas Topas Goal Aygegsin Ra Gory, Won” ala Maddy, Pu wth Deiter pane ene nes a DAK, Gate Toe Sere Regine DX Common Mistakes GY Tnteriew Cheat Sheet (Quick Recap) Y key Takeaways XN dr he in SOL: SELECT, JOD, GROUP BY, HAGNG, CTE, Wndm ction | | Y Undead the ba X ring oer prin emt | | Gat, ODA, ROOK, Pk Tl, Pw Ory Cone bs oi peas Pies (asd, gr, Mth San 7 ie bea de foe X Oo dort We Bina mat, b ean San || tn ty tte | Ra X_N ping wth ra aa Free: Ba Undrang, Ini, Sng V Donia atviat | Pere @gainsights | Quality Insights, Better Careers!

You might also like