Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added Business_Challenge_EDA_and_SQL_Presentation.pptx
Binary file not shown.
101 changes: 101 additions & 0 deletions Top 100 Languages.csv
Original file line number Diff line number Diff line change
@@ -0,0 +1,101 @@
Language,Total Speakers,Native Speakers,Origin
English,1132366680,379007140,Indo-European
Mandarin Chinese,1116596640,917868640,Sino-Tibetan
Hindi,615475540,341208640,Indo-European
Spanish,534335730,460093030,Indo-European
French,279821930,77177210,Indo-European
Standard Arabic,273989700,,Afro-Asiatic
Bengali,265042480,228289600,Indo-European
Russian,258227760,153746530,Indo-European
Portuguese,234168620,220762620,Indo-European
Indonesian,198733600,43364600,Austronesian
Urdu,170208780,68622980,Indo-European
Standard German,132176520,76090520,Indo-European
Japanese,128350830,128229330,Japanic
Swahili,98327740,16027740,Niger-Congo
Marathi,95312800,83112800,Indo-European
Telugu,93040340,82040340,Dravidian
Western Punjabi,92725700,92725700,Indo-European
Wu Chinese,81501290,81437890,Sino-Tibetan
Tamil,80989130,75039130,Dravidian
Turkish,79779360,79399060,Turkic
Korean,77264890,77264890,Koreanic
Vietnamese,76950770,75950770,Austronesian
Yue Chinese,73538610,73136610,Sino-Tibetan
Javanese,68277600,68277600,Austronesian
Italian,67894920,64844820,Indo-European
Egyptian Spoken Arabic,64618100,64618100,Afro-Asiatic
Hausa,63428100,43928100,Afro-Asiatic
Thai,60657660,20657660,Kra-Dai
Gujarati,60588970,56408970,Indo-European
Kannada,56463310,43563310,Dravidian
Iranian Persian,52782160,52782160,Indo-European
Bhojpuri,52405300,52245300,Indo-European
Southern Min Chinese,50462190,50075190,Sino-Tibetan
Hakka Chinese,48467490,48467490,Sino-Tibetan
Jinyu Chinese,46900000,46900000,Sino-Tibetan
Filipino,45000000,,Austronesian
Burmese,42912350,32912350,Sino-Tibetan
Polish,40378030,39713030,Indo-European
Yoruba,39844260,37844260,Niger-Congo
Odia,38051547,34461520,Indo-European
Malayalam ,37829870,37134870,Dravidian
Xiang Chinese,37300000,37300000,Sino-Tibetan
Maithili,34085000,33890000,Indo-European
Ukrainian,33082790,27282790,Indo-European
Moroccan Spoken Arabic,32608700,27488700,Afro-Asiatic
Eastern Punjabi,32601140,32600670,Indo-European
Sunda,32400000,32400000,Austronesian
Algerian Spoken Arabic,32387600,29387600,Afro-Asiatic
Sundanese Spoken Arabic,31940300,31940300,Afro-Asiatic
Nigerian Pidgin,30000000,,Indo-European
Zulu,27779100,12079100,Niger-Congo
Igbo,27014190,27014190,Niger-Congo
Amharic,25880630,21880630,Afro-Asiatic
Northern Uzbek,25164820,25164820,Turkic
Sindhi,24615591,24615550,Indo-European
North Levantine Spoken Arabic,24587400,24587400,Afro-Asiatic
Nepali,24528840,15848840,Indo-European
Romanian,24345750,24345750,Indo-European
Tagalog,23808890,23646890,Austronesian
Dutch,23069480,23069480,Indo-European
Sa'idi Spoken Arabic,22400000,22400000,Afro-Asiatic
Gan Chinese,22100000,22100000,Sino-Tibetan
Northern Pashto,20850900,20850900,Indo-European
Magahi,20746400,20735600,Indo-European
Saraiki,20009000,20009000,Indo-European
Xhosa,19183300,8183300,Niger-Congo
Malay,19092180,16092180,Austronesian
Khmer,17591230,16591230,Austronesian
Afrikaans,17534580,7234580,Indo-European
Sinhala,17287880,15287880,Indo-European
Somali,16321530,16225930,Afro-Asiatic
Chhattisgarhi,16300000,16300000,Indo-European
Cebuano,15942480,15942480,Austronesian
Mesopotamian Spoken Arabic,15655900,15655900,Afro-Asiatic
Assamese,15329040,15328790,Indo-European
Northeastern Thai,15000000,15000000,Kra-Dai
Northern Kurdish,14605670,14605670,Indo-European
Hijazi Spoken Arabic,14524500,14524500,Afro-Asiatic
Nigerian Fulfulde,14485000,14485000,Niger-Congo
Bavarian,14359000,14359000,Indo-European
Bamanankan,14102320,4102320,Niger-Congo
South Azerbaijani,13813750,13813750,Turkic
Northern Sotho,13731000,4631000,Niger-Congo
Setswana,13664710,5814710,Niger-Congo
Souther Sotho,13524520,5624520,Niger-Congo
Czech,13386850,10704850,Indo-European
Greek,13170460,13111960,Indo-European
Chittagonian,13000000,13000000,Indo-European
Kazakh,12934060,12934060,Turkic
Swedish,12804900,9654900,Indo-European
Deccan,12800000,12800000,Indo-European
Hungarian,12574280,12574280,Uralic
Jula,12486000,2208000,Niger-Congo
Sadri,12131225,5131180,Indo-European
Kinyarwanda,12120250,12120250,Niger-Congo
Cameroonian Pidgin,12000000,,Indo-European
Sylheti,11800000,10300000,Indo-European
South Levantine Spoken Arabic,11601100,11601100,Afro-Asiatic
Tunisian Spoken Arabic,11571600,11571600,Afro-Asiatic
Sanaani Spoken Arabic,11350000,11350000,Afro-Asiatic
70 changes: 70 additions & 0 deletions business_questions.sql
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
SELECT * FROM top_languages_db.top_languages_db;

USE top_languages_db;

SHOW tables;

SHOW COLUMNS FROM top_languages_db;

DESCRIBE top_languages_db;

-- 1. What are the top 5 most spoken languages in the world by total speakers?
SELECT Language, "Total Speakers"
FROM top_languages_db
ORDER BY "Total Speakers" DESC
LIMIT 5;

-- 2. What are the top 5 languages with the highest number of native speakers?
SELECT Language, "Native Speakers"
FROM top_languages_db
ORDER BY "Native Speakers" DESC
LIMIT 5;

-- 3. Which languages have the largest difference between native speakers and total speakers?
SELECT Language, ("Total Speakers" - "Native Speakers") AS Difference
FROM top_languages_db
ORDER BY Difference DESC
LIMIT 5;

-- 4. What is the proportion of native speakers compared to total speakers for each language?
SELECT Language, ("Native Speakers" / "Total Speakers") * 100 AS Native_To_Total_Ratio
FROM top_languages_db
ORDER BY Native_To_Total_Ratio DESC;

-- 5. Which language origins (language families) have the highest total number of speakers?
SELECT Origin, SUM("Total Speakers") AS "Total Speakers"
FROM top_languages_db
GROUP BY Origin
ORDER BY "Total Speakers" DESC;

-- 6. How has the number of native and total speakers for the main languages evolved over time?
SELECT Language, Year, "Total Speakers", "Native Speakers"
FROM language_speakers_history
WHERE Language IN ('English', 'Mandarin Chinese', 'Hindi', 'Spanish', 'French')
ORDER BY Year ASC;

-- 7. Which languages are the most spoken in specific continents (e.g., Europe)?
SELECT Language, Continent, "Total Speakers"
FROM top_languages_db
WHERE Continent = 'Europe'
ORDER BY "Total Speakers" DESC;

-- 8. Which language has seen the greatest growth in total speakers in recent decades?
SELECT Language, (MAX("Total Speakers") - MIN("Total Speakers")) AS Growth
FROM language_speakers_history
GROUP BY Language
ORDER BY Growth DESC
LIMIT 5;

-- 9. Which languages have more speakers outside their country of origin?
SELECT Language, ("Total Speakers" - "Native Speakers") AS Foreign_Speakers
FROM top_languages_db
WHERE Foreign_Speakers > "Native Speakers"
ORDER BY Foreign_Speakers DESC;

-- 10. Which countries contribute the most to the total number of speakers of a specific language?
SELECT Country, Language, SUM("Total Speakers") AS "Total Speakers"
FROM language_by_country
WHERE Language = 'English' -- Substitua pela língua desejada
GROUP BY Country
ORDER BY "Total Speakers" DESC;
Loading