s444409/BAD_Analytics
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Marcin 2019-05-13 17:47:18 +02:00
commit b3a3a28011
9 changed files with 161 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

109
R/bad_proj_analytics.Rmd Normal file
View File

@ -0,0 +1,109 @@
---
title: "BAD_Proj_Analytics"
author: "Marcin Kostrzewski"
date: "13/05/2019"
output: pdf_document
---
```{r, echo=FALSE}
con <- DBI::dbConnect(odbc::odbc(),
driver = "SQL Server",
database = "dbad_flights",
UID = "dbad_s444409",
PWD = "qAOKvlYA6e",
server = "mssql-2016.labs.wmi.amu.edu.pl",
port = 5432)
```
## Jakie było średnie opóźnienie przylotu?
```{sql, connection=con, tab.cap = NA}
SELECT CAST(AVG(arr_delay) AS NUMERIC(30,3)) AS 'Average delay (minutes)'
FROM Flight_delays
WHERE arr_delay IS NOT NULL;
```
## Jakie było maksymalne opóźnienie przylotu?
```{sql, connection=con, tab.cap = NA}
SELECT CAST(MAX(arr_delay)/60 AS NUMERIC(30,3)) AS 'Max delay (hours)'
FROM Flight_delays
WHERE arr_delay IS NOT NULL;
```
## Który lot miał największe opóźnienie przylotu?
```{sql, connection=con, tab.cap = NA}
SELECT carrier AS 'Carrier',
origin_city_name AS 'Origin',
dest_city_name AS 'Destination',
fl_date AS 'Date',
arr_delay AS 'Delay (minutes)'
FROM Flight_delays
WHERE arr_delay = (SELECT MAX(arr_delay)
FROM Flight_delays
WHERE arr_delay IS NOT NULL);
```
## Które dni tygodnia są najgorsze do podróżowania?
```{sql, connection=con, tab.cap = NA}
SELECT CASE WHEN day_of_week = 1 THEN 'Monday'
WHEN day_of_week = 2 THEN 'Tuesday'
WHEN day_of_week = 3 THEN 'Wednesday'
WHEN day_of_week = 4 THEN 'Thursday'
WHEN day_of_week = 5 THEN 'Friday'
WHEN day_of_week = 6 THEN 'Saturday'
WHEN day_of_week = 7 THEN 'Sunday'
END AS 'Day',
AVG(arr_delay) AS 'Average Delay (minutes)'
FROM Flight_delays
GROUP BY day_of_week
ORDER BY AVG(arr_delay) DESC;
```
## Które linie lotnicze latające z San Francisco (SFO) mają najmniejsze opóźnienia przylotu?
```{sql, connection=con, tab.cap = NA}
SELECT F1.carrier AS 'Carrier',
(SELECT AVG(F2.arr_delay) AS 'avg_delay'
FROM Flight_delays F2
WHERE F1.carrier = F2.carrier
GROUP BY F2.carrier) AS 'Delay (minutes)'
FROM Flight_delays F1
WHERE F1.origin_city_name LIKE 'San Francisco%'
GROUP BY F1.carrier
ORDER BY "Delay (minutes)" ASC;
```
*Pojawiające się w tabeli wartości ujemne oznaczają, że średnio samoloty lądowały wcześniej, niż przewidziano, czyli były przyśpieszone.*
## Jaka część linii lotniczych ma regularne opóźnienia, tj. jej lot ma średnio co najmniej 10 min. opóźnienia?
```{sql, connection=con, tab.cap = NA, echo=FALSE}
SELECT (SELECT COUNT(*)
FROM (SELECT F1.carrier,
(SELECT AVG(arr_delay)
FROM Flight_delays F2
WHERE F1.carrier=F2.carrier
GROUP BY F2.carrier
HAVING AVG(F1.arr_delay)>10) AS 'avg_delay'
FROM Flight_delays F1
GROUP BY F1.carrier) AS t
WHERE t.avg_delay IS NOT NULL) / CAST((SELECT COUNT(*)
FROM (SELECT COUNT(*) AS 'count'
FROM Flight_delays
GROUP BY carrier) AS T) AS FLOAT) AS 'Part of continuous delays';
```
## Jak opóźnienia wylotów wpływają na opóźnienia przylotów?
```{r, con, echo=FALSE}
data <- DBI::dbGetQuery(con, "SELECT dep_delay,
arr_delay
FROM Flight_delays
WHERE dep_delay IS NOT NULL AND arr_delay IS NOT NULL;")
library(knitr)
res <- cor(data, use = "all", method = "pearson")
kable(res[2:2])
```

BIN
R/bad_proj_analytics.pdf Normal file
View File

Binary file not shown.

3
SQL files/1.sql Normal file
View File

@ -0,0 +1,3 @@
SELECT AVG(arr_delay)
FROM Flight_delays
WHERE arr_delay IS NOT NULL;

3
SQL files/2.sql Normal file
View File

@ -0,0 +1,3 @@
SELECT MAX(arr_delay)/60
FROM Flight_delays
WHERE arr_delay IS NOT NULL;

9
SQL files/3.sql Normal file
View File

@ -0,0 +1,9 @@
SELECT carrier,
origin_city_name,
dest_city_name,
fl_date,
arr_delay
FROM Flight_delays
WHERE arr_delay = (SELECT MAX(arr_delay)
FROM Flight_delays
WHERE arr_delay IS NOT NULL);

12
SQL files/4.sql Normal file
View File

@ -0,0 +1,12 @@
SELECT CASE WHEN day_of_week = 1 THEN 'Monday'
WHEN day_of_week = 2 THEN 'Tuesday'
WHEN day_of_week = 3 THEN 'Wednesday'
WHEN day_of_week = 4 THEN 'Thursday'
WHEN day_of_week = 5 THEN 'Friday'
WHEN day_of_week = 6 THEN 'Saturday'
WHEN day_of_week = 7 THEN 'Sunday'
END AS 'day_of_week',
AVG(arr_delay)
FROM Flight_delays
GROUP BY day_of_week
ORDER BY AVG(arr_delay) DESC;

9
SQL files/5.sql Normal file
View File

@ -0,0 +1,9 @@
SELECT F1.carrier,
(SELECT AVG(F2.arr_delay)
FROM Flight_delays F2
WHERE F1.carrier = F2.carrier
GROUP BY F2.carrier) AS 'avg_delay'
FROM Flight_delays F1
WHERE F1.origin_city_name LIKE 'San Francisco%'
GROUP BY F1.carrier
ORDER BY avg_delay ASC;

13
SQL files/6.sql Normal file
View File

@ -0,0 +1,13 @@
SELECT (SELECT COUNT(*)
FROM (SELECT F1.carrier,
(SELECT AVG(arr_delay)
FROM Flight_delays F2
WHERE F1.carrier=F2.carrier
GROUP BY F2.carrier
HAVING AVG(F1.arr_delay)>10) AS 'avg_delay'
FROM Flight_delays F1
GROUP BY F1.carrier) AS t
WHERE t.avg_delay IS NOT NULL) / CAST((SELECT COUNT(*)
FROM (SELECT COUNT(*) AS 'count'
FROM Flight_delays
GROUP BY carrier) AS T) AS FLOAT) AS 'part_of_cont_delays';

3
SQL files/7.sql Normal file
View File

@ -0,0 +1,3 @@
SELECT dep_delay,
arr_delay
FROM Flight_delays;