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

Added more queries

Browse Source
This commit is contained in:
Marcin 2019-05-13 20:08:00 +02:00
parent b3a3a28011
commit a52a423413
5 changed files with 139 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

91
R/bad_proj_analytics.Rmd
View File

@ -1,10 +1,12 @@
--- ---
title: "BAD_Proj_Analytics" title: "BAD_Analytics_Project"
author: "Marcin Kostrzewski" author: "Marcin Kostrzewski"
date: "13/05/2019" date: "13/05/2019"
output: pdf_document output: pdf_document
--- ---
Raport został wygenerowany przy użyciu danych udostępnionych przez [Departament Transportu Stanów Zjednoczonych](https://www.transtats.bts.gov/DL_SelectFields.asp?Table_ID=236)
```{r, echo=FALSE} ```{r, echo=FALSE}
con <- DBI::dbConnect(odbc::odbc(), con <- DBI::dbConnect(odbc::odbc(),
driver = "SQL Server", driver = "SQL Server",
@ -15,7 +17,7 @@ con <- DBI::dbConnect(odbc::odbc(),
port = 5432) port = 5432)
``` ```
## Jakie było średnie opóźnienie przylotu? # Jakie było średnie opóźnienie przylotu?
```{sql, connection=con, tab.cap = NA} ```{sql, connection=con, tab.cap = NA}
SELECT CAST(AVG(arr_delay) AS NUMERIC(30,3)) AS 'Average delay (minutes)' SELECT CAST(AVG(arr_delay) AS NUMERIC(30,3)) AS 'Average delay (minutes)'
@ -23,7 +25,7 @@ FROM Flight_delays
WHERE arr_delay IS NOT NULL; WHERE arr_delay IS NOT NULL;
``` ```
## Jakie było maksymalne opóźnienie przylotu? # Jakie było maksymalne opóźnienie przylotu?
```{sql, connection=con, tab.cap = NA} ```{sql, connection=con, tab.cap = NA}
SELECT CAST(MAX(arr_delay)/60 AS NUMERIC(30,3)) AS 'Max delay (hours)' SELECT CAST(MAX(arr_delay)/60 AS NUMERIC(30,3)) AS 'Max delay (hours)'
@ -31,7 +33,7 @@ FROM Flight_delays
WHERE arr_delay IS NOT NULL; WHERE arr_delay IS NOT NULL;
``` ```
## Który lot miał największe opóźnienie przylotu? # Który lot miał największe opóźnienie przylotu?
```{sql, connection=con, tab.cap = NA} ```{sql, connection=con, tab.cap = NA}
SELECT carrier AS 'Carrier', SELECT carrier AS 'Carrier',
@ -45,7 +47,7 @@ WHERE arr_delay = (SELECT MAX(arr_delay)
WHERE arr_delay IS NOT NULL); WHERE arr_delay IS NOT NULL);
``` ```
## Które dni tygodnia są najgorsze do podróżowania? # Które dni tygodnia są najgorsze do podróżowania?
```{sql, connection=con, tab.cap = NA} ```{sql, connection=con, tab.cap = NA}
SELECT CASE WHEN day_of_week = 1 THEN 'Monday' SELECT CASE WHEN day_of_week = 1 THEN 'Monday'
@ -62,7 +64,7 @@ GROUP BY day_of_week
ORDER BY AVG(arr_delay) DESC; ORDER BY AVG(arr_delay) DESC;
``` ```
## Które linie lotnicze latające z San Francisco (SFO) mają najmniejsze opóźnienia przylotu? # Które linie lotnicze latające z San Francisco (SFO) mają najmniejsze opóźnienia przylotu?
```{sql, connection=con, tab.cap = NA} ```{sql, connection=con, tab.cap = NA}
SELECT F1.carrier AS 'Carrier', SELECT F1.carrier AS 'Carrier',
@ -78,7 +80,7 @@ ORDER BY "Delay (minutes)" ASC;
*Pojawiające się w tabeli wartości ujemne oznaczają, że średnio samoloty lądowały wcześniej, niż przewidziano, czyli były przyśpieszone.* *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? # 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} ```{sql, connection=con, tab.cap = NA, echo=FALSE}
SELECT (SELECT COUNT(*) SELECT (SELECT COUNT(*)
@ -96,8 +98,9 @@ SELECT (SELECT COUNT(*)
GROUP BY carrier) AS T) AS FLOAT) AS 'Part of continuous delays'; GROUP BY carrier) AS T) AS FLOAT) AS 'Part of continuous delays';
``` ```
## Jak opóźnienia wylotów wpływają na opóźnienia przylotów? # Jak opóźnienia wylotów wpływają na opóźnienia przylotów?
```{r, con, echo=FALSE}
```{r, connection=con, tab.cap = NA}
data <- DBI::dbGetQuery(con, "SELECT dep_delay, data <- DBI::dbGetQuery(con, "SELECT dep_delay,
arr_delay arr_delay
FROM Flight_delays FROM Flight_delays
@ -107,3 +110,73 @@ library(knitr)
res <- cor(data, use = "all", method = "pearson") res <- cor(data, use = "all", method = "pearson")
kable(res[2:2]) kable(res[2:2])
``` ```
# Która linia lotnicza miała największy wzrost (w wartościach bezwzględnych) średniego opóźnienia przylotów w ostatnim tygodniu miesiąca, tj. między 1-23 a 24-31 lipca?
```{sql, connection=con, tab.cap = NA, max.print = NA}
SET NOCOUNT ON
DECLARE @1_23avg TABLE
(
carrier VARCHAR(50),
avg FLOAT
);
INSERT INTO @1_23avg
SELECT carrier,
AVG(avg1) AS 'avg1A'
FROM (SELECT carrier,
AVG(arr_delay) AS 'avg1'
FROM Flight_delays
WHERE month = 7
GROUP BY carrier, day_of_month
HAVING day_of_month BETWEEN 1 AND 23) AS T1
GROUP BY carrier;
DECLARE @24_31avg TABLE
(
carrier VARCHAR(50),
avg FLOAT
);
INSERT INTO @24_31avg
SELECT carrier,
AVG(avg2) AS 'avg2A'
FROM (SELECT carrier,
AVG(arr_delay) AS 'avg2'
FROM Flight_delays
WHERE month = 7
GROUP BY carrier, day_of_month
HAVING day_of_month BETWEEN 24 AND 31) AS T2
GROUP BY carrier;
SET NOCOUNT OFF;
SELECT T1.carrier AS 'Carrier',
T1.avg-T2.avg AS 'Delay growth'
FROM @1_23avg T1 INNER JOIN @24_31avg T2
ON T1.carrier = T2.carrier
ORDER BY T1.avg-T2.avg DESC;
```
# Które linie lotnicze latają zarówno na trasie SFO → PDX (Portland), jak i SFO → EUG (Eugene)?
```{sql, connection=con, tab.cap = NA}
SELECT DISTINCT carrier AS 'Carrier'
FROM Flight_delays
WHERE origin LIKE 'SFO'
AND
(dest IN ('PDX', 'EUG'))
```
# Jak najszybciej dostać się z Chicago do Stanfordu, zakładając wylot po 14:00 czasu lokalnego?
```{sql, connection=con, tab.cap = NA}
SELECT origin AS 'Origin',
dest AS 'Destination',
AVG(arr_delay) AS 'Delay'
FROM Flight_delays
WHERE origin IN ('MDW', 'ORD')
AND dest IN ('SFO', 'SJC', 'OAK')
AND crs_dep_time>1400
GROUP BY origin, dest
ORDER BY AVG(arr_delay) DESC;
```

BIN
R/bad_proj_analytics.pdf
View File

Binary file not shown.

9
SQL files/10.sql Normal file
View File

@ -0,0 +1,9 @@
SELECT origin AS 'Origin',
dest AS 'Destination',
AVG(arr_delay) AS 'Delay'
FROM Flight_delays
WHERE origin IN ('MDW', 'ORD')
AND dest IN ('SFO', 'SJC', 'OAK')
AND crs_dep_time>1400
GROUP BY origin, dest
ORDER BY AVG(arr_delay) DESC;

43
SQL files/8.sql Normal file
View File

@ -0,0 +1,43 @@
--Average delays between 1 and 23 per carrier
DECLARE @1_23avg TABLE
(
carrier VARCHAR(50),
avg FLOAT
)
INSERT INTO @1_23avg
SELECT carrier,
AVG(avg1) AS 'avg1A'
FROM (SELECT carrier,
AVG(arr_delay) AS 'avg1'
FROM Flight_delays
WHERE month = 7
GROUP BY carrier, day_of_month
HAVING day_of_month BETWEEN 1 AND 23) AS T1
GROUP BY carrier;
--Average delays between 24 and 31 per carrier
DECLARE @24_31avg TABLE
(
carrier VARCHAR(50),
avg FLOAT
)
INSERT INTO @24_31avg
SELECT carrier,
AVG(avg2) AS 'avg2A'
FROM (SELECT carrier,
AVG(arr_delay) AS 'avg2'
FROM Flight_delays
WHERE month = 7
GROUP BY carrier, day_of_month
HAVING day_of_month BETWEEN 24 AND 31) AS T2
GROUP BY carrier;
--Final SELECT
SELECT T1.carrier AS 'Carrier',
T1.avg-T2.avg AS 'Delay growth'
FROM @1_23avg T1 INNER JOIN @24_31avg T2
ON T1.carrier = T2.carrier
ORDER BY T1.avg-T2.avg DESC;

5
SQL files/9.sql Normal file
View File

@ -0,0 +1,5 @@
SELECT DISTINCT carrier AS 'Carrier'
FROM Flight_delays
WHERE origin LIKE 'SFO'
AND
(dest IN ('PDX', 'EUG'))