Assignment 1 - Tiffany Luo

README.md

@@ -66,32 +66,62 @@ Write a query to answer each of the questions below.
 
 2. [What is the percent change in trips in Q3 2022 as compared to Q3 2021?](query02.sql)
 
+**Result:** 3.98%
+
 3. [What is the average duration of a trip for 2021?](query03.sql)
 
+**Result:** 18.86 minutes
+
 4. [What is the average duration of a trip for 2022?](query04.sql)
 
+**Result:** 17.88 minutes
+
 5. [What is the longest duration trip across the two quarters?](query05.sql)
 
     _Why are there so many trips of this duration?_
 
-    **Answer:**
+    **Answer:The result shows that the max duration for trips is 1440 minutes, equivalent to 24 hours, within the Indego bike-sharing dataset. It could be attributed to users forgetting to terminate their trips or due to a failure in locking the bikes, resulting in an improper check-in. Given that the bike-sharing service may have a daily maximum charge limit, thus, the duration of trips lasting exactly 1440 minutes could arise from users neglecting to end their trips. Furthermore, some trips consistently have identical start and end position, as evidenced by the exact matching of latitude and longitude coordinates, suggesting systemic issues with certain bikes.**
+
+
+**Result:** 1440 minutes
 
 6. [How many trips in each quarter were shorter than 10 minutes?](query06.sql)
 
+**Result:** 2021 q3: 124,582 trips; 2022 q3: 137,372 trips
+
 7. [How many trips started on one day and ended on a different day?](query07.sql)
 
+**Result:** 2021 q3: 2301 trips; 2022 q3: 2060 trips
+
 8. [Give the five most popular starting stations across all years between 7am and 9:59am.](query08.sql)
 
     _Hint: Use the `EXTRACT` function to get the hour of the day from the timestamp._
 
+ **Result:**   Five most popular station id: 3032, 3102, 3012, 3066, 3007
+
 9. [List all the passholder types and number of trips for each across all years.](query09.sql)
 
+**Result:**
+Day Pass: 61,659
+Indego30: 441,856
+Indego365: 109,251
+Null: 43
+Walk-up: 2
+
 10. [Using the station status dataset, find the distance in meters of each station from Meyerson Hall.](query10.sql)
 
 11. [What is the average distance (in meters) of all stations from Meyerson Hall?](query11.sql)
 
+**Result:** 3000 
+
 12. [How many stations are within 1km of Meyerson Hall?](query12.sql)
 
+**Result:** 16
+
 13. [Which station is furthest from Meyerson Hall?](query13.sql)
 
+**Result:** It's Manayunk Bridge Station
+
 14. [Which station is closest to Meyerson Hall?](query14.sql)
+
+**Result:** It's 34th and Spruce Station

__scripts__/create_trip_tables.sql

@@ -22,6 +22,7 @@ create table indego.trips_2021_q3 (
 
 drop table if exists indego.trips_2022_q3;
 
+
 create table indego.trips_2022_q3 (
     trip_id text,
     duration integer,

query01.sql

@@ -1,8 +1,11 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     Example: How many bike trips in Q3 2021. Name the resulting column
     num_trips.
 */
 
+-- 300,432 trips
+
 -- Enter your SQL query here
 select count(*) as num_trips
-from indego.trips_2021_q3
+from indego.trips_2021_q3

query02.sql

@@ -1,3 +1,4 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     What is the percent change in trips in Q3 2022 as compared to Q3 2021?
 
@@ -9,8 +10,32 @@
     Remember you can do calculations in the select clause.
 */
 
+-- 3.98
+
 -- Enter your SQL query here
 
+WITH Trips AS (
+    SELECT
+        COUNT(*) AS num_trips_21,
+        0 AS num_trips_22
+    FROM indego.trips_2021_q3
+    UNION ALL
+    SELECT
+        0 AS num_trips_21,
+        COUNT(*) AS num_trips_22
+    FROM indego.trips_2022_q3
+),
+AggregatedCounts AS (
+    SELECT
+        SUM(num_trips_21) AS num_trips_21,
+        SUM(num_trips_22) AS num_trips_22
+    FROM Trips
+)
+
+SELECT
+    ROUND(((num_trips_22 - num_trips_21)::numeric / num_trips_21) * 100, 2) AS perc_change
+FROM AggregatedCounts;
+
 
 
 /*

query03.sql

@@ -1,3 +1,4 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     What is the average duration of a trip for 2021?
 
@@ -6,3 +7,5 @@
 */
 
 -- Enter your SQL query here
+SELECT ROUND(AVG(duration)::NUMERIC, 2) AS avg_duration
+FROM indego.trips_2021_q3;

query04.sql

@@ -1,3 +1,4 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     What is the average duration of a trip for 2022?
 
@@ -6,3 +7,7 @@
 */
 
 -- Enter your SQL query here
+SELECT 
+  ROUND(AVG(duration)::NUMERIC, 2) AS avg_duration
+FROM 
+  indego.trips_2022_q3;

query05.sql

@@ -1,7 +1,17 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     What is the longest duration trip across the two quarters?
 
     Your result should have a single row with a single column named max_duration.
 */
 
 -- Enter your SQL query here
+WITH TwoTables AS (
+    SELECT duration FROM indego.trips_2021_q3
+    UNION ALL
+    SELECT duration FROM indego.trips_2022_q3
+)
+
+SELECT MAX(duration) AS max_duration
+FROM TwoTables;
+

query06.sql

@@ -1,3 +1,4 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     How many trips in each quarter were shorter than 10 minutes?
 
@@ -7,3 +8,17 @@
 */
 
 -- Enter your SQL query here
+
+SELECT
+    2021 AS trip_year,
+    '3' AS trip_quarter,
+    COUNT(*) AS num_trips
+FROM indego.trips_2021_q3
+WHERE duration < 10
+UNION
+SELECT
+    2022 AS trip_year,
+    '3' AS trip_quarter,
+    COUNT(*) AS num_trips
+FROM indego.trips_2022_q3
+WHERE duration < 10

query07.sql

@@ -1,3 +1,4 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     How many trips started on one day and ended on a different day?
 
@@ -6,7 +7,19 @@
 */
 
 -- Enter your SQL query here
-
+SELECT
+    2021 AS trip_year,
+    '3' AS trip_quarter,
+    COUNT(*) AS num_trips
+FROM indego.trips_2021_q3
+WHERE CAST(start_time AS date) != CAST(end_time AS date)
+UNION
+SELECT
+    2022 AS trip_year,
+    '3' AS trip_quarter,
+    COUNT(*) AS num_trips
+FROM indego.trips_2022_q3
+WHERE CAST(start_time AS date) != CAST(end_time AS date)
 
 
 /*

query08.sql

@@ -1,3 +1,4 @@
+- Active: 1707329957355@@localhost@5432@m509A1
 /*
     Give the five most popular starting stations across all years between 7am
     and 9:59am.
@@ -10,6 +11,45 @@
 
 -- Enter your SQL query here
 
+WITH
+trips_2021_q3 AS (
+    SELECT
+        start_station AS station_id,
+        ST_GEOMFROMTEXT('POINT(' || start_lon::text || ' ' || start_lat::text || ')')::geography AS station_geog
+    FROM indego.trips_2021_q3
+    WHERE EXTRACT(HOUR FROM start_time) >= 7 AND EXTRACT(HOUR FROM start_time) < 10
+),
+trips_2022_q3 AS (
+    SELECT
+        start_station AS station_id,
+        ST_GEOMFROMTEXT('POINT(' || start_lon::text || ' ' || start_lat::text || ')')::geography AS station_geog
+    FROM indego.trips_2022_q3
+    WHERE EXTRACT(HOUR FROM start_time) >= 7 AND EXTRACT(HOUR FROM start_time) < 10
+),
+combined_trips AS (
+    SELECT * FROM trips_2021_q3
+    UNION ALL
+    SELECT * FROM trips_2022_q3
+)
+
+SELECT
+    station_id,
+    station_geog,
+    COUNT(*) AS num_trips
+FROM combined_trips
+GROUP BY station_id, station_geog
+ORDER BY num_trips DESC
+LIMIT 5;
+
+
+
+
+
+
+
+
+
+
 
 /*
     Hint: Use the `EXTRACT` function to get the hour of the day from the

query09.sql

@@ -7,3 +7,14 @@
 */
 
 -- Enter your SQL query here
+SELECT
+    passholder_type,
+    COUNT(*) AS num_trips
+FROM (
+    SELECT passholder_type
+    FROM indego.trips_2021_q3
+    UNION ALL
+    SELECT passholder_type
+    FROM indego.trips_2022_q3
+) AS all_trips
+GROUP BY passholder_type;

query10.sql

@@ -1,3 +1,4 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     Using the station status dataset, find the distance in meters of each
     station from Meyerson Hall. Use latitude 39.952415 and longitude -75.192584
@@ -8,3 +9,11 @@
 */
 
 -- Enter your SQL query here
+SELECT
+    id AS station_id,
+    geog AS station_geog,
+    ROUND(ST_DISTANCE(geog, 'POINT(-75.192584 39.952415)'::geography) / 50) * 50 AS distance
+FROM
+    indego.station_statuses;
+
+

query11.sql

@@ -1,7 +1,10 @@
+-- Active: 1707329957355@@localhost@5432@m509A1
 /*
     What is the average distance (rounded to the nearest km) of all stations
     from Meyerson Hall? Your result should have a single record with a single
     column named avg_distance_km.
 */
 
 -- Enter your SQL query here
+SELECT ROUND(AVG(ST_DISTANCE(geog, ST_MAKEPOINT(-75.192584, 39.952415)::GEOGRAPHY)::NUMERIC) / 1000, 0) AS avg_distance_km
+FROM indego.station_statuses

query12.sql

@@ -6,3 +6,6 @@
 */
 
 -- Enter your SQL query here
+SELECT COUNT(*) AS num_stations
+FROM indego.station_statuses
+WHERE ST_DISTANCE(geog, ST_MAKEPOINT(-75.192584, 39.952415)::GEOGRAPHY) < 1000

query13.sql

@@ -7,3 +7,11 @@
 */
 
 -- Enter your SQL query here
+SELECT
+    id AS station_id,
+    name AS station_name,
+    ROUND(ST_DISTANCE(geog, 'POINT(-75.192584 39.952415)'::geography) / 50) * 50 AS distance
+FROM
+    indego.station_statuses
+ORDER BY distance DESC
+LIMIT 1

query14.sql

@@ -7,3 +7,10 @@
 */
 
 -- Enter your SQL query here
+SELECT
+    id AS station_id,
+    name AS station_name,
+    ROUND(ST_DISTANCE(geog, ST_MAKEPOINT(-75.192584, 39.952415)::GEOGRAPHY)::NUMERIC / 50, 0) * 50 AS distance
+FROM indego.station_statuses
+ORDER BY distance ASC
+LIMIT 1