-
Notifications
You must be signed in to change notification settings - Fork 0
/
IMDB+question (1).sql
1151 lines (847 loc) · 37.4 KB
/
IMDB+question (1).sql
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
USE imdb;
-- Problem Introduction
/*RSVP Movies is an Indian film production company which has produced many super-hit movies. They have usually released movies for the Indian audience
but for their next project, they are planning to release a movie for the global audience in 2022.
The production company wants to plan their every move analytically based on data and have approached you for help with this new project. You have been
provided with the data of the movies that have been released in the past three years. You have to analyse the data set and draw meaningful insights
that can help them start their new project.
*/
/* Now that you have imported the data sets, let’s explore some of the tables.
To begin with, it is beneficial to know the shape of the tables and whether any column has null values.
Further in this segment, you will take a look at 'movies' and 'genre' tables.*/
-- Segment 1:
-- Q1. Find the total number of rows in each table of the schema?
-- Type your code below:
SELECT table_name, table_rows AS Total_no_of_rows
FROM INFORMATION_SCHEMA.TABLES
WHERE TABLE_SCHEMA = 'imdb';
-- Q2. Which columns in the movie table have null values?
-- Type your code below:
with null_count as (select count(*) as total_count, count(id) as id_null,
count(title) as title_null, count(year) as year_null,count(date_published) as date_published_null, count(duration) as duration_null,
count(country) as country_null, count(worlwide_gross_income) as worldwide_grossing_null, count(languages) as lanuage_null ,
count(production_company) as production_companay_null from movie)
select (total_count-id_null) as missing_id,(total_count-title_null) missing_title,(total_count-year_null) missing_year,(total_count-date_published_null)
missing_published_date,(total_count-duration_null) missing_durations,
(total_count-country_null) missing_country_name,(total_count-worldwide_grossing_null) missing_earnings,(total_count-lanuage_null)
missing_movie_language,(total_count-production_companay_null) as missing_production_name from null_count;
/* only few missing in Country while there is lot of missing in worldwide_grossing, language and production of movie table
missing_country_name missing_earnings missing_movie_language missing_production_name
20 3724 194 528
*/
-- Now as you can see four columns of the movie table has null values. Let's look at the at the movies released each year.
-- Q3. Find the total number of movies released each year? How does the trend look month wise? (Output expected)
/* Output format for the first part:
+---------------+-------------------+
| Year | number_of_movies|
+-------------------+----------------
| 2017 | 2134 |
| 2018 | . |
| 2019 | . |
+---------------+-------------------+*/
select m.year as Year, count(distinct id) as number_of_movies from movie as m group by m.year;
/*Year, number_of_movies
2017 3052
2018 2944
2019 2001*/
/*
Output format for the second part of the question:
+---------------+-------------------+
| month_num | number_of_movies|
+---------------+----------------
| 1 | 134 |
| 2 | 231 |
| . | . |
+---------------+-------------------+ */
-- Type your code below:
select month(date_published) as Month, count(id) as number_of_movies from movie as m
group by month(date_published)
order by month(date_published);
/* top 3 month wiht highest movie reselese are march(824), sept(809), and jan(804)
while min in dec (438), july(493), june(580) are month wiht least movies*/
/*
Month, number_of_movies
1 804
2 640
3 824
4 680
5 625
6 580
7 493
8 678
9 809
10 801
11 625
12 438
*/
/*The highest number of movies is produced in the month of March.
So, now that you have understood the month-wise trend of movies, let’s take a look at the other details in the movies table.
We know USA and India produces huge number of movies each year. Lets find the number of movies produced by USA or India for the last year.*/
-- Q4. How many movies were produced in the USA or India in the year 2019??
-- Type your code below:
select country, count(id) number_of_movies from movie
where year =2019 and (country ='India' or country ='USA' )
group by country
order by country;
/*
country, number_of_movies
India 295
USA 592
*/
-- I was unable to group country using like function
/* USA and India produced more than a thousand movies(you know the exact number!) in the year 2019.
Exploring table Genre would be fun!!
Let’s find out the different genres in the dataset.*/
-- Q5. Find the unique list of the genres present in the data set?
-- Type your code below:
select distinct genre from genre
order by genre;
/*13 genre as follows: Action
Adventure
Comedy
Crime
Drama
Family
Fantasy
Horror
Mystery
Others
Romance
Sci-Fi
Thriller*/
/* So, RSVP Movies plans to make a movie of one of these genres.
Now, wouldn’t you want to know which genre had the highest number of movies produced in the last year?
Combining both the movie and genres table can give more interesting insights. */
-- Q6.Which genre had the highest number of movies produced overall?
-- Type your code below:
select genre, count(movie_id),year from genre as g join movie as m on g.movie_id =m.id
group by genre,year
order by count(movie_id) desc
limit 3;
-- question was intitally asking for number of movies in last year the it asked for over that why i split movie into years
/* genre count(movie_id) Year
Drama 1664 2017
Drama 1543 2018
Drama 1078 2019
*/
-- Drama has the maximum number of movies in 2019
/* So, based on the insight that you just drew, RSVP Movies should focus on the ‘Drama’ genre.
But wait, it is too early to decide. A movie can belong to two or more genres.
So, let’s find out the count of movies that belong to only one genre.*/
-- Q7. How many movies belong to only one genre?
-- Type your code below:
with genre_one as (SELECT
movie_id,COUNT(genre) AS genre_count
FROM genre AS g
GROUP BY g.movie_id
HAVING COUNT( genre) =1)
select count(*) from genre_one;
/*such movies are 3289 in count */
/* There are more than three thousand movies which has only one genre associated with them.
So, this figure appears significant.
Now, let's find out the possible duration of RSVP Movies’ next project.*/
-- Q8.What is the average duration of movies in each genre?
-- (Note: The same movie can belong to multiple genres.)
select genre,round(avg(duration),2) from genre join movie on genre.movie_id = movie.id
group by genre
order by avg(duration) desc;
/* Output format:
+---------------+-------------------+
| genre | avg_duration |
+-------------------+----------------
| thriller | 105 |
| . | . |
| . | . |
+---------------+-------------------+ */
-- Type your code below:
/*
genre avg(duration)
Action 112.88
Romance 109.53
Crime 107.05
Drama 106.77
Fantasy 105.14
Comedy 102.62
Adventure 101.87
Mystery 101.80
Thriller 101.58
Family 100.97
Others 100.16
Sci-Fi 97.94
Horror 92.72
*/
-- action genre has maximum average duration followed by romamce and then crime
/* Now you know, movies of genre 'Drama' (produced highest in number in 2019) has the average duration of 106.77 mins.
Lets find where the movies of genre 'thriller' on the basis of number of movies.*/
-- Q9.What is the rank of the ‘thriller’ genre of movies among all the genres in terms of number of movies produced?
-- (Hint: Use the Rank function)
with top_10 as (select genre,count(distinct movie_id)as number_of_movies, rank() over ( order by count(distinct movie_id)desc ) as Ranking
from genre
group by genre)
select *
from top_10
where genre ='Thriller'
;
/*
genr number_of_movies Ranking
Thriller 1484 3
*/
/* Output format:
+---------------+-------------------+---------------------+
| genre | movie_count | genre_rank |
+---------------+-------------------+---------------------+
|drama | 2312 | 2 |
+---------------+-------------------+---------------------+*/
-- Type your code below:
/*Thriller movies is in top 3 among all genres in terms of number of movies
In the previous segment, you analysed the movies and genres tables.
In this segment, you will analyse the ratings table as well.
To start with lets get the min and max values of different columns in the table*/
-- Segment 2:
-- Q10. Find the minimum and maximum values in each column of the ratings table except the movie_id column?
/* Output format:
+---------------+-------------------+---------------------+----------------------+-----------------+-----------------+
| min_avg_rating| max_avg_rating | min_total_votes | max_total_votes |min_median_rating|min_median_rating|
+---------------+-------------------+---------------------+----------------------+-----------------+-----------------+
| 0 | 5 | 177 | 2000 | 0 | 8 |
+---------------+-------------------+---------------------+----------------------+-----------------+-----------------+*/
-- Type your code below:
select min(avg_rating) as min_avg_rating,
max(avg_rating) as max_avg_rating, min(total_votes) as min_total_votes, max(total_votes) as max_total_votes,
min(median_rating) as min_median_rating,
max(median_rating) as max_median_rating from ratings;
/*
all things are in the range and as ideal datatype. no column is out of ranage
*/
/* So, the minimum and maximum values in each column of the ratings table are in the expected range.
This implies there are no outliers in the table.
Now, let’s find out the top 10 movies based on average rating.*/
-- Q11. Which are the top 10 movies based on average rating?
/* Output format:
+---------------+-------------------+---------------------+
| title | avg_rating | movie_rank |
+---------------+-------------------+---------------------+
| Fan | 9.6 | 5 |
| . | . | . |
| . | . | . |
| . | . | . |
+---------------+-------------------+---------------------+*/
-- Type your code below:
-- It's ok if RANK() or DENSE_RANK() is used too
select title, avg_rating, dense_rank() over ( order by avg_rating desc) as ranking from ratings r join movie m on m.id=r.movie_id limit 10;
/*
title avg_rating ranking
Kirket 10.0 1
Love in Kilnerry 10.0 1
Gini Helida Kathe 9.8 2
Runam 9.7 3
Fan 9.6 4
Android Kunjappan Version 5.25 9.6 4
Yeh Suhaagraat Impossible 9.5 5
Safe 9.5 5
The Brighton Miracle 9.5 5
Shibu 9.4 6
Our Little Haven 9.4 6
Zana 9.4 6
Family of Thakurganj 9.4 6
Ananthu V/S Nusrath 9.4 6
Eghantham 9.3 7
Wheels 9.3 7
Turnover 9.2 8
Digbhayam 9.2 8
Tõde ja õigus 9.2 8
Ekvtime: Man of God 9.2 8
Leera the Soulmate 9.2 8
AA BB KK 9.2 8
Peranbu 9.2 8
Dokyala Shot 9.2 8
Ardaas Karaan 9.2 8
Kuasha jakhon 9.1 9
Oththa Seruppu Size 7 9.1 9
Adutha Chodyam 9.1 9
The Colour of Darkness 9.1 9
Aloko Udapadi 9.1 9
C/o Kancharapalem 9.1 9
Nagarkirtan 9.1 9
Jelita Sejuba: Mencintai 9.1 9
Kesatria Negara
Shindisi 9.0 10
Officer Arjun Singh IPS 9.0 10
Oskars Amerika 9.0 10
Delaware Shore 9.0 10
Abstruse 9.0 10
National Theatre Live: Angels
in America Part Two - Perestroika9.0 10
Innocent 9.0 10
*/
/* Do you find you favourite movie FAN in the top 10 movies with an average rating of 9.6? If not, please check your code again!!
So, now that you know the top 10 movies, do you think character actors and filler actors can be from these movies?
Summarising the ratings table based on the movie counts by median rating can give an excellent insight.*/
-- Q12. Summarise the ratings table based on the movie counts by median ratings.
/* Output format:
+---------------+-------------------+
| median_rating | movie_count |
+-------------------+----------------
| 1 | 105 |
| . | . |
| . | . |
+---------------+-------------------+ */
-- Type your code below:
-- Order by is good to have
select median_rating, count(movie_id) as movie_count from ratings
group by median_rating
order by median_rating;
/* order by movie count
median_rating, movie_count
7 2257
6 1975
8 1030
5 985
4 479
9 429
10 346
3 283
2 119
1 94
maximun number of movies are with rating 7
*/
/* Movies with a median rating of 7 is highest in number.
Now, let's find out the production house with which RSVP Movies can partner for its next project.*/
-- Q13. Which production house has produced the most number of hit movies (average rating > 8)??
/* Output format:
+------------------+-------------------+---------------------+
|production_company|movie_count | prod_company_rank|
+------------------+-------------------+---------------------+
| The Archers | 1 | 1 |
+------------------+-------------------+---------------------+*/
-- Type your code below:
select production_company, count(id)as movie_count, dense_rank() over ( order by count(id) desc) as prod_company_rank from movie join ratings
on movie.id = ratings.movie_id
where avg_rating>8 and production_company is not null
group by production_company;
/*
production_company, movie_count, prod_company_rank
# production_company movie_count prod_company_rank
Dream Warrior Pictures 3 1
National Theatre Live 3 1
*/
/*Dream Warrior Pictures & National Theatre Live are the top production house that produces hit movies but there is missing data
so there is a tie in between them*/
-- It's ok if RANK() or DENSE_RANK() is used too
-- Answer can be Dream Warrior Pictures or National Theatre Live or both
-- Q14. How many movies released in each genre during March 2017 in the USA had more than 1,000 votes?
SELECT
genre, COUNT(movie_id) AS movie_count
FROM
movie m
INNER JOIN
genre g ON m.id = g.movie_id
INNER JOIN
ratings r USING (movie_id)
WHERE
m.year = 2017
AND MONTH(date_published) = 3
AND country LIKE '%USA%'
AND r.total_votes > 1000
GROUP BY genre
order by COUNT(movie_id) desc ;
/*
genre, movie_count
genre movie_count
Drama 24
Comedy 9
Action 8
Thriller 8
Sci-Fi 7
Crime 6
Horror 6
Mystery 4
Romance 4
Fantasy 3
Adventure 3
Family 1
*/
/* Output format:
+---------------+-------------------+
| genre | movie_count |
+-------------------+----------------
| thriller | 105 |
| . | . |
| . | . |
+---------------+-------------------+ */
-- Type your code below:
-- Lets try to analyse with a unique problem statement.
-- Q15. Find movies of each genre that start with the word ‘The’ and which have an average rating > 8?
/* Output format:
+---------------+-------------------+---------------------+
| title | avg_rating | genre |
+---------------+-------------------+---------------------+
| Theeran | 8.3 | Thriller |
| . | . | . |
| . | . | . |
| . | . | . |
+---------------+-------------------+---------------------+*/
-- Type your code below:
select title, avg_rating , genre from movie m join ratings r on m.id =r.movie_id join genre using(movie_id)
where title like 'the%' and avg_rating>8;
/*
title avg_rating genre
The Brighton Miracle 9.5 Drama
The Colour of Darkness 9.1 Drama
The Blue Elephant 2 8.8 Drama
The Blue Elephant 2 8.8 Horror
The Blue Elephant 2 8.8 Mystery
The Irishman 8.7 Crime
The Irishman 8.7 Drama
The Mystery of Godliness: The Sequel 8.5 Drama
The Gambinos 8.4 Crime
The Gambinos 8.4 Drama
Theeran Adhigaaram Ondru 8.3 Action
Theeran Adhigaaram Ondru 8.3 Crime
Theeran Adhigaaram Ondru 8.3 Thriller
The King and I 8.2 Drama
The King and I 8.2 Romance
*/
-- You should also try your hand at median rating and check whether the ‘median rating’ column gives any significant insights.
-- Q16. Of the movies released between 1 April 2018 and 1 April 2019, how many were given a median rating of 8?
-- Type your code below:
SELECT COUNT(m.id)
FROM movie m
JOIN ratings r ON m.id = r.movie_id
WHERE m.date_published BETWEEN '2018-04-01' AND '2019-04-01'
AND r.median_rating = 8;
-- number of movies wiht median rating 8 is 361
-- Once again, try to solve the problem given below.
-- Q17. Do German movies get more votes than Italian movies?
-- Hint: Here you have to find the total number of votes for both German and Italian movies.
-- Type your code below:
with german_votes as (select sum(total_votes) as total_votes_german_mov from ratings r
join movie m on r.movie_id = m.id where country ='Germany'),
italy_votes as (select sum(total_votes) as total_votes_italy_mov from ratings r
join movie m on r.movie_id = m.id where country ='Italy')
select total_votes_german_mov ,total_votes_italy_mov from german_votes , italy_votes ;
/*total_votes_german_mov, total_votes_italy_mov
106710 77965
*/
-- yes as german movies got more votes then italian movies
-- Answer is Yes
/* Now that you have analysed the movies, genres and ratings tables, let us now analyse another table, the names table.
Let’s begin by searching for null values in the tables.*/
-- Segment 3:
-- Q18. Which columns in the names table have null values??
/*Hint: You can find null values for individual columns or follow below output format
+---------------+-------------------+---------------------+----------------------+
| name_nulls | height_nulls |date_of_birth_nulls |known_for_movies_nulls|
+---------------+-------------------+---------------------+----------------------+
| 0 | 123 | 1234 | 12345 |
+---------------+-------------------+---------------------+----------------------+*/
-- Type your code below:
select sum(case when n.name is null then 1 else 0 end) as names_null_count ,
sum(case when n.height is null then 1 else 0 end) as height_null_count,
sum(case when n.date_of_birth is null then 1 else 0 end) as dob_null_count,
sum(case when n.known_for_movies is null then 1 else 0 end) as know_null_count
from names as n;
/*
names_null_count height_null_count dob_null_count, know_null_count
0 17335 13431 15226
*/
/* There are no Null value in the column 'name'.
The director is the most important person in a movie crew.
Let’s find out the top three directors in the top three genres who can be hired by RSVP Movies.*/
-- Q19. Who are the top three directors in the top three genres whose movies have an
-- average rating > 8?
-- (Hint: The top three genres would have the most number of movies with an average rating > 8.)
select name as director_name, count(genre.movie_id) as movie_count, ROW_NUMBER() OVER(ORDER BY COUNT(genre.movie_id) DESC) AS director_ranking
from names join director_mapping
on names.id= director_mapping.name_id
join genre on director_mapping.movie_id = genre.movie_id join ratings on genre.movie_id=ratings
.movie_id
where avg_rating>8
group by name
order by count(genre.movie_id) desc
limit 3;
/* top 3 directors are
director_name movie_count
Anthony Russo 6
Joe Russo 6
James Mangold 5
*/
#check
/* Output format:
+---------------+-------------------+
| director_name | movie_count |
+---------------+-------------------|
|James Mangold | 4 |
| . | . |
| . | . |
+---------------+-------------------+ */
-- Type your code below:
/* James Mangold can be hired as the director for RSVP's next project. Do you remeber his movies, 'Logan' and 'The Wolverine'.
Now, let’s find out the top two actors.*/
-- Q20. Who are the top two actors whose movies have a median rating >= 8?
select name as actor_name, count(ratings.movie_id) as movie_count
from role_mapping join names on role_mapping.name_id = names.id
join ratings on role_mapping.movie_id=ratings.movie_id
where median_rating >=8
group by name
order by count(ratings.movie_id) desc
limit 2;
/*
actor_name movie_count
Mammootty 8
Mohanlal 5
*/
/* Output format:
+---------------+-------------------+
| actor_name | movie_count |
+-------------------+----------------
|Christain Bale | 10 |
| . | . |
+---------------+-------------------+ */
-- Type your code below:
/* Have you find your favourite actor 'Mohanlal' in the list. If no, please check your code again.
RSVP Movies plans to partner with other global production houses.
Let’s find out the top three production houses in the world.*/
-- Q21. Which are the top three production houses based on the number of votes received by their movies?
select production_company , sum(total_votes) as vote_count, dense_rank()
over ( order by sum(ratings.total_votes) desc) as prod_comp_rank
from movie m join ratings on m.id = ratings.movie_id
group by production_company
limit 3;
/*
production_company vote_count prod_comp_rank
Marvel Studios 2656967 1
Twentieth Century Fox 2411163 2
Warner Bros. 2396057 3
*/
/* Output format:
+------------------+--------------------+---------------------+
|production_company|vote_count | prod_comp_rank|
+------------------+--------------------+---------------------+
| The Archers | 830 | 1 |
| . | . | . |
| . | . | . |
+-------------------+-------------------+---------------------+*/
-- Type your code below:
/*Yes Marvel Studios rules the movie world.
So, these are the top three production houses based on the number of votes received by the movies they have produced.
Since RSVP Movies is based out of Mumbai, India also wants to woo its local audience.
RSVP Movies also wants to hire a few Indian actors for its upcoming project to give a regional feel.
Let’s find who these actors could be.*/
-- Q22. Rank actors with movies released in India based on their average ratings. Which actor is at the top of the list?
-- Note: The actor should have acted in at least five Indian movies.
-- (Hint: You should use the weighted average based on votes. If the ratings clash, then the total number of votes should act as the tie breaker.)
select n.name as actor_name,sum(ratings.total_votes) as total_votes,count(role_mapping.movie_id) as movie_count, round(SUM(avg_rating*total_votes)/SUM(total_votes) ,2) as
actor_avg_rating, rank()
over (order by SUM(avg_rating*total_votes)/SUM(total_votes) desc) as actor_rank
from names as n join role_mapping on n.id=role_mapping.name_id join ratings
on role_mapping.movie_id=ratings.movie_id join movie on ratings.movie_id=movie.id
where movie.country like '%India%' and role_mapping.category='actor'
group by name
having count(role_mapping.movie_id) >4
order by SUM(avg_rating*total_votes)/SUM(total_votes)
desc , sum(ratings.total_votes) desc
limit 1;
/*
actor_name total_votes movie_count actor_avg_rating actor_rank
Vijay Sethupathi 23114 5 8.42 1
*/
/* Output format:
+---------------+-------------------+------
---------------+----------------------+-----------------+
| actor_name | total_votes | movie_count | actor_avg_rating |actor_rank |
+---------------+-------------------+---------------------+----------------------+-----------------+
| Yogi Babu | 3455 | 11 | 8.42 | 1 |
| . | . | . | . | . |
| . | . | . | . | . |
| . | . | . | . | . |
+---------------+-------------------+---------------------+----------------------+-----------------+*/
-- Type your code below:
-- code check
-- Top actor is Vijay Sethupathi
-- Q23.Find out the top five actresses in Hindi movies released in India based on their average ratings?
-- Note: The actresses should have acted in at least three Indian movies.
-- (Hint: You should use the weighted average based on votes. If the ratings clash, then the total number of votes should act as the tie breaker.)
select n.name as actress_name,sum(ratings.total_votes) as total_votes,count(role_mapping.movie_id) as movie_count, round(SUM(avg_rating*total_votes)/SUM(total_votes),2) as
actor_avg_rating, rank()
over (order by SUM(avg_rating*total_votes)/SUM(total_votes) desc) as actress_rank
from names as n join role_mapping on n.id=role_mapping.name_id join ratings
on role_mapping.movie_id=ratings.movie_id join movie on ratings.movie_id=movie.id
where movie.country like '%India%' and role_mapping.category='actress' and movie.languages like '%hindi%'
group by name
having count(role_mapping.movie_id) >2
order by SUM(avg_rating*total_votes)/SUM(total_votes)
desc , sum(ratings.total_votes) desc
limit 5;
/*
actor_name total_votes movie_count actor_avg_rating actress_rank
Taapsee Pannu 18061 3 7.74 1
Kriti Sanon 21967 3 7.05 2
Divya Dutta 8579 3 6.88 3
Shraddha Kapoor 26779 3 6.63 4
Kriti Kharbanda 2549 3 4.80 5
*/
/* Output format:
+---------------+-------------------+---------------------+----------------------+-----------------+
| actress_name | total_votes | movie_count | actress_avg_rating |actress_rank |
+---------------+-------------------+---------------------+----------------------+-----------------+
| Tabu | 3455 | 11 | 8.42 | 1 |
| . | . | . | . | . |
| . | . | . | . | . |
| . | . | . | . | . |
+---------------+-------------------+---------------------+----------------------+-----------------+*/
-- Type your code below:
/* Taapsee Pannu tops with average rating 7.74.
Now let us divide all the thriller movies in the following categories and find out their numbers.*/
/* Q24. Select thriller movies as per avg rating and classify them in the following category:
Rating > 8: Superhit movies
Rating between 7 and 8: Hit movies
Rating between 5 and 7: One-time-watch movies
Rating < 5: Flop movies
--------------------------------------------------------------------------------------------*/
-- Type your code below:
select title, case
when avg_rating>8 then 'Superhit movies'
when avg_rating between 7 and 8 then 'Hit movies'
when avg_rating between 5 and 7 then 'One-time-watch movies'
else 'Flop movies'
end as category
from ratings join genre using(movie_id) join movie on movie.id=genre.movie_id
where genre.genre='Thriller';
/* Until now, you have analysed various tables of the data set.
Now, you will perform some tasks that will give you a broader understanding of the data in this segment.*/
-- Segment 4:
-- Q25. What is the genre-wise running total and moving average of the average movie duration?
-- (Note: You need to show the output table in the question.)
-- code to check range interval to put
select genre,count(movie_id) from movie inner join genre on movie.id=genre.movie_id
group by genre
order by count(movie_id) desc;
-- as moving average interval is not given so based on others having 100 count using above code
select genre ,round( avg(duration),2) as avg_duration
, sum(avg(duration)) over (order by genre.genre rows unbounded preceding ) as running_total_duration,
avg(avg(duration)) over (order by genre.genre rows 20 preceding ) as moving_avg_duration
from genre join movie on movie.id=genre.movie_id
group by genre;
/*
genre avg_duration running_total_duration moving_avg_duration
Action 112.8829 112.88 112.88290000
Adventure 101.8714 214.75 107.37715000
Comedy 102.6227 317.38 105.79233333
Crime 107.0517 424.43 106.10717500
Drama 106.7746 531.20 106.24066000
Family 100.9669 632.17 105.36170000
Fantasy 105.1404 737.31 105.33008571
Horror 92.7243 830.03 103.75436250
Mystery 101.8000 931.84 103.53721111
Others 100.1600 1031.99 103.19949000
Romance 109.5342 1141.53 103.77537273
Sci-Fi 97.9413 1239.47 103.28920000
Thriller 101.5761 1341.05 103.15742308
*/
/* Output format:
+---------------+-------------------+---------------------+----------------------+
| genre | avg_duration |running_total_duration|moving_avg_duration |
+---------------+-------------------+---------------------+----------------------+
| comdy | 145 | 106.2 | 128.42 |
| . | . | . | . |
| . | . | . | . |
| . | . | . | . |
+---------------+-------------------+---------------------+----------------------+*/
-- Type your code below:
-- Round is good to have and not a must have; Same thing applies to sorting
-- Let us find top 5 movies of each year with top 3 genres.
-- Q26. Which are the five highest-grossing movies of each year that belong to the top three genres?
-- (Note: The top 3 genres would have the most number of movies.)
-- Data values have some error with them leading to wrong data sorting. Specially values starting with INR.
WITH top_3_genre AS (
SELECT genre
FROM genre
GROUP BY genre
ORDER BY COUNT(movie_id) DESC
LIMIT 3
), edit AS (
SELECT
*,
CASE
WHEN worlwide_gross_income LIKE '$%' THEN CAST(REPLACE(worlwide_gross_income, '$ ', '') AS DECIMAL(15))
ELSE CAST(REPLACE(worlwide_gross_income, 'INR%','') AS DECIMAL(15)) * 0.012
END AS numerical_worlwide_gross_income
FROM movie AS m
), high_gross AS (
SELECT
title AS movie_name, id as my_key, genre,
year, numerical_worlwide_gross_income,
DENSE_RANK() OVER (PARTITION BY m.year ORDER BY numerical_worlwide_gross_income DESC) AS movie_rank
FROM genre as g
JOIN edit AS e ON g.movie_id = e.id
WHERE g.genre IN (SELECT genre FROM top_3_genre)
)
SELECT
genre,
year,
movie_name,
numerical_worlwide_gross_income,
DENSE_RANK() OVER(PARTITION BY year ORDER BY numerical_worlwide_gross_income DESC, movie_name) AS movie_rank
FROM high_gross
WHERE movie_rank <= 5
ORDER BY year, numerical_worlwide_gross_income DESC, movie_rank;
/*
genre, year, movie_name, worldwide_gross_income, movie_rank
Thriller 2017 The Fate of the Furious 1236005118.000 1
Comedy 2017 Despicable Me 3 1034799409.000 2
Comedy 2017 Jumanji: Welcome to the Jungle 962102237.000 3
Drama 2017 Zhan lang II 870325439.000 4
Thriller 2017 Zhan lang II 870325439.000 4
Comedy 2017 Guardians of the Galaxy Vol. 2 863756051.000 5
Drama 2018 Bohemian Rhapsody 903655259.000 1
Thriller 2018 Venom 856085151.000 2
Thriller 2018 Mission: Impossible - Fallout 791115104.000 3
Comedy 2018 Deadpool 2 785046920.000 4
Comedy 2018 Ant-Man and the Wasp 622674139.000 5
Drama 2019 Avengers: Endgame 2797800564.000 1
Drama 2019 The Lion King 1655156910.000 2
Comedy 2019 Toy Story 4 1073168585.000 3
Drama 2019 Joker 995064593.000 4
Thriller 2019 Joker 995064593.000 4
Thriller 2019 Ne Zha zhi mo tong jiang shi 700547754.000 5
*/
/* Output format:
+---------------+-------------------+---------------------+----------------------+-----------------+
| genre | year | movie_name |worldwide_gross_income|movie_rank |
+---------------+-------------------+---------------------+----------------------+-----------------+
| comedy | 2017 | indian | $103244842 | 1 |
| . | . | . | . | . |
| . | . | . | . | . |
| . | . | . | . | . |
+---------------+-------------------+---------------------+----------------------+-----------------+*/
-- Type your code below:
-- Top 3 Genres based on most number of movies
-- Finally, let’s find out the names of the top two production houses that have produced the highest number of hits among multilingual movies.
-- Q27. Which are the top two production houses that have produced the highest number of hits (median rating >= 8) among multilingual movies?
select production_company, if( production_company is not null,count(id) ,0) as movie_count, rank() over ( order by count(id) desc ) as prod_comp_rank
from movie join ratings on movie.id = ratings.movie_id
where median_rating >= 8 and production_company is not null and languages like '%,%'
group by production_company
order by count(id) desc
limit 2 ;
/*
production_company, movie_count, prod_comp_rank
Star Cinema 7 1
Twentieth Century Fox 4 2
*/