og forecastuge 11. Dette valg tog vi dog af bekvemmelighedsgrunde for at have mest mulig data med mindst mulig ubalance. Ved at benytte andreaktivitetsuger og forcastuger vil vi med høj sandsynlighed få andre performance resultater for vores modeller.
Generelt vil modellerne få en bedre prædiktionsevne, jo mere data der er tilgængeligt.
Særligt kan det tænkes, at performance for Neuralt Netværk bliver forbedret ved mere data.
dog holdes op imod ressourcerne, institutionen benytter for at sikre de studerendes gennemførsel.
Derudover har uddannelse stor betydning for samfundsproduktivitet. En højere ud-dannet befolkning vil som regel medføre højere produktivitet og lavere arbejdsløshed.
Med andre ord vil samfundet på sigt nyde godt af at mindske antallet af studerende, der frafalder de gymnasiale uddannelser.
Litteratur
[1] Danske Erhvervsskoler Gymnasier, Jan 2019.
[2] Sebastian Raschka and Vahid Mirjalili. page 379–395. Packt, 2019.
[3] Finn Aarup Nielsen. A new anew: Evaluation of a word list for sentiment analysis in microblogs, May 2011.
[4] Charu C. Aggarwal. Neural networks and deep learning: a textbook. Springer, 2018.
[5] Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani.An Intro-duction to Statistical Learning: with Applications in R, pages 145–150; 304–330.
Springer, 2013.
[6] Jerome Friedman Trevor Hastie, Robert Tibshirani. The Elements of Statistical Learning - Data Mining, Inference, and Prediction, Second Edition. Addison-Wesley, Reading, Massachusetts, 2009.
[7] Pablo Aznar. Decision trees: Gini vs entropy ∗ quantdare, Dec 2020.
[8] Rick Wicklin. The average bootstrap sample omits 36.8% of the data, Jun 2017.
Klik her for link til kilde.
[9] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system.
2016.
[10] Brad Boehmke and Brandon Greenwell. Hands-on machine learning with R. CRC Press is an imprint of the Taylor & Francis Group, an informa busi-ness, 2020.
[11] Sarang Narkhede. Understanding auc - roc curve, Jan 2021.
[12] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, 2020. https://
scikit-learn.org/dev/glossary.html#term-class-weight.
[13] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Gri-sel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, 2020. https://scikit-learn.org/stable/modules/generated/sklearn.
utils.class_weight.compute_class_weight.html. [14] Langche Zeng and Gary King, Feb 2001.
[15] Andrew Ng. 06: Logistic regression, 2015.
[16] Yang S. An introduction to logistic regression, May 2020.
[17] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Gri-sel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, 2020. https://scikit-learn.org/stable/modules/generated/sklearn.
utils.class_weight.compute_class_weight.html.
[18] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, 2020. https://
scikit-learn.org/stable/modules/tree.html#classification.
[19] Jason Brownlee. How to configure xgboost for imbalanced classification, Aug 2020.
[20] Antonio Gulli and Sujit Pal. Deep learning with Keras. Packt Publishing Ltd, 2017.
[21] tensorflower gardener. tensorflow/tensorflow, Aug 2019.
Appendices
A Maks / Min af renhed mål
Gmin = 1(1−1) + 0(1−0) = 0 Gmax = 0.5(1−0.5) + 0.5(1−0.5) Entropymin =−1∗log(1)−0∗log(0) = 0 Entropymax =−0.5∗log(0.5)−0.5∗log(0.5)
B Balancerede klassifikationsresultater Neuralt Net-værk
Faktisk Ikke-frafald Frafald Prædiktion Ikke-frafald 765 151
Frafald 276 179
(a) Threshold 0.3
Faktisk Ikke-frafald Frafald Prædiktion Ikke-frafald 801 159
Frafald 240 171
(b) Threshold 0.5
Tabel 41: Confusion Matrix: Balanceret Neuralt Netværk uden regularisering
Klassifikations Ikke-frafald Frafald Samlet Parametre(threshold)
Precision(0.3) 0.84 0.39 0.61
Recall(0.3) 0.73 0.54 0.64
F1-score(0.3) 0.78 0.46 0.62
Precision(0.5) 0.83 0.42 0.63
Recall(0.5) 0.77 0.52 0.64
F1-score(0.5) 0.80 0.46 0.63
Tabel 42: Confusion Matrix: Balanceret Neuralt Netværk uden regularisering
Faktisk Ikke-frafald Frafald
Prædiktion Ikke-frafald 0 0
Frafald 1041 330
(a) Threshold 0.3
Faktisk Ikke-frafald Frafald Prædiktion Ikke-frafald 1041 330
Frafald 0 0
(b) Threshold 0.5
Tabel 43: Hyperparametre, Balanceret Neuralt Netværk med dropout regularisering
Klassifikations Ikke-frafald Frafald Samlet Parametre(threshold)
Precision(0.3) 0 0.24 0.12
Recall(0.3) 0 1 0.50
F1-score(0.3) 0 0.39 0.19
Precision(0.5) 0.76 0 0.38
Recall(0.5) 1 0 0.50
F1-score(0.5) 0.86 0 0.43
Tabel 44: Performance: Balanceret Neuralt Netværk med dropout regularisering
C MySQL query
1 DROP T A B L E F i n a l _ T a b l e;
2 C R E A T E T A B L E F i n a l _ T a b l e
3 S E L E C T
4 AL.a c t i v i t y _ i d,
5 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d,
6 AL.user_id,
7 F R O M _ U N I X T I M E(AL.r e a d _ d a t e) AS r e a d _ d a t e,
8 AL.a d a p t i v e _ o b j e c t _ i d,
9 F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) AS u n d e r s t o o d _ d a t e,
10 GM.group_id,
11 F R O M _ U N I X T I M E(UD.d r o p o u t _ t i m e) as d r o p o u t _ t i m e,
12 WEEK(F R O M _ U N I X T I M E(UD.d r o p o u t _ t i m e) ,2) as d r o p o u t _ w e e k,
13 m e d i a.t i t l e as video_id,
14 m e d i a.type as v i d e o _ t y p e,
15 u n i _ g r o u p s.u n i _ s t a r t _ d a t e as g r o u p _ s t a r t _ d a t e,
16 u n i _ g r o u p s.u n i _ e n d _ d a t e as g r o u p _ e n d _ d a t e,
17 YVS.t o t a l _ w a t c h _ t i m e,
18 YVS.m a x _ w a t c h _ t i m e,
19 YVS.l a t e s t _ w a t c h _ t i m e,
20 YVS.duration,
21 CASE
22 WHEN
23 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
24 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 5 THEN 1
25 WHEN
26 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) = 1970 AND
27 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 5 AND
28 t o t a l _ w a t c h _ t i m e > 7 THEN 1
29 WHEN
30 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 5 THEN NULL
31 ELSE
32 0
33 END AS v i d e o _ f l a g,
34 CASE
35 WHEN
36 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
37 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 1 THEN 1
38 WHEN
39 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 1 THEN NULL
40 ELSE
41 0
42 END as a s s i g n m e n t _ f l a g,
43 A S S P L A N. ‘time‘ as a s s i g n m e n t _ t i m e,
44 CASE
45 WHEN
46 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
47 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 6 THEN 1
48 WHEN
49 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 6 THEN NULL
50 ELSE
51 0
52 END as i n t e r a c t i v e s _ l i n k _ f l a g,
53 S B _ _ f l a s h c a r d s _ p e r _ c o l l e c t i o n. n u m b e r _ o f _ f l a s h c a r d s _ i n _ c o l l e c t i o n,
54 CASE
55 WHEN
56 A S _ _ A l l _ F l a s c a r d s _ C o l l e c t i o n _ I n f o. n u m b e r _ o f _ f l a s h c a r d s _ v i e w e d IS NULL AND
57 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 15 THEN 0
58 ELSE
59 A S _ _ A l l _ F l a s c a r d s _ C o l l e c t i o n _ I n f o. n u m b e r _ o f _ f l a s h c a r d s _ v i e w e d
60 END AS n u m b e r _ o f _ f l a s h c a r d s _ v i e w e d,
61 CASE
62 WHEN
63 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
64 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 15 THEN 1
65 WHEN
66 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 15 THEN NULL
67 ELSE
68 0
69 END AS f l a s h c a r d s _ f l a g,
70 S B _ _ q u e s t i o n s _ p e r _ q u e s t i o n a i r e.
n u m b e r _ o f _ q u e s t i o n s _ i n _ q u e s t i o n n a i r e,
71 CASE
72 WHEN
73 S B _ _ n u m b e r _ o f _ a n s w e r e d _ q u e s t i o n s _ q u e s t i o n a i r e .n u m b e r _ o f _ q u e s t i o n s _ a n s w e r e d _ q u e s t i o n a i r e IS NULL AND
74 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 13 THEN 0
75 ELSE
76 S B _ _ n u m b e r _ o f _ a n s w e r e d _ q u e s t i o n s _ q u e s t i o n a i r e .n u m b e r _ o f _ q u e s t i o n s _ a n s w e r e d _ q u e s t i o n a i r e
77 END AS n u m b e r _ o f _ q u e s t i o n s _ a n s w e r e d _ q u e s t i o n a i r e,
78 CASE
79 WHEN
80 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
81 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 13 THEN 1
82 WHEN
83 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 13 THEN NULL
84 ELSE
85 0
86 END AS q u e s t i o n a i r e _ f l a g,
87 S B _ _ q u e s t i o n s _ p e r _ q u i z.n u m b e r _ o f _ q u e s t i o n s _ i n _ q u i z,
88 CASE
89 WHEN
90 S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s. n u m b e r _ o f _ q u e s t i o n s _ a n s w e r e d IS NULL AND
91 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 2 THEN 0
92 ELSE
93 S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s. n u m b e r _ o f _ q u e s t i o n s _ a n s w e r e d
94 END AS n u m b e r _ o f _ q u i z _ q u e s t i o n s _ a n s w e r e d,
95 CASE
96 WHEN
97 S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s. n u m b e r _ o f _ q u e s t i o n s _ c o r r e c t l y _ a n s w e r e d IS NULL AND
98 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 2 THEN 0
99 ELSE
100 S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s. n u m b e r _ o f _ q u e s t i o n s _ c o r r e c t l y _ a n s w e r e d
101 END AS n u m b e r _ o f _ q u i z _ q u e s t i o n s _ c o r r e c t l y _ a n s w e r e d,
102 CASE
103 WHEN
104 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
105 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 2 THEN 1
106 WHEN
107 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 2 THEN NULL
108 ELSE
109 0
110 END AS q u i z _ f l a g,
111 l e n g t h(r a w _ t e x t.text) as r a w _ t e x t _ l e n g t h,
112 CASE
113 WHEN RTS.t o t a l _ t i m e _ s p e n t IS NULL THEN
114 0
115 ELSE
116 RTS.t o t a l _ t i m e _ s p e n t
117 END AS r a w _ t e x t _ t o t a l _ t i m e _ s p e n t,
118 CASE
119 WHEN
120 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) <>
1970 AND
121 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 3 THEN 1
122 WHEN
123 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 3 THEN NULL
124 ELSE
125 0
126 END as r a w _ t e x t _ i n f o _ f l a g,
127 u s e r s.i n s t i t u t i o n _ i d,
128 CASE
129 WHEN
130 u s e r s.p r o f i l e _ p i c t u r e <> 0 THEN 1
131 ELSE
132 0
133 END AS p r o f i l e _ p i c _ f l a g,
134 CASE
135 WHEN
136 YEAR(F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) >
1970 AND
137 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 12 THEN 1
138 WHEN
139 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d <> 12 THEN NULL
140 ELSE
141 0
142 END AS e x t e r n a l _ l i n k _ f l a g
143 FROM
144 a c t i v i t y _ l o g AL
145
146 I N N E R JOIN
147 g r o u p _ m a t e r i a l _ e l e m e n t s GME
148 ON
149 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = GME.o b j e c t _ t y p e _ i d AND
150 AL.a d a p t i v e _ o b j e c t _ i d = GME.o b j e c t _ i d
151
152 I N N E R JOIN
153 g r o u p _ m a t e r i a l s GM
154 ON
155 GME.g r o u p _ m a t e r i a l _ i d = GM.g r o u p _ m a t e r i a l _ i d
156
157 LEFT JOIN
158 u s e r _ d r o p o u t s UD
159 ON
160 AL.u s e r _ i d = UD.u s e r _ i d AND
161 GM.g r o u p _ i d = UD.g r o u p _ i d
162
163 LEFT JOIN
164 m e d i a
165 ON
166 AL.a d a p t i v e _ o b j e c t _ i d = m e d i a.m e d i a _ i d AND
167 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 5
168
169 LEFT JOIN
170 y o u t u b e _ v i d e o _ s t a t i s t i c s YVS
171 ON
172 m e d i a.t i t l e = YVS.v i d e o _ i d AND
173 AL.u s e r _ i d = YVS.u s e r _ i d
174
175 LEFT JOIN
176 a s s i g n m e n t s ASS
177 ON
178 AL.a d a p t i v e _ o b j e c t _ i d = ASS.a s s i g n m e n t _ i d AND
179 AL.u s e r _ i d = ASS.u s e r _ i d AND
180 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 1
181
182 LEFT JOIN
183 a s s i g n m e n t _ p l a n s A S S P L A N
184 ON
185 AL.a d a p t i v e _ o b j e c t _ i d = A S S P L A N.a s s i g n m e n t _ i d AND
186 AL.u s e r _ i d = A S S P L A N.u s e r _ i d AND
187 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 1
188
189 LEFT JOIN
190 S B _ _ f l a s h c a r d s _ p e r _ c o l l e c t i o n
191 ON
192 AL.a d a p t i v e _ o b j e c t _ i d = S B _ _ f l a s h c a r d s _ p e r _ c o l l e c t i o n .c o l l e c t i o n _ i d AND
193 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 15
194
195 LEFT JOIN
196 A S _ _ A l l _ F l a s c a r d s _ C o l l e c t i o n _ I n f o
197 ON
198 AL.a d a p t i v e _ o b j e c t _ i d =
A S _ _ A l l _ F l a s c a r d s _ C o l l e c t i o n _ I n f o. f l a s c a r d _ c o l l e c t i o n _ i d AND
199 AL.u s e r _ i d = A S _ _ A l l _ F l a s c a r d s _ C o l l e c t i o n _ I n f o. u s e r _ i d AND
200 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 15
201
202 LEFT JOIN
203 S B _ _ q u e s t i o n s _ p e r _ q u e s t i o n a i r e
204 ON
205 AL.a d a p t i v e _ o b j e c t _ i d =
S B _ _ q u e s t i o n s _ p e r _ q u e s t i o n a i r e.q u e s t i o n n a i r e _ i d AND
206 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 13
207
208 LEFT JOIN
209 S B _ _ n u m b e r _ o f _ a n s w e r e d _ q u e s t i o n s _ q u e s t i o n a i r e
210 ON
211 AL.a d a p t i v e _ o b j e c t _ i d =
S B _ _ n u m b e r _ o f _ a n s w e r e d _ q u e s t i o n s _ q u e s t i o n a i r e. q u e s t i o n n a i r e _ i d AND
212 AL.u s e r _ i d =
S B _ _ n u m b e r _ o f _ a n s w e r e d _ q u e s t i o n s _ q u e s t i o n a i r e.u s e r _ i d AND
213 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 13
214
215 LEFT JOIN
216 S B _ _ q u e s t i o n s _ p e r _ q u i z
217 ON
218 AL.a d a p t i v e _ o b j e c t _ i d = S B _ _ q u e s t i o n s _ p e r _ q u i z. q u i z _ i d AND
219 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 2
220
221 LEFT JOIN
222 S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s
223 ON
224 AL.a d a p t i v e _ o b j e c t _ i d =
S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s.q u i z _ i d AND
225 AL.u s e r _ i d =
S B _ _ n u m b e r _ a n d _ c o r r e c t _ a n s w e r e d _ q u e s t i o n s.u s e r _ i d AND
226 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 2
227
228 LEFT JOIN
229 r a w _ t e x t
230 ON
231 AL.a d a p t i v e _ o b j e c t _ i d = r a w _ t e x t.r a w _ t e x t _ i d AND
232 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 3
233
234 LEFT JOIN
235 r a w _ t e x t _ s t a t i s t i c s RTS
236 ON
237 AL.a d a p t i v e _ o b j e c t _ i d = RTS.r a w _ t e x t _ i d AND
238 AL.u s e r _ i d = RTS.u s e r _ i d AND
239 AL.a d a p t i v e _ o b j e c t _ t y p e _ i d = 3
240
241 LEFT JOIN
242 u s e r s
243 ON
244 AL.u s e r _ i d = u s e r s.u s e r _ i d
245
246 LEFT JOIN
247 u n i _ g r o u p s
248 ON
249 GM.g r o u p _ i d = u n i _ g r o u p s.g r o u p _ i d
250
251 LEFT JOIN
252 u n i _ a d m i n _ u s e r _ i d s UAUI
253 ON
254 AL.u s e r _ i d = UAUI.u s e r _ i d
255
256 W H E R E
257 F R O M _ U N I X T I M E(AL.r e a d _ d a t e) > ’ 2018-06-01 0 0 : 0 0 : 0 0 ’
258 AND UAUI.u s e r _ i d IS NULL
259 AND (F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) = ’ 1970-01-01 0 0 : 0 0 : 0 0 ’ OR t i m e s t a m p d i f f(SECOND,F R O M _ U N I X T I M E(AL. r e a d _ d a t e) ,F R O M _ U N I X T I M E(AL.u n d e r s t o o d _ d a t e) ) >= -60)
260
261 g r o u p by
262 AL.a c t i v i t y _ i d;
263
264
265 # I n c l u d i n g v i m e o _ v i d e o _ s t a t i s t i c s
266 U P D A T E F i n a l _ T a b l e a
267 I N N E R JOIN
268 v i m e o _ v i d e o _ s t a t i s t i c s b
269 ON
270 a.v i d e o _ i d = b.v i d e o _ i d AND
271 a.u s e r _ i d = b.u s e r _ i d
272 SET
273 a.t o t a l _ w a t c h _ t i m e = b.t o t a l _ w a t c h _ t i m e,
274 a.m a x _ w a t c h _ t i m e = b.m a x _ w a t c h _ t i m e,
275 a.l a t e s t _ w a t c h _ t i m e = b.l a t e s t _ w a t c h _ t i m e,
276 a.d u r a t i o n = b.d u r a t i o n;
277
278
279 # I n c l u d i n g m e d i a _ v i e w _ s t a t i s t i c s
280 U P D A T E F i n a l _ T a b l e a
281 I N N E R JOIN
282 m e d i a _ v i e w _ s t a t i s t i c s b
283 ON
284 a.a d a p t i v e _ o b j e c t _ i d = b.m e d i a _ i d AND
285 a.u s e r _ i d = b.u s e r _ i d AND
286 a.a d a p t i v e _ o b j e c t _ t y p e _ i d = 5
287 SET
288 a.t o t a l _ w a t c h _ t i m e = b.t o t a l _ w a t c h _ t i m e,
289 a.m a x _ w a t c h _ t i m e = b.m a x _ w a t c h _ t i m e,
290 a.l a t e s t _ w a t c h _ t i m e = b.l a t e s t _ w a t c h _ t i m e,
291 a.d u r a t i o n = b.d u r a t i o n;
292
293
294
295 # Add q u e s t i o n a i r e quiz to f i n a l t a b l e
296 DROP T A B L E F i n a l _ T a b l e _ Q u e s t i o n a i r e _ Q u i z;
297 C R E A T E T A B L E F i n a l _ T a b l e _ Q u e s t i o n a i r e _ Q u i z
298 S E L E C T
299 a.*,
300 b. ‘value‘ as q u e s t i o n a i r e _ q u i z _ r e s p o n s e
301 FROM
302 F i n a l _ T a b l e a
303 LEFT JOIN
304 q u e s t i o n n a i r e _ q u e s t i o n _ r e s p o n s e s b
305 ON
306 a.u s e r _ i d = b.u s e r _ i d AND
307 a.a d a p t i v e _ o b j e c t _ i d = b.q u e s t i o n n a i r e _ i d AND
308 a.a d a p t i v e _ o b j e c t _ t y p e _ i d = 13;
Listing 1: MySQL query, som bruges til at sammensætte det endlige dataset ud fra 98 undertabeller
D MySQL query
1 DROP T A B L E F i n a l _ T a b l e _ 1 _ A g g r e g a t i o n _ 1;
2