Skip to content

I
Intelligent English Tutor
Commit feeb76c8 authored by Udara Rangika Herath's avatar Udara Rangika Herath
Browse files
Options

Merge branch 'it20617400/proficiency_level_detection' into 'master' 

It20617400/proficiency level detection

See merge request 2023-24-027/implementation-of-an-intelligent-virtual-tutor-to-enhance-english-vocabulary-skills-of-grade-6-students!4
parents ab9626d8 8b4ad902
Show whitespace changes
Inline Side-by-side
Showing with 1586 additions and 32 deletions
ProficiencyLevelDetection/README.md 0 → 100644
View file @ feeb76c8
# **✒️Using Interactive Vocabulary Assessments and Proficiency Analysis, Create Personalized Learning Paths for Effective Vocabulary Development**
## **🎯Main Objective**
### Using interactive vocabulary assessments and proficiency analysis, determine each student's proficiency level and create personalized learning paths for effective vocabulary development.
## **❓Research Question**
### How can interactive vocabulary assessments effectively determine each student's proficiency level?
## **Sub Objectives**
* ### Update the difficulty level of exercises.
* ### Checking whether the student has achieved the required level to move to the next level.
* ### Provide diverse exercise methods.
* ### Offer interesting vocabulary activities to maintain student interest.
* ### Develop a user-friendly application to facilitate easy interaction with students.
ProficiencyLevelDetection/data/dataset.csv 0 → 100644
View file @ feeb76c8
Student_ID,Assessment_Scores,Text_Complexity,Word_Count,Text_Features,Engagement_Metrics,Progress_Over_Time,Language_Complexity,Time_On_Learning_Tasks,Contextual_Clues,Feedback,NLP_Features,Attention_Metrics,Proficiency_Level
1,91,13,350,8,38,22,5,15,6,5,0.4,0.4,Advanced
2,66,13,219,7,24,11,3,12,9,9,0.3,0.5,Intermediate
3,74,5,246,4,29,27,6,29,9,8,0.7,0.7,Intermediate
4,90,7,299,8,22,8,9,27,4,4,0.8,0.9,Intermediate
5,79,15,102,6,25,18,8,26,5,9,0.8,0.2,Basic
6,97,14,350,4,31,9,4,28,5,6,0.3,0.3,Advanced
7,42,8,243,15,34,28,5,12,7,9,0.6,0.6,Basic
8,35,13,114,11,31,9,7,10,8,9,0.5,0.3,Basic
9,36,10,367,8,28,27,3,29,7,5,0.2,0.3,Basic
10,72,5,205,13,31,16,9,16,7,4,0.5,0.6,Intermediate
11,70,17,307,6,37,29,7,26,4,8,0.5,0.4,Intermediate
12,85,8,154,4,28,19,6,23,6,5,0.4,0.3,Basic
13,92,17,133,9,35,21,2,27,6,6,0.6,0.4,Advanced
14,88,13,217,5,41,17,4,10,9,6,0.7,0.5,Advanced
15,37,5,334,14,28,7,7,21,7,6,0.6,0.7,Basic
16,67,6,310,9,30,25,2,15,3,8,0.5,0.8,Intermediate
17,59,15,273,12,30,4,3,15,5,5,0.4,0.3,Basic
18,91,6,106,15,16,25,6,8,5,9,0.4,0.5,Intermediate
19,55,5,142,13,30,16,6,14,8,4,0.4,0.5,Basic
20,37,8,359,15,29,29,3,17,5,9,0.4,0.8,Basic
21,75,16,142,15,28,28,2,20,9,4,0.7,0.6,Basic
22,85,5,389,5,27,6,7,16,6,7,0.3,0.2,Advanced
23,53,12,184,13,27,5,2,10,7,3,0.7,0.9,Basic
24,58,8,346,12,29,8,1,20,4,8,0.3,0.6,Basic
25,56,8,197,8,44,6,4,12,3,4,0.3,0.4,Basic
26,79,15,390,12,18,28,3,9,6,6,0.4,0.8,Intermediate
27,77,13,317,15,37,15,8,19,8,5,0.3,0.7,Intermediate
28,45,13,170,6,15,19,3,8,6,8,0.8,0.8,Basic
29,82,16,295,9,15,15,1,23,3,5,0.8,0.6,Advanced
30,45,9,324,13,40,25,5,13,7,4,0.4,0.6,Basic
31,43,8,313,13,17,12,3,18,4,3,0.7,0.8,Basic
32,51,6,281,15,42,18,8,28,6,6,0.7,0.3,Basic
33,47,6,216,6,27,26,7,13,7,4,0.7,0.8,Basic
34,85,15,170,11,29,16,6,20,8,9,0.8,0.2,Advanced
35,41,17,119,12,43,25,6,6,8,4,0.6,0.7,Basic
36,35,10,123,7,36,11,4,29,3,7,0.6,0.5,Basic
37,77,9,182,14,22,9,9,23,6,6,0.4,0.4,Basic
38,31,7,169,12,35,13,8,25,9,7,0.8,0.5,Basic
39,33,10,213,6,18,8,6,18,3,7,0.6,0.8,Basic
40,36,14,277,7,22,9,9,12,5,7,0.2,0.4,Basic
41,60,16,245,5,35,14,8,4,7,5,0.2,0.6,Basic
42,53,14,212,12,24,21,3,21,7,7,0.3,0.9,Basic
43,75,10,273,8,29,5,7,8,5,5,0.3,0.5,Basic
44,89,6,396,5,41,18,1,22,9,7,0.9,0.4,Advanced
45,59,15,231,7,23,12,4,15,9,5,0.6,0.8,Basic
46,87,13,108,13,25,29,3,19,9,8,0.4,0.8,Advanced
47,83,5,279,7,28,11,3,12,4,8,0.3,0.5,Intermediate
48,79,17,319,10,15,10,5,18,4,9,0.8,0.3,Intermediate
49,86,15,268,7,27,18,6,15,8,6,0.3,0.2,Advanced
50,69,12,151,15,38,5,9,23,4,5,0.7,0.6,Basic
51,81,14,144,7,32,19,1,28,7,8,0.9,0.6,Advanced
52,41,6,182,8,28,22,1,11,9,6,0.3,0.6,Basic
53,61,6,125,13,41,26,1,20,9,4,0.8,0.8,Basic
54,33,6,97,8,42,7,8,9,6,9,0.7,0.2,Basic
55,69,15,117,5,43,5,2,28,4,6,0.6,0.8,Basic
56,32,13,192,7,42,27,6,4,6,8,0.7,0.7,Basic
57,97,5,334,12,38,26,9,21,6,5,0.5,0.4,Advanced
58,82,7,205,11,42,4,7,23,3,9,0.8,0.5,Intermediate
59,67,7,149,14,36,12,9,12,4,3,0.5,0.8,Basic
60,72,7,374,7,42,17,8,22,8,6,0.2,0.8,Intermediate
61,59,16,297,13,33,13,9,25,6,3,0.8,0.7,Basic
62,39,13,335,9,31,5,8,26,8,9,0.7,0.7,Basic
63,42,9,112,7,38,20,2,27,8,8,0.7,0.4,Basic
64,80,13,136,14,21,25,7,29,5,8,0.3,0.5,Basic
65,78,6,305,6,36,4,5,11,6,3,0.7,0.9,Intermediate
66,69,6,284,15,32,21,9,23,9,5,0.8,0.6,Intermediate
67,31,6,261,10,26,16,6,7,6,9,0.5,0.8,Basic
68,68,11,81,12,39,6,5,23,7,3,0.4,0.8,Basic
69,71,11,313,12,42,27,9,8,7,3,0.3,0.9,Intermediate
70,70,5,139,12,29,29,2,28,3,4,0.8,0.5,Basic
71,55,15,349,7,40,25,6,22,7,4,0.9,0.3,Basic
72,98,7,180,15,24,29,3,15,5,8,0.7,0.3,Intermediate
73,82,11,346,13,44,17,7,25,9,5,0.7,0.4,Advanced
74,43,5,223,14,19,22,5,25,6,8,0.4,0.8,Basic
75,67,5,145,11,27,15,6,10,9,4,0.6,0.7,Basic
76,80,6,323,6,22,26,6,26,8,7,0.6,0.7,Intermediate
77,37,11,142,14,24,24,2,19,6,3,0.7,0.7,Basic
78,78,16,207,7,15,17,8,27,7,8,0.3,0.7,Intermediate
79,43,9,369,8,32,23,7,14,6,6,0.4,0.4,Basic
80,57,12,241,13,16,7,5,16,3,8,0.4,0.4,Basic
81,85,5,147,13,20,20,5,4,9,6,0.4,0.7,Basic
82,76,10,197,10,29,23,6,10,6,6,0.3,0.5,Basic
83,90,12,239,14,22,15,4,21,8,4,0.2,0.7,Advanced
84,96,13,148,9,32,28,4,23,5,4,0.5,0.3,Advanced
85,84,16,188,11,27,22,2,22,3,4,0.8,0.8,Advanced
86,43,11,112,6,37,21,9,21,6,3,0.9,0.7,Basic
87,89,12,140,14,38,23,1,10,3,3,0.6,0.2,Advanced
88,87,15,297,13,40,6,9,8,3,4,0.6,0.3,Advanced
89,88,13,120,13,31,23,8,29,9,7,0.7,0.3,Advanced
90,68,5,107,14,37,29,3,10,5,6,0.8,0.3,Basic
91,94,17,364,15,33,13,4,24,3,7,0.3,0.8,Advanced
92,94,15,285,9,37,11,8,4,3,3,0.8,0.5,Advanced
93,99,6,268,12,21,14,7,22,7,5,0.6,0.5,Intermediate
94,78,6,251,12,22,4,6,5,5,6,0.3,0.7,Basic
95,43,7,171,9,25,5,1,26,7,4,0.4,0.9,Basic
96,84,11,344,5,44,22,4,28,3,8,0.4,0.7,Advanced
97,49,14,162,4,27,27,6,7,8,8,0.6,0.6,Basic
98,68,5,84,14,33,25,9,24,6,4,0.3,0.6,Basic
99,58,7,307,14,23,18,8,18,7,7,0.3,0.8,Basic
100,93,13,334,9,19,6,3,9,7,7,0.4,0.3,Advanced
101,97,11,358,11,29,5,8,6,6,3,0.4,0.6,Advanced
102,90,13,99,8,33,6,6,28,7,5,0.5,0.8,Advanced
103,57,12,209,6,25,11,2,25,9,4,0.5,0.7,Basic
104,99,6,338,5,28,24,9,13,3,4,0.6,0.8,Intermediate
105,38,6,235,15,33,21,5,25,6,3,0.6,0.4,Basic
106,78,6,341,14,22,27,9,24,6,7,0.2,0.7,Intermediate
107,66,16,334,4,15,14,8,6,4,4,0.5,0.5,Intermediate
108,56,15,164,4,27,27,5,21,9,4,0.4,0.2,Basic
109,69,8,119,11,31,16,4,22,5,7,0.7,0.7,Basic
110,57,10,333,12,36,7,4,27,8,7,0.4,0.4,Basic
111,35,13,379,5,25,20,2,13,6,4,0.7,0.9,Basic
112,90,11,119,4,23,8,7,23,8,5,0.3,0.8,Advanced
113,41,16,85,12,44,5,8,13,7,6,0.3,0.4,Basic
114,82,5,377,11,15,9,5,27,9,3,0.6,0.7,Advanced
115,86,15,369,5,26,16,1,9,6,9,0.9,0.5,Advanced
116,56,14,127,7,32,14,4,9,4,4,0.5,0.9,Basic
117,55,10,283,5,15,4,4,14,9,7,0.8,0.2,Basic
118,61,12,275,14,35,26,6,7,6,7,0.6,0.4,Intermediate
119,97,9,336,13,16,24,6,11,4,4,0.5,0.3,Intermediate
120,83,10,89,7,17,8,7,6,4,5,0.7,0.4,Intermediate
121,69,17,310,9,40,23,1,16,9,4,0.7,0.7,Intermediate
122,78,5,397,11,23,28,1,20,6,7,0.7,0.7,Intermediate
123,78,5,177,9,37,20,2,28,3,6,0.2,0.4,Basic
124,30,16,251,11,42,25,6,14,9,5,0.3,0.9,Basic
125,96,15,143,15,20,20,8,13,5,5,0.3,0.3,Advanced
126,37,10,248,11,31,20,6,24,3,7,0.7,0.8,Basic
127,68,6,194,8,27,4,8,19,8,7,0.8,0.4,Basic
128,86,10,102,7,44,21,3,17,4,6,0.9,0.4,Intermediate
129,84,15,344,13,20,22,1,6,8,3,0.6,0.3,Advanced
130,86,13,223,12,32,26,2,26,7,8,0.6,0.8,Advanced
131,44,9,252,4,20,29,5,13,6,3,0.6,0.6,Basic
132,52,9,242,10,28,22,6,22,5,7,0.7,0.7,Basic
133,78,9,199,6,22,8,6,28,3,5,0.6,0.7,Basic
134,99,13,110,10,27,27,3,19,8,4,0.7,0.6,Advanced
135,79,5,168,6,23,15,2,27,7,8,0.2,0.2,Basic
136,81,5,285,12,22,9,2,5,8,3,0.5,0.6,Basic
137,30,7,306,13,16,15,6,9,3,5,0.4,0.6,Basic
138,81,5,96,15,37,6,1,12,8,3,0.5,0.3,Basic
139,82,14,203,5,38,21,1,15,7,9,0.2,0.4,Advanced
140,80,16,223,6,15,24,4,28,4,6,0.6,0.2,Intermediate
141,64,6,84,7,16,29,4,27,3,7,0.8,0.7,Basic
142,65,11,213,8,17,9,6,17,8,3,0.4,0.8,Intermediate
143,82,11,267,8,23,14,6,28,3,6,0.2,0.2,Advanced
144,85,12,399,15,15,6,8,4,7,4,0.6,0.3,Advanced
145,72,10,239,15,16,8,2,4,8,7,0.7,0.5,Intermediate
146,96,14,232,6,21,24,8,27,8,9,0.6,0.4,Advanced
147,40,8,181,11,44,11,8,29,5,9,0.6,0.4,Basic
148,61,14,239,9,15,28,7,6,9,6,0.4,0.3,Intermediate
149,95,9,266,15,32,11,2,4,3,7,0.8,0.6,Intermediate
150,63,13,98,4,35,17,5,23,8,7,0.2,0.2,Basic
151,42,15,311,8,22,27,2,10,9,5,0.4,0.8,Basic
152,54,15,145,12,22,6,6,10,7,4,0.3,0.6,Basic
153,57,7,201,12,17,9,6,29,6,5,0.9,0.4,Basic
154,51,7,182,13,25,27,8,6,8,3,0.4,0.4,Basic
155,34,6,126,14,29,11,6,16,6,4,0.3,0.7,Basic
156,72,14,367,7,24,27,4,21,8,5,0.6,0.5,Intermediate
157,30,17,288,10,19,21,3,26,9,4,0.4,0.7,Basic
158,73,10,134,11,44,22,2,16,3,3,0.6,0.5,Basic
159,42,5,295,9,33,26,9,11,5,3,0.4,0.6,Basic
160,57,7,118,12,30,6,8,23,3,9,0.5,0.3,Basic
161,97,12,253,6,20,8,9,12,4,7,0.8,0.8,Advanced
162,36,7,190,4,38,4,8,19,9,9,0.7,0.5,Basic
163,84,12,350,12,18,12,3,6,5,7,0.3,0.4,Advanced
164,70,6,275,4,21,5,6,27,4,8,0.8,0.5,Intermediate
165,86,9,121,7,33,17,1,19,7,6,0.6,0.5,Intermediate
166,44,6,290,9,18,10,9,12,3,9,0.5,0.5,Basic
167,34,8,89,9,25,22,4,19,6,8,0.6,0.6,Basic
168,66,13,151,8,21,4,6,23,9,7,0.3,0.9,Basic
169,35,13,243,10,20,15,5,25,3,8,0.7,0.8,Basic
170,99,17,367,9,16,16,3,23,8,8,0.9,0.7,Advanced
171,60,10,242,8,33,10,2,25,5,3,0.2,0.6,Basic
172,69,8,354,7,20,8,1,13,9,5,0.4,0.7,Basic
173,44,16,316,10,38,24,2,25,8,9,0.6,0.2,Basic
174,42,10,164,13,15,15,6,27,3,8,0.4,0.7,Basic
175,90,6,138,10,17,16,1,23,9,8,0.9,0.3,Intermediate
176,63,5,101,10,20,26,1,15,8,8,0.8,0.7,Basic
177,70,10,122,15,43,10,8,24,6,9,0.3,0.6,Basic
178,71,14,235,6,29,4,8,5,3,5,0.6,0.5,Intermediate
179,59,13,131,10,43,17,3,25,9,6,0.2,0.6,Basic
180,77,8,273,15,20,24,4,12,4,7,0.6,0.2,Intermediate
181,68,12,296,9,15,13,2,20,6,8,0.6,0.4,Intermediate
182,50,16,119,15,29,22,7,26,6,3,0.5,0.2,Basic
183,99,14,247,14,26,27,9,6,5,7,0.6,0.6,Advanced
184,70,13,343,4,43,7,7,5,5,5,0.7,0.7,Intermediate
185,39,14,108,7,27,13,8,21,7,3,0.2,0.6,Basic
186,72,6,190,7,34,24,1,20,4,5,0.7,0.6,Basic
187,66,7,206,4,18,7,7,18,8,8,0.6,0.5,Intermediate
188,86,10,100,4,33,25,4,25,7,5,0.2,0.8,Basic
189,52,15,134,7,16,26,9,9,5,8,0.8,0.5,Basic
190,90,5,277,7,40,6,8,14,3,8,0.6,0.5,Intermediate
191,58,10,311,13,28,27,9,19,6,8,0.4,0.8,Basic
192,63,5,396,9,31,15,3,23,3,3,0.3,0.3,Intermediate
193,55,17,248,14,40,21,9,12,9,3,0.5,0.7,Basic
194,92,15,164,14,18,11,8,23,9,3,0.7,0.5,Advanced
195,47,14,173,11,43,23,7,12,9,5,0.7,0.7,Basic
196,46,16,87,12,32,19,1,18,6,5,0.8,0.2,Basic
197,89,11,255,15,27,28,6,18,8,5,0.8,0.5,Advanced
198,44,10,304,13,33,22,8,26,5,6,0.4,0.7,Basic
199,40,7,248,10,43,14,8,12,8,7,0.5,0.4,Basic
200,57,10,385,13,32,6,4,6,8,8,0.7,0.9,Basic
201,83,14,212,8,16,8,9,29,8,9,0.7,0.7,Advanced
202,75,10,153,5,17,9,1,11,8,9,0.7,0.4,Basic
203,92,13,208,11,37,18,2,19,4,4,0.5,0.2,Advanced
204,67,14,116,4,25,26,6,28,5,3,0.5,0.3,Basic
205,96,17,258,7,22,18,4,9,6,4,0.4,0.5,Advanced
206,38,11,311,8,38,28,2,17,7,5,0.8,0.5,Basic
207,51,12,170,13,42,23,2,8,5,9,0.5,0.9,Basic
208,88,17,369,15,33,16,5,17,9,5,0.4,0.4,Advanced
209,43,13,92,11,36,27,2,16,7,7,0.4,0.4,Basic
210,76,16,279,12,18,6,7,12,9,6,0.9,0.6,Intermediate
211,84,11,334,7,44,19,3,24,6,3,0.6,0.7,Advanced
212,72,13,219,15,43,25,2,16,6,3,0.5,0.8,Intermediate
213,86,5,339,7,29,14,2,22,6,5,0.6,0.6,Advanced
214,58,15,353,5,35,29,3,12,5,9,0.3,0.8,Basic
215,40,14,256,9,23,12,5,4,8,9,0.5,0.3,Basic
216,90,5,305,14,43,14,6,19,9,4,0.2,0.5,Advanced
217,31,15,338,10,28,15,6,13,8,6,0.9,0.4,Basic
218,87,8,140,10,15,27,4,25,6,6,0.6,0.6,Intermediate
219,68,15,300,8,25,15,4,16,6,8,0.3,0.7,Intermediate
220,49,6,130,8,40,12,8,13,9,4,0.8,0.8,Basic
221,63,8,383,13,15,5,9,25,9,9,0.3,0.3,Basic
222,65,13,223,11,15,11,2,13,6,4,0.3,0.4,Intermediate
223,90,12,126,8,31,26,5,9,7,7,0.5,0.7,Advanced
224,72,10,366,8,22,27,8,17,9,6,0.4,0.8,Intermediate
225,43,8,306,7,37,6,8,12,7,9,0.8,0.8,Basic
226,74,15,109,4,44,15,3,25,6,7,0.5,0.6,Basic
227,89,15,279,5,22,19,9,12,8,6,0.7,0.9,Advanced
228,58,6,166,9,15,4,8,15,3,4,0.6,0.4,Basic
229,97,17,200,13,34,25,5,26,3,7,0.7,0.9,Advanced
230,34,12,102,5,37,12,4,15,7,9,0.5,0.9,Basic
231,59,12,89,9,34,25,6,22,3,3,0.4,0.3,Basic
232,77,15,357,13,16,11,6,25,7,9,0.6,0.5,Intermediate
233,88,5,159,14,26,11,6,6,6,4,0.8,0.4,Intermediate
234,33,10,310,13,35,10,1,14,5,7,0.3,0.5,Basic
235,43,16,336,9,35,5,2,28,8,3,0.7,0.6,Basic
236,51,6,111,12,15,21,8,4,5,7,0.7,0.8,Basic
237,82,8,276,9,34,16,6,28,6,4,0.8,0.2,Intermediate
238,52,16,231,10,35,8,9,5,5,3,0.5,0.8,Basic
239,72,9,230,8,34,17,1,26,8,3,0.6,0.7,Intermediate
240,42,5,146,9,21,12,7,4,4,8,0.5,0.5,Basic
241,69,5,116,6,20,20,8,28,7,3,0.9,0.6,Basic
242,67,13,347,12,32,28,1,25,6,7,0.3,0.8,Intermediate
243,94,14,350,12,23,8,3,26,3,8,0.4,0.6,Advanced
244,63,13,86,14,29,5,8,8,6,7,0.7,0.7,Basic
245,99,17,103,8,33,4,7,8,8,5,0.3,0.8,Advanced
246,49,17,333,14,17,21,9,5,9,8,0.5,0.2,Basic
247,63,6,375,5,20,26,4,6,8,3,0.8,0.4,Intermediate
248,99,16,353,5,37,29,7,12,8,8,0.8,0.5,Advanced
249,32,6,195,5,16,10,6,16,8,6,0.4,0.8,Basic
250,61,17,393,14,24,23,1,23,8,7,0.7,0.2,Intermediate
251,96,7,341,14,24,19,7,4,7,8,0.6,0.5,Intermediate
252,45,15,304,10,19,24,1,24,4,9,0.3,0.3,Basic
253,31,9,233,4,37,22,9,9,5,8,0.3,0.3,Basic
254,55,15,381,10,37,26,2,27,3,5,0.2,0.3,Basic
255,33,12,135,13,25,21,7,26,6,4,0.5,0.4,Basic
256,42,6,366,9,18,25,8,4,3,4,0.7,0.5,Basic
257,40,17,129,9,22,9,2,25,8,5,0.8,0.4,Basic
258,38,5,223,14,36,9,4,14,3,9,0.4,0.3,Basic
259,44,8,269,10,40,25,6,23,8,9,0.7,0.5,Basic
260,42,17,86,8,21,23,3,12,9,5,0.8,0.4,Basic
261,53,11,341,6,42,6,5,8,7,4,0.8,0.5,Basic
262,99,17,123,4,32,20,6,4,7,7,0.2,0.4,Advanced
263,57,13,208,8,30,14,6,4,7,8,0.3,0.8,Basic
264,87,7,118,12,19,4,8,29,7,8,0.8,0.6,Intermediate
265,68,14,99,13,17,10,8,22,4,7,0.3,0.5,Basic
266,39,8,245,9,33,17,6,9,4,9,0.4,0.4,Basic
267,53,16,199,9,40,5,6,23,7,5,0.7,0.6,Basic
268,73,16,268,8,21,23,8,25,6,5,0.6,0.5,Intermediate
269,41,6,305,10,42,20,4,24,6,7,0.3,0.2,Basic
270,65,17,320,8,16,14,2,26,9,6,0.4,0.3,Intermediate
271,72,14,275,15,27,21,5,9,9,8,0.7,0.3,Intermediate
272,33,10,324,10,20,29,4,11,3,6,0.6,0.5,Basic
273,74,13,301,4,31,21,4,16,3,5,0.5,0.4,Intermediate
274,70,10,160,9,35,5,7,28,6,8,0.2,0.8,Basic
275,30,5,151,14,19,29,6,25,9,5,0.4,0.2,Basic
276,95,12,152,4,31,20,5,13,4,7,0.3,0.7,Advanced
277,39,12,268,14,39,18,3,25,5,9,0.6,0.5,Basic
278,76,8,395,10,23,8,3,23,7,8,0.4,0.7,Basic
279,89,6,306,10,28,8,1,26,7,3,0.4,0.5,Advanced
280,76,15,216,6,16,25,1,18,6,4,0.5,0.2,Intermediate
281,58,17,206,14,40,7,5,11,8,8,0.3,0.9,Basic
282,77,13,163,14,21,20,4,8,4,5,0.6,0.8,Basic
283,46,7,366,6,27,17,7,9,4,8,0.3,0.9,Basic
284,34,9,343,9,33,11,6,17,7,9,0.8,0.5,Basic
285,67,15,145,15,43,25,2,7,8,8,0.4,0.7,Basic
286,55,10,382,11,31,13,4,15,7,3,0.5,0.2,Basic
287,82,13,370,6,25,22,1,28,8,5,0.6,0.8,Advanced
288,89,13,302,7,20,15,4,8,8,3,0.7,0.5,Advanced
289,41,15,102,11,33,24,4,15,5,8,0.8,0.4,Basic
290,88,16,269,10,35,13,4,29,3,4,0.6,0.4,Advanced
291,72,8,311,11,43,17,3,21,6,3,0.4,0.4,Intermediate
292,72,12,301,4,32,14,9,4,7,6,0.7,0.4,Intermediate
293,89,12,248,13,37,13,8,4,9,5,0.4,0.7,Advanced
294,41,16,316,8,19,4,2,12,7,4,0.4,0.2,Basic
295,62,8,98,9,15,17,1,6,3,8,0.2,0.4,Basic
296,94,13,148,7,20,21,2,27,4,5,0.6,0.8,Advanced
297,73,13,217,10,17,25,5,10,8,3,0.6,0.6,Intermediate
298,94,15,118,15,20,9,8,8,5,7,0.5,0.8,Advanced
299,82,11,265,14,26,4,2,6,8,8,0.5,0.6,Advanced
300,57,8,229,10,32,27,5,7,5,5,0.2,0.3,Basic
301,42,7,249,14,20,13,9,10,5,9,0.8,0.3,Basic
302,75,17,132,12,21,13,4,24,4,3,0.5,0.6,Basic
303,58,17,184,12,30,7,4,20,4,3,0.6,0.7,Basic
304,59,5,343,8,31,22,1,29,4,7,0.6,0.3,Basic
305,74,13,166,7,40,11,8,27,6,4,0.3,0.5,Basic
306,46,7,267,7,17,23,1,15,6,6,0.7,0.6,Basic
307,33,12,241,10,27,12,2,19,9,3,0.7,0.6,Basic
308,86,17,183,9,28,11,9,6,4,4,0.7,0.8,Advanced
309,70,5,330,10,32,11,5,13,5,3,0.7,0.4,Intermediate
310,76,9,255,12,15,24,1,23,3,9,0.6,0.5,Intermediate
311,69,12,145,4,30,12,6,12,3,7,0.7,0.3,Basic
312,57,16,193,7,27,12,4,21,8,9,0.6,0.3,Basic
313,77,16,113,7,43,24,7,25,7,9,0.6,0.6,Basic
314,45,9,240,13,33,28,3,19,3,5,0.6,0.7,Basic
315,41,10,131,4,33,10,2,6,9,7,0.6,0.3,Basic
316,56,7,166,4,29,8,1,10,5,9,0.9,0.8,Basic
317,62,12,146,12,29,22,4,22,7,5,0.8,0.3,Basic
318,65,15,185,4,30,29,3,19,7,7,0.4,0.7,Basic
319,58,6,341,10,17,21,2,12,8,3,0.5,0.8,Basic
320,85,12,276,7,27,26,3,27,9,4,0.8,0.3,Advanced
321,58,10,126,14,21,23,9,7,6,3,0.5,0.5,Basic
322,57,14,85,12,38,4,5,24,5,8,0.4,0.8,Basic
323,62,7,121,13,28,17,2,4,7,4,0.5,0.6,Basic
324,97,15,200,12,16,7,3,20,6,8,0.9,0.4,Advanced
325,60,16,399,14,42,28,1,5,7,9,0.7,0.4,Basic
326,86,12,320,8,27,9,9,4,7,8,0.8,0.8,Advanced
327,63,6,280,15,16,18,9,8,7,7,0.7,0.6,Intermediate
328,36,9,288,4,40,9,9,11,8,4,0.8,0.4,Basic
329,56,5,268,6,33,25,2,22,5,6,0.4,0.6,Basic
330,85,11,187,14,23,26,6,6,6,9,0.3,0.8,Advanced
331,37,15,307,7,35,5,1,19,7,4,0.5,0.7,Basic
332,30,14,376,15,33,15,9,15,8,3,0.3,0.2,Basic
333,40,13,86,12,19,26,3,29,4,7,0.3,0.8,Basic
334,95,8,268,13,17,27,3,26,7,5,0.4,0.7,Basic
335,60,6,137,14,22,26,6,13,4,5,0.6,0.4,Basic
336,86,17,355,6,26,5,6,24,8,7,0.8,0.2,Advanced
337,70,9,167,12,26,12,4,25,5,5,0.8,0.7,Basic
338,48,14,190,13,39,14,2,25,8,6,0.8,0.7,Basic
339,98,13,383,10,16,18,2,10,9,4,0.6,0.2,Advanced
340,81,5,218,4,23,18,7,26,9,9,0.8,0.3,Intermediate
341,83,12,145,6,21,24,4,17,3,7,0.8,0.8,Advanced
342,92,9,259,11,33,17,7,11,4,3,0.5,0.6,Basic
343,82,15,128,7,25,8,8,15,5,6,0.9,0.8,Advanced
344,62,14,243,7,37,25,2,17,3,8,0.8,0.8,Intermediate
345,63,17,172,7,43,4,8,8,7,8,0.4,0.9,Basic
346,31,14,184,9,17,4,5,4,3,3,0.6,0.6,Basic
347,35,10,291,6,44,18,2,9,8,4,0.5,0.6,Basic
348,81,14,326,4,44,8,6,24,4,8,0.6,0.8,Advanced
349,56,5,306,4,29,4,2,10,3,5,0.4,0.4,Basic
350,61,9,124,13,41,5,1,27,8,9,0.9,0.8,Basic
351,55,5,293,12,16,12,4,28,9,4,0.5,0.6,Basic
352,90,10,142,6,25,15,3,8,8,6,0.4,0.8,Basic
353,49,11,118,15,29,28,1,8,9,4,0.6,0.6,Basic
354,93,17,320,13,26,28,7,7,5,5,0.6,0.4,Advanced
355,42,14,103,8,43,21,1,26,8,8,0.4,0.5,Basic
356,68,10,123,11,31,9,8,4,9,7,0.4,0.4,Basic
357,68,9,193,14,36,13,7,5,6,6,0.2,0.2,Basic
358,41,9,91,8,17,4,1,8,7,9,0.6,0.3,Basic
359,82,15,173,12,23,22,3,11,4,8,0.9,0.8,Advanced
360,49,5,395,4,33,13,4,9,5,4,0.8,0.6,Basic
361,86,12,382,7,38,16,6,26,6,6,0.5,0.7,Advanced
362,82,7,374,11,24,13,1,4,3,8,0.4,0.3,Intermediate
363,77,12,283,14,15,25,9,23,5,3,0.8,0.6,Intermediate
364,60,11,109,11,41,14,8,9,9,5,0.5,0.2,Basic
365,32,6,158,14,27,18,2,27,8,5,0.7,0.4,Basic
366,84,10,199,10,17,4,4,17,4,8,0.4,0.4,Intermediate
367,88,11,241,14,37,18,7,10,4,5,0.4,0.5,Advanced
368,48,12,220,7,24,11,7,24,4,9,0.3,0.4,Basic
369,97,11,252,10,25,27,3,15,8,6,0.7,0.4,Advanced
370,68,16,324,9,17,27,7,17,9,7,0.3,0.4,Intermediate
371,63,13,315,5,17,27,4,26,3,5,0.4,0.5,Intermediate
372,39,7,317,12,41,18,2,25,6,5,0.3,0.6,Basic
373,42,17,328,5,38,6,3,17,4,6,0.7,0.4,Basic
374,49,8,170,7,31,28,7,12,4,6,0.5,0.6,Basic
375,79,6,268,4,35,19,5,20,3,7,0.8,0.7,Intermediate
376,94,12,279,8,23,17,7,27,3,8,0.5,0.4,Advanced
377,42,16,107,9,40,22,1,10,6,4,0.6,0.8,Basic
378,95,17,181,5,24,24,1,4,4,3,0.8,0.3,Advanced
379,95,9,386,12,17,25,3,12,4,7,0.9,0.5,Intermediate
380,96,14,99,6,32,27,7,22,5,8,0.8,0.2,Advanced
381,68,6,300,14,22,18,5,13,9,8,0.9,0.3,Intermediate
382,49,16,273,12,20,23,3,5,8,4,0.6,0.2,Basic
383,43,15,285,7,31,9,6,24,3,3,0.3,0.5,Basic
384,34,13,96,12,42,23,9,16,3,8,0.8,0.3,Basic
385,40,9,141,14,26,8,2,5,4,5,0.3,0.6,Basic
386,72,15,337,4,43,5,9,14,5,9,0.4,0.3,Basic
387,46,11,87,9,37,10,6,29,5,4,0.7,0.6,Basic
388,84,15,387,11,32,18,9,7,9,6,0.5,0.5,Advanced
389,79,6,150,15,30,9,6,15,9,3,0.6,0.6,Basic
390,33,6,202,6,37,16,8,11,3,4,0.5,0.7,Basic
391,70,12,151,12,40,27,1,18,7,3,0.4,0.9,Basic
392,78,5,257,15,26,5,4,18,5,4,0.4,0.3,Basic
393,57,7,204,11,40,28,2,17,3,4,0.3,0.5,Basic
394,72,5,162,8,31,28,7,19,7,4,0.2,0.9,Basic
395,88,6,304,14,25,12,1,10,7,9,0.6,0.2,Intermediate
396,40,7,263,4,16,13,7,14,3,5,0.4,0.5,Basic
397,68,11,118,4,19,18,3,12,7,9,0.6,0.3,Basic
398,33,10,380,4,44,21,9,10,7,7,0.2,0.5,Basic
399,65,5,196,7,42,24,8,29,3,5,0.5,0.6,Basic
400,57,12,218,12,31,5,7,27,3,8,0.4,0.7,Basic
401,63,8,282,4,35,13,7,27,3,5,0.5,0.3,Intermediate
402,74,15,274,12,17,25,4,9,6,6,0.2,0.6,Intermediate
403,95,9,108,14,33,9,6,8,4,4,0.4,0.8,Basic
404,82,9,306,9,26,28,6,14,8,7,0.7,0.4,Intermediate
405,88,9,296,11,40,12,6,22,4,9,0.7,0.5,Intermediate
406,56,12,139,15,21,13,8,29,7,4,0.8,0.6,Basic
407,33,6,328,5,36,23,4,29,5,9,0.4,0.7,Basic
408,70,11,360,14,43,4,8,19,9,3,0.7,0.2,Intermediate
409,76,16,260,4,17,25,6,22,4,4,0.4,0.4,Intermediate
410,56,10,90,7,33,18,2,28,9,5,0.6,0.4,Basic
411,39,8,156,11,37,13,4,25,8,9,0.5,0.7,Basic
412,69,17,377,7,33,12,1,6,7,5,0.7,0.8,Intermediate
413,87,7,107,4,37,24,6,4,9,7,0.5,0.5,Basic
414,68,5,381,7,40,18,2,6,9,6,0.8,0.2,Intermediate
415,65,10,179,5,21,13,4,28,4,9,0.3,0.5,Basic
416,88,15,335,10,19,29,6,6,6,3,0.8,0.4,Advanced
417,78,7,337,13,42,24,1,24,4,3,0.6,0.7,Intermediate
418,53,8,192,5,34,23,3,5,9,3,0.4,0.8,Basic
419,41,17,180,10,15,8,9,24,5,5,0.6,0.7,Basic
420,60,11,173,15,26,14,8,13,7,6,0.7,0.7,Basic
421,62,6,141,8,38,24,9,16,6,6,0.6,0.4,Basic
422,57,10,232,11,16,9,7,18,8,6,0.8,0.4,Basic
423,62,15,126,14,29,5,3,26,3,9,0.2,0.9,Basic
424,63,5,317,7,35,7,4,5,9,4,0.5,0.5,Intermediate
425,71,14,217,6,21,23,2,7,4,3,0.4,0.6,Intermediate
426,66,15,253,9,39,23,3,29,9,3,0.7,0.3,Intermediate
427,74,10,290,9,26,11,1,29,8,5,0.5,0.5,Intermediate
428,86,5,399,5,34,8,7,23,6,9,0.4,0.8,Advanced
429,33,16,238,6,26,18,6,26,6,9,0.3,0.8,Basic
430,74,17,178,12,26,15,7,4,5,4,0.5,0.2,Basic
431,85,12,253,9,34,25,1,7,6,9,0.5,0.6,Advanced
432,69,17,98,13,34,8,9,20,6,8,0.6,0.5,Basic
433,45,6,130,13,30,10,8,18,8,7,0.7,0.3,Basic
434,46,12,205,10,23,20,7,4,4,4,0.5,0.3,Basic
435,91,10,287,13,35,16,1,4,4,8,0.2,0.2,Intermediate
436,51,13,101,5,26,28,7,10,9,5,0.5,0.6,Basic
437,31,6,261,14,36,27,4,19,6,3,0.7,0.4,Basic
438,63,13,281,5,27,14,5,29,5,8,0.3,0.6,Intermediate
439,88,16,375,15,31,7,9,8,9,9,0.6,0.7,Advanced
440,74,8,251,9,21,25,1,28,8,9,0.4,0.3,Intermediate
441,91,9,355,5,32,20,5,15,3,7,0.7,0.6,Intermediate
442,97,8,114,4,40,29,7,15,9,8,0.8,0.8,Intermediate
443,45,15,381,10,22,20,9,22,8,8,0.2,0.2,Basic
444,74,17,238,10,34,20,8,20,8,3,0.8,0.3,Intermediate
445,42,12,146,5,44,26,8,20,3,5,0.3,0.7,Basic
446,45,6,153,12,24,16,3,4,8,3,0.3,0.8,Basic
447,70,17,311,12,23,5,7,22,9,9,0.8,0.5,Intermediate
448,66,16,148,12,40,25,5,16,6,5,0.9,0.7,Basic
449,93,9,117,8,22,4,5,6,9,3,0.5,0.3,Basic
450,48,14,380,11,24,29,7,5,7,6,0.4,0.3,Basic
451,63,6,162,14,24,29,4,21,6,3,0.2,0.4,Basic
452,92,14,330,15,25,10,5,22,5,6,0.8,0.4,Advanced
453,99,16,104,14,33,14,7,20,6,6,0.6,0.4,Advanced
454,75,6,243,15,28,20,5,12,4,6,0.3,0.7,Intermediate
455,78,5,336,12,37,22,7,20,5,3,0.5,0.7,Intermediate
456,85,10,351,15,30,21,5,5,5,8,0.5,0.8,Intermediate
457,81,17,364,14,44,19,1,18,4,5,0.4,0.3,Advanced
458,33,6,375,12,29,29,5,18,8,6,0.7,0.3,Basic
459,69,11,144,9,29,16,1,10,5,6,0.8,0.4,Basic
460,46,10,332,9,40,16,4,12,6,9,0.4,0.7,Basic
461,73,13,126,12,33,22,3,7,3,7,0.8,0.4,Basic
462,61,8,114,15,38,20,9,26,4,9,0.4,0.7,Basic
463,55,8,361,7,31,15,8,27,8,5,0.4,0.2,Basic
464,52,9,366,9,28,21,3,27,7,3,0.4,0.2,Basic
465,39,13,355,12,20,25,8,29,7,7,0.5,0.5,Basic
466,78,14,326,13,21,21,4,17,7,8,0.8,0.8,Intermediate
467,86,17,324,7,42,19,4,10,8,7,0.6,0.9,Advanced
468,59,8,378,12,19,8,2,21,6,9,0.9,0.3,Basic
469,40,10,196,5,23,27,2,27,4,6,0.3,0.3,Basic
470,42,12,277,8,15,14,5,18,7,9,0.8,0.5,Basic
471,60,13,151,8,20,5,9,8,6,8,0.7,0.9,Basic
472,41,7,356,6,24,19,7,11,8,8,0.2,0.8,Basic
473,51,13,120,6,24,14,5,17,7,8,0.4,0.9,Basic
474,47,6,246,5,41,29,9,20,7,6,0.5,0.6,Basic
475,62,7,192,10,24,4,6,17,3,8,0.6,0.3,Basic
476,95,14,350,6,20,18,7,11,4,4,0.6,0.5,Advanced
477,98,16,218,4,30,15,1,5,3,6,0.5,0.3,Advanced
478,93,12,169,14,36,18,1,7,7,6,0.6,0.8,Advanced
479,80,13,211,10,24,25,4,15,8,7,0.9,0.6,Intermediate
480,54,9,135,8,41,24,7,28,4,6,0.5,0.8,Basic
481,90,12,111,4,37,16,7,22,7,7,0.5,0.4,Advanced
482,75,8,348,5,42,13,6,8,9,4,0.6,0.3,Intermediate
483,80,12,163,11,28,16,2,15,3,4,0.8,0.4,Basic
484,98,10,375,10,23,22,8,21,8,7,0.8,0.2,Advanced
485,96,8,250,4,25,4,9,11,8,9,0.5,0.3,Intermediate
486,93,16,381,14,36,21,1,18,5,3,0.4,0.2,Advanced
487,77,6,168,10,36,8,8,17,4,6,0.8,0.9,Basic
488,44,5,134,15,26,11,8,29,9,3,0.7,0.4,Basic
489,52,6,196,13,18,11,6,10,8,3,0.6,0.5,Basic
490,65,8,126,5,38,11,4,15,6,4,0.3,0.9,Basic
491,62,17,315,11,21,18,4,26,8,6,0.7,0.6,Intermediate
492,84,14,230,5,40,16,2,15,9,9,0.4,0.5,Advanced
493,30,12,320,12,39,6,7,25,4,6,0.8,0.5,Basic
494,61,9,365,14,30,29,5,7,9,7,0.4,0.3,Intermediate
495,42,13,225,6,24,12,5,4,3,5,0.8,0.8,Basic
496,97,7,275,6,21,20,9,22,6,4,0.5,0.3,Basic
497,66,8,292,6,16,19,1,9,6,4,0.6,0.4,Intermediate
498,92,7,393,15,35,23,5,19,5,3,0.8,0.7,Advanced
499,58,6,93,10,40,5,7,22,5,3,0.5,0.7,Basic
500,64,9,84,13,37,9,5,16,8,9,0.2,0.5,Basic
501,32,6,92,8,39,21,6,22,7,3,0.7,0.6,Basic
502,79,8,272,4,19,6,7,19,9,4,0.4,0.7,Basic
503,92,12,381,8,21,27,9,10,8,5,0.8,0.6,Advanced
504,37,10,216,10,20,28,8,22,9,8,0.3,0.8,Basic
505,30,11,176,15,31,12,2,11,4,3,0.3,0.3,Basic
506,39,9,254,10,43,24,4,8,9,6,0.7,0.3,Basic
507,35,14,113,5,37,23,7,22,3,3,0.8,0.4,Basic
508,97,17,85,13,15,24,4,23,7,7,0.9,0.3,Advanced
509,55,11,154,8,29,25,5,18,6,7,0.3,0.3,Basic
510,90,14,94,9,41,26,8,15,3,9,0.3,0.5,Advanced
511,96,10,82,11,31,6,1,12,8,5,0.6,0.3,Intermediate
512,38,17,329,9,27,24,7,20,4,9,0.9,0.6,Basic
513,37,12,224,12,38,19,1,25,4,9,0.9,0.5,Basic
514,50,12,124,9,18,4,5,7,9,6,0.7,0.2,Basic
515,98,6,100,8,37,10,4,22,4,8,0.9,0.8,Intermediate
516,70,17,83,8,37,26,2,8,4,9,0.8,0.6,Basic
517,98,9,285,6,43,29,4,22,5,9,0.6,0.4,Intermediate
518,48,9,388,11,30,17,4,6,9,8,0.8,0.6,Basic
519,45,17,324,9,31,10,6,11,5,4,0.5,0.6,Basic
520,86,11,132,8,29,19,4,15,8,9,0.9,0.8,Advanced
521,94,6,202,5,36,19,7,4,7,7,0.5,0.8,Basic
522,51,10,216,4,39,4,6,7,8,6,0.3,0.3,Basic
523,99,12,229,4,28,24,4,8,9,5,0.3,0.5,Advanced
524,61,14,273,7,41,4,7,22,5,6,0.2,0.3,Basic
525,60,5,117,7,37,23,5,17,6,5,0.5,0.6,Basic
526,56,13,150,8,40,6,7,7,5,5,0.7,0.7,Basic
527,49,17,135,6,17,25,9,14,9,5,0.9,0.8,Basic
528,43,12,322,13,23,9,1,11,5,3,0.4,0.7,Basic
529,91,8,317,15,25,4,6,26,4,4,0.8,0.3,Advanced
530,57,9,370,4,42,10,7,29,8,5,0.3,0.8,Basic
531,43,9,167,9,33,22,3,15,5,8,0.8,0.6,Basic
532,41,9,288,10,35,15,2,21,3,3,0.9,0.4,Basic
533,31,8,183,15,20,20,1,29,5,6,0.7,0.7,Basic
534,48,9,317,8,26,18,1,6,6,6,0.4,0.7,Basic
535,77,15,319,11,24,10,3,10,8,3,0.6,0.8,Intermediate
536,31,16,315,4,35,5,7,20,5,7,0.3,0.6,Basic
537,98,10,107,10,29,16,8,17,5,3,0.8,0.8,Intermediate
538,35,9,116,11,31,28,8,9,6,9,0.8,0.3,Basic
539,73,5,275,9,42,6,4,23,5,8,0.5,0.3,Intermediate
540,74,16,340,8,39,28,6,22,8,5,0.5,0.3,Intermediate
541,98,12,399,5,23,22,8,4,7,8,0.7,0.9,Advanced
542,31,14,325,6,36,13,1,7,5,9,0.4,0.8,Basic
543,65,17,193,11,24,21,3,26,7,6,0.7,0.8,Basic
544,61,11,100,14,35,5,4,21,9,5,0.5,0.5,Basic
545,70,16,240,9,20,24,8,27,3,5,0.5,0.8,Intermediate
546,32,12,369,6,33,7,8,4,3,4,0.4,0.5,Basic
547,61,14,190,9,32,19,7,6,7,4,0.3,0.9,Basic
548,75,5,278,10,15,23,9,24,5,9,0.6,0.7,Intermediate
549,77,5,186,6,27,28,9,19,3,4,0.5,0.4,Basic
550,30,15,260,10,24,24,1,8,5,8,0.8,0.5,Basic
551,92,10,367,6,42,29,7,12,9,8,0.3,0.8,Intermediate
552,32,6,388,13,31,6,3,22,7,3,0.8,0.5,Basic
553,64,9,299,9,44,15,5,14,8,7,0.2,0.2,Intermediate
554,36,7,187,4,33,14,9,9,3,3,0.7,0.6,Basic
555,77,17,283,12,39,17,3,29,6,3,0.6,0.5,Intermediate
556,51,16,293,5,38,18,9,12,8,9,0.5,0.7,Basic
557,32,17,288,11,32,10,6,15,4,8,0.4,0.8,Basic
558,99,12,306,11,30,10,4,12,4,5,0.4,0.2,Advanced
559,97,7,82,4,29,8,6,11,3,5,0.8,0.5,Intermediate
560,37,5,207,8,16,12,2,14,7,9,0.6,0.5,Basic
561,77,10,206,11,25,11,6,7,7,9,0.8,0.6,Intermediate
562,63,9,117,10,28,22,2,13,9,3,0.8,0.3,Basic
563,98,6,245,13,31,7,7,7,5,7,0.7,0.3,Intermediate
564,37,7,328,6,25,26,7,9,8,6,0.8,0.4,Basic
565,51,15,246,13,18,16,8,12,5,6,0.2,0.2,Basic
566,57,16,228,14,34,16,3,11,9,3,0.3,0.4,Basic
567,40,14,394,6,40,5,5,21,7,3,0.6,0.7,Basic
568,40,7,135,13,42,22,4,20,9,6,0.4,0.5,Basic
569,54,15,221,13,25,25,3,16,8,6,0.9,0.4,Basic
570,82,12,277,7,26,6,5,4,9,3,0.2,0.6,Advanced
571,50,17,270,9,38,7,8,12,4,8,0.5,0.7,Basic
572,90,8,336,9,42,24,1,13,5,7,0.3,0.5,Intermediate
573,63,11,297,9,44,22,3,21,3,3,0.4,0.9,Intermediate
574,46,17,87,5,41,13,6,17,7,6,0.2,0.5,Basic
575,87,17,233,15,16,7,7,5,9,9,0.4,0.4,Advanced
576,39,15,252,12,19,7,3,4,4,7,0.3,0.8,Basic
577,84,15,278,13,44,27,1,15,7,3,0.6,0.6,Advanced
578,93,15,354,11,17,23,5,19,4,4,0.5,0.6,Advanced
579,59,12,197,5,34,6,9,26,5,9,0.6,0.5,Basic
580,40,5,382,10,28,13,7,7,8,4,0.7,0.7,Basic
581,86,7,380,7,15,24,8,25,9,3,0.6,0.7,Advanced
582,34,17,174,6,21,7,3,26,8,3,0.4,0.4,Basic
583,73,6,122,11,36,13,4,18,7,4,0.4,0.2,Basic
584,38,6,100,4,31,20,2,17,7,3,0.6,0.7,Basic
585,58,13,174,4,27,19,5,19,6,8,0.4,0.9,Basic
586,84,17,133,12,44,6,2,9,8,9,0.9,0.8,Advanced
587,33,13,135,14,30,25,5,12,9,4,0.2,0.9,Basic
588,34,15,190,8,44,25,8,11,4,8,0.2,0.5,Basic
589,76,5,131,14,27,8,9,27,6,7,0.9,0.5,Basic
590,30,14,236,14,42,21,2,25,4,5,0.2,0.6,Basic
591,36,5,85,11,34,15,7,27,9,9,0.3,0.8,Basic
592,61,17,132,5,31,6,8,29,9,7,0.7,0.7,Basic
593,73,8,181,6,31,21,1,18,9,9,0.3,0.2,Basic
594,77,6,221,11,39,23,7,10,9,5,0.3,0.8,Intermediate
595,68,16,121,12,41,20,5,29,3,6,0.8,0.7,Basic
596,61,15,90,6,24,23,3,14,7,6,0.8,0.5,Basic
597,56,14,244,14,37,19,6,21,5,8,0.5,0.2,Basic
598,38,12,325,12,15,19,7,23,8,4,0.3,0.5,Basic
599,65,15,109,4,40,22,7,25,6,4,0.4,0.8,Basic
600,95,15,200,15,15,14,4,24,7,8,0.2,0.8,Advanced
601,84,9,313,6,36,9,1,16,4,6,0.7,0.8,Advanced
602,83,14,252,8,15,6,8,13,5,9,0.7,0.7,Advanced
603,49,9,178,9,27,9,4,25,6,8,0.5,0.9,Basic
604,90,12,94,5,40,11,1,15,9,8,0.5,0.3,Advanced
605,72,10,162,12,38,11,3,25,4,6,0.7,0.9,Basic
606,35,15,255,5,34,21,9,22,7,3,0.6,0.8,Basic
607,88,13,206,6,29,6,7,4,9,7,0.2,0.5,Advanced
608,33,15,189,10,37,14,2,14,4,5,0.6,0.5,Basic
609,81,17,222,15,35,28,6,21,6,7,0.2,0.8,Advanced
610,45,16,213,4,20,23,4,28,8,4,0.6,0.7,Basic
611,51,6,209,14,35,28,4,12,5,5,0.5,0.8,Basic
612,54,11,81,13,33,20,3,12,9,6,0.6,0.2,Basic
613,75,12,356,8,37,23,8,29,5,3,0.3,0.8,Intermediate
614,56,17,125,10,32,29,4,4,8,5,0.7,0.5,Basic
615,90,6,279,7,21,13,4,12,9,9,0.9,0.5,Intermediate
616,30,13,83,10,33,5,6,22,3,6,0.5,0.2,Basic
617,93,14,274,12,37,21,2,4,9,6,0.3,0.4,Advanced
618,58,13,200,14,41,26,2,25,7,9,0.9,0.7,Basic
619,31,6,104,7,36,4,8,21,7,7,0.6,0.4,Basic
620,63,12,357,11,17,17,6,17,7,6,0.2,0.3,Intermediate
621,45,8,146,9,41,25,4,22,4,9,0.5,0.6,Basic
622,33,7,381,11,35,23,3,19,4,9,0.7,0.4,Basic
623,37,6,388,11,37,10,3,27,6,4,0.4,0.5,Basic
624,89,6,372,9,36,20,2,14,4,6,0.4,0.3,Intermediate
625,90,9,315,15,21,27,9,22,5,4,0.5,0.4,Advanced
626,61,8,321,12,22,14,4,24,6,3,0.5,0.5,Intermediate
627,34,5,121,12,25,7,8,11,8,8,0.5,0.3,Basic
628,52,12,324,14,17,17,9,9,7,9,0.8,0.7,Basic
629,74,17,368,8,42,11,9,25,6,8,0.8,0.5,Intermediate
630,79,16,356,12,20,5,5,14,4,9,0.7,0.4,Intermediate
631,60,5,179,14,37,8,7,23,9,8,0.7,0.4,Basic
632,40,16,245,10,21,25,3,22,4,5,0.8,0.8,Basic
633,86,9,95,7,42,12,8,21,6,8,0.9,0.4,Intermediate
634,30,8,281,7,39,15,8,11,4,3,0.7,0.7,Basic
635,38,16,252,6,44,15,1,12,9,4,0.7,0.5,Basic
636,30,8,321,15,40,22,1,25,7,5,0.5,0.4,Basic
637,31,11,329,10,16,16,4,15,8,8,0.6,0.9,Basic
638,33,16,191,8,29,13,2,6,6,4,0.7,0.6,Basic
639,87,15,90,13,32,28,1,5,8,6,0.7,0.4,Advanced
640,42,14,342,12,27,19,7,12,8,3,0.3,0.6,Basic
641,35,7,243,11,39,29,9,22,4,7,0.2,0.6,Basic
642,75,16,385,7,19,4,5,28,7,6,0.8,0.3,Intermediate
643,45,14,261,9,35,17,8,4,7,5,0.2,0.3,Basic
644,53,17,218,10,34,11,4,14,5,5,0.9,0.6,Basic
645,43,9,314,10,30,15,8,10,8,4,0.6,0.7,Basic
646,35,16,169,7,34,25,2,17,8,7,0.7,0.7,Basic
647,46,12,314,7,37,4,4,11,9,4,0.7,0.3,Basic
648,33,5,217,5,27,4,3,4,4,3,0.7,0.5,Basic
649,62,16,162,13,44,22,1,15,3,6,0.8,0.4,Basic
650,90,16,191,15,17,6,4,28,8,5,0.8,0.7,Advanced
651,49,15,95,7,34,11,1,17,9,7,0.6,0.7,Basic
652,93,6,178,11,38,19,5,28,9,6,0.4,0.5,Basic
653,69,15,337,9,28,12,8,24,6,8,0.5,0.4,Intermediate
654,41,11,269,9,29,12,9,27,9,8,0.7,0.9,Basic
655,36,17,246,6,15,21,8,20,4,5,0.4,0.3,Basic
656,57,12,197,14,40,5,5,23,6,5,0.3,0.4,Basic
657,44,7,383,10,29,16,7,22,5,8,0.3,0.9,Basic
658,47,13,160,5,37,23,4,23,8,5,0.4,0.6,Basic
659,74,16,259,4,36,21,9,15,9,3,0.6,0.2,Intermediate
660,93,13,198,9,31,15,2,5,3,6,0.4,0.5,Advanced
661,66,11,370,7,15,23,4,6,5,6,0.3,0.5,Intermediate
662,76,15,218,15,44,24,3,26,6,3,0.8,0.6,Intermediate
663,41,5,231,4,44,21,3,12,3,7,0.2,0.4,Basic
664,69,6,341,4,15,8,5,21,9,3,0.8,0.7,Intermediate
665,73,8,318,4,18,9,2,5,9,5,0.5,0.2,Intermediate
666,46,5,226,15,27,19,1,20,8,9,0.8,0.4,Basic
667,90,11,364,6,44,15,2,11,9,9,0.9,0.8,Advanced
668,79,13,345,15,41,20,2,8,5,5,0.3,0.6,Intermediate
669,72,14,177,7,22,22,7,13,9,3,0.7,0.6,Basic
670,41,12,135,9,44,18,3,16,6,7,0.4,0.2,Basic
671,60,15,241,10,43,8,4,21,5,9,0.7,0.3,Basic
672,86,7,144,15,38,9,3,6,4,6,0.7,0.3,Intermediate
673,72,5,371,13,17,14,1,18,7,7,0.5,0.4,Intermediate
674,80,9,181,4,17,7,1,8,3,3,0.5,0.2,Basic
675,70,12,299,8,44,11,1,4,7,3,0.4,0.5,Intermediate
676,38,6,330,10,15,4,1,5,4,4,0.3,0.8,Basic
677,82,10,331,13,21,16,1,15,8,5,0.3,0.5,Intermediate
678,53,8,291,8,37,21,3,24,8,3,0.4,0.4,Basic
679,75,7,322,8,31,15,5,5,4,3,0.6,0.7,Intermediate
680,36,9,107,12,26,23,9,26,9,8,0.4,0.7,Basic
681,87,10,301,5,29,15,8,23,6,7,0.7,0.6,Advanced
682,52,7,348,13,43,25,3,6,5,7,0.8,0.6,Basic
683,32,11,381,14,19,22,5,15,4,8,0.7,0.3,Basic
684,43,9,99,4,32,24,4,28,9,6,0.7,0.5,Basic
685,66,13,377,15,21,26,1,20,5,3,0.8,0.6,Intermediate
686,53,13,165,12,44,24,2,23,3,8,0.3,0.5,Basic
687,51,9,287,7,38,20,8,18,8,3,0.2,0.8,Basic
688,31,17,92,10,38,12,1,13,7,3,0.4,0.8,Basic
689,63,6,397,9,25,9,3,26,6,6,0.7,0.3,Intermediate
690,37,7,156,8,22,13,8,28,9,8,0.3,0.2,Basic
691,39,13,121,5,43,18,7,7,8,5,0.3,0.5,Basic
692,86,17,90,13,28,19,4,22,5,7,0.6,0.8,Advanced
693,93,8,281,6,31,27,1,13,6,4,0.3,0.4,Basic
694,80,8,88,8,41,18,9,24,5,7,0.2,0.8,Basic
695,44,13,399,6,17,15,8,17,3,3,0.3,0.4,Basic
696,41,9,250,10,41,18,9,19,9,8,0.3,0.7,Basic
697,98,7,166,11,23,7,4,7,8,7,0.4,0.4,Basic
698,54,13,133,15,23,26,4,10,5,5,0.3,0.5,Basic
699,60,15,325,12,19,9,7,18,4,3,0.8,0.6,Basic
700,47,17,370,13,31,28,1,15,6,7,0.8,0.7,Basic
701,82,14,364,14,26,19,6,19,9,5,0.4,0.2,Advanced
702,87,16,203,14,41,23,5,10,8,9,0.3,0.5,Advanced
703,71,8,228,7,32,28,7,25,6,4,0.4,0.8,Intermediate
704,94,17,336,10,31,5,4,16,5,6,0.6,0.4,Advanced
705,89,5,249,12,30,17,9,23,8,4,0.8,0.6,Intermediate
706,46,12,303,13,21,19,2,14,7,9,0.3,0.8,Basic
707,70,13,132,11,38,22,4,24,3,9,0.8,0.3,Basic
708,35,13,153,7,39,18,8,15,9,4,0.5,0.3,Basic
709,43,17,234,10,31,16,1,8,3,7,0.2,0.9,Basic
710,53,12,325,10,20,11,8,24,6,8,0.9,0.2,Basic
711,70,13,323,15,29,8,1,9,6,7,0.7,0.4,Intermediate
712,49,7,183,13,39,17,6,18,7,3,0.4,0.3,Basic
713,69,8,144,6,43,28,4,4,4,4,0.4,0.5,Basic
714,64,6,103,11,33,14,1,19,8,4,0.6,0.2,Basic
715,32,10,346,5,26,23,3,25,4,4,0.3,0.7,Basic
716,50,7,329,8,23,25,6,15,9,7,0.6,0.2,Basic
717,82,11,150,12,22,22,3,4,9,5,0.6,0.7,Advanced
718,83,8,350,8,35,12,9,19,4,9,0.8,0.3,Advanced
719,47,13,200,7,40,22,1,23,4,6,0.2,0.2,Basic
720,32,8,376,8,28,12,1,17,7,8,0.4,0.5,Basic
721,35,5,396,13,15,20,9,25,6,5,0.6,0.4,Basic
722,74,15,110,12,29,18,3,29,3,8,0.2,0.8,Basic
723,71,6,109,13,23,6,8,15,3,9,0.7,0.9,Basic
724,37,9,236,15,16,21,4,7,4,9,0.5,0.2,Basic
725,88,8,172,9,33,19,2,27,5,8,0.4,0.6,Intermediate
726,89,7,175,12,43,4,8,15,6,3,0.8,0.9,Intermediate
727,79,9,310,9,39,17,5,17,7,4,0.5,0.6,Intermediate
728,95,9,165,12,41,18,4,16,4,9,0.4,0.4,Intermediate
729,69,10,97,5,22,17,5,11,3,6,0.8,0.5,Basic
730,90,7,246,13,21,8,4,22,4,7,0.4,0.8,Basic
731,93,8,275,7,16,24,1,13,8,3,0.8,0.7,Intermediate
732,82,14,385,9,37,18,6,28,6,3,0.3,0.9,Advanced
733,64,17,127,10,28,6,4,16,8,9,0.3,0.7,Basic
734,98,13,263,10,43,22,2,14,5,7,0.3,0.4,Advanced
735,99,16,159,11,39,23,4,8,7,4,0.4,0.4,Advanced
736,66,8,303,4,43,29,2,24,7,7,0.5,0.3,Intermediate
737,40,14,347,5,17,18,8,18,7,6,0.6,0.5,Basic
738,45,16,250,11,24,18,6,27,9,7,0.8,0.6,Basic
739,54,10,250,6,36,4,9,25,7,9,0.9,0.3,Basic
740,68,8,273,7,26,11,6,8,8,6,0.4,0.5,Intermediate
741,86,9,373,7,23,18,4,8,7,6,0.7,0.5,Intermediate
742,77,10,161,5,25,7,6,28,5,3,0.8,0.8,Basic
743,48,8,313,8,18,20,2,17,9,6,0.4,0.7,Basic
744,79,14,169,5,25,21,3,27,8,7,0.8,0.5,Basic
745,50,13,114,7,27,12,4,11,4,3,0.6,0.9,Basic
746,37,5,388,10,37,25,8,14,4,9,0.4,0.6,Basic
747,83,9,116,6,33,7,1,18,9,8,0.4,0.8,Intermediate
748,49,10,265,6,37,7,8,28,8,4,0.2,0.7,Basic
749,89,16,243,6,39,19,1,7,8,6,0.6,0.8,Advanced
750,42,7,110,6,32,15,4,27,5,5,0.7,0.7,Basic
751,35,8,354,15,37,6,6,6,3,6,0.5,0.8,Basic
752,90,11,196,5,39,6,6,9,9,5,0.6,0.4,Advanced
753,49,14,214,15,44,26,7,11,5,4,0.7,0.3,Basic
754,70,13,102,12,24,26,6,22,9,8,0.4,0.8,Basic
755,47,9,92,12,35,26,8,19,9,8,0.2,0.8,Basic
756,61,9,371,13,32,20,7,24,4,3,0.7,0.8,Intermediate
757,35,10,353,4,36,25,9,23,3,3,0.8,0.5,Basic
758,45,8,137,6,33,17,6,23,7,9,0.4,0.9,Basic
759,55,14,204,13,29,14,7,22,6,6,0.4,0.3,Basic
760,45,7,210,14,44,27,1,17,4,7,0.4,0.6,Basic
761,70,16,231,10,16,26,8,23,5,9,0.8,0.5,Intermediate
762,39,14,191,4,42,4,2,22,8,6,0.5,0.6,Basic
763,91,8,291,12,36,26,1,13,4,8,0.3,0.6,Intermediate
764,81,8,236,14,31,13,9,27,6,5,0.5,0.6,Basic
765,64,6,381,5,22,4,7,9,4,3,0.3,0.6,Basic
766,48,14,399,10,44,7,4,5,5,8,0.9,0.5,Basic
767,61,6,379,4,42,26,9,5,8,8,0.4,0.2,Intermediate
768,88,10,337,10,20,20,2,13,8,4,0.4,0.3,Intermediate
769,44,8,125,13,20,4,7,20,7,7,0.2,0.3,Basic
770,56,13,97,12,22,17,7,13,6,4,0.7,0.4,Basic
771,35,17,224,6,37,18,2,11,6,7,0.4,0.3,Basic
772,83,14,229,8,33,15,3,10,7,5,0.6,0.6,Advanced
773,85,17,257,14,44,26,2,29,3,9,0.3,0.4,Advanced
774,87,15,211,12,43,15,9,26,3,8,0.4,0.7,Advanced
775,37,6,92,4,41,13,2,29,8,9,0.5,0.6,Basic
776,30,6,336,11,40,26,9,28,6,8,0.6,0.3,Basic
777,41,7,320,13,44,21,7,29,7,8,0.9,0.4,Basic
778,63,7,366,8,28,14,6,21,5,8,0.9,0.6,Intermediate
779,37,15,171,13,27,11,3,26,7,6,0.9,0.5,Basic
780,53,17,266,15,39,26,2,11,3,7,0.8,0.3,Basic
781,97,17,129,6,31,26,5,20,9,4,0.4,0.2,Advanced
782,76,14,328,9,34,11,7,23,6,6,0.4,0.4,Intermediate
783,59,10,314,6,40,8,4,21,8,4,0.4,0.7,Basic
784,49,7,381,8,43,27,6,28,4,5,0.5,0.5,Basic
785,67,5,290,11,36,16,5,10,9,6,0.5,0.2,Intermediate
786,34,6,393,6,16,6,5,28,7,5,0.8,0.6,Basic
787,52,7,270,6,21,23,4,22,8,7,0.7,0.4,Basic
788,90,10,292,8,21,22,2,25,5,6,0.5,0.6,Basic
789,98,17,159,4,18,25,4,8,7,6,0.8,0.7,Advanced
790,99,8,224,4,44,25,5,26,6,3,0.8,0.3,Intermediate
791,86,13,241,8,40,19,4,12,8,4,0.6,0.4,Advanced
792,84,6,390,7,21,22,7,22,9,3,0.8,0.2,Advanced
793,93,13,222,15,18,17,7,10,5,4,0.3,0.8,Advanced
794,32,9,165,9,32,13,7,22,5,4,0.8,0.6,Basic
795,74,15,186,4,29,8,5,10,3,5,0.2,0.4,Basic
796,49,6,391,5,44,11,3,16,4,3,0.5,0.3,Basic
797,99,14,392,6,18,25,2,28,5,7,0.7,0.2,Advanced
798,48,11,270,14,16,22,5,8,3,4,0.3,0.5,Basic
799,61,5,170,6,42,23,9,28,3,5,0.6,0.8,Basic
800,32,5,93,5,25,8,2,17,4,7,0.5,0.3,Basic
801,81,17,299,8,19,11,7,13,9,3,0.6,0.5,Advanced
802,84,8,198,13,17,27,8,9,4,3,0.9,0.3,Intermediate
803,31,8,339,14,34,16,6,7,5,3,0.2,0.4,Basic
804,66,8,394,6,42,29,8,23,8,4,0.5,0.6,Intermediate
805,87,17,363,10,41,15,5,6,8,4,0.4,0.5,Advanced
806,45,7,227,12,35,6,4,24,5,7,0.6,0.7,Basic
807,88,10,86,12,27,25,3,27,5,7,0.8,0.2,Intermediate
808,60,13,227,12,36,5,1,6,9,8,0.2,0.7,Basic
809,46,17,82,8,42,5,7,21,7,6,0.5,0.9,Basic
810,80,11,261,8,42,17,8,9,8,3,0.7,0.6,Intermediate
811,49,11,94,11,18,25,1,16,9,5,0.4,0.8,Basic
812,70,16,139,15,28,13,7,26,6,4,0.3,0.5,Basic
813,67,6,162,7,38,11,2,28,9,8,0.8,0.5,Basic
814,78,13,145,6,35,28,8,24,7,6,0.3,0.4,Basic
815,87,7,172,11,37,21,2,29,4,8,0.5,0.7,Intermediate
816,43,11,388,13,42,21,2,8,7,7,0.4,0.8,Basic
817,86,17,361,7,29,26,3,24,9,9,0.7,0.8,Advanced
818,73,8,119,8,19,4,9,6,5,3,0.2,0.4,Basic
819,34,10,175,14,18,11,2,25,5,5,0.4,0.5,Basic
820,74,13,238,7,25,16,5,16,9,4,0.4,0.2,Intermediate
821,88,17,194,6,34,10,3,7,7,9,0.6,0.6,Advanced
822,62,15,150,8,15,28,3,6,7,8,0.3,0.8,Basic
823,76,8,375,13,32,23,8,15,7,4,0.6,0.8,Intermediate
824,68,13,271,11,43,7,7,22,4,6,0.2,0.4,Basic
825,38,13,239,7,44,4,5,21,9,8,0.6,0.7,Basic
826,67,11,238,11,41,10,9,15,6,6,0.3,0.5,Intermediate
827,32,5,303,7,39,20,6,10,5,8,0.6,0.6,Basic
828,71,5,199,11,26,5,3,9,9,7,0.7,0.3,Basic
829,93,5,262,14,28,4,2,20,4,4,0.4,0.3,Basic
830,88,16,246,13,43,4,2,26,5,3,0.7,0.8,Advanced
831,90,17,129,6,43,11,8,9,7,4,0.7,0.3,Advanced
832,57,11,205,7,34,20,1,14,9,4,0.9,0.6,Basic
833,58,11,339,9,35,4,2,13,3,6,0.3,0.8,Basic
834,85,16,97,10,34,4,2,20,7,7,0.9,0.7,Advanced
835,81,10,138,6,15,27,3,13,5,5,0.9,0.2,Intermediate
836,40,17,398,12,37,26,7,28,5,9,0.4,0.7,Basic
837,83,7,311,11,31,18,8,8,4,6,0.7,0.4,Intermediate
838,41,8,334,6,30,27,6,11,5,5,0.4,0.9,Basic
839,69,6,134,10,15,19,8,25,6,5,0.6,0.3,Basic
840,58,6,195,11,43,7,6,9,6,3,0.3,0.6,Basic
841,54,15,232,12,21,17,9,23,3,7,0.7,0.5,Basic
842,95,16,264,11,33,26,9,23,6,8,0.4,0.6,Advanced
843,85,6,391,11,15,4,3,4,9,5,0.6,0.9,Intermediate
844,36,10,301,9,24,27,3,6,8,3,0.4,0.2,Basic
845,90,6,312,11,29,10,3,26,3,8,0.5,0.5,Advanced
846,96,14,309,8,34,24,7,20,7,7,0.9,0.3,Advanced
847,36,17,367,14,30,10,9,5,5,7,0.4,0.8,Basic
848,42,15,194,13,17,22,7,6,5,3,0.5,0.5,Basic
849,82,12,372,10,42,20,5,14,6,3,0.4,0.8,Advanced
850,62,14,190,14,38,7,7,21,5,9,0.6,0.7,Basic
851,48,7,167,13,27,8,2,5,8,4,0.8,0.4,Basic
852,67,5,379,7,20,13,6,23,8,7,0.6,0.8,Intermediate
853,68,9,278,6,18,24,7,26,9,3,0.4,0.7,Intermediate
854,67,9,85,6,31,4,9,29,4,9,0.5,0.4,Basic
855,84,10,110,14,29,18,5,15,3,3,0.3,0.7,Basic
856,61,13,100,5,41,29,7,29,7,7,0.6,0.8,Basic
857,49,6,366,6,32,29,3,23,6,5,0.7,0.8,Basic
858,98,5,368,13,38,17,4,26,8,5,0.9,0.7,Advanced
859,78,11,226,6,28,11,3,14,5,5,0.2,0.3,Intermediate
860,43,10,170,12,38,23,6,25,8,6,0.9,0.4,Basic
861,99,13,296,14,27,5,7,15,5,8,0.7,0.6,Advanced
862,48,14,191,4,28,22,2,28,3,4,0.6,0.8,Basic
863,88,15,281,7,36,19,9,8,9,4,0.8,0.6,Advanced
864,74,12,146,8,24,22,2,14,9,3,0.3,0.3,Basic
865,33,11,371,11,26,27,1,13,9,9,0.3,0.7,Basic
866,61,14,99,9,28,19,5,10,6,4,0.7,0.4,Basic
867,64,6,373,7,40,23,3,13,6,8,0.6,0.7,Intermediate
868,76,5,390,15,22,29,8,6,4,9,0.7,0.7,Intermediate
869,44,5,251,6,19,4,6,29,4,3,0.8,0.4,Basic
870,36,14,127,15,32,9,9,24,6,7,0.9,0.5,Basic
871,95,11,119,12,24,23,5,13,9,3,0.3,0.5,Advanced
872,36,13,278,7,23,25,4,14,4,7,0.3,0.6,Basic
873,66,10,200,7,41,13,7,27,4,9,0.4,0.4,Basic
874,45,16,260,6,25,27,1,9,8,9,0.3,0.3,Basic
875,58,8,170,14,41,9,3,4,9,4,0.9,0.3,Basic
876,85,12,262,9,20,14,7,19,4,3,0.8,0.7,Advanced
877,43,12,134,4,28,8,5,21,9,8,0.8,0.7,Basic
878,56,15,97,5,27,5,3,6,7,3,0.9,0.7,Basic
879,39,17,152,5,43,20,7,5,3,4,0.9,0.6,Basic
880,54,14,161,6,25,22,3,10,5,7,0.8,0.8,Basic
881,55,6,171,10,17,25,6,10,4,8,0.8,0.5,Basic
882,44,11,172,6,43,25,6,13,9,6,0.3,0.5,Basic
883,33,15,152,4,41,14,1,12,8,3,0.7,0.5,Basic
884,82,14,361,4,40,25,4,26,8,8,0.5,0.7,Advanced
885,99,6,382,4,37,27,1,20,8,3,0.6,0.5,Advanced
886,91,10,347,5,35,28,2,17,3,6,0.7,0.3,Advanced
887,81,12,90,13,24,24,9,27,9,8,0.6,0.8,Advanced
888,40,11,193,8,33,22,1,24,7,4,0.5,0.7,Basic
889,44,5,213,6,18,16,6,25,3,9,0.5,0.2,Basic
890,74,13,299,5,27,11,4,27,3,3,0.3,0.9,Intermediate
891,43,7,223,10,18,10,6,13,6,4,0.4,0.5,Basic
892,46,16,107,8,30,7,3,23,3,3,0.5,0.3,Basic
893,60,17,389,7,28,25,3,16,9,6,0.6,0.7,Basic
894,52,8,245,8,18,25,5,26,4,9,0.2,0.7,Basic
895,96,12,216,14,38,5,7,9,9,7,0.4,0.9,Advanced
896,31,10,261,8,35,5,6,17,3,4,0.6,0.7,Basic
897,93,13,339,12,40,5,7,23,3,9,0.3,0.8,Advanced
898,88,9,100,14,44,25,2,10,7,6,0.6,0.5,Intermediate
899,74,12,328,7,26,10,3,11,3,3,0.3,0.3,Intermediate
900,93,10,198,7,40,13,8,6,6,6,0.4,0.3,Basic
901,83,8,250,8,43,11,9,23,3,5,0.8,0.8,Intermediate
902,42,10,266,7,40,18,2,17,9,8,0.2,0.4,Basic
903,45,8,176,10,28,17,4,27,7,9,0.5,0.2,Basic
904,53,12,271,7,33,9,5,17,4,4,0.5,0.8,Basic
905,99,13,103,9,35,21,4,24,8,5,0.7,0.7,Advanced
906,56,17,184,4,31,13,5,20,6,7,0.7,0.2,Basic
907,30,8,266,12,36,6,1,12,3,5,0.5,0.5,Basic
908,54,12,127,12,33,25,1,17,5,3,0.4,0.8,Basic
909,79,11,365,10,23,28,7,28,9,4,0.4,0.9,Intermediate
910,59,17,89,6,38,13,5,29,6,8,0.2,0.6,Basic
911,98,5,224,13,16,25,6,27,4,3,0.8,0.8,Intermediate
912,92,7,113,13,40,26,4,20,3,4,0.4,0.3,Basic
913,64,13,186,12,15,18,2,16,6,9,0.4,0.3,Basic
914,77,15,116,8,21,27,2,12,6,4,0.5,0.6,Basic
915,84,17,351,9,19,25,1,15,6,3,0.9,0.8,Advanced
916,70,13,394,10,26,22,8,24,4,4,0.7,0.6,Intermediate
917,91,14,238,6,44,11,7,29,4,3,0.3,0.8,Advanced
918,37,10,357,7,44,28,3,28,6,9,0.4,0.3,Basic
919,56,7,323,4,31,9,3,17,8,5,0.4,0.8,Basic
920,57,6,301,14,42,14,8,5,8,6,0.2,0.7,Basic
921,85,7,179,8,16,6,3,16,4,6,0.9,0.7,Intermediate
922,62,7,279,7,32,22,4,11,6,4,0.7,0.6,Intermediate
923,84,5,379,13,25,24,1,21,3,8,0.7,0.9,Advanced
924,90,15,277,12,41,9,1,18,4,3,0.7,0.7,Advanced
925,38,10,288,7,16,18,4,21,4,9,0.7,0.4,Basic
926,83,13,199,6,23,11,5,16,6,9,0.7,0.3,Advanced
927,88,17,350,6,44,25,6,12,6,6,0.4,0.4,Advanced
928,31,5,184,13,26,4,5,25,3,8,0.4,0.5,Basic
929,66,7,336,7,35,10,8,12,8,9,0.6,0.6,Intermediate
930,76,6,186,7,29,14,7,19,7,3,0.3,0.3,Basic
931,88,12,226,9,24,15,3,16,8,5,0.4,0.3,Advanced
932,54,16,223,15,16,5,2,26,6,6,0.5,0.6,Basic
933,61,17,230,8,28,29,6,21,8,6,0.5,0.3,Intermediate
934,69,6,141,15,33,23,2,19,9,9,0.4,0.4,Basic
935,83,13,107,9,40,28,7,24,8,4,0.3,0.4,Advanced
936,42,15,387,6,19,5,1,4,9,8,0.5,0.8,Basic
937,86,16,367,6,31,13,9,16,5,3,0.7,0.6,Advanced
938,69,12,215,9,36,8,7,5,3,3,0.5,0.8,Intermediate
939,39,8,336,11,32,11,5,7,5,7,0.8,0.7,Basic
940,56,16,213,14,35,6,1,4,6,3,0.8,0.7,Basic
941,86,12,392,10,19,21,3,13,4,7,0.3,0.3,Advanced
942,76,13,204,4,29,14,5,20,6,8,0.3,0.6,Intermediate
943,91,15,178,15,19,22,6,22,3,6,0.8,0.7,Advanced
944,30,13,185,11,40,15,5,26,9,5,0.8,0.8,Basic
945,80,6,275,10,40,9,2,15,8,4,0.9,0.4,Intermediate
946,81,6,218,12,24,4,2,6,6,5,0.4,0.8,Basic
947,44,11,351,5,40,13,6,26,6,7,0.4,0.7,Basic
948,56,17,163,13,31,27,5,5,9,7,0.6,0.7,Basic
949,35,14,373,8,38,19,8,10,7,6,0.6,0.7,Basic
950,35,9,125,9,37,5,8,28,4,6,0.3,0.9,Basic
951,80,9,387,8,36,13,1,27,4,9,0.7,0.5,Intermediate
952,63,7,209,13,34,21,4,26,7,3,0.4,0.3,Intermediate
953,95,12,348,13,26,6,6,9,3,3,0.8,0.5,Advanced
954,99,11,182,10,41,8,6,25,9,8,0.6,0.3,Advanced
955,55,9,196,5,28,17,4,27,9,7,0.8,0.4,Basic
956,43,5,133,8,22,6,5,28,9,8,0.5,0.2,Basic
957,59,10,86,5,17,28,9,18,9,4,0.8,0.3,Basic
958,98,15,234,9,43,8,5,20,8,7,0.4,0.7,Advanced
959,97,12,256,8,30,19,4,9,5,9,0.3,0.3,Advanced
960,88,9,160,7,17,19,2,14,9,3,0.8,0.8,Intermediate
961,99,16,156,15,23,26,3,6,5,4,0.3,0.5,Advanced
962,47,16,143,9,27,17,5,12,8,3,0.7,0.6,Basic
963,89,8,174,13,16,25,3,8,8,6,0.6,0.4,Intermediate
964,62,10,281,12,25,23,8,8,8,8,0.5,0.8,Intermediate
965,71,16,139,10,16,21,4,9,4,7,0.4,0.4,Basic
966,43,9,133,10,22,10,9,4,3,4,0.8,0.5,Basic
967,62,11,225,8,33,8,2,11,5,6,0.9,0.4,Intermediate
968,96,17,281,12,21,12,3,24,3,3,0.7,0.3,Advanced
969,80,13,152,13,32,23,9,16,8,4,0.7,0.6,Basic
970,84,8,319,13,31,23,1,5,5,4,0.8,0.3,Intermediate
971,49,15,176,14,30,6,4,4,9,5,0.3,0.2,Basic
972,77,12,311,11,16,17,1,14,8,9,0.6,0.6,Intermediate
973,63,7,113,13,33,21,3,11,3,3,0.8,0.7,Basic
974,49,15,189,7,25,25,2,16,6,4,0.4,0.5,Basic
975,75,17,396,4,21,15,6,17,6,8,0.6,0.4,Intermediate
976,53,12,226,8,32,25,9,18,9,5,0.8,0.8,Basic
977,86,7,144,14,31,29,8,8,7,7,0.4,0.6,Basic
978,82,9,389,4,44,22,8,12,8,6,0.6,0.6,Intermediate
979,31,6,80,8,41,6,8,19,3,5,0.3,0.9,Basic
980,62,15,245,14,36,16,7,28,6,7,0.7,0.2,Intermediate
981,60,7,316,8,15,13,1,27,3,5,0.5,0.7,Basic
982,94,9,231,11,26,27,2,13,3,6,0.6,0.5,Intermediate
983,74,12,297,10,27,5,8,19,3,8,0.8,0.4,Intermediate
984,74,15,138,7,41,28,3,19,4,4,0.4,0.5,Basic
985,52,16,118,14,29,27,5,13,5,9,0.3,0.6,Basic
986,59,5,200,10,29,11,6,26,9,3,0.8,0.4,Basic
987,63,15,85,6,37,17,3,9,8,8,0.7,0.7,Basic
988,82,10,342,5,28,19,6,21,3,5,0.6,0.4,Advanced
989,60,7,377,5,31,18,9,16,4,6,0.8,0.7,Basic
990,91,13,219,6,15,24,5,7,8,8,0.2,0.5,Advanced
991,81,7,208,8,33,27,4,13,3,5,0.7,0.6,Intermediate
992,87,14,344,5,32,23,9,17,8,7,0.8,0.4,Advanced
993,37,11,338,13,42,24,3,19,3,3,0.2,0.7,Basic
994,79,17,141,4,38,27,6,22,4,5,0.3,0.4,Basic
995,40,12,124,12,16,26,8,21,4,9,0.7,0.8,Basic
996,81,10,319,9,15,14,1,4,8,7,0.5,0.8,Intermediate
997,66,17,122,4,42,23,7,18,9,3,0.4,0.7,Basic
998,72,5,266,13,16,16,2,6,8,3,0.8,0.2,Intermediate
999,78,11,267,9,20,21,8,26,8,9,0.2,0.3,Intermediate
1000,66,14,296,13,33,5,6,20,8,3,0.5,0.7,Intermediate
ProficiencyLevelDetection/proficiency-identification.ipynb 0 → 100644
View file @ feeb76c8
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pickle, os\n",
"import numpy as np\n",
"import pandas as pd\n",
"from collections import defaultdict \n",
"from sklearn.preprocessing import LabelEncoder\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"class_dict = {\n",
" 'Basic' : 0,\n",
" 'Intermediate' : 1,\n",
" 'Advanced' : 2\n",
" }\n",
"\n",
"class_dict_rev = {\n",
" 0 : 'Basic',\n",
" 1 : 'Intermediate',\n",
" 2 : 'Advanced'\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Student_ID</th>\n",
" <th>Assessment_Scores</th>\n",
" <th>Text_Complexity</th>\n",
" <th>Word_Count</th>\n",
" <th>Text_Features</th>\n",
" <th>Engagement_Metrics</th>\n",
" <th>Progress_Over_Time</th>\n",
" <th>Language_Complexity</th>\n",
" <th>Time_On_Learning_Tasks</th>\n",
" <th>Contextual_Clues</th>\n",
" <th>Feedback</th>\n",
" <th>NLP_Features</th>\n",
" <th>Attention_Metrics</th>\n",
" <th>Proficiency_Level</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>91</td>\n",
" <td>13</td>\n",
" <td>350</td>\n",
" <td>8</td>\n",
" <td>38</td>\n",
" <td>22</td>\n",
" <td>5</td>\n",
" <td>15</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>0.4</td>\n",
" <td>0.4</td>\n",
" <td>Advanced</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>66</td>\n",
" <td>13</td>\n",
" <td>219</td>\n",
" <td>7</td>\n",
" <td>24</td>\n",
" <td>11</td>\n",
" <td>3</td>\n",
" <td>12</td>\n",
" <td>9</td>\n",
" <td>9</td>\n",
" <td>0.3</td>\n",
" <td>0.5</td>\n",
" <td>Intermediate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>74</td>\n",
" <td>5</td>\n",
" <td>246</td>\n",
" <td>4</td>\n",
" <td>29</td>\n",
" <td>27</td>\n",
" <td>6</td>\n",
" <td>29</td>\n",
" <td>9</td>\n",
" <td>8</td>\n",
" <td>0.7</td>\n",
" <td>0.7</td>\n",
" <td>Intermediate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>90</td>\n",
" <td>7</td>\n",
" <td>299</td>\n",
" <td>8</td>\n",
" <td>22</td>\n",
" <td>8</td>\n",
" <td>9</td>\n",
" <td>27</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>0.8</td>\n",
" <td>0.9</td>\n",
" <td>Intermediate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>79</td>\n",
" <td>15</td>\n",
" <td>102</td>\n",
" <td>6</td>\n",
" <td>25</td>\n",
" <td>18</td>\n",
" <td>8</td>\n",
" <td>26</td>\n",
" <td>5</td>\n",
" <td>9</td>\n",
" <td>0.8</td>\n",
" <td>0.2</td>\n",
" <td>Basic</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Student_ID Assessment_Scores Text_Complexity Word_Count Text_Features \\\n",
"0 1 91 13 350 8 \n",
"1 2 66 13 219 7 \n",
"2 3 74 5 246 4 \n",
"3 4 90 7 299 8 \n",
"4 5 79 15 102 6 \n",
"\n",
" Engagement_Metrics Progress_Over_Time Language_Complexity \\\n",
"0 38 22 5 \n",
"1 24 11 3 \n",
"2 29 27 6 \n",
"3 22 8 9 \n",
"4 25 18 8 \n",
"\n",
" Time_On_Learning_Tasks Contextual_Clues Feedback NLP_Features \\\n",
"0 15 6 5 0.4 \n",
"1 12 9 9 0.3 \n",
"2 29 9 8 0.7 \n",
"3 27 4 4 0.8 \n",
"4 26 5 9 0.8 \n",
"\n",
" Attention_Metrics Proficiency_Level \n",
"0 0.4 Advanced \n",
"1 0.5 Intermediate \n",
"2 0.7 Intermediate \n",
"3 0.9 Intermediate \n",
"4 0.2 Basic "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('data/dataset.csv')\n",
"df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Load Data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('data/dataset.csv')\n",
"del df['Student_ID']\n",
"\n",
"df['Proficiency_Level'] = df['Proficiency_Level'].map(class_dict)\n",
"\n",
"Y = df['Proficiency_Level'].values\n",
"del df['Proficiency_Level']\n",
"\n",
"X = df.values\n",
"X_train, X_test, y_train, y_test = train_test_split(\n",
" X, \n",
" Y, \n",
" test_size=0.15, \n",
" random_state=42\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Models"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import seaborn as sns\n",
"from sklearn.svm import SVC\n",
"from xgboost import XGBClassifier\n",
"from matplotlib import pyplot as plt\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.metrics import confusion_matrix, classification_report"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Random Forest Classifier Trained\n",
"XGBoost Classifier Trained\n",
"Support Vector Machine Trained\n",
"KNN Classifier Trained\n"
]
}
],
"source": [
"# Random Forest Classifier\n",
"rfc = RandomForestClassifier(\n",
" n_estimators=100, \n",
" random_state=42\n",
" )\n",
"rfc.fit(X, Y)\n",
"print(\"Random Forest Classifier Trained\")\n",
"\n",
"# XGBoost Classifier\n",
"xgb = XGBClassifier(\n",
" n_estimators=100, \n",
" random_state=42\n",
" )\n",
"xgb.fit(X, Y)\n",
"print(\"XGBoost Classifier Trained\")\n",
"\n",
"# Support Vector Machine\n",
"svc = SVC(\n",
" kernel='linear',\n",
" random_state=42\n",
" )\n",
"svc.fit(X, Y)\n",
"print(\"Support Vector Machine Trained\")\n",
"\n",
"# KNN Classifier\n",
"knn = KNeighborsClassifier(\n",
" n_neighbors=5,\n",
" metric='minkowski',\n",
" p=2\n",
" )\n",
"knn.fit(X, Y)\n",
"print(\"KNN Classifier Trained\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"P_rfc = rfc.predict(X_test)\n",
"P_xgb = xgb.predict(X_test)\n",
"P_svc = svc.predict(X_test)\n",
"P_knn = knn.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Classification Report - Random Forest Classifier\n",
" precision recall f1-score support\n",
"\n",
" 0 1.00 1.00 1.00 96\n",
" 1 1.00 1.00 1.00 28\n",
" 2 1.00 1.00 1.00 26\n",
"\n",
" accuracy 1.00 150\n",
" macro avg 1.00 1.00 1.00 150\n",
"weighted avg 1.00 1.00 1.00 150\n",
"\n",
"\n",
"Classification Report - XGBoost Classifier\n",
" precision recall f1-score support\n",
"\n",
" 0 1.00 1.00 1.00 96\n",
" 1 1.00 1.00 1.00 28\n",
" 2 1.00 1.00 1.00 26\n",
"\n",
" accuracy 1.00 150\n",
" macro avg 1.00 1.00 1.00 150\n",
"weighted avg 1.00 1.00 1.00 150\n",
"\n",
"\n",
"Classification Report - Support Vector Machine\n",
" precision recall f1-score support\n",
"\n",
" 0 0.99 0.93 0.96 96\n",
" 1 0.81 0.89 0.85 28\n",
" 2 0.79 0.88 0.84 26\n",
"\n",
" accuracy 0.91 150\n",
" macro avg 0.86 0.90 0.88 150\n",
"weighted avg 0.92 0.91 0.92 150\n",
"\n",
"\n",
"Classification Report - KNN Classifier\n",
" precision recall f1-score support\n",
"\n",
" 0 0.96 0.94 0.95 96\n",
" 1 0.89 0.89 0.89 28\n",
" 2 0.86 0.92 0.89 26\n",
"\n",
" accuracy 0.93 150\n",
" macro avg 0.90 0.92 0.91 150\n",
"weighted avg 0.93 0.93 0.93 150\n",
"\n"
]
}
],
"source": [
"print(\"Classification Report - Random Forest Classifier\")\n",
"print(classification_report(y_test, P_rfc))\n",
"\n",
"print(\"\\nClassification Report - XGBoost Classifier\")\n",
"print(classification_report(y_test, P_xgb))\n",
"\n",
"print(\"\\nClassification Report - Support Vector Machine\")\n",
"print(classification_report(y_test, P_svc))\n",
"\n",
"print(\"\\nClassification Report - KNN Classifier\")\n",
"print(classification_report(y_test, P_knn))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1000x1000 with 8 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"cm1 = confusion_matrix(y_test, P_rfc)\n",
"cm2 = confusion_matrix(y_test, P_xgb)\n",
"cm3 = confusion_matrix(y_test, P_svc)\n",
"cm4 = confusion_matrix(y_test, P_knn)\n",
"\n",
"plt.figure(figsize=(10, 10))\n",
"plt.subplot(2, 2, 1)\n",
"sns.heatmap(cm1, annot=True, fmt='d', cmap='Blues')\n",
"plt.title('Random Forest Classifier - CM')\n",
"plt.xlabel('Predicted')\n",
"plt.ylabel('Actual')\n",
"\n",
"plt.subplot(2, 2, 2)\n",
"sns.heatmap(cm2, annot=True, fmt='d', cmap='Blues')\n",
"plt.title('XGBoost Classifier - CM')\n",
"plt.xlabel('Predicted')\n",
"plt.ylabel('Actual')\n",
"\n",
"plt.subplot(2, 2, 3)\n",
"sns.heatmap(cm3, annot=True, fmt='d', cmap='Blues')\n",
"plt.title('Support Vector Machine - CM')\n",
"plt.xlabel('Predicted')\n",
"plt.ylabel('Actual')\n",
"\n",
"plt.subplot(2, 2, 4)\n",
"sns.heatmap(cm4, annot=True, fmt='d', cmap='Blues')\n",
"plt.title('KNN Classifier - CM')\n",
"plt.xlabel('Predicted')\n",
"plt.ylabel('Actual')\n",
"\n",
"plt.tight_layout()\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"# Save Random Forest Classifier\n",
"with open('weights/proficiency-rf.pickle', 'wb') as f:\n",
" pickle.dump(rfc, f)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Inference"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import warnings\n",
"import pickle, os\n",
"import numpy as np\n",
"import pandas as pd\n",
"warnings.filterwarnings('ignore')"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"sample_json ={\n",
" \"Assessment_Scores\":91.0,\n",
" \"Text_Complexity\":13.0,\n",
" \"Word_Count\":350.0,\n",
" \"Text_Features\":8.0,\n",
" \"Engagement_Metrics\":38.0,\n",
" \"Progress_Over_Time\":22.0,\n",
" \"Language_Complexity\":5.0,\n",
" \"Time_On_Learning_Tasks\":15.0,\n",
" \"Contextual_Clues\":6.0,\n",
" \"Feedback\":5.0,\n",
" \"NLP_Features\":0.4,\n",
" \"Attention_Metrics\":0.4\n",
" }\n",
"\n",
"model_proficiency_path = 'weights/proficiency-rf.pickle'\n",
"\n",
"with open(model_proficiency_path, 'rb') as f:\n",
" model_proficiency = pickle.load(f)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"def inference_proficiency(\n",
" sample_json,\n",
" class_dict_rev = {\n",
" 0 : 'Basic',\n",
" 1 : 'Intermediate',\n",
" 2 : 'Advanced'\n",
" }\n",
" ):\n",
" sample_json = pd.DataFrame(sample_json, index=[0])\n",
" sample_json = sample_json.values\n",
" pred = model_proficiency.predict(sample_json)\n",
" pred = pred[0]\n",
" pred = class_dict_rev[pred]\n",
" return pred"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Advanced'"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"inference_proficiency(sample_json)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "project",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.18"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
README.md deleted 100644 → 0
View file @ ab9626d8
# **✒️Implementation of an Intelligent Virtual Tutor to Enhance English Vocabulary Skills of Grade 6 Students**
## **🎯Main Objective**
### To develop a virtual tutor system that effectively enhances the vocabulary skills of Grade 6 students in rural schools. The system will utilize innovative components, such as vocabulary assessment, personalized learning paths, adaptive emotion recognition, and progress tracking, to provide a tailored and engaging vocabulary learning experience.
## **❓Main Research Questions**
* ### How can interactive vocabulary assessments effectively determine each student's proficiency level?
* ### How to improve students’ vocabulary writing skill using handwriting character recognition?
* ### How can facial expression detection be effectively used to assess users' attention and engagement levels?
* ### How can voice recognition technologies be integrated to facilitate students’ vocabulary development?
## **Sub Objectives**
* ### Conduct interactive vocabulary assessments to analyze each student's proficiency level and create personalized learning paths.
* ### Analyze student handwritings using pre-trained handwriting recognition model.
* ### Implement attention detection using facial expression analysis to keep users engaged and focused during activities.
* ### Develop vocabulary through interactive vocabulary exercises using voice recognition technology.
## **Group Information Details**
| **Description** | **Student ID** | **Student Name** |
| ------ | ------ | ------ |
| Member 1 | Herath H.M.U.R. | IT20617400 |
| Member 2 | Wanni Arachchige P.N | IT20617028 |
| Member 3 | De Silva W.S.S | IT20601188 |
| Member 4 | Shalinda R.M.M | IT20607128 |
### Supervisor: Ms. Bhagyanie Chathurika
### Co-Supervisor: Ms. Thilini Jayalath
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment