Upload 43 files

.gitattributes

@@ -35,3 +35,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Analyze-and-predict-student-scores/All_maj.csv filter=lfs diff=lfs merge=lfs -text
 All_maj.csv filter=lfs diff=lfs merge=lfs -text
+All_major.csv filter=lfs diff=lfs merge=lfs -text
+database.db filter=lfs diff=lfs merge=lfs -text
+Student[[:space:]]System[[:space:]]·[[:space:]]Streamlit.pdf filter=lfs diff=lfs merge=lfs -text

All_major.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b38ab80266b79882e1dcf3e7a5e0344f75651804c68adee1ae9d93c325d56c
+size 36064560

Columns/column_BA.txt

@@ -0,0 +1,111 @@
+BA0005
+BA002
+BA003
+BA005
+BA006
+BA007
+BA010
+BA011
+BA015
+BA016
+BA018
+BA020
+BA022
+BA023
+BA027
+BA028
+BA029
+BA030
+BA032
+BA035
+BA038
+BA045
+BA051
+BA054
+BA057
+BA065
+BA068
+BA080
+BA081
+BA082
+BA083
+BA084
+BA086
+BA087
+BA094
+BA098
+BA115
+BA116
+BA117
+BA118
+BA119
+BA120
+BA123
+BA130
+BA134
+BA138
+BA140
+BA142
+BA145
+BA146
+BA151
+BA153
+BA154
+BA155
+BA156
+BA160
+BA161
+BA162
+BA164
+BA167
+BA168
+BA169
+BA170
+BA171
+BA172
+BA174
+BA176
+BA182
+BA183
+BA184
+BA185
+BA186
+BA189
+BA190
+BA191
+BA192
+BA197
+BA198
+BA206
+BA207
+BA213
+BA214
+BA216
+BA217
+BA218
+BA222
+BA223
+BA226
+BA228
+BA229
+BA231
+BA232
+BA233
+BA243
+BA245
+BA254
+BA256
+BA257
+BA272
+BA273
+BA274
+BA275
+BA276
+BA277
+BA278
+BA279
+BA280
+BA281
+BA282
+BA283
+BA284

Columns/column_BE.txt

@@ -0,0 +1,53 @@
+BM003
+BM004
+BM005
+BM007
+BM008
+BM009
+BM010
+BM011
+BM012
+BM013
+BM017
+BM020
+BM030
+BM033
+BM050
+BM052
+BM058
+BM060
+BM061
+BM062
+BM063
+BM064
+BM067
+BM068
+BM069
+BM070
+BM073
+BM074
+BM075
+BM076
+BM077
+BM078
+BM079
+BM080
+BM082
+BM083
+BM084
+BM085
+BM086
+BM089
+BM090
+BM091
+BM092
+BM094
+BM095
+BM096
+BM098
+BM099
+BM100
+BM101
+BM102
+BM103
+BM104

Columns/column_BT.txt

@@ -0,0 +1,195 @@
+BT008
+BT009
+BT010
+BT150
+BT152
+BT155
+BT156
+BT162
+BT163
+BT164
+BT168
+BT172
+BT174
+BT179
+BT184
+BT185
+BT200
+BT201
+BT203
+BT205
+BT207
+BT210
+BT211
+BT212
+BT213
+BT214
+BT216
+BT217
+BT218
+BT220
+BT221
+BT222
+BT223
+BT224
+BT225
+BT306
+BT307
+BT308
+BT309
+BT310
+BT311
+BT312
+BT313
+BT314
+BT315
+BT316
+BT317
+BT318
+BT319
+BT320
+BT321
+BT322
+BT333
+BT334
+BT335
+BT336
+BT337
+BT338
+BT339
+BT340
+BT343
+BT344
+BT345
+BT346
+BT347
+BT348
+BT349
+BT350
+BT351
+BT352
+BT353
+BT354
+BT355
+BT356
+BT357
+BT358
+BT359
+BT360
+BT405
+BT500
+BTAR101
+BTAR102
+BTAR201
+BTAR202
+BTAR205
+BTAR206
+BTAR207
+BTAR208
+BTAR306
+BTAR308
+BTAR310
+BTAR311
+BTAR312
+BTAR313
+BTAR314
+BTBC101
+BTBC102
+BTBC103
+BTBC104
+BTBC201
+BTBC202
+BTBC203
+BTBC204
+BTBC205
+BTBC206
+BTBC207
+BTBC209
+BTBC210
+BTBC211
+BTBC212
+BTBC213
+BTBC214
+BTBC215
+BTBC216
+BTBC301
+BTBC302
+BTBC304
+BTBC309
+BTBC311
+BTBC312
+BTBC313
+BTBC314
+BTBC315
+BTBC316
+BTBC317
+BTBC318
+BTBC402
+BTBC403
+BTBC405
+BTBC406
+BTBC408
+BTBC409
+BTBC410
+BTBC411
+BTBC412
+BTBC413
+BTBC414
+BTBC415
+BTBC416
+BTBC419
+BTBC420
+BTBC421
+BTBC422
+BTBC500
+BTFT201
+BTFT202
+BTFT203
+BTFT204
+BTFT205
+BTFT206
+BTFT208
+BTFT234
+BTFT236
+BTFT254
+BTFT256
+BTFT301
+BTFT302
+BTFT303
+BTFT304
+BTFT305
+BTFT306
+BTFT309
+BTFT310
+BTFT311
+BTFT316
+BTFT331
+BTFT332
+BTFT334
+BTFT337
+BTFT351
+BTFT352
+BTFT354
+BTFT357
+BTFT401
+BTFT402
+BTFT403
+BTFT405
+BTFT406
+BTFT407
+BTFT408
+BTFT409
+BTFT411
+BTFT431
+BTFT432
+BTFT435
+BTFT436
+BTFT437
+BTFT438
+BTFT451
+BTFT452
+BTFT455
+BTFT456
+BTFT457
+BTFT458
+BTFT500

Columns/column_CE.txt

@@ -0,0 +1,41 @@
+CE100
+CE101
+CE102
+CE103
+CE104
+CE105
+CE201
+CE202
+CE203
+CE205
+CE206
+CE208
+CE209
+CE210
+CE211
+CE213
+CE214
+CE215
+CE216
+CE301
+CE302
+CE303
+CE304
+CE305
+CE306
+CE307
+CE308
+CE309
+CE310
+CE311
+CE312
+CE313
+CE314
+CE401
+CE402
+CE403
+CE404
+CE405
+CE406
+CE407
+CE420

Columns/column_EE.txt

@@ -0,0 +1,66 @@
+EE010
+EE049
+EE050
+EE051
+EE052
+EE053
+EE054
+EE055
+EE056
+EE057
+EE058
+EE061
+EE062
+EE063
+EE068
+EE070
+EE072
+EE079
+EE083
+EE084
+EE088
+EE089
+EE090
+EE091
+EE092
+EE093
+EE094
+EE095
+EE097
+EE102
+EE103
+EE104
+EE105
+EE107
+EE112
+EE114
+EE115
+EE116
+EE117
+EE118
+EE119
+EE120
+EE122
+EE124
+EE125
+EE126
+EE127
+EE128
+EE129
+EE130
+EE131
+EE133
+EEAC001
+EEAC003
+EEAC004
+EEAC005
+EEAC006
+EEAC007
+EEAC008
+EEAC009
+EEAC010
+EEAC014
+EEAC015
+EEAC017
+EEAC020
+EEAC021

Columns/column_EN.txt

@@ -0,0 +1,48 @@
+EL001
+EL002
+EL003
+EL004
+EL005
+EL006
+EL007
+EL008
+EL009
+EL010
+EL011
+EL012
+EL013
+EL014
+EL015
+EL016
+EL017
+EL018
+EL019
+EL020
+EL021
+EL022
+EL023
+EL024
+EL025
+EL026
+EL027
+EL028
+EL029
+EL030
+EL031
+EL032
+EL033
+EL034
+EL035
+EL036
+EL037
+EL038
+EL039
+EL040
+EL041
+EL042
+EL043
+EL044
+EL045
+EL046
+EL048
+EL049

Columns/column_EV.txt

@@ -0,0 +1,41 @@
+ENEE1001
+ENEE1002
+ENEE1003
+ENEE1004
+ENEE1005
+ENEE1006
+ENEE1007
+ENEE1010
+ENEE2001
+ENEE2002
+ENEE2003
+ENEE2004
+ENEE2005
+ENEE2006
+ENEE2007
+ENEE2008
+ENEE2009
+ENEE2010
+ENEE2011
+ENEE2013
+ENEE2014
+ENEE2015
+ENEE2016
+ENEE2017
+ENEE3101
+ENEE3102
+ENEE3103
+ENEE3104
+ENEE3106
+ENEE3108
+ENEE3109
+ENEE3110
+ENEE3111
+ENEE3202
+ENEE3208
+ENEE3301
+ENEE4002
+ENEE4013
+ENEE4016
+ENEE5001
+ENEE5002

Columns/column_IE.txt

@@ -0,0 +1,64 @@
+IS001
+IS003
+IS004
+IS005
+IS006
+IS012
+IS013
+IS014
+IS015
+IS016
+IS017
+IS018
+IS019
+IS020
+IS023
+IS024
+IS025
+IS026
+IS027
+IS028
+IS031
+IS032
+IS033
+IS034
+IS035
+IS040
+IS041
+IS043
+IS045
+IS048
+IS050
+IS052
+IS053
+IS054
+IS055
+IS056
+IS057
+IS058
+IS059
+IS062
+IS063
+IS066
+IS067
+IS068
+IS069
+IS070
+IS071
+IS072
+IS073
+IS074
+IS076
+IS077
+IS078
+IS079
+IS081
+IS082
+IS083
+IS084
+IS085
+IS086
+IS087
+IS089
+IS090
+IS091

Columns/column_IT.txt

@@ -0,0 +1,91 @@
+IT001
+IT002
+IT003
+IT004
+IT006
+IT007
+IT008
+IT009
+IT010
+IT011
+IT012
+IT013
+IT014
+IT015
+IT016
+IT017
+IT018
+IT019
+IT020
+IT022
+IT024
+IT025
+IT027
+IT031
+IT034
+IT041
+IT044
+IT045
+IT046
+IT056
+IT057
+IT058
+IT060
+IT063
+IT064
+IT065
+IT067
+IT068
+IT069
+IT072
+IT073
+IT075
+IT076
+IT077
+IT079
+IT080
+IT082
+IT083
+IT089
+IT090
+IT091
+IT092
+IT093
+IT094
+IT096
+IT097
+IT098
+IT099
+IT100
+IT103
+IT107
+IT112
+IT114
+IT115
+IT116
+IT117
+IT119
+IT120
+IT122
+IT124
+IT125
+IT130
+IT131
+IT132
+IT133
+IT134
+IT135
+IT136
+IT137
+IT138
+IT139
+IT140
+IT142
+IT143
+IT145
+IT149
+IT150
+IT151
+IT153
+IT154
+IT155

Columns/column_MA.txt

@@ -0,0 +1,37 @@
+MAFE101
+MAFE102
+MAFE103
+MAFE104
+MAFE105
+MAFE109
+MAFE201
+MAFE202
+MAFE203
+MAFE204
+MAFE205
+MAFE206
+MAFE207
+MAFE208
+MAFE209
+MAFE212
+MAFE214
+MAFE215
+MAFE301
+MAFE302
+MAFE303
+MAFE305
+MAFE306
+MAFE307
+MAFE308
+MAFE309
+MAFE311
+MAFE312
+MAFE313
+MAFE314
+MAFE315
+MAFE316
+MAFE401
+MAFE402
+MAFE403
+MAFE404
+MAFE409

Columns/column_SE.txt

@@ -0,0 +1,37 @@
+PH012
+PH013
+PH014
+PH015
+PH016
+PH018
+PH019
+PH020
+PH024
+PH025
+PH026
+PH027
+PH029
+PH030
+PH031
+PH035
+PH036
+PH037
+PH038
+PH039
+PH040
+PH041
+PH042
+PH043
+PH044
+PH045
+PH046
+PH047
+PH049
+PH050
+PH051
+PH052
+PH053
+PH054
+PH055
+PH056
+PH057

README.md

@@ -1,9 +1,2 @@
----
-app_file: app.py
-license: apache-2.0
-title: Student System
-sdk: streamlit
-emoji: 🚀
-colorFrom: yellow
-colorTo: blue
----
+# Analyze-and-predict-student-performance
+Link to web-app: https://itdsiu19001-analyze-and-predict-student-performance-main-oiibq6.streamlit.app/

Student System · Streamlit.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1eb029a6a4fa063f49620a31e797b71e23dc329841d6ac712f84f1ac3b0d739
+size 1963686

Userscript re-installation.html

@@ -0,0 +1,14 @@
+<!DOCTYPE html>
+<!-- saved from url=(0101)chrome-extension://dhdgffkkebhmkfjojejmpbldmpobfkfo/ask.html?aid=5b119d14-6ed7-47e6-bf66-89933b7227d2 -->
+<html class="desktop dark"><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
+    
+    <link href="chrome-extension://dhdgffkkebhmkfjojejmpbldmpobfkfo/editor.css" rel="stylesheet" type="text/css">
+    <link href="chrome-extension://dhdgffkkebhmkfjojejmpbldmpobfkfo/style.css" rel="stylesheet" type="text/css">
+
+    <script src="chrome-extension://dhdgffkkebhmkfjojejmpbldmpobfkfo/editor.js"></script>
+    <script src="chrome-extension://dhdgffkkebhmkfjojejmpbldmpobfkfo/extension.js"></script><title>Userscript re-installation</title>
+</head>
+<body class="main">
+
+
+<div id="div_Y3RfMA_p" class="curouter hide" style="z-index: 10000"><div id="div_Y3RfMA_d" class="curmiddle_fixed"><table id="table_Y3RfMA_table" class="curtable"><tr id="tr_Y3RfMA_tr2"><td id="td_Y3RfMA_td1" class="curtableoutertd"></td><td id="td_Y3RfMA_td2" class="curtableinner"><div class="curcontainer"><div class="curwaithead"></div><div class="curwaitmsg"><div class="lds-css ng-scope"><div class="lds-dual-ring"><div></div><div></div></div></div><div class="curtext">Please wait...</div></div></div></td><td id="td_Y3RfMA_td3" class="curtableoutertd"></td></tr></table></div><div id="div_Y3RfMA_c" class="curbg"></div></div><div id="div_YXNrX21haW4" class="content_wrapper"><div id="div_YXNrX2hlYWRfY29udGFpbmVy" class="head_container"><a id="a_aGVhZF9saW5rX2Fzaw_head_link" href="https://www.tampermonkey.net/" target="_blank"><div id="div_YXNrX2hlYWQx" class="float"><img id="img_YXNrX3VuZGVmaW5lZA" class="banner" src="data:image/svg+xml,%3C?xml%20version=%271.0%27%20encoding=%27utf-8%27?%3E%3Csvg%20xmlns=%27http://www.w3.org/2000/svg%27%20viewBox=%270%200%20400%20400%27%3E%3Cg%20id=%27XMLID_273_%27%3E%3Cg%20id=%27XMLID_78_%27%3E%3Cpath%20id=%27XMLID_83_%27%20class=%27st0%27%20d=%27M304.8,0H95.2C42.6,0,0,42.6,0,95.2v209.6C0,357.4,42.6,400,95.2,400h209.6%20c52.6,0,95.2-42.6,95.2-95.2V95.2C400,42.6,357.4,0,304.8,0z%20M106.3,375C61.4,375,25,338.6,25,293.8c0-44.9,36.4-81.3,81.3-81.3%20c44.9,0,81.3,36.4,81.3,81.3C187.5,338.6,151.1,375,106.3,375z%20M293.8,375c-44.9,0-81.3-36.4-81.3-81.3%20c0-44.9,36.4-81.3,81.3-81.3c44.9,0,81.3,36.4,81.3,81.3C375,338.6,338.6,375,293.8,375z%27/%3E%3C/g%3E%3Cg%20id=%27XMLID_67_%27%20class=%27st2%27%3E%3Cpath%20id=%27XMLID_74_%27%20class=%27st3%27%20d=%27M304.8,0H95.2C42.6,0,0,42.6,0,95.2v209.6C0,357.4,42.6,400,95.2,400h209.6%20c52.6,0,95.2-42.6,95.2-95.2V95.2C400,42.6,357.4,0,304.8,0z%20M106.3,375C61.4,375,25,338.6,25,293.8c0-44.9,36.4-81.3,81.3-81.3%20c44.9,0,81.3,36.4,81.3,81.3C187.5,338.6,151.1,375,106.3,375z%20M293.8,375c-44.9,0-81.3-36.4-81.3-81.3%20c0-44.9,36.4-81.3,81.3-81.3c44.9,0,81.3,36.4,81.3,81.3C375,338.6,338.6,375,293.8,375z%27/%3E%3C/g%3E%3C/g%3E%3C/svg%3E"></div><div id="div_YXNrX2hlYWQy" class="float head"><div id="div_aGVhZGluZ191bmRlZmluZWQ" class="header_title">Tampermonkey<sup>®</sup></div><div id="div_dmVyc2lvbl92ZXJzaW9u" class="version">v4.18.1</div></div></a><div id="div_c2VhcmNoX2JveA_"></div></div><div id="div_YXNrX3R2X2NvbnRhaW5lcg" class="tv_container_fit"><div id="div_bWFpbm1haW5fdW5kZWZpbmVk" class="tv"><table id="table_bWFpbl90YWJsZW1haW5fdW5kZWZpbmVk" class="tv_table noborder"><tr id="tr_dGFic2Rpdl9ZWE5yWDNSMlgyTnZiblJoYVc1bGNnbWFpbl91bmRlZmluZWQ" class="tr_tabs"><td id="td_cGFnZXNtYWluX3VuZGVmaW5lZA" class="td_tabs"><div id="div_dHZfdGFic19maWxsbWFpbl91bmRlZmluZWQ" class="tv_tabs_fill"><div id="div_dHZfdGFic190YWJsZW1haW5fdW5kZWZpbmVk" class="tv_tabs_table"><div id="div_dHZfdGFic19hbGlnbm1haW5fdW5kZWZpbmVk" class="tv_tabs_align"><div id="div_dGFiX2JXRnBibDl0WVdsdV9jb250ZW50bWFpbg" tvid="bWFpbl9tYWlu" name="tabview_tabmain" class="tv_tab tv_selected" style="undefined" vis="true"><div id="div_bWFpbl9tYWlu_tab_content_h">Install<div id="div_dGFiX2JXRnBibDl0WVdsdV9oZWFkX3RleHRtYWlu"></div></div></div></div></div></div></td></tr><tr id="tr_Y29udGVudGRpdl9ZWE5yWDNSMlgyTnZiblJoYVc1bGNnbWFpbl91bmRlZmluZWQ" class="tr_content"><td id="td_Y29udGVudG1haW5fdW5kZWZpbmVk" class="td_content"><div id="div_dHZfY29udGVudG1haW5fdW5kZWZpbmVk" class="tv_contents"><div id="div_bWFpbl9tYWlu_tab_content" name="tabview_contentmain" class="tv_content" style="undefined" vis="true"><div id="div_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X2luc3RhbGxfc3Jj" class="section"><div id="div_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="viewer_upper"><div id="div_Z2VuZXJhbF82NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDc" class="viewer_info viewer_info_multiple"><h3 id="h3_aW5zdGFsbF9oZWFkaW5n_675d1929-24cc-4b5a-9513-9389e4063d47"><span id="span_bmFtZV9oZWFkaW5n_675d1929-24cc-4b5a-9513-9389e4063d47">Quizlet Editor</span><span id="span_aGVhZGluZ182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDc" class="view_version">v0.2</span></h3><div id="div_Z2VuZXJhbF9jb250ZW50XzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0Nw" class="viewer_content"><table id="table_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="script_desc"><tr id="tr_YXV0aG9yXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0Nw" class="script_desc"><td id="td_YXV0aG9yXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0N2R0" class="script_desc">Author</td><td id="td_YXV0aG9yXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0N2Rk" class="script_desc">troop129 + josephyooo</td></tr><tr id="tr_ZGVzY3JpcHRpb25fNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3" class="script_desc"><td id="td_ZGVzY3JpcHRpb25fNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3ZHQ" class="script_desc">Description</td><td id="td_ZGVzY3JpcHRpb25fNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3ZGQ" class="script_desc">Remove paywall for Quizlet answers</td></tr><tr id="tr_ZmlsZVVSTF82NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDc" class="script_desc"><td id="td_ZmlsZVVSTF82NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDdkdA" class="script_desc">Source</td><td id="td_ZmlsZVVSTF82NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDdkZA" class="script_desc">https://greasyfork.org/scripts/438663-quizlet-editor/code/Quizlet%20Editor.user.js</td></tr></table></div></div><div id="div_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDc" class="viewer_info viewer_info_multiple"><div id="div_aW5mb19jb250ZW50XzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0Nw" class="viewer_content"><h4 id="h4_YWN0aW9uX2hlYWRpbmc_675d1929-24cc-4b5a-9513-9389e4063d47">Userscript re-installation</h4><table id="table_ZXJyb3JzXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0NzA"></table><table id="table_d2FybmluZ3NfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3MA"><tr id="tr_d2FybmluZ3NfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3MQ"><td id="td_d2FybmluZ3NfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3ZHQx"><i class="far fa-exclamation-triangle orange"></i>&nbsp;</td><td id="td_d2FybmluZ3NfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3ZGQx">All script settings will be reset!</td></tr></table><table id="table_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDcx"><tr id="tr_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDcy"><td id="td_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDdkdDI">Installed Version</td><td id="td_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDdkZDI">v0.2</td></tr><tr id="tr_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDcz"><td id="td_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDdkdDM">Note</td><td id="td_aW5mb182NzVkMTkyOS0yNGNjLTRiNWEtOTUxMy05Mzg5ZTQwNjNkNDdkZDM">A recheck of the GreaseMonkey/FF compatibility options may be required in order to run this script.</td></tr></table><table id="table_aW5jbHVkZXNfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3"><tr id="tr_aHR0cCo6Ly93d3cucXVpemxldC5jb20vZXhwbGFuYXRpb25zL3RleHRib29rLXNvbHV0aW9ucy8qXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0NzA" class="includesdesc"><td id="td_aHR0cCo6Ly93d3cucXVpemxldC5jb20vZXhwbGFuYXRpb25zL3RleHRib29rLXNvbHV0aW9ucy8qXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0NzBkdA" class="includesdesc">Include(s)</td><td id="td_aHR0cCo6Ly93d3cucXVpemxldC5jb20vZXhwbGFuYXRpb25zL3RleHRib29rLXNvbHV0aW9ucy8qXzY3NWQxOTI5LTI0Y2MtNGI1YS05NTEzLTkzODllNDA2M2Q0NzBkZA" class="includesdesc">http*://www.quizlet.com/explanations/textbook-solutions/*</td></tr><tr id="tr_aHR0cCo6Ly9xdWl6bGV0LmNvbS9leHBsYW5hdGlvbnMvdGV4dGJvb2stc29sdXRpb25zLypfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3MQ" class="includesdesc"><td id="td_aHR0cCo6Ly9xdWl6bGV0LmNvbS9leHBsYW5hdGlvbnMvdGV4dGJvb2stc29sdXRpb25zLypfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3MWR0" class="includesdesc">&nbsp;</td><td id="td_aHR0cCo6Ly9xdWl6bGV0LmNvbS9leHBsYW5hdGlvbnMvdGV4dGJvb2stc29sdXRpb25zLypfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3MWRk" class="includesdesc">http*://quizlet.com/explanations/textbook-solutions/*</td></tr></table><table id="table_ZXhjbHVkZXNfNjc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3"></table></div></div></div><div id="div_aW5zdGFsbF91bmRlZmluZWQ" class="viewer_last"><div id="div_aW5zdGFsbF9jb250ZW50X3VuZGVmaW5lZA" class="viewer_content"><div id="div_aW5zdGFsbF9idXR0b25zX3VuZGVmaW5lZA" class="ask_action_buttons"><input id="input_UmVpbnN0YWxsX3VuZGVmaW5lZA_bu" class="button install" name="Reinstall" type="button" value="Reinstall"><input id="input_Q2FuY2VsX3VuZGVmaW5lZA_bu" class="button install" name="Cancel" type="button" value="Cancel"></div></div></div><div id="div_Ym90dG9tXw" class="viewer_bottom_tab"><div id="div_bWFpbnNvdXJjZTY3NWQxOTI5MjRjYzRiNWE5NTEzOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="tv tv_alt"><table id="table_bWFpbl90YWJsZXNvdXJjZTY3NWQxOTI5MjRjYzRiNWE5NTEzOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="tv_table tv_table_alt noborder"><tr id="tr_dGFic2Rpdl9ZbTkwZEc5dFh3c291cmNlNjc1ZDE5MjkyNGNjNGI1YTk1MTM5Mzg5ZTQwNjNkNDdfdW5kZWZpbmVk" class="tr_tabs tr_tabs_alt"><td id="td_cGFnZXNzb3VyY2U2NzVkMTkyOTI0Y2M0YjVhOTUxMzkzODllNDA2M2Q0N191bmRlZmluZWQ" class="td_tabs td_tabs_alt"><div id="div_dHZfdGFic19maWxsc291cmNlNjc1ZDE5MjkyNGNjNGI1YTk1MTM5Mzg5ZTQwNjNkNDdfdW5kZWZpbmVk" class="tv_tabs_fill tv_tabs_fill_alt"><div id="div_dHZfdGFic190YWJsZXNvdXJjZTY3NWQxOTI5MjRjYzRiNWE5NTEzOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="tv_tabs_table tv_tabs_table_alt"><div id="div_dHZfdGFic19hbGlnbnNvdXJjZTY3NWQxOTI5MjRjYzRiNWE5NTEzOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="tv_tabs_align tv_tabs_align_alt"><div id="div_dGFiX3NvdXJjZV9jb250ZW50c291cmNlNjc1ZDE5MjkyNGNjNGI1YTk1MTM5Mzg5ZTQwNjNkNDc" tvid="source" name="tabview_tabsource675d192924cc4b5a95139389e4063d47" class="tv_tab tv_selected tv_tab_alt tv_selected_alt" style="undefined" vis="true"><div id="div_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3NvdXJjZV9o">Source Code<div id="div_dGFiX3NvdXJjZV9oZWFkX3RleHRzb3VyY2U2NzVkMTkyOTI0Y2M0YjVhOTUxMzkzODllNDA2M2Q0Nw"></div></div></div></div></div></div></td></tr><tr id="tr_Y29udGVudGRpdl9ZbTkwZEc5dFh3c291cmNlNjc1ZDE5MjkyNGNjNGI1YTk1MTM5Mzg5ZTQwNjNkNDdfdW5kZWZpbmVk" class="tr_content tr_content_alt"><td id="td_Y29udGVudHNvdXJjZTY3NWQxOTI5MjRjYzRiNWE5NTEzOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="td_content td_content_alt"><div id="div_dHZfY29udGVudHNvdXJjZTY3NWQxOTI5MjRjYzRiNWE5NTEzOTM4OWU0MDYzZDQ3X3VuZGVmaW5lZA" class="tv_contents tv_contents_alt"><div id="div_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3NvdXJjZWNvbnRhaW5lcl9v" class="tv_content tv_content_alt" name="tabview_contentsource675d192924cc4b5a95139389e4063d47" style="undefined" vis="true"><table id="table_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3NvdXJjZWNvbnRhaW5lcl9v" class="editor_container_o editor_400p_container_o p100100 noborder"><tr id="tr_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3NvdXJjZWNvbnRhaW5lcg" class="editor_container p100100"><td id="td_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3NvdXJjZWVkaXQ" class="editor_outer editor_400p_outer"><div id="div_Njc1ZDE5MjktMjRjYy00YjVhLTk1MTMtOTM4OWU0MDYzZDQ3X3NvdXJjZWVkaXQ" class="editor_100 editor_border"><div class="CodeMirror-editor" style="font-size:1.00em;"><div class="CodeMirror cm-s-monokai CodeMirror-focused"><div style="overflow: hidden; position: relative; width: 3px; height: 0px; top: 72.9375px; left: 149.828px;"><textarea autocorrect="off" autocapitalize="off" spellcheck="false" readonly="" tabindex="0" style="position: absolute; bottom: -1em; padding: 0px; width: 1000px; height: 1em; outline: none;"></textarea></div><div class="CodeMirror-vscrollbar" tabindex="-1" cm-not-content="true"><div style="min-width: 1px; height: 0px;"></div></div><div class="CodeMirror-hscrollbar" tabindex="-1" cm-not-content="true"><div style="height: 100%; min-height: 1px; width: 0px;"></div></div><div class="CodeMirror-scrollbar-filler" cm-not-content="true"></div><div class="CodeMirror-gutter-filler" cm-not-content="true"></div><div class="CodeMirror-scroll" tabindex="-1"><div class="CodeMirror-sizer" style="margin-left: 0px; min-width: 867.375px; margin-bottom: -10px; border-right-width: 40px; min-height: 387px; padding-right: 0px; padding-bottom: 0px;"><div style="position: relative; top: 0px;"><div class="CodeMirror-lines" role="presentation"><div role="presentation" style="position: relative; outline: none;"><div class="CodeMirror-measure"><pre class="CodeMirror-line-like"><span>xxxxxxxxxx</span></pre></div><div class="CodeMirror-measure"></div><div style="position: relative; z-index: 1;"></div><div class="CodeMirror-cursors" style=""><div class="CodeMirror-cursor" style="left: 149.828px; top: 68.9375px; height: 17.2344px;">&nbsp;</div></div><div class="CodeMirror-code" role="presentation" style=""><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// ==UserScript==</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @name         Quizlet Editor</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @match        http*://www.quizlet.com/explanations/textbook-solutions/*</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @match        http*://quizlet.com/explanations/textbook-solutions/*</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @version      0.</span><span class="cm-comment cm-overlay cm-matchhighlight">2</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @description  Remove paywall for Quizlet answers</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @author       troop129 + josephyooo</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @grant        none</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @run-at  document-end</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// @namespace Quizlet Explanations Unlocker</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-comment">// ==/UserScript==</span></span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span class="cm-variable">window</span>.<span class="cm-property">addEventListener</span>(<span class="cm-string">'load'</span>, <span class="cm-keyword">function</span>() {</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">    <span class="cm-string">'use strict'</span>;</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">    <span class="cm-keyword">var</span> <span class="cm-def">paywall</span> <span class="cm-operator">=</span> <span class="cm-variable">document</span>.<span class="cm-property">getElementsByClassName</span>(<span class="cm-string">'wugyavo'</span>);</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">    <span class="cm-keyword">if</span>(<span class="cm-variable-2">paywall</span>.<span class="cm-property">length</span> <span class="cm-operator">!=</span> <span class="cm-number">0</span>){</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">        <span class="cm-variable-2">paywall</span>[<span class="cm-number">0</span>].<span class="cm-property">remove</span>();</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">        <span class="cm-variable">document</span>.<span class="cm-property">getElementsByClassName</span>(<span class="cm-string">'ExplanationSolutionsContainer hnqbbas s1oluvjw'</span>)[<span class="cm-number">0</span>].<span class="cm-property">style</span>.<span class="cm-property">overflow</span><span class="cm-operator">=</span><span class="cm-string">"visible"</span>;</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">        <span class="cm-keyword">let</span> <span class="cm-def">newHeight</span> <span class="cm-operator">=</span> <span class="cm-variable">document</span>.<span class="cm-property">getElementsByClassName</span>(<span class="cm-string">'ExplanationsSolutionCard c5ngj6s'</span>)[<span class="cm-number">0</span>].<span class="cm-property">offsetHeight</span>;</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">        <span class="cm-variable">document</span>.<span class="cm-property">getElementsByClassName</span>(<span class="cm-string">'mv7e89c'</span>)[<span class="cm-number">0</span>].<span class="cm-property">style</span>.<span class="cm-property">minHeight</span><span class="cm-operator">=</span><span class="cm-variable-2">newHeight</span><span class="cm-operator">+</span><span class="cm-string">"px"</span>;</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">    }</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;">}, <span class="cm-atom">false</span>);</span></pre><pre class=" CodeMirror-line " role="presentation"><span role="presentation" style="padding-right: 0.1px;"><span cm-text="">​</span></span></pre></div></div></div></div></div><div style="position: absolute; height: 40px; width: 1px; border-bottom: 0px solid transparent; top: 387px;"></div><div class="CodeMirror-gutters" style="display: none; height: 427px;"></div></div><div style="position: absolute; right: 0px; top: 0px; z-index: 7; pointer-events: none;"></div></div></div></div></td></tr></table></div></div></td></tr><tfoot id="tfoot_dHZfZm9vdGVyX3Rzb3VyY2U2NzVkMTkyOTI0Y2M0YjVhOTUxMzkzODllNDA2M2Q0N191bmRlZmluZWQ"><tr id="tr_dHZfZm9vdGVyX3Ryc291cmNlNjc1ZDE5MjkyNGNjNGI1YTk1MTM5Mzg5ZTQwNjNkNDdfdW5kZWZpbmVk"><td id="td_dHZfZm9vdGVyX3Rkc291cmNlNjc1ZDE5MjkyNGNjNGI1YTk1MTM5Mzg5ZTQwNjNkNDdfdW5kZWZpbmVk"></td></tr></tfoot></table></div></div></div></div></div></td></tr><tfoot id="tfoot_dHZfZm9vdGVyX3RtYWluX3VuZGVmaW5lZA"><tr id="tr_dHZfZm9vdGVyX3RybWFpbl91bmRlZmluZWQ"><td id="td_dHZfZm9vdGVyX3RkbWFpbl91bmRlZmluZWQ"></td></tr></tfoot></table></div></div></div><div id="div_YXNrX3N0YXR1cw" class="ask status"></div></body></html>

app.bat

@@ -0,0 +1,3 @@
+@echo off
+cd /d D:\Analyze-and-predict-student-performance
+start /B cmd /C "python -m streamlit run main.py & timeout /T 1 > nul"

database.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0114a7fefb66a7de43db5fa10c330fe7883c4592a23968d4f8fe97d0de6fc9de
+size 11698176

function.py

@@ -4,230 +4,317 @@ import plotly.express as px
 import plotly.graph_objs as go
 import streamlit as st
 import joblib
+import re
 
 
 def get_year(student_id):
-    return int(student_id[6:8])
+    year_str = ""
+    for char in student_id:
+        if char.isdigit():
+            year_str += char
+            if len(year_str) == 2:
+                break
+    return int(year_str)
 
+
+@st.cache_data()
 def process_data(raw_data):
-    # Pivot the DataFrame
-    pivot_df = pd.pivot_table(raw_data, values='DiemHP', index='MaSV', columns='TenMH', aggfunc='first')
+
+    raw_data = raw_data[
+        ~raw_data["TenMH"].str.contains("IE|Intensive English|IE2|IE1|IE3|IE0")
+    ]
+
+    pivot_df = pd.pivot_table(
+        raw_data, values="DiemHP", index="MaSV", columns="TenMH", aggfunc="first"
+    )
     pivot_df = pivot_df.reset_index().rename_axis(None, axis=1)
     pivot_df.columns.name = None
     pivot_df = pivot_df.dropna(thresh=50, axis=1)
     pivot_df = pivot_df.rename(columns=lambda x: x.strip())
-    # Drop unnecessary columns
-    cols_to_drop = []
-    with open('cols_to_drop.txt', 'r') as f:
-      for line in f:
-        cols_to_drop.append(str(line.strip()))
-    existing_cols = [col for col in cols_to_drop if col in pivot_df.columns]
-    if existing_cols:
-        pivot_df.drop(existing_cols, axis=1, inplace=True)
-
-    # Merge with the XepLoaiNH column
-    df = pd.merge(pivot_df, raw_data[['MaSV', 'XepLoaiNH']], on='MaSV')
-    df.drop_duplicates(subset='MaSV', keep='last', inplace=True)
-    dfid=df['MaSV']
-    df.drop(['MaSV', 'XepLoaiNH'], axis=1, inplace=True)
-    df.replace(['WH', 'VT',"I"], np.nan, inplace=True)
+
+    df = pd.merge(pivot_df, raw_data[["MaSV"]], on="MaSV")
+    df.drop_duplicates(subset="MaSV", keep="last", inplace=True)
+    dfid = df["MaSV"]
+    df.drop(["MaSV"], axis=1, inplace=True)
+    df.replace(["WH", "VT", "I"], np.nan, inplace=True)
     df.iloc[:, :-1] = df.iloc[:, :-1].apply(pd.to_numeric)
-    df = pd.merge(dfid,df,left_index=True, right_index=True)
-    df['MaSV_school'] = df['MaSV'].str.slice(2, 4)
-    df['Major'] = df['MaSV'].str.slice(0, 2)
+    df = pd.merge(dfid, df, left_index=True, right_index=True)
+    df["MaSV_school"] = df["MaSV"].str.slice(2, 4)
+    df["Major"] = df["MaSV"].str.slice(0, 2)
     df["Year"] = 2000 + df["MaSV"].apply(get_year)
-    df["Year"]=df["Year"].astype(str)
-    df=df.drop(columns='MaSV')
-    
+    df["Year"] = df["Year"].astype(str)
+    df = pd.merge(df, raw_data[["MaSV", "DTBTK"]].drop_duplicates(), on="MaSV")
+    df = df.drop(columns="MaSV")
+
     return df
-    
+
+
 def process_data_per(raw_data):
-    # Pivot the DataFrame
-    pivot_df = pd.pivot_table(raw_data, values='DiemHP', index='MaSV', columns='TenMH', aggfunc='first')
+
+    raw_data = raw_data[
+        ~raw_data["TenMH"].str.contains("IE|Intensive English|IE2|IE1|IE3|IE0")
+    ]
+    pivot_df = pd.pivot_table(
+        raw_data, values="DiemHP", index="MaSV", columns="TenMH", aggfunc="first"
+    )
     pivot_df = pivot_df.reset_index().rename_axis(None, axis=1)
     pivot_df.columns.name = None
     pivot_df = pivot_df.dropna(thresh=50, axis=1)
     pivot_df = pivot_df.rename(columns=lambda x: x.strip())
 
-    # Drop unnecessary columns
-    cols_to_drop = []
-    with open('cols_to_drop.txt', 'r') as f:
-      for line in f:
-        cols_to_drop.append(str(line.strip()))
-    existing_cols = [col for col in cols_to_drop if col in pivot_df.columns]
-    if existing_cols:
-        pivot_df.drop(existing_cols, axis=1, inplace=True)
-    pivot_df.replace('WH', np.nan, inplace=True)
+    pivot_df.replace(["WH", "VT", "I"], np.nan, inplace=True)
     pivot_df.iloc[:, 1:] = pivot_df.iloc[:, 1:].apply(pd.to_numeric)
-    # Merge with the XepLoaiNH column
-    df = pd.merge(pivot_df, raw_data[['MaSV', 'XepLoaiNH']], on='MaSV')
-    df.drop_duplicates(subset='MaSV', keep='last', inplace=True)
-    df.drop(['XepLoaiNH'], axis=1, inplace=True)
-    
-    return df
+
+    return pivot_df
 
 
 def process_predict_data(raw_data):
     dtk = raw_data[["MaSV", "DTBTKH4"]].copy()
     dtk.drop_duplicates(subset="MaSV", keep="last", inplace=True)
 
-    count_duplicates = raw_data.groupby(["MaSV", "MaMH"]).size().reset_index(name="Times")
-    courses = raw_data[raw_data['MaMH'].str.startswith('IT')]
-    courses_list=courses['MaMH'].unique().tolist()
+    count_duplicates = (
+        raw_data.groupby(["MaSV", "MaMH"]).size().reset_index(name="Times")
+    )
+    courses = raw_data[
+        raw_data["MaMH"].str.startswith(
+            ("IT", "BA", "BM", "BT", "MA", "CE", "EE", "EL", "ENEE", "IS", "MAFE", "PH")
+        )
+    ]
+
+    courses_list = courses["MaMH"].unique().tolist()
 
-  # Create two new columns for counting courses that are in the courses_list or not
     count_duplicates["fail_courses_list"] = (
         (count_duplicates["MaMH"].isin(courses_list)) & (count_duplicates["Times"] >= 2)
     ).astype(int)
 
     count_duplicates["fail_not_courses_list"] = (
-        (~count_duplicates["MaMH"].isin(courses_list)) & (count_duplicates["Times"] >= 2)
+        (~count_duplicates["MaMH"].isin(courses_list))
+        & (count_duplicates["Times"] >= 2)
     ).astype(int)
 
     count_duplicates["pass_courses"] = (
-        (~count_duplicates["MaMH"].isin(courses_list)) & (count_duplicates["Times"] == 1)
+        (~count_duplicates["MaMH"].isin(courses_list))
+        & (count_duplicates["Times"] == 1)
     ).astype(int)
 
-    # Group the data by "MaSV" and sum the counts for the two new columns
     fail = (
         count_duplicates.groupby("MaSV")[["fail_courses_list", "fail_not_courses_list"]]
         .sum()
         .reset_index()
     )
 
-    # Rename the columns to reflect the split of courses_list and not courses_list
     fail.columns = ["MaSV", "fail_courses_list_count", "fail_not_courses_list_count"]
 
     df = pd.merge(dtk, fail, on="MaSV")
     df = df.rename(columns={"DTBTKH4": "GPA"})
 
-    data = raw_data[['MaSV','NHHK','SoTCDat']]
-    data = data.drop_duplicates()
-    data = data.groupby(['MaSV'])['SoTCDat'].median().reset_index(name='Mean_Cre').round(2)
-
-    df = pd.merge(df, data, on='MaSV')
-    df1=raw_data[['MaSV','MaMH','NHHK']]
-    courses_list = raw_data[(raw_data['MaMH'].str.startswith('EN')) & ~(raw_data['MaMH'].str.contains('EN007|EN008|EN011|EN012'))].MaMH.tolist()
-    filtered_df = df1[df1['MaMH'].isin(courses_list)]
-    nhhk_counts = filtered_df.groupby('MaSV')['NHHK'].nunique().reset_index(name='EPeriod')
-    df = pd.merge(df, nhhk_counts, on='MaSV', how='left').fillna(0)
-    df=df[['MaSV','GPA'	,'Mean_Cre',	'fail_courses_list_count'	,'fail_not_courses_list_count'	,'EPeriod']]
+    data = raw_data[["MaSV", "NHHK", "SoTCDat"]]
+    data = (
+        data.groupby(["MaSV"])["SoTCDat"].mean().reset_index(name="Mean_Cre").round(2)
+    )
+
+    df = pd.merge(df, data, on="MaSV")
+    df1 = raw_data[["MaSV", "MaMH", "NHHK"]]
+    courses_list = raw_data[
+        (raw_data["MaMH"].str.startswith("EN"))
+        & ~(raw_data["MaMH"].str.contains("EN007|EN008|EN011|EN012"))
+    ].MaMH.tolist()
+    filtered_df = df1[df1["MaMH"].isin(courses_list)]
+    nhhk_counts = (
+        filtered_df.groupby("MaSV")["NHHK"].nunique().reset_index(name="EPeriod")
+    )
+    df = pd.merge(df, nhhk_counts, on="MaSV", how="left").fillna(0)
+    df = df[
+        [
+            "MaSV",
+            "GPA",
+            "Mean_Cre",
+            "fail_courses_list_count",
+            "fail_not_courses_list_count",
+            "EPeriod",
+        ]
+    ]
     return df
 
+
 def predict_late_student(test_df):
-    # Load the pre-trained model
-    model=joblib.load("model/R_Late.joblib")
-    model1=joblib.load("model/R_Sem.joblib")
-    # Process the student data
+
+    model = joblib.load("model/Time/Late.joblib")
+    model1 = joblib.load("model/Time/Sem.joblib")
+
     test_dfed = process_predict_data(test_df)
 
-    # Save the student ID column
     std_id = test_dfed.iloc[:, 0]
 
-    # Drop the student ID column
     test_dfed = test_dfed.drop(test_dfed.columns[0], axis=1)
 
-    # Make predictions using the pre-trained model
     prediction = model.predict(test_dfed)
 
-    # Add a new column to the student data indicating if the student is late
-    
-
     prediction1 = model1.predict(test_dfed)
 
-    # Add a new column to the student data indicating if the student is late
-    test_dfed['Period'] = prediction1
-    test_dfed['Result'] = ['late' if p == 1 else 'not late' for p in prediction]
+    test_dfed["Semeters"] = prediction1
+    test_dfed["Progress"] = ["late" if p == 1 else "not late" for p in prediction]
+
+    test_dfed.insert(0, "MaSV", std_id)
 
-    # Add the student ID column back to the beginning of the DataFrame
-    test_dfed.insert(0, 'MaSV', std_id)
-    
     for index, row in test_dfed.iterrows():
-      if row['Period'] <= 9 and row['Result'] == 'late':
-        test_dfed.loc[index, 'Period'] = row['Period'] / 2
-        test_dfed.loc[index, 'Result'] = 'may late'
-      else:
-        test_dfed.loc[index, 'Period'] = row['Period'] / 2
+        if row["Semeters"] <= 9 and row["Progress"] == "late":
+            test_dfed.loc[index, "Semeters"] = row["Semeters"] / 2
+            test_dfed.loc[index, "Progress"] = "may late"
+        else:
+            test_dfed.loc[index, "Semeters"] = row["Semeters"] / 2
 
     return test_dfed
-def predict_rank(raw_data):
-    # Pivot the DataFrame
-    raw_data = raw_data[raw_data["MaSV"].str.startswith("IT")]
-    raw_data = raw_data[raw_data['MaMH'].str.startswith('IT')]
+
+
+def get_major(raw_data):
+    major_mapping = {
+        "BA": "BA",
+        "BE": "BM",
+        "BT": "BT",
+        "CE": "CE",
+        "EE": "EE",
+        "EN": "EL",
+        "EV": "ENEE",
+        "IE": "IS",
+        "IT": "IT",
+        "MA": "MAFE",
+        "SE": "PH",
+    }
+    for major, ma_mh in major_mapping.items():
+        if raw_data["MaSV"].str[:2].str.contains(major).any():
+            return major, ma_mh
+    return None, None
+
+
+def create_pivot_table(raw_data):
     pivot_df = pd.pivot_table(
-        raw_data, values="DiemHP", index="MaSV", columns="TenMH", aggfunc="first"
+        raw_data, values="DiemHP", index="MaSV", columns="MaMH", aggfunc="first"
     )
     pivot_df = pivot_df.reset_index().rename_axis(None, axis=1)
     pivot_df.columns.name = None
-    pivot_df = pivot_df.dropna(thresh=50, axis=1)
-    pivot_df = pivot_df.rename(columns=lambda x: x.strip())
+    return pivot_df
 
-    pivot_df.replace("WH", np.nan, inplace=True)
+
+def drop_nan_columns(pivot_df):
+    pivot_df = pivot_df.rename(columns=lambda x: x.strip())
+    pivot_df.replace(["WH", "VT", "I", "P", "F"], np.nan, inplace=True)
     pivot_df.iloc[:, 1:] = pivot_df.iloc[:, 1:].apply(pd.to_numeric)
+    return pivot_df
 
-    # Merge with the XepLoaiNH column
+
+def merge_with_xeploainh(pivot_df, raw_data):
     df = pd.merge(pivot_df, raw_data[["MaSV", "DTBTK"]], on="MaSV")
     df.drop_duplicates(subset="MaSV", keep="last", inplace=True)
-    col=df.drop(['MaSV', 'DTBTK'], axis=1)
-    
-    columns_data = []
-    with open('column_all.txt', 'r') as f:
-      for line in f:
-        columns_data.append(str(line.strip()))
-    
-
-    r=df.drop(columns=['MaSV','DTBTK'])
-    merge=r.columns.tolist()
-    dup=pd.DataFrame(columns=columns_data)
-    df= pd.merge(dup, df, on=merge, how='outer')
+    return df
+
+
+def fill_missing_values(df):
+    col = df.drop(["MaSV", "DTBTK"], axis=1)
+    columns_data = get_column_data(df)
+    dup = pd.DataFrame(columns=columns_data)
+    df = pd.merge(dup, df, on=col.columns.tolist(), how="outer")
     for col in df.columns:
-          if df[col].isnull().values.any():
+        if df[col].isnull().values.any():
             df[col].fillna(value=df["DTBTK"], inplace=True)
-    std_id = df['MaSV'].copy()
-    df=df.drop(['MaSV', 'DTBTK'], axis=1)
+    return df
+
+
+def get_column_data(df):
+    major = df["MaSV"].str[:2].unique()[0]
+    column_file = f"Columns/column_{major}.txt"
+    columns_data = []
+    with open(column_file, "r") as f:
+        for line in f:
+            columns_data.append(str(line.strip()))
+    return columns_data
+
+
+def prepare_data(df):
+    std_id = df["MaSV"].copy()
+    df = df.drop(["MaSV", "DTBTK"], axis=1)
     df.sort_index(axis=1, inplace=True)
-    model=joblib.load("model/R_rank.joblib")
-    prediction = model.predict(df)
-    df['Pred Rank'] = prediction
-    df.insert(0, 'MaSV', std_id)
-    df=df[['MaSV','Pred Rank']]
     return df
 
 
+def predict_rank(raw_data):
+    major, ma_mh = get_major(raw_data)
+    if major:
+        raw_data["MaMH"] = raw_data["MaMH"].str[:-2]
+        raw_data = raw_data[raw_data["MaMH"].str.startswith(ma_mh)]
+
+        pivot_df = create_pivot_table(raw_data)
+        pivot_df = drop_nan_columns(pivot_df)
+
+        df = merge_with_xeploainh(pivot_df, raw_data)
+        df = fill_missing_values(df)
+
+        std_id = df["MaSV"].copy()
+        df = prepare_data(df)
+
+        model = joblib.load(f"model/{major}_rank.joblib")
+        prediction = model.predict(df)
+
+        new_columns = pd.concat(
+            [pd.Series(std_id, name="MaSV"), pd.Series(prediction, name="Pred Rank")],
+            axis=1,
+        )
+        df = pd.concat([new_columns, df], axis=1)
+        newframe = df.copy()
+
+        df = newframe[["MaSV", "Pred Rank"]]
+        return df
+    else:
+        return None
+
+
 def predict_one_student(raw_data, student_id):
-    # Subset the DataFrame to relevant columns and rows
-      student = process_data_per(raw_data)
-      filtered_df = student[student["MaSV"] == student_id]
-      if len(filtered_df) > 0:
+
+    student = process_data_per(raw_data)
+    filtered_df = student[student["MaSV"] == student_id]
+    if len(filtered_df) > 0:
         selected_row = filtered_df.iloc[0, 1:].dropna()
-        colname = filtered_df.dropna().columns.tolist()
         values = selected_row.values.tolist()
+        course_data_filtered = [x for x in selected_row if not np.isnan(x)]
+        counts, bins = np.histogram(course_data_filtered, bins=np.arange(0, 110, 10))
+        grade_bins = [f"{bins[i]}-{bins[i+1]}" for i in range(len(bins) - 1)]
+        total_count = len(selected_row)
+        frequencies_percentage = (counts / total_count) * 100
 
-      # create a line chart using plotly
         fig1 = go.Figure()
-        fig1.add_trace(go.Histogram(x=values, nbinsx=40, name=student_id,marker=dict(color='rgba(50, 100, 200, 0.7)')))
 
-        # set the chart title and axis labels
+        fig1.add_trace(
+            go.Scatter(
+                x=bins[:-1], y=frequencies_percentage, mode="lines", name="Frequency"
+            )
+        )
+
         fig1.update_layout(
-            title="Histogram for student {}".format(student_id),
-            xaxis_title="Value",
-            yaxis_title="Frequency",
-            width=500
+            title="Frequency Range for",
+            xaxis_title="Score",
+            yaxis_title="Percentage",
+            height=400,
+            width=400,
         )
 
-        # create a bar chart using plotly express
-        data = raw_data[['MaSV', 'NHHK', 'TenMH', 'DiemHP']]
-        data['TenMH'] = data['TenMH'].str.lstrip()
-        data['NHHK'] = data['NHHK'].apply(lambda x: str(x)[:4] + ' S ' + str(x)[4:])
+        data = raw_data[["MaSV", "NHHK", "TenMH", "DiemHP"]]
+        data["TenMH"] = data["TenMH"].str.lstrip()
+        data["NHHK"] = data["NHHK"].apply(lambda x: str(x)[:4] + " S " + str(x)[4:])
         rows_to_drop = []
-        with open('rows_to_drop.txt', 'r') as f:
+        with open("rows_to_drop.txt", "r") as f:
             for line in f:
                 rows_to_drop.append(str(line.strip()))
-        data = data[~data['TenMH'].isin(rows_to_drop)]
-        student_data = data[data['MaSV'] == student_id][['NHHK', 'TenMH', 'DiemHP']]
-        student_data['DiemHP'] = pd.to_numeric(student_data['DiemHP'], errors='coerce')
-
-        fig2 = px.bar(student_data, x='TenMH', y='DiemHP', color='NHHK', title='Student Score vs. Course')
+        data = data[~data["TenMH"].isin(rows_to_drop)]
+        student_data = data[data["MaSV"] == student_id][["NHHK", "TenMH", "DiemHP"]]
+        student_data["DiemHP"] = pd.to_numeric(student_data["DiemHP"], errors="coerce")
+
+        fig2 = px.bar(
+            student_data,
+            x="TenMH",
+            y="DiemHP",
+            color="NHHK",
+            title="Student Score vs. Course",
+        )
         fig2.update_layout(
             title="Student Score vs. Course",
             xaxis_title=None,
@@ -237,17 +324,78 @@ def predict_one_student(raw_data, student_id):
             type="line",
             x0=0,
             y0=50,
-            x1=len(student_data['TenMH'])-1,
+            x1=len(student_data["TenMH"]) - 1,
             y1=50,
-            line=dict(color='red', width=3)
+            line=dict(color="red", width=3),
         )
 
-        # display the charts using st.column
         col1, col2 = st.columns(2)
         with col1:
-            st.plotly_chart(fig1)
+            st.plotly_chart(fig1, use_container_width=True)
 
         with col2:
-            st.plotly_chart(fig2)
-      else:
-        st.write("No data found for student {}".format(student_id))
+            st.plotly_chart(fig2, use_container_width=True)
+    else:
+        st.write("No data found for student {}".format(student_id))
+
+
+def show_boxplot1(
+    new1_df, new1_dfa, major, school, year, additional_selection="", year_a=""
+):
+    if additional_selection != " ":
+        show_boxplot = st.checkbox(
+            "Show Boxplot for student's performance", key="checkbox2"
+        )
+
+        if show_boxplot:
+            fig = px.box(new1_df)
+            fig1 = px.box(new1_dfa)
+            fig.update_layout(
+                title="Boxplot of " + major + school + " student in " + year
+            )
+            fig1.update_layout(
+                title="Boxplot of "
+                + major
+                + additional_selection
+                + " student in "
+                + year_a
+            )
+            col1, col2 = st.columns(2)
+
+            with col1:
+                st.plotly_chart(fig, use_container_width=True)
+
+            with col2:
+                st.plotly_chart(fig1, use_container_width=True)
+
+    elif additional_selection == " " and year_a != " ":
+        show_boxplot = st.checkbox(
+            "Show Boxplot for student's performance", key="checkbox2"
+        )
+
+        if show_boxplot:
+            fig = px.box(new1_df)
+            fig1 = px.box(new1_dfa)
+            fig.update_layout(
+                title="Boxplot of " + major + school + " student in " + year
+            )
+            fig1.update_layout(
+                title="Boxplot of " + major + school + " student in " + year_a
+            )
+            col1, col2 = st.columns(2)
+
+            with col1:
+                st.plotly_chart(fig, use_container_width=True)
+
+            with col2:
+                st.plotly_chart(fig1, use_container_width=True)
+
+    elif additional_selection == " ":
+        show_boxplot = st.checkbox(
+            "Show Boxplot for student's performance", key="checkbox2"
+        )
+
+        if show_boxplot:
+            fig = px.box(new1_df)
+            fig.update_layout(title="Boxplot of " + major + " student in " + year)
+            st.plotly_chart(fig, use_container_width=True)

main.py

@@ -0,0 +1,888 @@
+import pandas as pd
+import streamlit as st
+import plotly.express as px
+import numpy as np
+import plotly.graph_objs as go
+from function import (
+    process_data,
+    predict_late_student,
+    predict_rank,
+    predict_one_student,
+    show_boxplot1,
+)
+from datetime import datetime
+from PIL import Image
+import base64
+import re
+import sqlite3
+
+df = pd.DataFrame()
+
+
+def color_cell(val):
+    if val == "not late":
+        color = "green"
+    elif val == "may late":
+        color = "yellow"
+    elif val == "late":
+        color = "red"
+    else:
+        color = "black"
+
+    return f"color: {color};"
+
+
+def clear_resources():
+    """Clears all resources from the st.session_state."""
+    for key in list(st.session_state.keys()):
+        if key.startswith("resource"):
+            del st.session_state[key]
+
+
+def get_year(student_id):
+    year_str = ""
+    for char in student_id:
+        if char.isdigit():
+            year_str += char
+            if len(year_str) == 2:
+                break
+    return int(year_str)
+
+
+def generate_comment(median):
+    if median < 30:
+        comment = f"The median score for {course} is quite low at {median}. Students may need to work harder to improve their performance."
+    elif median < 50:
+        comment = f"The median score for {course} is below average at {median}. Students should work on improving their understanding of the material."
+    elif median < 80:
+        comment = f"The median score for {course} is solid at {median}. Students are making good progress but could still work on improving their skills."
+    else:
+        comment = f"The median score for {course} is outstanding at {median}. Students are doing an excellent job in this course."
+    return comment
+
+
+favicon = "R.png"
+hcm = "HCM.png"
+intera = "Logo-iuoss-trans.png"
+st.set_page_config(
+    page_title="Student System",
+    page_icon=favicon,
+    layout="wide",
+)
+currentYear = datetime.now().year
+im1 = Image.open("R.png")
+im2 = Image.open("HCM.png")
+im3 = Image.open("Logo-iuoss-trans.png")
+
+
+col1, col2, col3 = st.columns([1, 3, 1])
+
+
+with col1:
+    st.image(im1, width=150)
+
+
+with col2:
+    st.markdown(
+        "<h1 style='text-align: center;'>TRUONG QUOC AN'S THESIS</h1>",
+        unsafe_allow_html=True,
+    )
+
+
+with col3:
+    st.image(im2, width=250)
+
+
+@st.cache_data()
+def score_table():
+    # Establish a connection to the database
+    conn = sqlite3.connect("database.db")
+    cursor = conn.cursor()
+
+    # Fetch data from the tables
+    cursor.execute('''SELECT Students.MaSV, Enrollment.MaMH, Courses.TenMH, Enrollment.NHHK, Enrollment.DiemHP, Students.DTBTK
+                      FROM Students
+                      INNER JOIN Enrollment ON Students.MaSV = Enrollment.MaSV
+                      INNER JOIN Courses ON Enrollment.MaMH = Courses.MaMH''')
+    data = cursor.fetchall()
+
+    # Create a DataFrame
+    df = pd.DataFrame(data, columns=['MaSV', 'MaMH', 'TenMH', 'NHHK', 'DiemHP', 'DTBTK'])
+    df = df.drop_duplicates()
+
+    # Close the database connection
+    conn.close()
+
+    return df
+
+@st.cache_data()
+def score_table_for_student():
+    with sqlite3.connect("database.db") as conn:
+        cursor = conn.cursor()
+
+        cursor.execute('''
+            SELECT DISTINCT Students.MaSV, Enrollment.MaMH, Courses.TenMH, Enrollment.NHHK, Enrollment.DiemHP, Students.DTBTK
+            FROM Students
+            INNER JOIN Enrollment ON Students.MaSV = Enrollment.MaSV
+            INNER JOIN Courses ON Enrollment.MaMH = Courses.MaMH
+        ''')
+        results = cursor.fetchall()
+        df = pd.DataFrame(results, columns=['MaSV', 'MaMH', 'TenMH', 'NHHK', 'DiemHP', 'DTBTK'])
+
+        cursor.execute('''
+            SELECT MaSV, NHHK, SoTCDat
+            FROM Students
+        ''')
+        results = cursor.fetchall()
+        df1 = pd.DataFrame(results, columns=['MaSV', 'NHHK', 'SoTCDat'])
+        merged_df = pd.merge(df, df1, on=['MaSV', 'NHHK'])
+
+    return merged_df
+
+
+
+
+st.sidebar.image(im3)
+st.sidebar.title("Student Performance Prediction System")
+option = ["Dashboard","Prediction Performance",  "Grade Distribution Tables"]
+
+tabs = st.sidebar.selectbox("Select an option", option)
+
+
+def filter_dataframe(df, column, value):
+    if value == "All":
+        return df
+    else:
+        return df[df[column] == value]
+
+
+if tabs == "Dashboard":
+    clear_resources()
+    raw_data = score_table()
+    df = process_data(raw_data)
+    additional_selection = " "
+    unique_values_major = df["Major"].unique()
+    unique_values_major = [
+        "BA",
+        "BE",
+        "BT",
+        "CE",
+        "EE",
+        "EN",
+        "EV",
+        "IE",
+        "MA",
+        "SE",
+        "IT",
+    ]
+    unique_values_major = sorted(unique_values_major, key=lambda s: s)
+    major = st.selectbox("Select a school:", unique_values_major)
+    df = filter_dataframe(df, "Major", major)
+    dfa = filter_dataframe(df, "Major", major)
+
+    unique_values_school = df["MaSV_school"].unique()
+    all_values_school = np.concatenate([["All"], unique_values_school])
+    no_numbers = [x for x in all_values_school if not re.search(r"\d", str(x))]
+
+    if len(no_numbers) == 2:
+        school = no_numbers[1]
+    else:
+        col1, col2 = st.columns(2)
+
+        with col1:
+            school = st.selectbox("Select a major:", no_numbers)
+
+        if school != "All":
+            values = [x for x in no_numbers if x != "All" and x != school]
+            values = np.concatenate([[" "], values])
+
+            with col2:
+                additional_selection = st.selectbox(
+                    "Select another major for comparisons:", values
+                )
+                if additional_selection != " ":
+                    dfa = filter_dataframe(dfa, "MaSV_school", additional_selection)
+
+    df = filter_dataframe(df, "MaSV_school", school)
+
+    unique_values_year = df["Year"].unique()
+    all_values_year = np.concatenate([["All"], unique_values_year])
+
+    col1, col2 = st.columns(2)
+
+    with col1:
+        year = st.selectbox("Select a year:", all_values_year)
+
+    with col2:
+        if year != "All" and additional_selection == " ":
+            year_list = [x for x in all_values_year if x != "All" and x != year]
+            year_list = np.concatenate([[" "], year_list])
+            year_a = st.selectbox("Select another year for comparisons:", year_list)
+        elif year == "All":
+            year_a = " "
+        elif year != "All" and additional_selection != " ":
+            year_a = year
+            if year_a != " ":
+                dfa = filter_dataframe(dfa, "Year", year_a)
+                dfa.dropna(axis=1, thresh=1, inplace=True)
+            else:
+                year_a = " "
+
+    df = filter_dataframe(df, "Year", year)
+    new1_df = df.DTBTK
+    new1_dfa = dfa.DTBTK
+    show_boxplot1(
+        new1_df, new1_dfa, major, school, year, additional_selection="", year_a=""
+    )
+
+    df.dropna(axis=1, thresh=1, inplace=True)
+
+    new_df = df.iloc[:, :-4].dropna(axis=1, thresh=10).apply(pd.to_numeric)
+    new_dfa = dfa.iloc[:, :-4].dropna(axis=1, thresh=10).apply(pd.to_numeric)
+    list1 = new_df.columns.tolist()
+    list2 = new_dfa.columns.tolist()
+    if (year != "All" and year_a != " ") or (
+        school != "All" and additional_selection != " "
+    ):
+        dfac = new_dfa.columns[:-4].tolist()
+        common_elements = np.intersect1d(list1, list2)
+
+        merged_array = np.concatenate((list1, list2), axis=None)
+
+        list3 = np.intersect1d(merged_array, common_elements)
+        new_df = new_df[list3]
+        new_dfa = new_dfa[list3]
+    if additional_selection != " ":
+        show_boxplot = st.checkbox("Show Boxplot for All Course", key="checkbox1")
+
+        if show_boxplot:
+            fig = px.box(new_df)
+            fig1 = px.box(new_dfa)
+            fig.update_layout(
+                title="Boxplot of " + major + school + " student in " + year
+            )
+            fig1.update_layout(
+                title="Boxplot of "
+                + major
+                + additional_selection
+                + " student in "
+                + year
+            )
+
+            st.plotly_chart(fig, use_container_width=True)
+            st.plotly_chart(fig1, use_container_width=True)
+
+    elif additional_selection == " " and year_a != " ":
+        show_boxplot = st.checkbox("Show Boxplot for All Course", key="checkbox1")
+
+        if show_boxplot:
+            fig = px.box(new_df)
+            fig1 = px.box(new_dfa)
+            fig.update_layout(
+                title="Boxplot of " + major + school + " student in " + year
+            )
+            fig1.update_layout(
+                title="Boxplot of " + major + school + " student in " + year_a
+            )
+
+            st.plotly_chart(fig, use_container_width=True)
+            st.plotly_chart(fig1, use_container_width=True)
+
+    elif additional_selection == " ":
+        show_boxplot = st.checkbox("Show Boxplot for All Course", key="checkbox1")
+
+        if show_boxplot:
+            fig = px.box(new_df)
+            fig.update_layout(title="Boxplot of " + major + " student in " + year)
+
+            st.plotly_chart(fig, use_container_width=True)
+
+    options = df.columns[:-4]
+
+    course_data_dict = {course: df[course].dropna() for course in options}
+    valid_courses = [
+        course for course, data in course_data_dict.items() if len(data) > 1
+    ]
+
+    if (year != "All" and year_a != " ") or (
+        school != "All" and additional_selection != " "
+    ):
+        dfac = new_dfa.columns[:-4].tolist()
+        common_elements = np.intersect1d(valid_courses, dfac)
+
+        merged_array = np.concatenate((valid_courses, dfac), axis=None)
+
+        valid_courses = np.intersect1d(merged_array, common_elements)
+
+    if len(valid_courses) > 5:
+        course = st.selectbox("Select a course:", valid_courses)
+    elif len(valid_courses) == 1:
+        course = valid_courses[0]
+    else:
+        st.write("No valid course data found!")
+        st.stop()
+
+    course_data = course_data_dict[course]
+
+    if len(course_data) > 1:
+        if school == "All":
+            st.write("Course:", course, " of ", major, " student")
+        else:
+            st.write("Course:", course, " of ", major + school, " student")
+        st.write(generate_comment(course_data.median()))
+    else:
+        st.write("No data available for the selected course.")
+
+    col1, col2, col3, col4 = st.columns(4)
+
+    with col1:
+        counts, bins = np.histogram(course_data, bins=np.arange(0, 110, 10))
+        total_count = len(course_data)
+        frequencies_percentage = (counts / total_count) * 100
+        grade_bins = [f"{bins[i]}-{bins[i+1]}" for i in range(len(bins) - 1)]
+
+        df = pd.DataFrame(
+            {"Grade": grade_bins, "Grading percentage": frequencies_percentage}
+        )
+        df["Grading percentage"] = df["Grading percentage"].map(
+            lambda x: "{:.2f}".format(x)
+        )
+
+        st.table(df)
+
+    with col2:
+
+        fig = go.Figure()
+        fig.add_trace(
+            go.Scatter(
+                x=bins[:-1], y=frequencies_percentage, mode="lines", name="Frequency"
+            )
+        )
+
+        fig.update_layout(
+            title="Frequency Range for {}".format(course),
+            xaxis_title="Score",
+            yaxis_title="Percentage",
+            height=400,
+            width=400,
+        )
+        st.plotly_chart(fig, use_container_width=True)
+
+    with col3:
+        fig = go.Figure()
+        fig.add_trace(go.Box(y=course_data, name="Box plot"))
+        fig.update_layout(
+            title="Box plot of Scores for {}".format(course),
+            yaxis_title="Score",
+            height=400,
+            width=400,
+        )
+        st.plotly_chart(fig, use_container_width=True)
+
+    with col4:
+        raw_data1 = raw_data.copy()
+        raw_data1["major"] = raw_data1["MaSV"].str.slice(0, 2)
+        raw_data1.replace(["WH", "VT", "I"], np.nan, inplace=True)
+        raw_data1 = raw_data1[~raw_data1["DiemHP"].isin(["P", "F", "PC"])]
+        if major != "All":
+            raw_data1 = raw_data1[raw_data1["major"] == major]
+
+        raw_data1["MaSV_school"] = raw_data1["MaSV"].str.slice(2, 4)
+        if school != "All":
+            raw_data1 = raw_data1[raw_data1["MaSV_school"] == school]
+
+        df1 = raw_data1[["TenMH", "NHHK", "DiemHP"]].copy()
+        
+        df1["DiemHP"] = df1["DiemHP"].replace('', pd.NA).dropna().astype(float)
+        df1["NHHK"] = df1["NHHK"].apply(lambda x: str(x)[:4] + " S " + str(x)[4:])
+
+        selected_TenMH = " " + course
+        filtered_df1 = df1[df1["TenMH"] == selected_TenMH]
+
+        mean_DiemHP = (
+            filtered_df1.groupby("NHHK")["DiemHP"]
+            .mean()
+            .round(1)
+            .reset_index(name="Mean")
+        )
+
+        if year != "All":
+            st.write("")
+        else:
+            fig = px.line(
+                mean_DiemHP,
+                x="NHHK",
+                y="Mean",
+                title=f"Mean Course Score for{selected_TenMH} through Semeters",
+            )
+            fig.update_layout(xaxis_title="Semeters",height=400, width=400)
+            st.plotly_chart(fig, use_container_width=True)
+
+    if (year != "All" and year_a != " ") or (
+        school != "All" and additional_selection != " "
+    ):
+        course_data_dict = {course: new_dfa[course]}
+        course_data = course_data_dict[course]
+
+        st.write(
+            "Course:",
+            course,
+            " of ",
+            major + additional_selection,
+            " student in ",
+            year_a,
+        )
+        col1, col2, col3, col4 = st.columns(4)
+
+        with col1:
+            course_data_filtered = [x for x in course_data if not np.isnan(x)]
+            counts, bins = np.histogram(
+                course_data_filtered, bins=np.arange(0, 110, 10)
+            )
+            total_count = len(course_data_filtered)
+            frequencies_percentage = (counts / total_count) * 100
+            grade_bins = [f"{bins[i]}-{bins[i+1]}" for i in range(len(bins) - 1)]
+
+            df1 = pd.DataFrame(
+                {"Grade": grade_bins, "Grading percentage": frequencies_percentage}
+            )
+            df1["Grading percentage"] = df1["Grading percentage"].map(
+                lambda x: "{:.2f}".format(x)
+            )
+
+            st.table(df1)
+
+        with col2:
+
+            fig = go.Figure()
+            fig.add_trace(
+                go.Scatter(
+                    x=bins[:-1],
+                    y=frequencies_percentage,
+                    mode="lines",
+                    name="Frequency",
+                )
+            )
+
+            fig.update_layout(
+                title="Frequency Range for {}".format(course),
+                xaxis_title="Score",
+                yaxis_title="Percentage",
+                height=400,
+                width=400,
+            )
+            st.plotly_chart(fig, use_container_width=True)
+
+        with col3:
+            fig = go.Figure()
+            fig.add_trace(go.Box(y=course_data, name="Box plot"))
+            fig.update_layout(
+                title="Box plot of Scores for {}".format(course),
+                yaxis_title="Score",
+                height=400,
+                width=400,
+            )
+            st.plotly_chart(fig, use_container_width=True)
+
+        with col4:
+            raw_data["major"] = raw_data["MaSV"].str.slice(0, 2)
+            raw_data.replace(["WH", "VT", "I"], np.nan, inplace=True)
+            raw_data = raw_data[~raw_data["DiemHP"].isin(["P", "F", "PC"])]
+            if major != "All":
+                raw_data = raw_data[raw_data["major"] == major]
+
+            raw_data["MaSV_school"] = raw_data["MaSV"].str.slice(2, 4)
+            raw_data = raw_data[raw_data["MaSV_school"] == additional_selection]
+
+            df1 = raw_data[["TenMH", "NHHK", "DiemHP"]].copy()
+            df1["DiemHP"] = df1["DiemHP"].replace('', pd.NA).dropna().astype(float)
+            df1["NHHK"] = df1["NHHK"].apply(lambda x: str(x)[:4] + " S " + str(x)[4:])
+
+            selected_TenMH = " " + course
+            filtered_df1 = df1[df1["TenMH"] == selected_TenMH]
+
+            mean_DiemHP = (
+                filtered_df1.groupby("NHHK")["DiemHP"]
+                .mean()
+                .round(1)
+                .reset_index(name="Mean")
+            )
+
+            if year != "All":
+                st.write("")
+            else:
+                fig = px.line(
+                    mean_DiemHP,
+                    x="NHHK",
+                    y="Mean",
+                    title=f"Mean Course Score for{selected_TenMH} through Semeters",
+                )
+                fig.update_layout(xaxis_title="Semeters",height=400, width=400)
+                st.plotly_chart(fig, use_container_width=True)
+    variables_to_delete = [
+        'raw_data1', 'df1', 'filtered_df1', 'mean_DiemHP', 'counts', 'bins',
+        'total_count', 'frequencies_percentage', 'grade_bins', 'fig1',
+        'common_elements', 'merged_array', 'list3', 'dfac', 'fig', 'new_df',
+        'new_dfa', 'new1_df', 'new1_dfa', 'course_data',
+        'options', 'valid_courses', 'list2', 'list1'
+    ]
+
+    for variable in variables_to_delete:
+        if variable in locals():
+            del locals()[variable]
+
+
+
+elif tabs == "Prediction Performance":
+
+    clear_resources()
+
+    raw_data = score_table_for_student()
+    raw_data["DTBTKH4"] = raw_data["DTBTK"]/25
+    df=raw_data.copy()
+    df["MaSV_school"] = df["MaSV"].str.slice(2, 4)
+    df["Major"] = df["MaSV"].str.slice(0, 2)
+    unique_values_major = df["Major"].unique()
+    unique_values_major = [
+        "BA",
+        "BE",
+        "BT",
+        "CE",
+        "EE",
+        "EN",
+        "EV",
+        "IE",
+        "MA",
+        "SE",
+        "IT",
+    ]
+    unique_values_major = sorted(unique_values_major, key=lambda s: s)
+    col1, col2 = st.columns(2)
+    with col1:
+        major = st.selectbox("Select a school:", unique_values_major)
+        df = filter_dataframe(df, "Major", major)
+
+        unique_values_school = df["MaSV_school"].unique()
+        all_values_school = np.concatenate([["All"], unique_values_school])
+        no_numbers = [x for x in all_values_school if not re.search(r"\d", str(x))]
+
+        if len(no_numbers) == 2:
+            school = no_numbers[1]
+    with col2:
+        school = st.selectbox("Select a major:", no_numbers)
+
+    df = filter_dataframe(df, "MaSV_school", school)
+    predict = predict_late_student(df)
+    rank = predict_rank(df)
+    predict = pd.merge(predict, rank, on="MaSV")
+    predict.rename(columns={"Mean_Cre": "Mean Credit"}, inplace=True)
+
+    rank_mapping = {
+        "Khá": "Good",
+        "Trung Bình Khá": "Average good",
+        "Giỏi": "Very good",
+        "Kém": "Very weak",
+        "Trung Bình": "Ordinary",
+        "Yếu": "Weak",
+        "Xuất Sắc": "Excellent",
+    }
+    predict["Pred Rank"].replace(rank_mapping, inplace=True)
+
+    df_late = predict
+
+    MaSV = st.text_input("Enter Student ID:", key="MaSV")
+
+    def clear_form():
+        st.session_state["MaSV"] = ""
+
+    if st.button("Clear", on_click=clear_form):
+        MaSV = ""
+
+    if MaSV:
+        df_filtered = predict[predict["MaSV"] == MaSV]
+        styled_table = (
+            df_filtered[
+                ["MaSV", "GPA", "Mean Credit", "Pred Rank", "Progress", "Semeters"]
+            ]
+            .style.applymap(color_cell)
+            .format({"GPA": "{:.2f}", "Mean Credit": "{:.1f}", "Semeters": "{:.1f}"})
+        )
+
+        with st.container():
+            st.table(styled_table)
+            predict_one_student(df, MaSV)
+    else:
+        df_late = predict
+
+        df_late["Year"] = 2000 + df_late["MaSV"].apply(get_year)
+        df_late = df_late[
+            (df_late["Year"] != currentYear - 1) & (df_late["Year"] != currentYear - 2)
+        ]
+        year = st.selectbox("Select Year", options=df_late["Year"].unique())
+        df_filtered = df_late[df_late["Year"] == year]
+        styled_table = (
+            df_filtered[
+                ["MaSV", "GPA", "Mean Credit", "Pred Rank", "Progress", "Semeters"]
+            ]
+            .style.applymap(color_cell)
+            .format({"GPA": "{:.2f}", "Mean Credit": "{:.2f}", "Semeters": "{:.2f}"})
+        )
+        csv = df_filtered.to_csv(index=False)
+        b64 = base64.b64encode(csv.encode()).decode()
+        href = f'<a href="data:file/csv;base64,{b64}" download="Preidct data.csv">Download CSV</a>'
+        st.markdown(href, unsafe_allow_html=True)
+
+        legend_order = [
+            "Excellent",
+            "Very good",
+            "Good",
+            "Average good",
+            "Ordinary",
+            "Weak",
+            "Very weak",
+        ]
+
+        fig1 = px.pie(
+            df_filtered,
+            names="Pred Rank",
+            title="Pred Rank",
+            color_discrete_sequence=px.colors.sequential.Mint,
+            height=400,
+            width=400,
+            labels=legend_order,
+        )
+
+        fig2 = px.pie(
+            df_filtered,
+            names="Progress",
+            title="Progress",
+            color_discrete_sequence=px.colors.sequential.Peach,
+            height=400,
+            width=400,
+        )
+
+        fig1.update_layout(
+            title={
+                "text": "Pred Rank",
+                "y": 0.95,
+                "x": 0.35,
+                "xanchor": "center",
+                "yanchor": "top",
+            }
+        )
+        fig2.update_layout(
+            title={
+                "text": "Progress",
+                "y": 0.95,
+                "x": 0.35,
+                "xanchor": "center",
+                "yanchor": "top",
+            }
+        )
+
+        col3, col1, col2 = st.columns([2, 1, 1])
+        with col3:
+            st.dataframe(styled_table,use_container_width=True)
+        with col1:
+            st.plotly_chart(fig1, use_container_width=True)
+        with col2:
+            st.plotly_chart(fig2, use_container_width=True)
+    variables_to_delete = [
+    "raw_data",
+    "df",
+    "df_late",
+    "MaSV",
+    "predict",
+    "rank",
+    "rank_mapping",
+    "styled_table",
+    "df_filtered",
+    "csv",
+    "b64",
+    "href",
+    "legend_order",
+    "fig1",
+    "fig2",
+    "col1",
+    "col2",
+    "col3"
+    ]
+
+    # Delete the variables after running the code
+    for variable_name in variables_to_delete:
+        if variable_name in locals():
+            del locals()[variable_name]
+
+elif tabs == "Grade Distribution Tables":
+    clear_resources()
+    raw_data = score_table()
+    df = process_data(raw_data)
+    additional_selection = " "
+
+    unique_values_major = df["Major"].unique()
+    unique_values_major = [
+        "BA",
+        "BE",
+        "BT",
+        "CE",
+        "EE",
+        "EN",
+        "EV",
+        "IE",
+        "MA",
+        "SE",
+        "IT",
+    ]
+    unique_values_major = sorted(unique_values_major, key=lambda s: s)
+    col1, col2 = st.columns(2)
+    with col1:
+        major = st.selectbox("Select a school:", unique_values_major)
+        df = filter_dataframe(df, "Major", major)
+
+        unique_values_school = df["MaSV_school"].unique()
+        all_values_school = np.concatenate([["All"], unique_values_school])
+        no_numbers = [x for x in all_values_school if not re.search(r"\d", str(x))]
+
+        if len(no_numbers) == 2:
+            school = no_numbers[1]
+    with col2:
+        school = st.selectbox("Select a major:", no_numbers)
+
+    df = filter_dataframe(df, "MaSV_school", school)
+
+    unique_values_year = df["Year"].unique()
+    all_values_year = np.concatenate([["All"], unique_values_year])
+
+    year = st.selectbox("Select a year:", all_values_year)
+
+    options = df.columns[:-4]
+    
+
+    course_data_dict = {course: df[course].dropna() for course in options}
+    
+    valid_courses = [
+        course for course, data in course_data_dict.items() if len(data) > 1
+    ]
+
+    course = "All"
+
+    if st.button("Generate Chart"):
+        courses_per_row = 4
+        num_courses = len(valid_courses)
+        num_rows = (num_courses + courses_per_row - 1) // courses_per_row
+
+        for row in range(num_rows):
+            start_index = row * courses_per_row
+            end_index = min((row + 1) * courses_per_row, num_courses)
+            courses_in_row = valid_courses[start_index:end_index]
+
+            for course in courses_in_row:
+                course_data = course_data_dict[course]
+                course_data = course_data.astype(float)
+                st.markdown(f"Course:  **{course}**")
+                st.write("Number of examinations: ", str(len(course_data)))
+                col1, col2, col3, col4 = st.columns(4)
+
+                with col1:
+                    counts, bins = np.histogram(course_data, bins=np.arange(0, 110, 10))
+                    total_count = len(course_data)
+                    frequencies_percentage = (counts / total_count) * 100
+                    grade_bins = [
+                        f"{bins[i]}-{bins[i+1]}" for i in range(len(bins) - 1)
+                    ]
+                    result_array = []
+                    cumulative_sum = 0
+
+                    for element in frequencies_percentage:
+                        cumulative_sum += element
+                        result_array.append(cumulative_sum)
+
+                    df = pd.DataFrame(
+                        {
+                            "Grade": grade_bins,
+                            "Grading percentage": frequencies_percentage,
+                            "Cumulative percentage": result_array
+                        }
+                    )
+                    df["Grading percentage"] = df["Grading percentage"].map(
+                        lambda x: "{:.2f}".format(x)
+                    )
+                    df["Cumulative percentage"] = df["Cumulative percentage"].map(
+                        lambda x: "{:.2f}".format(x)
+                    )
+
+                    st.table(df)
+
+                with col2:
+                    fig = go.Figure()
+                    fig.add_trace(
+                        go.Scatter(
+                            x=bins[:-1],
+                            y=frequencies_percentage,
+                            mode="lines",
+                            name="Frequency",
+                        )
+                    )
+
+                    fig.update_layout(
+                        title="Frequency Range",
+                        xaxis_title="Score",
+                        yaxis_title="Percentage",
+                        height=400,
+                        width=400,
+                    )
+                    st.plotly_chart(fig, use_container_width=True)
+
+                with col3:
+                    fig = go.Figure()
+                    fig.add_trace(go.Box(y=course_data, name="Box plot"))
+                    fig.update_layout(
+                        title="Box plot",
+                        yaxis_title="Score",
+                        height=400,
+                        width=400,
+                    )
+                    st.plotly_chart(fig, use_container_width=True)
+
+                with col4:
+                    raw_data1 = raw_data.copy()
+                    raw_data1["major"] = raw_data1["MaSV"].str.slice(0, 2)
+                    raw_data1.replace(["WH", "VT", "I"], np.nan, inplace=True)
+                    raw_data1 = raw_data1[~raw_data1["DiemHP"].isin(["P", "F", "PC"])]
+                    if major != "All":
+                        raw_data1 = raw_data1[raw_data1["major"] == major]
+
+                    raw_data1["MaSV_school"] = raw_data1["MaSV"].str.slice(2, 4)
+                    if school != "All":
+                        raw_data1 = raw_data1[raw_data1["MaSV_school"] == school]
+
+                    df1 = raw_data1[["TenMH", "NHHK", "DiemHP"]].copy()
+                    df1["DiemHP"] = df1["DiemHP"].astype(float)
+                    df1["NHHK"] = df1["NHHK"].apply(
+                        lambda x: str(x)[:4] + " S " + str(x)[4:]
+                    )
+
+                    selected_TenMH = " " + course
+                    filtered_df1 = df1[df1["TenMH"] == selected_TenMH]
+
+                    mean_DiemHP = (
+                        filtered_df1.groupby("NHHK")["DiemHP"]
+                        .mean()
+                        .round(1)
+                        .reset_index(name="Mean")
+                    )
+
+                    if year != "All":
+                        st.write("")
+                    else:
+                        fig = px.line(
+                            mean_DiemHP,
+                            x="NHHK",
+                            y="Mean",
+                            title=f"Mean DiemHP through Semesters",
+                        )
+                        fig.update_layout(height=400, width=400)
+                        st.plotly_chart(fig, use_container_width=True)
+                        del raw_data1, df1, filtered_df1, mean_DiemHP, counts, bins, total_count, frequencies_percentage, grade_bins, fig
+        del course_data, course_data_dict,  valid_courses
+    st.stop()

model/BA_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11d4c28f682d07bda4d4adfe64ef76ac692cc88af9d3a1b2551226cc2e4fa73
+size 992753

model/BE_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720a598596eeab9ed2f7f4fec18076ec7eed80bde81750e70fd6194194105a36
+size 956225

model/BT_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ebe7baa44bc48cd34bc9d03e29848c77bae585df28ed25f0db57603b0c811b
+size 970705

model/CE_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1618dfb0ad4439038f7d20267ae871ed01dc2593fa92cfda4a0afbdf76bccd57
+size 699689

model/EE_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2758fe04674069b630752eedafeebed5873b4cf4ff2760b5985553a71d36c6e5
+size 937585

model/EN_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667d9d1423ffbdc8992dd4356c4edebb1f19f443ad4726a04dbafa6fc1f4bd29
+size 801689

model/EV_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecf3c8a4e79a4e809cc8eff9bb3448c308020b8253941a4ce449c97b326aceb
+size 595841

model/IE_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88caec0a36dd42cbb9a5b721270263b37d64c713e4852c0279924d4c986938f
+size 997569

model/IT_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1501f7d0d2fa69383152b743d6b64d81d483054ec38ef95bedde9667fff68636
+size 1041793

model/MA_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de5f4e973abab2d91c18f88e4cd88ac8d1f3b358b827dec03fb75c5c0f9ef4e
+size 885313

model/SE_rank.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6202e55a86124de781d7aa456e995a98f1e2810c5b9dc4c7efa5a61fbf2e396
+size 556705

model/Time/Late.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8a028c74d33d2ee4237cc6e1fc017d51e276bad5ccf752a608e4eab9d5249b
+size 540660

model/Time/Sem.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfbee871506a3a7e6e3ca02d7bd205cceab50fdbec47878d01773ed59dd5e7c
+size 2638353

requirements.txt

@@ -6,3 +6,4 @@ plotly
 scipy
 pyDOE
 openpyxl
+matplotlib