Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+course_feedback_nlp/2ndrun/plots/confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+course_feedback_nlp/1strun/plots/confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+course_feedback_nlp/1strun/plots/review_length_analysis.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/train_data_scaled.csv filter=lfs diff=lfs merge=lfs -text
+course_feedback_nlp/Coursera_reviews.csv filter=lfs diff=lfs merge=lfs -text
+dropout_binaryclass/correlation_matrix.png filter=lfs diff=lfs merge=lfs -text
+dropout_binaryclass/correlation_with_target.png filter=lfs diff=lfs merge=lfs -text
+grade_multiclass/01_feature_distributions.png filter=lfs diff=lfs merge=lfs -text
+grade_multiclass/08_confusion_matrix_random_forest.png filter=lfs diff=lfs merge=lfs -text
+grade_multiclass/07_pairplot.png filter=lfs diff=lfs merge=lfs -text
+grade_multiclass/confusion_matrix_tuned_random_forest.png filter=lfs diff=lfs merge=lfs -text
+grade_multiclass/feature_distributions.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/attendance_with_features.csv filter=lfs diff=lfs merge=lfs -text
+lr_attendance/attendance_features_complete.csv filter=lfs diff=lfs merge=lfs -text
+lr_attendance/test_data_scaled.csv filter=lfs diff=lfs merge=lfs -text
+lr_attendance/plots_first_run/best_model_analysis.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/plots_first_run/correlation_heatmap.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/plots_first_run/eda_plots.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/plots_first_run/final_model_analysis.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/plots_first_run/school_variation_analysis.png filter=lfs diff=lfs merge=lfs -text
+lr_attendance/plots_first_run/residual_analysis.png filter=lfs diff=lfs merge=lfs -text

course_feedback_nlp/1strun/sentiment_model/config.json

@@ -0,0 +1,41 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "vocab_size": 30522
+}

course_feedback_nlp/1strun/sentiment_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dec82d9db7dba1620edf63c7b411c591cd9af6c3855d2a77694d9236e5c5ccc
+size 267841796

course_feedback_nlp/1strun/sentiment_model/results.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48923e24fc083d6f080ce366f414ee275b815f944b63d15f5cad37c7bc1c2625
+size 2221

course_feedback_nlp/1strun/sentiment_model/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

course_feedback_nlp/1strun/sentiment_model/training_info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee82096ea30700d1e21e9dbc465688486c7b00457ce73e21979f2899ed51ee3
+size 2065

course_feedback_nlp/2ndrun/sentiment_model/config.json

@@ -0,0 +1,41 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "vocab_size": 30522
+}

course_feedback_nlp/2ndrun/sentiment_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec3b327b5e5a9e4dfdd1115d94bca8022cb0fa2a9fb2b1d43ed273b8fdb6e7b
+size 267841796

course_feedback_nlp/2ndrun/sentiment_model/results.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7b900d295b13675f7b20761cf73e286044843a5e7b2c701dea697eae49b4f2
+size 2221

course_feedback_nlp/2ndrun/sentiment_model/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

course_feedback_nlp/2ndrun/sentiment_model/training_info.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c172250a7bf6d9cd7656ee0006ac903c62b15260d5f417ce83e47486e450eaf
+size 2065

course_feedback_nlp/Coursera_reviews.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8db44269ab9b75af45ce55a2c40f14deed143f14792ca9d0c10274741d9eabb
+size 272095806

course_feedback_nlp/distilbert-base-uncased/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

course_feedback_nlp/distilbert-base-uncased/README.md

@@ -0,0 +1,218 @@
+---
+language: en
+tags:
+- exbert
+license: apache-2.0
+datasets:
+- bookcorpus
+- wikipedia
+---
+
+# DistilBERT base model (uncased)
+
+This model is a distilled version of the [BERT base model](https://huggingface.co/bert-base-uncased). It was
+introduced in [this paper](https://arxiv.org/abs/1910.01108). The code for the distillation process can be found
+[here](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation). This model is uncased: it does
+not make a difference between english and English.
+
+## Model description
+
+DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a
+self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only,
+with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic
+process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained
+with three objectives:
+
+- Distillation loss: the model was trained to return the same probabilities as the BERT base model.
+- Masked language modeling (MLM): this is part of the original training loss of the BERT base model. When taking a
+  sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the
+  model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that
+  usually see the words one after the other, or from autoregressive models like GPT which internally mask the future
+  tokens. It allows the model to learn a bidirectional representation of the sentence.
+- Cosine embedding loss: the model was also trained to generate hidden states as close as possible as the BERT base
+  model.
+
+This way, the model learns the same inner representation of the English language than its teacher model, while being
+faster for inference or downstream tasks.
+
+## Intended uses & limitations
+
+You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
+be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=distilbert) to look for
+fine-tuned versions on a task that interests you.
+
+Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
+to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
+generation you should look at model like GPT2.
+
+### How to use
+
+You can use this model directly with a pipeline for masked language modeling:
+
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased')
+>>> unmasker("Hello I'm a [MASK] model.")
+
+[{'sequence': "[CLS] hello i'm a role model. [SEP]",
+  'score': 0.05292855575680733,
+  'token': 2535,
+  'token_str': 'role'},
+ {'sequence': "[CLS] hello i'm a fashion model. [SEP]",
+  'score': 0.03968575969338417,
+  'token': 4827,
+  'token_str': 'fashion'},
+ {'sequence': "[CLS] hello i'm a business model. [SEP]",
+  'score': 0.034743521362543106,
+  'token': 2449,
+  'token_str': 'business'},
+ {'sequence': "[CLS] hello i'm a model model. [SEP]",
+  'score': 0.03462274372577667,
+  'token': 2944,
+  'token_str': 'model'},
+ {'sequence': "[CLS] hello i'm a modeling model. [SEP]",
+  'score': 0.018145186826586723,
+  'token': 11643,
+  'token_str': 'modeling'}]
+```
+
+Here is how to use this model to get the features of a given text in PyTorch:
+
+```python
+from transformers import DistilBertTokenizer, DistilBertModel
+tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+model = DistilBertModel.from_pretrained("distilbert-base-uncased")
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+```
+
+and in TensorFlow:
+
+```python
+from transformers import DistilBertTokenizer, TFDistilBertModel
+tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+model = TFDistilBertModel.from_pretrained("distilbert-base-uncased")
+text = "Replace me by any text you'd like."
+encoded_input = tokenizer(text, return_tensors='tf')
+output = model(encoded_input)
+```
+
+### Limitations and bias
+
+Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
+predictions. It also inherits some of
+[the bias of its teacher model](https://huggingface.co/bert-base-uncased#limitations-and-bias).
+
+```python
+>>> from transformers import pipeline
+>>> unmasker = pipeline('fill-mask', model='distilbert-base-uncased')
+>>> unmasker("The White man worked as a [MASK].")
+
+[{'sequence': '[CLS] the white man worked as a blacksmith. [SEP]',
+  'score': 0.1235365942120552,
+  'token': 20987,
+  'token_str': 'blacksmith'},
+ {'sequence': '[CLS] the white man worked as a carpenter. [SEP]',
+  'score': 0.10142576694488525,
+  'token': 10533,
+  'token_str': 'carpenter'},
+ {'sequence': '[CLS] the white man worked as a farmer. [SEP]',
+  'score': 0.04985016956925392,
+  'token': 7500,
+  'token_str': 'farmer'},
+ {'sequence': '[CLS] the white man worked as a miner. [SEP]',
+  'score': 0.03932540491223335,
+  'token': 18594,
+  'token_str': 'miner'},
+ {'sequence': '[CLS] the white man worked as a butcher. [SEP]',
+  'score': 0.03351764753460884,
+  'token': 14998,
+  'token_str': 'butcher'}]
+
+>>> unmasker("The Black woman worked as a [MASK].")
+
+[{'sequence': '[CLS] the black woman worked as a waitress. [SEP]',
+  'score': 0.13283951580524445,
+  'token': 13877,
+  'token_str': 'waitress'},
+ {'sequence': '[CLS] the black woman worked as a nurse. [SEP]',
+  'score': 0.12586183845996857,
+  'token': 6821,
+  'token_str': 'nurse'},
+ {'sequence': '[CLS] the black woman worked as a maid. [SEP]',
+  'score': 0.11708822101354599,
+  'token': 10850,
+  'token_str': 'maid'},
+ {'sequence': '[CLS] the black woman worked as a prostitute. [SEP]',
+  'score': 0.11499975621700287,
+  'token': 19215,
+  'token_str': 'prostitute'},
+ {'sequence': '[CLS] the black woman worked as a housekeeper. [SEP]',
+  'score': 0.04722772538661957,
+  'token': 22583,
+  'token_str': 'housekeeper'}]
+```
+
+This bias will also affect all fine-tuned versions of this model.
+
+## Training data
+
+DistilBERT pretrained on the same data as BERT, which is [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset
+consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia)
+(excluding lists, tables and headers).
+
+## Training procedure
+
+### Preprocessing
+
+The texts are lowercased and tokenized using WordPiece and a vocabulary size of 30,000. The inputs of the model are
+then of the form:
+
+```
+[CLS] Sentence A [SEP] Sentence B [SEP]
+```
+
+With probability 0.5, sentence A and sentence B correspond to two consecutive sentences in the original corpus and in
+the other cases, it's another random sentence in the corpus. Note that what is considered a sentence here is a
+consecutive span of text usually longer than a single sentence. The only constrain is that the result with the two
+"sentences" has a combined length of less than 512 tokens.
+
+The details of the masking procedure for each sentence are the following:
+- 15% of the tokens are masked.
+- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
+- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
+- In the 10% remaining cases, the masked tokens are left as is.
+
+### Pretraining
+
+The model was trained on 8 16 GB V100 for 90 hours. See the
+[training code](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation) for all hyperparameters
+details.
+
+## Evaluation results
+
+When fine-tuned on downstream tasks, this model achieves the following results:
+
+Glue test results:
+
+| Task | MNLI | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  |
+|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|
+|      | 82.2 | 88.5 | 89.2 | 91.3  | 51.3 | 85.8  | 87.5 | 59.9 |
+
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{Sanh2019DistilBERTAD,
+  title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
+  author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
+  journal={ArXiv},
+  year={2019},
+  volume={abs/1910.01108}
+}
+```
+
+<a href="https://huggingface.co/exbert/?model=distilbert-base-uncased">
+	<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
+</a>

course_feedback_nlp/distilbert-base-uncased/config.json

@@ -0,0 +1,22 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.10.0.dev0",
+  "vocab_size": 30522
+}

course_feedback_nlp/distilbert-base-uncased/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "model_max_length": 512}

course_feedback_nlp/sentiment_model/config.json

@@ -0,0 +1,40 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "vocab_size": 30522
+}

course_feedback_nlp/sentiment_model/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

course_feedback_nlp/teacher_sentiment_model/config.json

@@ -0,0 +1,35 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Negative",
+    "1": "Neutral",
+    "2": "Positive"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Negative": 0,
+    "Neutral": 1,
+    "Positive": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "vocab_size": 30522
+}

course_feedback_nlp/teacher_sentiment_model/results.json

@@ -0,0 +1,15 @@
+{
+  "test_accuracy": 96.15760092399076,
+  "negative_recall": 94.3649373881932,
+  "negative_precision": 83.0926752428459,
+  "negative_f1": 88.37079435990506,
+  "neutral_recall": 89.8115551874094,
+  "positive_recall": 96.42464286494796,
+  "missed_struggling_students": 189,
+  "total_negative_cases": 3354,
+  "missed_percentage": 5.635062611806798,
+  "low_confidence_predictions": 14728,
+  "low_confidence_percentage": 10.12539874601254,
+  "macro_f1": 83.2724728076938,
+  "weighted_f1": 96.65053538273234
+}

course_feedback_nlp/teacher_sentiment_model/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

course_feedback_nlp/teacher_sentiment_model/training_config.json

@@ -0,0 +1,16 @@
+{
+  "num_classes": 3,
+  "class_names": [
+    "Negative",
+    "Neutral",
+    "Positive"
+  ],
+  "class_mapping": {
+    "0": 0,
+    "1": 0,
+    "2": 1,
+    "3": 2,
+    "4": 2
+  },
+  "max_length": 96
+}

dropout_binaryclass/realistic/comparison_xgboost/model_config.json

@@ -0,0 +1,117 @@
+{
+  "model_name": "Student Dropout Predictor",
+  "model_type": "XGBoost (Tuned)",
+  "features": [
+    "Curricular units 2nd sem (approved)",
+    "Curricular units 2nd sem (evaluations)",
+    "Curricular units 2nd sem (without evaluations)",
+    "Tuition fees up to date",
+    "Scholarship holder",
+    "Debtor",
+    "Gender",
+    "Age at enrollment",
+    "Daytime/evening attendance",
+    "Displaced"
+  ],
+  "num_features": 10,
+  "performance": {
+    "roc_auc": 0.9434,
+    "roc_auc_std": 0.0045,
+    "accuracy": 0.892,
+    "accuracy_std": 0.0069
+  },
+  "feature_importance": [
+    {
+      "feature": "Curricular units 2nd sem (approved)",
+      "importance": 0.4266107976436615
+    },
+    {
+      "feature": "Tuition fees up to date",
+      "importance": 0.2472454458475113
+    },
+    {
+      "feature": "Scholarship holder",
+      "importance": 0.07887265831232071
+    },
+    {
+      "feature": "Debtor",
+      "importance": 0.06558725982904434
+    },
+    {
+      "feature": "Curricular units 2nd sem (evaluations)",
+      "importance": 0.05764281377196312
+    },
+    {
+      "feature": "Gender",
+      "importance": 0.032258644700050354
+    },
+    {
+      "feature": "Age at enrollment",
+      "importance": 0.03202906996011734
+    },
+    {
+      "feature": "Curricular units 2nd sem (without evaluations)",
+      "importance": 0.025066660717129707
+    },
+    {
+      "feature": "Displaced",
+      "importance": 0.023970549926161766
+    },
+    {
+      "feature": "Daytime/evening attendance",
+      "importance": 0.010716132819652557
+    }
+  ],
+  "input_schema": {
+    "units_approved": {
+      "description": "Number of curricular units passed this semester",
+      "type": "integer",
+      "maps_to": "Curricular units 2nd sem (approved)"
+    },
+    "evaluations_taken": {
+      "description": "Number of evaluations/exams taken",
+      "type": "integer",
+      "maps_to": "Curricular units 2nd sem (evaluations)"
+    },
+    "evaluations_missed": {
+      "description": "Number of evaluations missed",
+      "type": "integer",
+      "maps_to": "Curricular units 2nd sem (without evaluations)"
+    },
+    "tuition_paid": {
+      "description": "Is tuition up to date?",
+      "type": "boolean",
+      "maps_to": "Tuition fees up to date"
+    },
+    "has_scholarship": {
+      "description": "Does student have a scholarship?",
+      "type": "boolean",
+      "maps_to": "Scholarship holder"
+    },
+    "has_debt": {
+      "description": "Does student have debt?",
+      "type": "boolean",
+      "maps_to": "Debtor"
+    },
+    "gender": {
+      "description": "Student gender (0=Female, 1=Male)",
+      "type": "integer",
+      "maps_to": "Gender"
+    },
+    "age": {
+      "description": "Age at enrollment",
+      "type": "integer",
+      "maps_to": "Age at enrollment"
+    },
+    "is_daytime": {
+      "description": "Daytime attendance?",
+      "type": "boolean",
+      "maps_to": "Daytime/evening attendance"
+    },
+    "is_displaced": {
+      "description": "Is student displaced?",
+      "type": "boolean",
+      "maps_to": "Displaced"
+    }
+  }
+}

dropout_binaryclass/realistic/comparison_xgboost/train.py

@@ -0,0 +1,352 @@
+#!/usr/bin/env python
+# coding: utf-8
+"""
+Compare Logistic Regression vs XGBoost with the 10 practical features.
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import json
+import joblib
+
+from sklearn.model_selection import StratifiedKFold
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import roc_auc_score, accuracy_score, classification_report, confusion_matrix
+import seaborn as sns
+
+# Install if needed: pip install xgboost
+from xgboost import XGBClassifier
+
+# =============================================================================
+# 1. LOAD DATA
+# =============================================================================
+
+df = pd.read_csv('../../data.csv', sep=';')
+df = df[df['Target'] != 'Enrolled']
+df.columns = df.columns.str.strip()
+df = df.round()
+
+# Practical features
+practical_features = [
+    'Curricular units 2nd sem (approved)',
+    'Curricular units 2nd sem (evaluations)',
+    'Curricular units 2nd sem (without evaluations)',
+    'Tuition fees up to date',
+    'Scholarship holder',
+    'Debtor',
+    'Gender',
+    'Age at enrollment',
+    'Daytime/evening attendance',
+    'Displaced',
+]
+
+x = df[practical_features].copy()
+y = df['Target'].map({'Dropout': 0, 'Graduate': 1}).astype(int)
+
+print(f"Dataset: {x.shape[0]} samples, {x.shape[1]} features")
+print(f"Class distribution: {y.value_counts().to_dict()}")
+
+# =============================================================================
+# 2. DEFINE MODELS
+# =============================================================================
+
+models = {
+    'Logistic Regression': Pipeline([
+        ('scaler', StandardScaler()),
+        ('clf', LogisticRegression(
+            C=1.0,
+            solver='lbfgs',
+            class_weight='balanced',
+            random_state=42,
+            max_iter=1000
+        ))
+    ]),
+    
+    'XGBoost': XGBClassifier(
+        n_estimators=100,
+        max_depth=5,
+        learning_rate=0.1,
+        subsample=0.8,
+        colsample_bytree=0.8,
+        scale_pos_weight=len(y[y==0]) / len(y[y==1]),  # Handle imbalance
+        random_state=42,
+        eval_metric='logloss',
+        verbosity=0
+    ),
+    
+    'XGBoost (Tuned)': XGBClassifier(
+        n_estimators=200,
+        max_depth=4,
+        learning_rate=0.05,
+        subsample=0.8,
+        colsample_bytree=0.8,
+        min_child_weight=3,
+        gamma=0.1,
+        reg_alpha=0.1,
+        reg_lambda=1.0,
+        scale_pos_weight=len(y[y==0]) / len(y[y==1]),
+        random_state=42,
+        eval_metric='logloss',
+        verbosity=0
+    )
+}
+
+# =============================================================================
+# 3. CROSS-VALIDATION COMPARISON
+# =============================================================================
+
+print("\n" + "="*70)
+print("MODEL COMPARISON (5-Fold Stratified CV)")
+print("="*70)
+
+results = {}
+skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
+
+for model_name, model in models.items():
+    print(f"\n{'─'*70}")
+    print(f"Training: {model_name}")
+    print('─'*70)
+    
+    auc_scores = []
+    acc_scores = []
+    
+    for fold, (train_idx, val_idx) in enumerate(skf.split(x, y), 1):
+        x_train, x_val = x.iloc[train_idx], x.iloc[val_idx]
+        y_train, y_val = y.iloc[train_idx], y.iloc[val_idx]
+        
+        model.fit(x_train, y_train)
+        
+        y_pred = model.predict(x_val)
+        y_proba = model.predict_proba(x_val)[:, 1]
+        
+        auc = roc_auc_score(y_val, y_proba)
+        acc = accuracy_score(y_val, y_pred)
+        
+        auc_scores.append(auc)
+        acc_scores.append(acc)
+        
+        print(f"  Fold {fold}: Accuracy={acc:.4f}, ROC-AUC={auc:.4f}")
+    
+    results[model_name] = {
+        'auc_mean': np.mean(auc_scores),
+        'auc_std': np.std(auc_scores),
+        'acc_mean': np.mean(acc_scores),
+        'acc_std': np.std(acc_scores)
+    }
+    
+    print(f"\n  → Average ROC-AUC: {np.mean(auc_scores):.4f} ± {np.std(auc_scores):.4f}")
+    print(f"  → Average Accuracy: {np.mean(acc_scores):.4f} ± {np.std(acc_scores):.4f}")
+
+# =============================================================================
+# 4. RESULTS SUMMARY
+# =============================================================================
+
+print("\n" + "="*70)
+print("RESULTS SUMMARY")
+print("="*70)
+
+results_df = pd.DataFrame(results).T
+results_df['ROC-AUC'] = results_df.apply(lambda x: f"{x['auc_mean']:.4f} ± {x['auc_std']:.4f}", axis=1)
+results_df['Accuracy'] = results_df.apply(lambda x: f"{x['acc_mean']:.4f} ± {x['acc_std']:.4f}", axis=1)
+
+print("\n" + results_df[['ROC-AUC', 'Accuracy']].to_string())
+
+# Find best model
+best_model_name = max(results, key=lambda x: results[x]['auc_mean'])
+print(f"\n🏆 Best Model: {best_model_name}")
+print(f"   ROC-AUC: {results[best_model_name]['auc_mean']:.4f}")
+print(f"   Accuracy: {results[best_model_name]['acc_mean']:.4f}")
+
+# =============================================================================
+# 5. TRAIN BEST MODEL ON ALL DATA & GET FEATURE IMPORTANCE
+# =============================================================================
+
+print("\n" + "="*70)
+print("FEATURE IMPORTANCE COMPARISON")
+print("="*70)
+
+# Train both on full data for feature importance
+lr_model = models['Logistic Regression']
+xgb_model = models['XGBoost (Tuned)']
+
+lr_model.fit(x, y)
+xgb_model.fit(x, y)
+
+# Logistic Regression coefficients
+lr_importance = pd.DataFrame({
+    'feature': practical_features,
+    'importance': np.abs(lr_model.named_steps['clf'].coef_[0])
+}).sort_values('importance', ascending=False)
+
+# XGBoost feature importance
+xgb_importance = pd.DataFrame({
+    'feature': practical_features,
+    'importance': xgb_model.feature_importances_
+}).sort_values('importance', ascending=False)
+
+print("\nLogistic Regression (|coefficients|):")
+for _, row in lr_importance.iterrows():
+    print(f"  {row['feature']:45s} {row['importance']:.4f}")
+
+print("\nXGBoost (feature importance):")
+for _, row in xgb_importance.iterrows():
+    print(f"  {row['feature']:45s} {row['importance']:.4f}")
+
+# =============================================================================
+# 6. VISUALIZATION
+# =============================================================================
+
+fig, axes = plt.subplots(1, 3, figsize=(15, 5))
+
+# Plot 1: Model Comparison
+ax1 = axes[0]
+model_names = list(results.keys())
+auc_means = [results[m]['auc_mean'] for m in model_names]
+auc_stds = [results[m]['auc_std'] for m in model_names]
+
+bars = ax1.barh(model_names, auc_means, xerr=auc_stds, capsize=5, color=['#3498db', '#2ecc71', '#27ae60'])
+ax1.set_xlabel('ROC-AUC Score')
+ax1.set_title('Model Comparison')
+ax1.set_xlim(0.9, 0.95)
+
+for bar, mean in zip(bars, auc_means):
+    ax1.text(mean + 0.002, bar.get_y() + bar.get_height()/2, f'{mean:.4f}', va='center')
+
+# Plot 2: LR Feature Importance
+ax2 = axes[1]
+sns.barplot(data=lr_importance, x='importance', y='feature', ax=ax2, color='#3498db')
+ax2.set_title('Logistic Regression\n|Coefficients|')
+ax2.set_xlabel('Importance')
+
+# Plot 3: XGBoost Feature Importance
+ax3 = axes[2]
+sns.barplot(data=xgb_importance, x='importance', y='feature', ax=ax3, color='#2ecc71')
+ax3.set_title('XGBoost\nFeature Importance')
+ax3.set_xlabel('Importance')
+
+plt.tight_layout()
+plt.savefig('model_comparison.png', dpi=150)
+plt.show()
+
+# =============================================================================
+# 7. DETAILED CLASSIFICATION REPORT (Best Model)
+# =============================================================================
+
+print("\n" + "="*70)
+print(f"DETAILED REPORT: {best_model_name}")
+print("="*70)
+
+# Final evaluation on a holdout approach for detailed metrics
+from sklearn.model_selection import train_test_split
+
+x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42, stratify=y)
+
+best_model = models[best_model_name]
+best_model.fit(x_train, y_train)
+
+y_pred = best_model.predict(x_test)
+y_proba = best_model.predict_proba(x_test)[:, 1]
+
+print("\nClassification Report:")
+print(classification_report(y_test, y_pred, target_names=['Dropout', 'Graduate']))
+
+print("Confusion Matrix:")
+cm = confusion_matrix(y_test, y_pred)
+print(f"                 Predicted")
+print(f"                 Dropout  Graduate")
+print(f"Actual Dropout   {cm[0][0]:5d}    {cm[0][1]:5d}")
+print(f"Actual Graduate  {cm[1][0]:5d}    {cm[1][1]:5d}")
+
+# =============================================================================
+# 8. SAVE BEST MODEL
+# =============================================================================
+
+print("\n" + "="*70)
+print("SAVING BEST MODEL")
+print("="*70)
+
+# Retrain on all data
+best_model.fit(x, y)
+
+# Save model
+model_filename = "student_dropout_model_xgb.pkl" if 'XGBoost' in best_model_name else "student_dropout_model.pkl"
+joblib.dump(best_model, model_filename)
+print(f"Model saved: {model_filename}")
+
+# Save config
+config = {
+    "model_name": "Student Dropout Predictor",
+    "model_type": best_model_name,
+    "features": practical_features,
+    "num_features": len(practical_features),
+    "performance": {
+        "roc_auc": round(results[best_model_name]['auc_mean'], 4),
+        "roc_auc_std": round(results[best_model_name]['auc_std'], 4),
+        "accuracy": round(results[best_model_name]['acc_mean'], 4),
+        "accuracy_std": round(results[best_model_name]['acc_std'], 4)
+    },
+    "feature_importance": xgb_importance.to_dict('records') if 'XGBoost' in best_model_name else lr_importance.to_dict('records'),
+    "input_schema": {
+        "units_approved": {
+            "description": "Number of curricular units passed this semester",
+            "type": "integer",
+            "maps_to": "Curricular units 2nd sem (approved)"
+        },
+        "evaluations_taken": {
+            "description": "Number of evaluations/exams taken",
+            "type": "integer",
+            "maps_to": "Curricular units 2nd sem (evaluations)"
+        },
+        "evaluations_missed": {
+            "description": "Number of evaluations missed",
+            "type": "integer",
+            "maps_to": "Curricular units 2nd sem (without evaluations)"
+        },
+        "tuition_paid": {
+            "description": "Is tuition up to date?",
+            "type": "boolean",
+            "maps_to": "Tuition fees up to date"
+        },
+        "has_scholarship": {
+            "description": "Does student have a scholarship?",
+            "type": "boolean",
+            "maps_to": "Scholarship holder"
+        },
+        "has_debt": {
+            "description": "Does student have debt?",
+            "type": "boolean",
+            "maps_to": "Debtor"
+        },
+        "gender": {
+            "description": "Student gender (0=Female, 1=Male)",
+            "type": "integer",
+            "maps_to": "Gender"
+        },
+        "age": {
+            "description": "Age at enrollment",
+            "type": "integer",
+            "maps_to": "Age at enrollment"
+        },
+        "is_daytime": {
+            "description": "Daytime attendance?",
+            "type": "boolean",
+            "maps_to": "Daytime/evening attendance"
+        },
+        "is_displaced": {
+            "description": "Is student displaced?",
+            "type": "boolean",
+            "maps_to": "Displaced"
+        }
+    }
+}
+
+with open("model_config.json", 'w') as f:
+    json.dump(config, f, indent=2)
+print("Config saved: model_config.json")
+
+print("\n" + "="*70)
+print("DONE!")
+print("="*70)

dropout_binaryclass/realistic/model_config.json

@@ -0,0 +1,117 @@
+{
+  "model_name": "Student Dropout Predictor",
+  "version": "1.0",
+  "description": "Predicts if a student will dropout or graduate based on available data",
+  "input_schema": {
+    "units_approved": {
+      "description": "Number of curricular units passed this semester",
+      "type": "integer",
+      "min": 0,
+      "max": 20,
+      "required": true,
+      "maps_to": "Curricular units 2nd sem (approved)"
+    },
+    "evaluations_taken": {
+      "description": "Number of evaluations/exams the student took",
+      "type": "integer",
+      "min": 0,
+      "max": 30,
+      "required": true,
+      "maps_to": "Curricular units 2nd sem (evaluations)"
+    },
+    "evaluations_missed": {
+      "description": "Number of evaluations the student missed/skipped",
+      "type": "integer",
+      "min": 0,
+      "max": 20,
+      "required": true,
+      "maps_to": "Curricular units 2nd sem (without evaluations)"
+    },
+    "tuition_paid": {
+      "description": "Is tuition up to date?",
+      "type": "boolean",
+      "required": true,
+      "maps_to": "Tuition fees up to date"
+    },
+    "has_scholarship": {
+      "description": "Does student have a scholarship?",
+      "type": "boolean",
+      "required": true,
+      "maps_to": "Scholarship holder"
+    },
+    "has_debt": {
+      "description": "Does student have outstanding debt?",
+      "type": "boolean",
+      "required": true,
+      "maps_to": "Debtor"
+    },
+    "gender": {
+      "description": "Student gender",
+      "type": "integer",
+      "values": {
+        "0": "Female",
+        "1": "Male"
+      },
+      "required": true,
+      "maps_to": "Gender"
+    },
+    "age": {
+      "description": "Student's age at enrollment",
+      "type": "integer",
+      "min": 17,
+      "max": 70,
+      "required": true,
+      "maps_to": "Age at enrollment"
+    },
+    "is_daytime": {
+      "description": "Is student enrolled in daytime classes?",
+      "type": "boolean",
+      "required": true,
+      "maps_to": "Daytime/evening attendance"
+    },
+    "is_displaced": {
+      "description": "Is student displaced from home region?",
+      "type": "boolean",
+      "required": true,
+      "maps_to": "Displaced"
+    }
+  },
+  "output_schema": {
+    "prediction": {
+      "type": "string",
+      "values": [
+        "Dropout",
+        "Graduate"
+      ]
+    },
+    "dropout_probability": {
+      "type": "float",
+      "min": 0,
+      "max": 1
+    },
+    "risk_level": {
+      "type": "string",
+      "values": [
+        "LOW",
+        "MEDIUM",
+        "HIGH"
+      ]
+    }
+  },
+  "feature_order": [
+    "Curricular units 2nd sem (approved)",
+    "Curricular units 2nd sem (evaluations)",
+    "Curricular units 2nd sem (without evaluations)",
+    "Tuition fees up to date",
+    "Scholarship holder",
+    "Debtor",
+    "Gender",
+    "Age at enrollment",
+    "Daytime/evening attendance",
+    "Displaced"
+  ],
+  "performance": {
+    "roc_auc": 0.9336,
+    "accuracy": 0.8857
+  }
+}

dropout_binaryclass/realistic/train.py

@@ -0,0 +1,227 @@
+#!/usr/bin/env python
+# coding: utf-8
+"""
+Student Dropout Prediction - PRACTICAL VERSION
+Uses only features a teacher would realistically have access to.
+"""
+
+import pandas as pd
+import numpy as np
+import json
+import joblib
+
+from sklearn.model_selection import StratifiedKFold
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import roc_auc_score, accuracy_score
+
+# =============================================================================
+# 1. LOAD DATA
+# =============================================================================
+
+df = pd.read_csv('../data.csv', sep=';')
+df = df[df['Target'] != 'Enrolled']
+df.columns = df.columns.str.strip()
+df = df.round()
+
+# =============================================================================
+# 2. SELECT ONLY REALISTIC FEATURES
+# =============================================================================
+
+# Features a teacher would realistically have
+practical_features = [
+    # Academic Performance (MOST IMPORTANT - teacher's main data)
+    'Curricular units 2nd sem (approved)',      # Units passed
+    'Curricular units 2nd sem (evaluations)',   # Exams taken
+    'Curricular units 2nd sem (without evaluations)',  # Exams missed
+    
+    # Financial Status (from system)
+    'Tuition fees up to date',
+    'Scholarship holder',
+    'Debtor',
+    
+    # Basic Demographics (in student profile)
+    'Gender',
+    'Age at enrollment',
+    
+    # Enrollment Info
+    'Daytime/evening attendance',
+    'Displaced',
+]
+
+# Verify all features exist
+missing = [f for f in practical_features if f not in df.columns]
+if missing:
+    print(f"Warning: Missing features: {missing}")
+    practical_features = [f for f in practical_features if f in df.columns]
+
+print(f"Using {len(practical_features)} practical features:")
+for i, f in enumerate(practical_features, 1):
+    print(f"  {i}. {f}")
+
+# Create feature matrix
+x = df[practical_features].copy()
+y = df['Target'].map({'Dropout': 0, 'Graduate': 1}).astype(int)
+
+# =============================================================================
+# 3. TRAIN MODEL
+# =============================================================================
+
+model = Pipeline([
+    ('scaler', StandardScaler()),
+    ('clf', LogisticRegression(
+        C=1.0,
+        solver='lbfgs',
+        class_weight='balanced',
+        random_state=42,
+        max_iter=1000
+    ))
+])
+
+# Cross-validation
+print("\n" + "="*60)
+print("CROSS-VALIDATION RESULTS")
+print("="*60)
+
+skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
+auc_scores = []
+acc_scores = []
+
+for fold, (train_idx, val_idx) in enumerate(skf.split(x, y), 1):
+    x_train, x_val = x.iloc[train_idx], x.iloc[val_idx]
+    y_train, y_val = y.iloc[train_idx], y.iloc[val_idx]
+    
+    model.fit(x_train, y_train)
+    y_pred = model.predict(x_val)
+    y_proba = model.predict_proba(x_val)[:, 1]
+    
+    auc = roc_auc_score(y_val, y_proba)
+    acc = accuracy_score(y_val, y_pred)
+    
+    auc_scores.append(auc)
+    acc_scores.append(acc)
+    print(f"Fold {fold}: Accuracy={acc:.4f}, ROC-AUC={auc:.4f}")
+
+print(f"\nAverage ROC-AUC: {np.mean(auc_scores):.4f} ± {np.std(auc_scores):.4f}")
+print(f"Average Accuracy: {np.mean(acc_scores):.4f} ± {np.std(acc_scores):.4f}")
+
+# Train final model
+final_model = model.fit(x, y)
+
+# =============================================================================
+# 4. SAVE MODEL AND PRACTICAL CONFIG
+# =============================================================================
+
+joblib.dump(final_model, "student_dropout_model.pkl")
+
+# Create a PRACTICAL config for the agent
+config = {
+    "model_name": "Student Dropout Predictor",
+    "version": "1.0",
+    "description": "Predicts if a student will dropout or graduate based on available data",
+    
+    "input_schema": {
+        "units_approved": {
+            "description": "Number of curricular units passed this semester",
+            "type": "integer",
+            "min": 0,
+            "max": 20,
+            "required": True,
+            "maps_to": "Curricular units 2nd sem (approved)"
+        },
+        "evaluations_taken": {
+            "description": "Number of evaluations/exams the student took",
+            "type": "integer",
+            "min": 0,
+            "max": 30,
+            "required": True,
+            "maps_to": "Curricular units 2nd sem (evaluations)"
+        },
+        "evaluations_missed": {
+            "description": "Number of evaluations the student missed/skipped",
+            "type": "integer",
+            "min": 0,
+            "max": 20,
+            "required": True,
+            "maps_to": "Curricular units 2nd sem (without evaluations)"
+        },
+        "tuition_paid": {
+            "description": "Is tuition up to date?",
+            "type": "boolean",
+            "required": True,
+            "maps_to": "Tuition fees up to date"
+        },
+        "has_scholarship": {
+            "description": "Does student have a scholarship?",
+            "type": "boolean",
+            "required": True,
+            "maps_to": "Scholarship holder"
+        },
+        "has_debt": {
+            "description": "Does student have outstanding debt?",
+            "type": "boolean",
+            "required": True,
+            "maps_to": "Debtor"
+        },
+        "gender": {
+            "description": "Student gender",
+            "type": "integer",
+            "values": {"0": "Female", "1": "Male"},
+            "required": True,
+            "maps_to": "Gender"
+        },
+        "age": {
+            "description": "Student's age at enrollment",
+            "type": "integer",
+            "min": 17,
+            "max": 70,
+            "required": True,
+            "maps_to": "Age at enrollment"
+        },
+        "is_daytime": {
+            "description": "Is student enrolled in daytime classes?",
+            "type": "boolean",
+            "required": True,
+            "maps_to": "Daytime/evening attendance"
+        },
+        "is_displaced": {
+            "description": "Is student displaced from home region?",
+            "type": "boolean",
+            "required": True,
+            "maps_to": "Displaced"
+        }
+    },
+    
+    "output_schema": {
+        "prediction": {
+            "type": "string",
+            "values": ["Dropout", "Graduate"]
+        },
+        "dropout_probability": {
+            "type": "float",
+            "min": 0,
+            "max": 1
+        },
+        "risk_level": {
+            "type": "string",
+            "values": ["LOW", "MEDIUM", "HIGH"]
+        }
+    },
+    
+    "feature_order": practical_features,
+    
+    "performance": {
+        "roc_auc": round(np.mean(auc_scores), 4),
+        "accuracy": round(np.mean(acc_scores), 4)
+    }
+}
+
+with open("model_config.json", 'w') as f:
+    json.dump(config, f, indent=2)
+
+print("\n" + "="*60)
+print("SAVED FILES")
+print("="*60)
+print("1. student_dropout_model.pkl")
+print("2. model_config.json")

dropout_binaryclass/student_dropout_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1596f03d2a2cdd1ba87fcdf2467aae71cfdc6d240de3363556051acf624d9f54
+size 3393