Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+language:
+  - en
+tags:
+  - text-classification
+  - cognitive-distortion
+  - mental-health
+  - cbt
+---
+
+# CBT Cognitive Distortion Classifier
+
+Classifies text into cognitive distortion groups for CBT therapy applications.
+
+## Model Details
+
+- **Best Model**: SVM
+- **Model Type**: Traditional ML
+- **Classes**: 5 distortion groups
+
+## Performance
+
+| Metric | Clean Data | Real-World |
+|--------|------------|------------|
+| Accuracy | 0.4125 | 0.3250 |
+| F1 Score | 0.4107 | 0.3208 |
+
+## Distortion Groups
+
+| Group | Distortions | Treatment |
+|-------|-------------|-----------||
+| G0 | No Distortion | Supportive listening |
+| G1 | All-or-nothing, Labeling | Gradient restructuring |
+| G2 | Overgeneralization, Mind Reading, Fortune-telling | Evidence testing |
+| G3 | Mental filter, Magnification | Attention rebalancing |
+| G4 | Emotional Reasoning, Personalization, Should statements | Metacognitive distancing |
+
+## All Models Compared (Real-World F1)
+
+| Model | Accuracy | F1 Score |
+|-------|----------|----------|
+| SVM | 0.3250 | 0.3208 |
+| Logistic Regression | 0.2781 | 0.2647 |
+| Random Forest | 0.2781 | 0.2615 |
+| XGBoost | 0.2188 | 0.2099 |
+| TinyBERT | 0.2500 | 0.1997 |
+
+## Usage
+
+See config.json for model type and loading instructions.
+
+## Disclaimer
+
+For educational and supportive purposes only. Not a substitute for professional mental health care.

config.json

@@ -0,0 +1,109 @@
+{
+  "model_type": "SVM",
+  "is_transformer": false,
+  "num_labels": 5,
+  "label_mapping": {
+    "G0_No_Distortion": 0,
+    "G1_Gradient_Restructuring": 1,
+    "G2_Evidence_Testing": 2,
+    "G3_Attention_Rebalancing": 3,
+    "G4_Metacognitive_Distancing": 4
+  },
+  "id_to_label": {
+    "0": "G0_No_Distortion",
+    "1": "G1_Gradient_Restructuring",
+    "2": "G2_Evidence_Testing",
+    "3": "G3_Attention_Rebalancing",
+    "4": "G4_Metacognitive_Distancing"
+  },
+  "accuracy_clean": 0.4125,
+  "f1_clean": 0.4107350537733271,
+  "accuracy_realworld": 0.325,
+  "f1_realworld": 0.3207581458641578,
+  "groups": {
+    "G0_No_Distortion": {
+      "name": "No Distortion",
+      "treatment": "Supportive listening"
+    },
+    "G1_Gradient_Restructuring": {
+      "name": "Gradient Restructuring",
+      "distortions": [
+        "All-or-nothing",
+        "Labeling"
+      ],
+      "treatment": "Spectrum thinking"
+    },
+    "G2_Evidence_Testing": {
+      "name": "Evidence Testing",
+      "distortions": [
+        "Overgeneralization",
+        "Mind Reading",
+        "Fortune-telling"
+      ],
+      "treatment": "Challenge with evidence"
+    },
+    "G3_Attention_Rebalancing": {
+      "name": "Attention Rebalancing",
+      "distortions": [
+        "Mental filter",
+        "Magnification"
+      ],
+      "treatment": "See full picture"
+    },
+    "G4_Metacognitive_Distancing": {
+      "name": "Metacognitive Distancing",
+      "distortions": [
+        "Emotional Reasoning",
+        "Personalization",
+        "Should statements"
+      ],
+      "treatment": "Observe thoughts objectively"
+    }
+  },
+  "all_model_results": {
+    "clean": {
+      "Logistic Regression": {
+        "accuracy": 0.4375,
+        "f1": 0.4339342742940156
+      },
+      "SVM": {
+        "accuracy": 0.4125,
+        "f1": 0.4107350537733271
+      },
+      "Random Forest": {
+        "accuracy": 0.35625,
+        "f1": 0.34116718928806056
+      },
+      "XGBoost": {
+        "accuracy": 0.340625,
+        "f1": 0.33509732163919337
+      },
+      "TinyBERT": {
+        "accuracy": 0.603125,
+        "f1": 0.6012083383624693
+      }
+    },
+    "realworld": {
+      "Logistic Regression": {
+        "accuracy": 0.278125,
+        "f1": 0.2647432278367442
+      },
+      "SVM": {
+        "accuracy": 0.325,
+        "f1": 0.3207581458641578
+      },
+      "Random Forest": {
+        "accuracy": 0.278125,
+        "f1": 0.2614757594604754
+      },
+      "XGBoost": {
+        "accuracy": 0.21875,
+        "f1": 0.20994533926416956
+      },
+      "TinyBERT": {
+        "accuracy": 0.25,
+        "f1": 0.19974747542329035
+      }
+    }
+  }
+}

label_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de01416fa91ba92e79d9c86bd9f455e7d37bfa9919d3954f9aec37b08bc0673
+size 369

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16bdd4767f22a1a4ebbb8c5331114f5d596b7978eea38a6b0ada8c1f16459b8
+size 256462

stopwords.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adf4e8a08be04a2bb4cfefdacb276b81eedee8be59fb765738d7aece569835a
+size 2817

tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d4d9e29ce0014508f68ef1881c1e156a5890e0dd816f1a79c6865ff8cd235f
+size 88784