---
language: en
license: mit
tags:
- regression
- xgboost
- soulprint
- imani
datasets:
- custom
metrics:
- mse
- r2
model-index:
- name: Imani XGBoost Regression Model
  results:
  - task:
      type: regression
      name: Soulprint Archetype Scoring
    dataset:
      name: Imani-regression-data
      type: custom
    metrics:
    - name: MSE
      type: mse
      value: 0.00866
    - name: R²
      type: r2
      value: 0.892
---

# 🕊️ Imani XGBoost Regression Model

This model is part of the **Soulprint archetype system**, designed to measure the presence of the **Imani (Faithful)** archetype in text.  
It outputs a **score between 0.0 and 1.0** that reflects the degree of *faith, resilience, and affirmation* expressed.

- **Framework:** XGBoost  
- **Embeddings:** SentenceTransformer (`all-mpnet-base-v2`)  
- **Training Data Size:** 819 samples  
- **Balanced dataset:** Low, mid, and high Imani scores evenly distributed (~33% each)  

---

## 🧾 Model Details

- **Archetype:** Imani (Faithful)  
- **Description:** Sacred conviction and hope, even in adversity.  
- **Traits captured:** Encouraging, spiritual, consistent, compassionate.  
- **Perspective:** *Faith is the seed, action is the rain.*  
- **Output range:** `0.0 – 1.0`  

---

## 📊 Training Results

- **MSE:** `0.00866`  
- **R²:** `0.892`  

These metrics indicate that the model is highly accurate, with predictions averaging less than `0.1` away from true labels on the 0–1 scale.

---

## 🚀 Usage

You can load the model directly from Hugging Face Hub and run predictions:

```python
import xgboost as xgb
from sentence_transformers import SentenceTransformer
from huggingface_hub import hf_hub_download

# -----------------------------
# 1. Download model from Hugging Face
# -----------------------------
REPO_ID = "mjpsm/Imani-xgb-model"
FILENAME = "Imani_xgb_model.json"

model_path = hf_hub_download(repo_id=REPO_ID, filename=FILENAME)

# -----------------------------
# 2. Load Model + Embedder
# -----------------------------
model = xgb.XGBRegressor()
model.load_model(model_path)

embedder = SentenceTransformer("all-mpnet-base-v2")

# -----------------------------
# 3. Example Prediction
# -----------------------------
text = "I reminded my cousin that storms always pass."
embedding = embedder.encode([text])
score = model.predict(embedding)[0]

print("Predicted Imani Score:", round(float(score), 3))
```