Upload 3 files
Browse files- README.md +30 -1
- ridge_model.pkl +3 -0
- tfidf_vectorizer.pkl +3 -0
README.md
CHANGED
@@ -1,3 +1,32 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- nlp
|
4 |
+
- regression
|
5 |
+
- tfidf
|
6 |
+
- ridge
|
7 |
+
- summaries
|
8 |
+
- kaggle
|
9 |
---
|
10 |
+
|
11 |
+
# 🧠 CommonLit Summary Scoring Model
|
12 |
+
|
13 |
+
This model was trained using the **CommonLit Evaluate Student Summaries** dataset on Kaggle.
|
14 |
+
It predicts two scores for student-written summaries:
|
15 |
+
|
16 |
+
- `content` → Idea coverage quality
|
17 |
+
- `wording` → Clarity and phrasing quality
|
18 |
+
|
19 |
+
Built with:
|
20 |
+
- TF-IDF vectorizer
|
21 |
+
- Ridge Regression (scikit-learn)
|
22 |
+
- MultiOutputRegressor wrapper
|
23 |
+
|
24 |
+
Example usage:
|
25 |
+
```python
|
26 |
+
from joblib import load
|
27 |
+
|
28 |
+
model = load("ridge_model.pkl")
|
29 |
+
tfidf = load("tfidf_vectorizer.pkl")
|
30 |
+
summary = "This text discusses..."
|
31 |
+
X = tfidf.transform([summary])
|
32 |
+
pred = model.predict(X)
|
ridge_model.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7847461d512d3a8c63cc88709507420f6cc6648046249b57a53fd50286d2774c
|
3 |
+
size 160856
|
tfidf_vectorizer.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cddd5f8a72d4fd3cab8a19bd7ff58a02bb1f7236d99c1417e156b9fcc9197bf
|
3 |
+
size 373282
|