add widget
Browse files
README.md
CHANGED
|
@@ -1,14 +1,52 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
---
|
| 4 |
-
|
| 5 |
-
---
|
| 6 |
tags:
|
| 7 |
- tabular-classification
|
| 8 |
- sklearn
|
| 9 |
datasets:
|
| 10 |
-
- wine-quality
|
| 11 |
- imodels/compas-recidivism
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
|
|
@@ -31,14 +69,6 @@ X_test = df.drop(columns=['is_recid'])
|
|
| 31 |
y_test = df['is_recid'].values
|
| 32 |
```
|
| 33 |
|
| 34 |
-
### Load the model
|
| 35 |
-
## Wine Quality classification
|
| 36 |
-
|
| 37 |
-
### A Simple Example of Scikit-learn Pipeline
|
| 38 |
-
|
| 39 |
-
> Inspired by https://towardsdatascience.com/a-simple-example-of-pipeline-in-machine-learning-with-scikit-learn-e726ffbb6976 by Saptashwa Bhattacharyya
|
| 40 |
-
|
| 41 |
-
|
| 42 |
### Load the model
|
| 43 |
|
| 44 |
```python
|
|
@@ -61,4 +91,5 @@ model = joblib.load(cached_download(
|
|
| 61 |
```
|
| 62 |
preds = model.predict(X_test)
|
| 63 |
print('accuracy', np.mean(preds==y_test))
|
|
|
|
| 64 |
```
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- tabular-classification
|
| 5 |
- sklearn
|
| 6 |
datasets:
|
|
|
|
| 7 |
- imodels/compas-recidivism
|
| 8 |
+
widget:
|
| 9 |
+
structuredData:
|
| 10 |
+
age:
|
| 11 |
+
- 40.0
|
| 12 |
+
priors_count:
|
| 13 |
+
- 0.0
|
| 14 |
+
days_b_screening_arrest:
|
| 15 |
+
- -1.0
|
| 16 |
+
c_jail_time:
|
| 17 |
+
- 0.0
|
| 18 |
+
juv_fel_count:
|
| 19 |
+
- 0.0
|
| 20 |
+
juv_other_count:
|
| 21 |
+
- 0.0
|
| 22 |
+
juv_misd_count:
|
| 23 |
+
- 0.0
|
| 24 |
+
c_charge_degree:F:
|
| 25 |
+
- 0.0
|
| 26 |
+
c_charge_degree:M:
|
| 27 |
+
- 1.0
|
| 28 |
+
race:African-American:
|
| 29 |
+
- 0.0
|
| 30 |
+
race:Asian:
|
| 31 |
+
- 0.0
|
| 32 |
+
race:Caucasian:
|
| 33 |
+
- 1.0
|
| 34 |
+
race:Hispanic:
|
| 35 |
+
- 0.0
|
| 36 |
+
race:Native_American:
|
| 37 |
+
- 0.0
|
| 38 |
+
race:Other:
|
| 39 |
+
- 0.0
|
| 40 |
+
age_cat:25_-_45:
|
| 41 |
+
- 1.0
|
| 42 |
+
age_cat:Greater_than_45:
|
| 43 |
+
- 0.0
|
| 44 |
+
age_cat:Less_than_25:
|
| 45 |
+
- 0.0
|
| 46 |
+
sex:Female:
|
| 47 |
+
- 0.0
|
| 48 |
+
sex:Male:
|
| 49 |
+
- 1.0
|
| 50 |
---
|
| 51 |
|
| 52 |
|
|
|
|
| 69 |
y_test = df['is_recid'].values
|
| 70 |
```
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
### Load the model
|
| 73 |
|
| 74 |
```python
|
|
|
|
| 91 |
```
|
| 92 |
preds = model.predict(X_test)
|
| 93 |
print('accuracy', np.mean(preds==y_test))
|
| 94 |
+
# accuracy 0.6759165485112416
|
| 95 |
```
|