Skip to content

Commit 0c932b0

Browse files
docs(KDP): improving some remaining docs
1 parent 45f8872 commit 0c932b0

File tree

5 files changed

+597
-108
lines changed

5 files changed

+597
-108
lines changed

docs/advanced/custom-preprocessing.md

Lines changed: 23 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
# 🛠️ Custom Preprocessing Pipelines
22

3-
<div class="feature-header">
4-
<div class="feature-title">
5-
<h2>Custom Preprocessing Pipelines</h2>
6-
<p>Create specialized preprocessing flows for your features with complete control over transformations</p>
3+
<div class="intro-container">
4+
<div class="intro-content">
5+
<h2>Create specialized preprocessing flows with complete control</h2>
6+
<p>Design custom transformations for your features when standard preprocessing doesn't meet your specific needs.</p>
77
</div>
88
</div>
99

@@ -13,37 +13,44 @@
1313
<p>KDP allows you to define custom preprocessing pipelines for your features, giving you complete control over how each feature is processed before being fed into your model. This is particularly useful when the standard preprocessing options don't meet your specific needs.</p>
1414
</div>
1515

16-
<div class="key-benefits">
17-
<div class="benefit-card">
18-
<span class="benefit-icon">🔍</span>
16+
## ✨ Key Benefits
17+
18+
<div class="grid-container">
19+
<div class="grid-item">
20+
<span class="feature-icon">🔍</span>
1921
<h3>Specific Transformations</h3>
2022
<p>Define custom preprocessing steps not covered by built-in options</p>
2123
</div>
22-
<div class="benefit-card">
23-
<span class="benefit-icon">🔄</span>
24+
<div class="grid-item">
25+
<span class="feature-icon">🔄</span>
2426
<h3>Combined Techniques</h3>
2527
<p>Combine multiple preprocessing techniques in a single pipeline</p>
2628
</div>
27-
<div class="benefit-card">
28-
<span class="benefit-icon">🧪</span>
29+
<div class="grid-item">
30+
<span class="feature-icon">🧪</span>
2931
<h3>Domain-Specific</h3>
3032
<p>Handle specialized data with custom preprocessing logic</p>
3133
</div>
32-
<div class="benefit-card">
33-
<span class="benefit-icon">🔬</span>
34+
<div class="grid-item">
35+
<span class="feature-icon">🔬</span>
3436
<h3>Novel Approaches</h3>
3537
<p>Experiment with new preprocessing methods</p>
3638
</div>
37-
<div class="benefit-card">
38-
<span class="benefit-icon">🧩</span>
39+
<div class="grid-item">
40+
<span class="feature-icon">🧩</span>
3941
<h3>Legacy Integration</h3>
4042
<p>Incorporate existing preprocessing logic</p>
4143
</div>
4244
</div>
4345

4446
## 🚀 Getting Started
4547

46-
<div class="code-container">
48+
<div class="step-card">
49+
<div class="step-header">
50+
<span class="step-number">1</span>
51+
<h3>Basic Example</h3>
52+
</div>
53+
<div class="code-container">
4754

4855
```python
4956
from kdp.features import NumericalFeature, FeatureType

docs/advanced/numerical-embeddings.md

Lines changed: 81 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,28 +1,82 @@
11
# 🔢 Advanced Numerical Embeddings
22

3-
> Transform raw numerical features into powerful representations for deep learning.
3+
<div class="intro-container">
4+
<div class="intro-content">
5+
<h2>Transform raw numerical features into powerful representations</h2>
6+
<p>Enhance your model's ability to learn from numerical data with KDP's sophisticated dual-branch embedding architecture.</p>
7+
</div>
8+
</div>
49

5-
## 📋 Overview
10+
## 📋 Architecture Overview
611

7-
**Advanced Numerical Embeddings** in KDP provide a sophisticated way to transform continuous numerical values into meaningful embeddings using a dual-branch architecture:
12+
<div class="architecture-container">
13+
<p><strong>Advanced Numerical Embeddings</strong> in KDP transform continuous values into meaningful embeddings using a dual-branch architecture:</p>
814

9-
1. **Continuous Branch**: Processes raw values through a small MLP for smooth pattern learning
10-
2. **Discrete Branch**: Discretizes values into learnable bins with trainable boundaries
15+
<div class="architecture-branches">
16+
<div class="branch-card">
17+
<div class="branch-header">
18+
<span class="branch-number">1</span>
19+
<h3>Continuous Branch</h3>
20+
</div>
21+
<p>Processes raw values through a small MLP for smooth pattern learning</p>
22+
</div>
1123

12-
The outputs from both branches are combined using a learnable gate mechanism, providing the perfect balance between continuous and discrete representations.
24+
<div class="branch-card">
25+
<div class="branch-header">
26+
<span class="branch-number">2</span>
27+
<h3>Discrete Branch</h3>
28+
</div>
29+
<p>Discretizes values into learnable bins with trainable boundaries</p>
30+
</div>
31+
</div>
1332

14-
### ✨ Key Benefits
33+
<p>The outputs from both branches are combined using a learnable gate mechanism, providing the perfect balance between continuous and discrete representations.</p>
34+
</div>
1535

16-
- **Dual-Branch Architecture**: Combines the best of both continuous and discrete processing
17-
- **Learnable Boundaries**: Adapts bin edges during training for optimal discretization
18-
- **Feature-Specific Processing**: Each feature gets its own specialized embedding
19-
- **Memory Efficient**: Optimized for handling large-scale tabular datasets
20-
- **Flexible Integration**: Works seamlessly with other KDP features
21-
- **Residual Connections**: Ensures stability during training
36+
## ✨ Key Benefits
37+
38+
<div class="grid-container">
39+
<div class="grid-item">
40+
<span class="feature-icon">🛠️</span>
41+
<h3>Dual-Branch Architecture</h3>
42+
<p>Combines the best of both continuous and discrete processing</p>
43+
</div>
44+
<div class="grid-item">
45+
<span class="feature-icon">📏</span>
46+
<h3>Learnable Boundaries</h3>
47+
<p>Adapts bin edges during training for optimal discretization</p>
48+
</div>
49+
<div class="grid-item">
50+
<span class="feature-icon">🎛️</span>
51+
<h3>Feature-Specific Processing</h3>
52+
<p>Each feature gets its own specialized embedding</p>
53+
</div>
54+
<div class="grid-item">
55+
<span class="feature-icon">💾</span>
56+
<h3>Memory Efficient</h3>
57+
<p>Optimized for handling large-scale tabular datasets</p>
58+
</div>
59+
<div class="grid-item">
60+
<span class="feature-icon">🔗</span>
61+
<h3>Flexible Integration</h3>
62+
<p>Works seamlessly with other KDP features</p>
63+
</div>
64+
<div class="grid-item">
65+
<span class="feature-icon">🔧</span>
66+
<h3>Residual Connections</h3>
67+
<p>Ensures stability during training</p>
68+
</div>
69+
</div>
2270

2371
## 🚀 Getting Started
2472

25-
### Basic Usage
73+
<div class="steps-container">
74+
<div class="step-card">
75+
<div class="step-header">
76+
<span class="step-number">1</span>
77+
<h3>Basic Usage</h3>
78+
</div>
79+
<div class="code-container">
2680

2781
```python
2882
from kdp import PreprocessingModel, FeatureType
@@ -44,7 +98,15 @@ preprocessor = PreprocessingModel(
4498
)
4599
```
46100

47-
### Advanced Configuration
101+
</div>
102+
</div>
103+
104+
<div class="step-card">
105+
<div class="step-header">
106+
<span class="step-number">2</span>
107+
<h3>Advanced Configuration</h3>
108+
</div>
109+
<div class="code-container">
48110

49111
```python
50112
from kdp import PreprocessingModel
@@ -84,6 +146,10 @@ preprocessor = PreprocessingModel(
84146
)
85147
```
86148

149+
</div>
150+
</div>
151+
</div>
152+
87153
## 🧠 How It Works
88154

89155
### Individual Feature Embeddings (`NumericalEmbedding`)

0 commit comments

Comments
 (0)