0
# Data Analysis
1

2
Tools for understanding dataset characteristics and feature distributions to inform model selection and feature engineering decisions.
3

4
## Capabilities
5

6
### Class Distribution Analysis
7

8
Analyzes class distributions in classification datasets to identify imbalances and understand target variable characteristics.
9

10
```python { .api }
11
class ClassHistogram:
12
    def __init__(self, feature_names=None, **kwargs):
13
        """
14
        Class distribution analyzer.
15
        
16
        Parameters:
17
            feature_names (list, optional): Names for features
18
            **kwargs: Additional arguments
19
        """
20
    
21
    def explain_data(self, X, y, name=None):
22
        """
23
        Analyze class distributions in the dataset.
24
        
25
        Parameters:
26
            X (array-like): Feature data
27
            y (array-like): Target labels
28
            name (str, optional): Name for explanation
29
            
30
        Returns:
31
            Explanation object with class distribution analysis
32
        """
33
```
34

35
### Marginal Distribution Analysis
36

37
Analyzes marginal distributions of features to understand data characteristics and identify potential issues.
38

39
```python { .api }
40
class Marginal:
41
    def __init__(self, feature_names=None, feature_types=None, **kwargs):
42
        """
43
        Marginal distribution analyzer.
44
        
45
        Parameters:
46
            feature_names (list, optional): Names for features
47
            feature_types (list, optional): Types for features
48
            **kwargs: Additional arguments
49
        """
50
    
51
    def explain_data(self, X, y=None, name=None):
52
        """
53
        Analyze marginal feature distributions.
54
        
55
        Parameters:
56
            X (array-like): Feature data
57
            y (array-like, optional): Target labels
58
            name (str, optional): Name for explanation
59
            
60
        Returns:
61
            Explanation object with marginal distribution analysis
62
        """
63
```
64

65
## Usage Examples
66

67
```python
68
from interpret.data import ClassHistogram, Marginal
69
from interpret import show
70
from sklearn.datasets import load_wine
71

72
# Load dataset
73
data = load_wine()
74
X, y = data.data, data.target
75

76
# Analyze class distribution
77
class_hist = ClassHistogram(feature_names=data.feature_names)
78
class_exp = class_hist.explain_data(X, y, name="Class Distribution")
79
show(class_exp)
80

81
# Analyze feature distributions
82
marginal = Marginal(feature_names=data.feature_names)
83
marginal_exp = marginal.explain_data(X, y, name="Feature Distributions")
84
show(marginal_exp)
85
```