datarobot-feature-engineering

Name: datarobot-feature-engineering
Author: datarobot-oss

22stars19forks

How to install datarobot-feature-engineering?

datarobot-oss/datarobot-agent-skills/datarobot-feature-engineering

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-feature-engineering

Installs into the current project.

Summary

Guidance for feature engineering, feature discovery, feature importance analysis, and understanding DataRobot's automated feature engineering capabilities. Use when working with feature engineering, feature discovery, or analyzing feature importance in DataRobot.

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Feature Engineering Skill
2
3	This skill provides guidance for working with features in DataRobot, including understanding automated feature engineering, analyzing feature importance, and optimizing feature sets.
4
5	## Quick Start
6
7	Most common use case: Analyze feature importance for a model
8
9	1. Get feature importance: `get_feature_importance(model_id)` to get importance scores
10	2. Analyze top features: Sort by importance and identify key drivers
11	3. Export feature list: `export_feature_list(project_id)` to document features
12
13	Example: "Show me the top 10 most important features for model xyz123"
14
15	## When to use this skill
16
17	Use this skill when you need to:
18	- Understand what features DataRobot creates automatically
19	- Analyze feature importance for models
20	- Discover which features drive predictions
21	- Optimize feature sets for better performance
22	- Understand feature types and transformations
23	- Export feature lists and definitions
24
25	## Key capabilities
26
27	### 1. Feature Discovery
28
29	- Understand automated feature engineering in DataRobot
30	- Review derived features and transformations
31	- Identify feature types (numeric, categorical, text, date)
32	- Explore feature relationships and interactions
33
34	### 2. Feature Importance Analysis
35
36	- Get feature importance scores for models
37	- Understand which features drive predictions
38	- Compare feature importance across models
39	- Identify redundant or low-value features
40
41	### 3. Feature Optimization
42
43	- Select important features for model performance
44	- Remove low-importance features to reduce complexity
45	- Understand feature impact on predictions
46	- Optimize feature sets for deployment
47
48	### 4. Feature Documentation
49
50	- Export feature lists and definitions
51	- Document feature transformations
52	- Understand feature derivation logic
53	- Share feature information with stakeholders
54
55	## Workflow examples
56
57	### Example 1: Analyze feature importance
58
59	User request: "Show me the top 10 most important features for model xyz123 and explain what they mean."
60
61	Agent workflow:
62	1. Get feature importance scores for the model
63	2. Sort features by importance (descending)
64	3. Get top 10 features with their scores
65	4. Retrieve feature metadata and descriptions
66	5. Explain what each feature represents and why it's important
67	6. Provide insights on feature relationships
68
69	### Example 2: Optimize feature set for deployment
70
71	User request: "Create a simplified feature set for deployment abc123, keeping only features with importance > 0.1."
72
73	Agent workflow:
74	1. Get feature importance for the deployed model
75	2. Filter features by importance threshold (> 0.1)
76	3. Verify filtered features are sufficient for predictions
77	4. Document the optimized feature set
78	5. Update deployment configuration if needed
79
80	## Using DataRobot SDK
81
82	This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
83
84	```bash
85	pip install datarobot
86	```
87
88	### Key SDK Operations
89
90	Use these DataRobot SDK methods for feature analysis:
91
92	Feature Information:
93	- `model.get_features()` - List all features in a model
94	- `model.get_feature_impact()` - Get feature importance scores
95	- `project.get_features()` - List features in a project
96
97	Feature Analysis:
98	- `feature.name` - Feature name
99	- `feature.feature_type` - Feature type (Numeric, Categorical, etc.)
100	- `feature.importance` - Feature importance score
101
102	See the [Common Patterns](#common-patterns) section below for complete examples.
103
104	## Best practices
105
106	1. Review automated features: DataRobot creates many derived features automatically - review them
107	2. Focus on important features: Pay attention to high-importance features for insights
108	3. Understand feature types: Different feature types require different handling
109	4. Feature documentation: Document important features for stakeholders
110	5. Feature selection: Consider removing very low-importance features for simplicity
111	6. Feature stability: Consider feature stability over time, not just importance
112
113	## Common patterns
114
115	### Pattern 1: Feature importance analysis
116	```python
117	import datarobot as dr
118	import os
119
120	# Initialize client
121	client = dr.Client(
122	token=os.getenv("DATAROBOT_API_TOKEN"),
123	endpoint=os.getenv("DATAROBOT_ENDPOINT")
124	)
125
126	# Get model and feature importance
127	model = dr.Model.get("xyz123")
128	feature_impact = model.get_feature_impact()
129
130	# Sort by importance
131	sorted_features = sorted(
132	feature_impact,
133	key=lambda x: x.get('impactNormalized', 0),
134	reverse=True
135	)
136
137	# Get top 10 features
138	top_features = sorted_features[:10]
139	for feature in top_features:
140	print(f"{feature['featureName']}: {feature.get('impactNormalized', 0):.3f}")
141	```
142
143	### Pattern 2: Feature filteri

People who liked this also viewed

6 picks

Type

datarobot-feature-engineering

22stars19forks

View on GitHub

How to install datarobot-feature-engineering?

datarobot-oss/datarobot-agent-skills/datarobot-feature-engineering

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-feature-engineering

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Feature Engineering Skill
2
3	This skill provides guidance for working with features in DataRobot, including understanding automated feature engineering, analyzing feature importance, and optimizing feature sets.
4
5	## Quick Start
6
7	Most common use case: Analyze feature importance for a model
8
9	1. Get feature importance: `get_feature_importance(model_id)` to get importance scores
10	2. Analyze top features: Sort by importance and identify key drivers
11	3. Export feature list: `export_feature_list(project_id)` to document features
12
13	Example: "Show me the top 10 most important features for model xyz123"
14
15	## When to use this skill
16
17	Use this skill when you need to:
18	- Understand what features DataRobot creates automatically
19	- Analyze feature importance for models
20	- Discover which features drive predictions
21	- Optimize feature sets for better performance
22	- Understand feature types and transformations
23	- Export feature lists and definitions
24
25	## Key capabilities
26
27	### 1. Feature Discovery
28
29	- Understand automated feature engineering in DataRobot
30	- Review derived features and transformations
31	- Identify feature types (numeric, categorical, text, date)
32	- Explore feature relationships and interactions
33
34	### 2. Feature Importance Analysis
35
36	- Get feature importance scores for models
37	- Understand which features drive predictions
38	- Compare feature importance across models
39	- Identify redundant or low-value features
40
41	### 3. Feature Optimization
42
43	- Select important features for model performance
44	- Remove low-importance features to reduce complexity
45	- Understand feature impact on predictions
46	- Optimize feature sets for deployment
47
48	### 4. Feature Documentation
49
50	- Export feature lists and definitions
51	- Document feature transformations
52	- Understand feature derivation logic
53	- Share feature information with stakeholders
54
55	## Workflow examples
56
57	### Example 1: Analyze feature importance
58
59	User request: "Show me the top 10 most important features for model xyz123 and explain what they mean."
60
61	Agent workflow:
62	1. Get feature importance scores for the model
63	2. Sort features by importance (descending)
64	3. Get top 10 features with their scores
65	4. Retrieve feature metadata and descriptions
66	5. Explain what each feature represents and why it's important
67	6. Provide insights on feature relationships
68
69	### Example 2: Optimize feature set for deployment
70
71	User request: "Create a simplified feature set for deployment abc123, keeping only features with importance > 0.1."
72
73	Agent workflow:
74	1. Get feature importance for the deployed model
75	2. Filter features by importance threshold (> 0.1)
76	3. Verify filtered features are sufficient for predictions
77	4. Document the optimized feature set
78	5. Update deployment configuration if needed
79
80	## Using DataRobot SDK
81
82	This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
83
84	```bash
85	pip install datarobot
86	```
87
88	### Key SDK Operations
89
90	Use these DataRobot SDK methods for feature analysis:
91
92	Feature Information:
93	- `model.get_features()` - List all features in a model
94	- `model.get_feature_impact()` - Get feature importance scores
95	- `project.get_features()` - List features in a project
96
97	Feature Analysis:
98	- `feature.name` - Feature name
99	- `feature.feature_type` - Feature type (Numeric, Categorical, etc.)
100	- `feature.importance` - Feature importance score
101
102	See the [Common Patterns](#common-patterns) section below for complete examples.
103
104	## Best practices
105
106	1. Review automated features: DataRobot creates many derived features automatically - review them
107	2. Focus on important features: Pay attention to high-importance features for insights
108	3. Understand feature types: Different feature types require different handling
109	4. Feature documentation: Document important features for stakeholders
110	5. Feature selection: Consider removing very low-importance features for simplicity
111	6. Feature stability: Consider feature stability over time, not just importance
112
113	## Common patterns
114
115	### Pattern 1: Feature importance analysis
116	```python
117	import datarobot as dr
118	import os
119
120	# Initialize client
121	client = dr.Client(
122	token=os.getenv("DATAROBOT_API_TOKEN"),
123	endpoint=os.getenv("DATAROBOT_ENDPOINT")
124	)
125
126	# Get model and feature importance
127	model = dr.Model.get("xyz123")
128	feature_impact = model.get_feature_impact()
129
130	# Sort by importance
131	sorted_features = sorted(
132	feature_impact,
133	key=lambda x: x.get('impactNormalized', 0),
134	reverse=True
135	)
136
137	# Get top 10 features
138	top_features = sorted_features[:10]
139	for feature in top_features:
140	print(f"{feature['featureName']}: {feature.get('impactNormalized', 0):.3f}")
141	```
142
143	### Pattern 2: Feature filteri

People who liked this also viewed

6 picks

Type