datarobot-data-preparation

Name: datarobot-data-preparation
Author: datarobot-oss

22stars19forks

How to install datarobot-data-preparation?

datarobot-oss/datarobot-agent-skills/datarobot-data-preparation

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-data-preparation

Installs into the current project.

Summary

Tools and guidance for data upload, dataset management, data validation, and preparing data for DataRobot projects. Use when uploading datasets, managing data, or validating data for DataRobot.

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Data Preparation Skill
2
3	This skill provides guidance for preparing and managing data in DataRobot, including uploading datasets, validating data quality, and managing dataset versions.
4
5	## Quick Start
6
7	Most common use case: Upload and validate a dataset
8
9	1. Upload dataset: `upload_dataset(file_path, dataset_name)` to upload data
10	2. Validate data: `validate_dataset(dataset_id)` to check data quality
11	3. Check schema: `get_dataset_schema(dataset_id)` to review structure
12
13	Example: "Upload sales_data.csv and check if it's ready for training"
14
15	## When to use this skill
16
17	Use this skill when you need to:
18	- Upload datasets to DataRobot
19	- Validate data before project creation
20	- Manage dataset versions and updates
21	- Check data quality and completeness
22	- Prepare data for training or predictions
23	- Handle data format conversions
24	- Connect to external data sources
25
26	## Key capabilities
27
28	### 1. Dataset Upload
29
30	- Upload CSV, Parquet, and other file formats
31	- Connect to databases and data warehouses
32	- Handle large datasets efficiently
33	- Manage dataset metadata and descriptions
34
35	### 2. Data Validation
36
37	- Validate data formats and schemas
38	- Check for missing values and data quality issues
39	- Verify column types and formats
40	- Identify potential data problems
41
42	### 3. Dataset Management
43
44	- List and search datasets
45	- Update dataset metadata
46	- Create dataset versions
47	- Delete or archive old datasets
48
49	### 4. Data Preparation
50
51	- Clean and preprocess data
52	- Handle missing values
53	- Format data for DataRobot requirements
54	- Prepare prediction datasets
55
56	## Workflow examples
57
58	### Example 1: Upload and validate dataset
59
60	User request: "Upload my sales_data.csv file and check if it's ready for training."
61
62	Agent workflow:
63	1. Upload the CSV file to DataRobot
64	2. Validate the dataset structure and format
65	3. Check for missing values and data quality issues
66	4. Verify column types are appropriate
67	5. Check for potential issues (leakage, formatting)
68	6. Report validation results and recommendations
69
70	### Example 2: Prepare prediction dataset
71
72	User request: "Prepare a prediction dataset based on the training data structure from project abc123."
73
74	Agent workflow:
75	1. Get the training dataset structure from the project
76	2. Identify required columns and data types
77	3. Create a template with the same structure
78	4. Validate the template matches requirements
79	5. Provide guidance on filling in prediction values
80
81	## Using DataRobot SDK
82
83	This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
84
85	```bash
86	pip install datarobot
87	```
88
89	### Key SDK Operations
90
91	Use these DataRobot SDK methods for data management:
92
93	Dataset Operations:
94	- `dr.Dataset.create_from_file(file_path, name)` - Upload dataset
95	- `dr.Dataset.get(dataset_id)` - Get dataset details
96	- `dr.Dataset.list()` - List all datasets
97	- `dataset.row_count` - Get row count
98	- `dataset.column_count` - Get column count
99
100	Dataset Information:
101	- `dataset.name` - Dataset name
102	- `dataset.id` - Dataset ID
103	- `dataset.created_at` - Creation timestamp
104
105	See the [Common Patterns](#common-patterns) section below for complete examples.
106
107	## Helper Scripts
108
109	This skill includes executable helper scripts that Claude can run directly:
110
111	- `scripts/upload_dataset.py` - Upload a dataset file to DataRobot
112
113	Usage example:
114	```bash
115	# Upload dataset
116	python scripts/upload_dataset.py sales_data.csv "Sales Data Q4 2024"
117	```
118
119	Claude can run this script directly or use it as reference when writing code.
120
121	## Best practices
122
123	1. Data quality: Clean and validate data before upload
124	2. File formats: Use appropriate formats (CSV for small, Parquet for large)
125	3. Naming conventions: Use clear, descriptive dataset names
126	4. Metadata: Add descriptions and tags for better organization
127	5. Versioning: Create versions for important datasets
128	6. Data validation: Always validate data before using in projects
129
130	## Common patterns
131
132	### Pattern 1: Upload and validate
133	```python
134	import datarobot as dr
135	import os
136
137	# Initialize client
138	client = dr.Client(
139	token=os.getenv("DATAROBOT_API_TOKEN"),
140	endpoint=os.getenv("DATAROBOT_ENDPOINT")
141	)
142
143	# Upload dataset
144	dataset = dr.Dataset.create_from_file(
145	file_path="sales_data.csv",
146	name="Sales Data Q4 2024"
147	)
148
149	print(f"Dataset ID: {dataset.id}")
150	print(f"Rows: {dataset.row_count}, Columns: {dataset.column_count}")
151
152	# Get dataset details
153	dataset_info = dr.Dataset.get(dataset.id)
154	print(f"Dataset name: {dataset_info.name}")
155	print(f"Created: {dataset_info.created_at}")
156	```
157
158	### Pattern 2: Dataset management
159	```python
160	import datarobot as dr
161
162	# List all datasets
163	datasets = dr.Dataset.list()
164	print(f"Found {len(datasets)} datasets")
165
166	# Search for specific dataset
167	for dataset in dat

People who liked this also viewed

6 picks

Type

datarobot-data-preparation

22stars19forks

View on GitHub

How to install datarobot-data-preparation?

datarobot-oss/datarobot-agent-skills/datarobot-data-preparation

$npx -y skills add datarobot-oss/datarobot-agent-skills --skill datarobot-data-preparation

Installs into the current project.

Summary

Tools and guidance for data upload, dataset management, data validation, and preparing data for DataRobot projects. Use when uploading datasets, managing data, or validating data for DataRobot.

Files · 1

View on GitHub

SKILL.md

1	# DataRobot Data Preparation Skill
2
3	This skill provides guidance for preparing and managing data in DataRobot, including uploading datasets, validating data quality, and managing dataset versions.
4
5	## Quick Start
6
7	Most common use case: Upload and validate a dataset
8
9	1. Upload dataset: `upload_dataset(file_path, dataset_name)` to upload data
10	2. Validate data: `validate_dataset(dataset_id)` to check data quality
11	3. Check schema: `get_dataset_schema(dataset_id)` to review structure
12
13	Example: "Upload sales_data.csv and check if it's ready for training"
14
15	## When to use this skill
16
17	Use this skill when you need to:
18	- Upload datasets to DataRobot
19	- Validate data before project creation
20	- Manage dataset versions and updates
21	- Check data quality and completeness
22	- Prepare data for training or predictions
23	- Handle data format conversions
24	- Connect to external data sources
25
26	## Key capabilities
27
28	### 1. Dataset Upload
29
30	- Upload CSV, Parquet, and other file formats
31	- Connect to databases and data warehouses
32	- Handle large datasets efficiently
33	- Manage dataset metadata and descriptions
34
35	### 2. Data Validation
36
37	- Validate data formats and schemas
38	- Check for missing values and data quality issues
39	- Verify column types and formats
40	- Identify potential data problems
41
42	### 3. Dataset Management
43
44	- List and search datasets
45	- Update dataset metadata
46	- Create dataset versions
47	- Delete or archive old datasets
48
49	### 4. Data Preparation
50
51	- Clean and preprocess data
52	- Handle missing values
53	- Format data for DataRobot requirements
54	- Prepare prediction datasets
55
56	## Workflow examples
57
58	### Example 1: Upload and validate dataset
59
60	User request: "Upload my sales_data.csv file and check if it's ready for training."
61
62	Agent workflow:
63	1. Upload the CSV file to DataRobot
64	2. Validate the dataset structure and format
65	3. Check for missing values and data quality issues
66	4. Verify column types are appropriate
67	5. Check for potential issues (leakage, formatting)
68	6. Report validation results and recommendations
69
70	### Example 2: Prepare prediction dataset
71
72	User request: "Prepare a prediction dataset based on the training data structure from project abc123."
73
74	Agent workflow:
75	1. Get the training dataset structure from the project
76	2. Identify required columns and data types
77	3. Create a template with the same structure
78	4. Validate the template matches requirements
79	5. Provide guidance on filling in prediction values
80
81	## Using DataRobot SDK
82
83	This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
84
85	```bash
86	pip install datarobot
87	```
88
89	### Key SDK Operations
90
91	Use these DataRobot SDK methods for data management:
92
93	Dataset Operations:
94	- `dr.Dataset.create_from_file(file_path, name)` - Upload dataset
95	- `dr.Dataset.get(dataset_id)` - Get dataset details
96	- `dr.Dataset.list()` - List all datasets
97	- `dataset.row_count` - Get row count
98	- `dataset.column_count` - Get column count
99
100	Dataset Information:
101	- `dataset.name` - Dataset name
102	- `dataset.id` - Dataset ID
103	- `dataset.created_at` - Creation timestamp
104
105	See the [Common Patterns](#common-patterns) section below for complete examples.
106
107	## Helper Scripts
108
109	This skill includes executable helper scripts that Claude can run directly:
110
111	- `scripts/upload_dataset.py` - Upload a dataset file to DataRobot
112
113	Usage example:
114	```bash
115	# Upload dataset
116	python scripts/upload_dataset.py sales_data.csv "Sales Data Q4 2024"
117	```
118
119	Claude can run this script directly or use it as reference when writing code.
120
121	## Best practices
122
123	1. Data quality: Clean and validate data before upload
124	2. File formats: Use appropriate formats (CSV for small, Parquet for large)
125	3. Naming conventions: Use clear, descriptive dataset names
126	4. Metadata: Add descriptions and tags for better organization
127	5. Versioning: Create versions for important datasets
128	6. Data validation: Always validate data before using in projects
129
130	## Common patterns
131
132	### Pattern 1: Upload and validate
133	```python
134	import datarobot as dr
135	import os
136
137	# Initialize client
138	client = dr.Client(
139	token=os.getenv("DATAROBOT_API_TOKEN"),
140	endpoint=os.getenv("DATAROBOT_ENDPOINT")
141	)
142
143	# Upload dataset
144	dataset = dr.Dataset.create_from_file(
145	file_path="sales_data.csv",
146	name="Sales Data Q4 2024"
147	)
148
149	print(f"Dataset ID: {dataset.id}")
150	print(f"Rows: {dataset.row_count}, Columns: {dataset.column_count}")
151
152	# Get dataset details
153	dataset_info = dr.Dataset.get(dataset.id)
154	print(f"Dataset name: {dataset_info.name}")
155	print(f"Created: {dataset_info.created_at}")
156	```
157
158	### Pattern 2: Dataset management
159	```python
160	import datarobot as dr
161
162	# List all datasets
163	datasets = dr.Dataset.list()
164	print(f"Found {len(datasets)} datasets")
165
166	# Search for specific dataset
167	for dataset in dat

People who liked this also viewed

6 picks

Type