Skip to content

Commit 2d40df8

Browse files
authored
Merge pull request #92777 from j-martens/patch-698
Update how-to-configure-auto-train.md
2 parents facda06 + e067d6b commit 2d40df8

File tree

1 file changed

+13
-17
lines changed

1 file changed

+13
-17
lines changed

articles/machine-learning/service/how-to-configure-auto-train.md

Lines changed: 13 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -66,28 +66,24 @@ automl_config = AutoMLConfig(task = "classification")
6666

6767
## Data source and format
6868

69-
Automated machine learning supports data that resides on your local desktop or in the cloud such as Azure Blob Storage. The data can be read into a Pandas DataFrame or an Azure Machine Learning dataset. The following code examples demonstrate how to store the data in these formats. [Learn more about datatsets](https://github.com/MicrosoftDocs/azure-docs-pr/pull/how-to-create-register-datasets.md).
69+
Automated machine learning supports data that resides on your local desktop or in the cloud such as Azure Blob Storage. The data can be read into a **Pandas DataFrame** or an **Azure Machine Learning TabularDataset**. [Learn more about datatsets](https://github.com/MicrosoftDocs/azure-docs-pr/pull/how-to-create-register-datasets.md).
7070

71-
* TabularDataset
72-
* Pandas dataframe
73-
74-
>[!Important]
75-
> Requirements for training data:
76-
>* Data must be in tabular form.
77-
>* The value you want to predict (target column) must be present in the data.
71+
Requirements for training data:
72+
- Data must be in tabular form.
73+
- The value to predict, target column, must be in the data.
7874

79-
Examples:
75+
The following code examples demonstrate how to store the data in these formats.
8076

8177
* TabularDataset
82-
```python
83-
from azureml.core.dataset import Dataset
84-
85-
tabular_dataset = Dataset.Tabular.from_delimited_files("https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv")
86-
train_dataset, test_dataset = tabular_dataset.random_split(percentage = 0.1, seed = 42)
87-
label = "Label"
88-
```
78+
```python
79+
from azureml.core.dataset import Dataset
80+
81+
tabular_dataset = Dataset.Tabular.from_delimited_files("https://automldemods.blob.core.windows.net/datasets/PlayaEvents2016,_1.6MB,_3.4k-rows.cleaned.2.tsv")
82+
train_dataset, test_dataset = tabular_dataset.random_split(percentage = 0.1, seed = 42)
83+
label = "Label"
84+
```
8985

90-
* Pandas dataframe
86+
* Pandas dataframe
9187

9288
```python
9389
import pandas as pd

0 commit comments

Comments
 (0)