diff --git a/bootstrap/README.md b/bootstrap/README.md
index d5db8a62..027512bf 100644
--- a/bootstrap/README.md
+++ b/bootstrap/README.md
@@ -4,7 +4,7 @@ To use this existing project structure and scripts for your new ML project, you
Bootstrapping will prepare a directory structure for your project which includes:
-* renaming files and folders from the base project name `diabetes` to your project name
+* renaming files and folders from the base project name `diabetes_regression` to your project name
* fixing imports and absolute path based on your project name
* deleting and cleaning up some directories
diff --git a/diabetes_regression/training/test_train.py b/diabetes_regression/training/test_train.py
index d121ecbc..e1a79781 100644
--- a/diabetes_regression/training/test_train.py
+++ b/diabetes_regression/training/test_train.py
@@ -10,7 +10,7 @@ def test_train_model():
reg_model = train_model(data, {"alpha": 1.2})
preds = reg_model.predict([[1], [2]])
- np.testing.assert_equal(preds, [9.93939393939394, 9.03030303030303])
+ np.testing.assert_almost_equal(preds, [9.93939393939394, 9.03030303030303])
def test_get_model_metrics():
diff --git a/docs/custom_model.md b/docs/custom_model.md
index 6515bcbe..bce1fb8a 100644
--- a/docs/custom_model.md
+++ b/docs/custom_model.md
@@ -2,8 +2,8 @@
This document provides steps to follow when using this repository as a template to train models and deploy the models with real-time inference in Azure ML with your own scripts and data.
-1. Follow the MLOpsPython [Getting Started](https://github.com/microsoft/MLOpsPython/blob/master/docs/getting_started.md) guide
-1. Follow the MLOpsPython [bootstrap instructions](https://github.com/microsoft/MLOpsPython/blob/master/bootstrap/README.md) to create your project starting point
+1. Follow the MLOpsPython [Getting Started](getting_started.md) guide
+1. Follow the MLOpsPython [bootstrap instructions](../bootstrap/README.md) to create your project starting point
1. Configure training data
1. [If necessary] Convert your ML experimental code into production ready code
1. Replace the training code
@@ -13,11 +13,13 @@ This document provides steps to follow when using this repository as a template
## Follow the Getting Started guide
-Follow the [Getting Started](https://github.com/microsoft/MLOpsPython/blob/master/docs/getting_started.md) guide to set up the infrastructure and pipelines to execute MLOpsPython.
+Follow the [Getting Started](getting_started.md) guide to set up the infrastructure and pipelines to execute MLOpsPython.
+
+Take a look at the [Repo Details](code_description.md) document for a description of the structure of this repository.
## Follow the Bootstrap instructions
-The [Bootstrap from MLOpsPython repository](https://github.com/microsoft/MLOpsPython/blob/master/bootstrap/README.md) guide will help you to quickly prepare the repository for your project.
+The [Bootstrap from MLOpsPython repository](../bootstrap/README.md) guide will help you to quickly prepare the repository for your project.
**Note:** Since the bootstrap script will rename the `diabetes_regression` folder to the project name of your choice, we'll refer to your project as `[project name]` when paths are involved.
diff --git a/experimentation/Diabetes Ridge Regression Training.ipynb b/experimentation/Diabetes Ridge Regression Training.ipynb
index 5e507f96..fa192115 100644
--- a/experimentation/Diabetes Ridge Regression Training.ipynb
+++ b/experimentation/Diabetes Ridge Regression Training.ipynb
@@ -16,7 +16,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@@ -24,7 +24,8 @@
"from sklearn.linear_model import Ridge\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.model_selection import train_test_split\n",
- "import joblib"
+ "import joblib\n",
+ "import pandas as pd"
]
},
{
@@ -36,16 +37,21 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
- "X, y = load_diabetes(return_X_y=True)"
+ "sample_data = load_diabetes()\n",
+ "\n",
+ "df = pd.DataFrame(\n",
+ " data=sample_data.data,\n",
+ " columns=sample_data.feature_names)\n",
+ "df['Y'] = sample_data.target"
]
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -57,29 +63,12 @@
}
],
"source": [
- "print(X.shape)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "(442,)\n"
- ]
- }
- ],
- "source": [
- "print(y.shape)"
+ "print(df.shape)"
]
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -103,16 +92,17 @@
" \n",
" \n",
" \n",
" \n",
" \n",
- " 0 \n",
- " 1 \n",
- " 2 \n",
- " 3 \n",
- " 4 \n",
- " 5 \n",
- " 6 \n",
- " 7 \n",
- " 8 \n",
- " 9 \n",
+ " age \n",
+ " sex \n",
+ " bmi \n",
+ " bp \n",
+ " s1 \n",
+ " s2 \n",
+ " s3 \n",
+ " s4 \n",
+ " s5 \n",
+ " s6 \n",
+ " Y \n",
"