Update vineyard notebook

Signed-off-by: trafalgarzzz <trafalgarz@outlook.com>

Author: TrafalgarZZZ

examples/03_dataflow_with_vineyard/vineyard.ipynb

@@ -63,12 +63,50 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": [
+    "%pip install oss2 numpy pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"OSS_ACCESS_KEY_ID\"] = \"<YOUR_ACCESS_KEY>\"\n",
+    "os.environ[\"OSS_ACCESS_KEY_SECRET\"] = \"<YOUR_ACCESS_SECRET>\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "DataFrame initialized.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<oss2.models.PutObjectResult at 0x7f8e7b9b1de0>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "import pandas as pd\n",
     "\n",
-    "# 生成大小约为22G的dataframe\n",
-    "num_rows = 6000 * 10000\n",
+    "# Fake data\n",
+    "num_rows = 600 * 1000\n",
     "df = pd.DataFrame({\n",
     "    'Id': np.random.randint(1, 100000, num_rows),\n",
     "    'MSSubClass': np.random.randint(20, 201, size=num_rows),\n",
@@ -118,13 +156,15 @@
     "    'SalePrice': np.random.randint(50000, 800001, num_rows),\n",
     "})\n",
     "\n",
+    "print(\"DataFrame initialized.\")\n",
+    "\n",
     "import oss2\n",
     "import io\n",
     "from oss2.credentials import EnvironmentVariableCredentialsProvider\n",
     "# 请将您的 OSS accessKeyID 和 accessKeySecret 分别设置成环境变量 OSS_ACCESS_KEY_ID 和 OSS_ACCESS_KEY_SECRET\n",
     "auth = oss2.ProviderAuth(EnvironmentVariableCredentialsProvider())\n",
     "# 请将 OSS_ENDPOINT 和 BUCKET_NAME 替换为您的 OSS Endpoint 和 Bucket\n",
-    "bucket = oss2.Bucket(auth, 'OSS_ENDPOINT', 'BUCKET_NAME')\n",
+    "bucket = oss2.Bucket(auth, 'oss-cn-beijing.aliyuncs.com', 'fluid-demo')\n",
     "\n",
     "bytes_buffer = io.BytesIO()\n",
     "df.to_pickle(bytes_buffer)\n",
@@ -140,7 +180,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -190,18 +230,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "from kubernetes.client import models as k8s_models\n",
     "# 定义任务运行模版，并挂载OSS Volume\n",
     "def create_processor(script):\n",
     "    return models.Processor(\n",
-    "        # 当按照前面的可选步骤开启fuse亲和性调度后, 添加下列标签, 从而实现数据处理的最佳性能\n",
-    "        # pod_metadata=models.PodMetadata(\n",
-    "        #     labels={\"fuse.serverful.fluid.io/inject\": \"true\"},\n",
-    "        # ),\n",
     "        script=models.ScriptProcessor(\n",
     "            command=[\"bash\"],\n",
     "            source=script,\n",
@@ -229,14 +265,22 @@
     "- **创建任务模版:** 代码中封装了一个名为`create_processor`的任务模板函数，该函数接收一个bash脚本并把它传入作为某个容器的启动命令。该容器中定义了Python 3.10的运行环境，并在`/data`目录下挂载了OSS存储数据源。"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "> 注意：挂载OSS存储数据源前需要在集群提前创建名为`pvc-oss`的PersistentVolumeClaim（PVC）资源，并将其绑定一个OSS类型的PersistentVolume（PV）资源上。PV资源需要指定数据准备步骤中上传的Bucket路径。"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
     "# 定义数据预处理脚本\n",
     "preprocess_data_script = \"\"\"\n",
+    "# pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple\n",
     "pip3 install numpy pandas pyarrow requests vineyard scikit-learn==1.4.0 joblib==1.3.2\n",
     "#!/bin/bash\n",
     "set -ex\n",
@@ -272,6 +316,7 @@
     "\n",
     "# 定义模型训练脚本\n",
     "train_data_script = \"\"\"\n",
+    "# pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple\n",
     "pip3 install numpy pandas pyarrow requests vineyard scikit-learn==1.4.0 joblib==1.3.2\n",
     "#!/bin/bash\n",
     "set -ex\n",
@@ -297,6 +342,7 @@
     "\n",
     "# 定义模型测试脚本\n",
     "test_data_script = \"\"\"\n",
+    "# pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple\n",
     "pip3 install numpy pandas pyarrow requests vineyard scikit-learn==1.4.0 joblib==1.3.2\n",
     "#!/bin/bash\n",
     "set -ex\n",
@@ -339,7 +385,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -352,7 +398,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -370,7 +416,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -380,8 +426,22 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "python",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,