Update 'Introduction to generic pipelines' tutorial

pipelines/introduction-to-generic-pipelines/Part 3 - Data Classification.ipynb

@@ -0,0 +1,154 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "702729a9-40d0-47a1-94e1-96ac60a96ce2",
+   "metadata": {},
+   "source": [
+    "## Copyright 2018-2022 Elyra Authors"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b02ab100-90c5-4364-9e13-2c5e2b15dd58",
+   "metadata": {},
+   "source": [
+    "Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+    "you may not use this file except in compliance with the License.\n",
+    "You may obtain a copy of the License at\n",
+    "\n",
+    "http://www.apache.org/licenses/LICENSE-2.0\n",
+    "\n",
+    "Unless required by applicable law or agreed to in writing, software\n",
+    "distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+    "WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+    "See the License for the specific language governing permissions and\n",
+    "limitations under the License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cb48220c-fb29-4b50-9868-a27d75523d9d",
+   "metadata": {},
+   "source": [
+    "## Classify data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c36d1686-5165-48ca-9906-a6bb99901b15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Uncomment this line to install scikit-learn\n",
+    "! pip install scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8ce06184-2db2-42c7-bc39-0d323c487981",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6cb6e348-8297-41a5-b839-ba0c8db36109",
+   "metadata": {},
+   "source": [
+    "Load processed CSV file into Pandas DataFrame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39f922b3-3c3f-474a-b7f5-af42db0cff3c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_filename_in = os.getenv(\"DATASET_FILENAME\", \"iris.csv\")\n",
+    "iris_df = pd.read_csv(data_filename_in)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "540c6b4e-d0b1-4ea3-923a-f22fd19e31a7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iris_df.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "535cc7df-fb5e-4e35-a965-feeb9ca93aa2",
+   "metadata": {},
+   "source": [
+    "Split the dataset into training set and testing set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "371604d1-30e5-4035-944c-a6dbd8bf0426",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = iris_df.drop([\"class\"], axis=1)\n",
+    "y = iris_df[\"class\"]\n",
+    "X_train, X_test, y_train, y_test = train_test_split(\n",
+    "    X, y, test_size=0.35, random_state=5\n",
+    ")\n",
+    "\n",
+    "print(f\"Training feature {X_train.shape}\")\n",
+    "print(f\"Training outcome {y_train.shape}\")\n",
+    "print(f\"Test feature {X_test.shape}\")\n",
+    "print(f\"Test outcome {y_test.shape}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1c2b6027-3f9d-4de9-9447-0555b62d7ed5",
+   "metadata": {},
+   "source": [
+    "Lorem Ipsum"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "41590a00-68ff-4df2-8c90-b1819cfb7a20",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}