From 67952a9a92d6f8304899182f730e35f02aab87ce Mon Sep 17 00:00:00 2001
From: gsingh58 <gurmail-singh@wisc.edu>
Date: Mon, 8 Apr 2024 05:50:59 -0500
Subject: [PATCH] lec24 updated

---
 .../24-clustering/24-clustering.ipynb         | 2093 +++++++++++++++++
 .../24-clustering/24-clustering_001.ipynb     |  916 ++++++++
 .../24-clustering/24-clustering_002.ipynb     |  916 ++++++++
 3 files changed, 3925 insertions(+)
 create mode 100644 lecture_material/24-clustering/24-clustering.ipynb
 create mode 100644 lecture_material/24-clustering/24-clustering_001.ipynb
 create mode 100644 lecture_material/24-clustering/24-clustering_002.ipynb

diff --git a/lecture_material/24-clustering/24-clustering.ipynb b/lecture_material/24-clustering/24-clustering.ipynb
new file mode 100644
index 0000000..05131a6
--- /dev/null
+++ b/lecture_material/24-clustering/24-clustering.ipynb
@@ -0,0 +1,2093 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "035e9e2c-9781-4b9c-8395-be9e55e4e082",
+   "metadata": {},
+   "source": [
+    "# Clustering"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cbd48a28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import geopandas as gpd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression, LogisticRegression\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.preprocessing import PolynomialFeatures\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "# new import statements\n",
+    "from sklearn.cluster import KMeans, AgglomerativeClustering"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e72ea2f4",
+   "metadata": {},
+   "source": [
+    "# Unsupervised Machine Learning: Clustering\n",
+    "\n",
+    "- In classification (supervised), we try to find boundaries/rules to separate points according to pre-determined labels.\n",
+    "- In clustering, the algorithm chooses the labels.  Goal is to choose labels so that similar rows get labeled the same.\n",
+    "\n",
+    "### K-Means Clustering\n",
+    "\n",
+    "- K: number of clusters:\n",
+    "    - 3-Means => 3 clusters\n",
+    "    - 4-Means => 4 clusters, and so on\n",
+    "- Means: we will find centroids (aka means aka averages) to create clusters\n",
+    "\n",
+    "- import statement:\n",
+    "```python\n",
+    "from sklearn.cluster import KMeans\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a0ad5a5",
+   "metadata": {},
+   "source": [
+    "#### Iterative algorithm for K-Means"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "0b83aaf3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>x0</th>\n",
+       "      <th>x1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8.370099</td>\n",
+       "      <td>7.747045</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-2.701740</td>\n",
+       "      <td>0.395336</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>-3.204128</td>\n",
+       "      <td>-0.407438</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-3.132762</td>\n",
+       "      <td>-1.335692</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.152737</td>\n",
+       "      <td>6.069995</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         x0        x1\n",
+       "0  8.370099  7.747045\n",
+       "1 -2.701740  0.395336\n",
+       "2 -3.204128 -0.407438\n",
+       "3 -3.132762 -1.335692\n",
+       "4  7.152737  6.069995"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Generate random data\n",
+    "x, y = datasets.make_blobs(n_samples=100, centers=3, cluster_std=1.2, random_state=3)\n",
+    "df = pd.DataFrame(x, columns=[\"x0\", \"x1\"])\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "fbced908",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "def km_scatter(df, **kwargs):\n",
+    "    \"\"\"\n",
+    "    Produces scatter plot visualizations with x0 on x-axis and y0 on y-axis.\n",
+    "    It can also plot the centroids for clusters.\n",
+    "    Parameters:\n",
+    "        x0 => x-axis\n",
+    "        x1 => y-axis\n",
+    "        cluster => marker type\n",
+    "    \"\"\"\n",
+    "    ax = kwargs.pop(\"ax\", None)\n",
+    "    if not \"label\" in df.columns:\n",
+    "        return df.plot.scatter(x=\"x0\", y=\"x1\", marker=\"$?$\", ax=ax, **kwargs)\n",
+    "\n",
+    "    for marker in set(df[\"label\"]):\n",
+    "        sub_df = df[df[\"label\"] == marker]\n",
+    "        ax = sub_df.plot.scatter(x=\"x0\", y=\"x1\", marker=marker, ax=ax, **kwargs)\n",
+    "    return ax\n",
+    "\n",
+    "ax = km_scatter(df, s=100, c=\"0.7\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "47686eee",
+   "metadata": {},
+   "source": [
+    "### Hard Problem\n",
+    "\n",
+    "Finding the best answer. What is the answer? Determing the centroids of the clusters.\n",
+    "\n",
+    "### Easier Problem\n",
+    "\n",
+    "Taking a random answer and make it a little better. Then repeat!\n",
+    "Downside? If randomization leads to very bad initial choice of centroids, that might lead to bad clustering (fewer clusters)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6f8bde9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='x0', ylabel='x1'>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "clusters = np.random.uniform(-5, 5, size=(3, 2))\n",
+    "clusters = pd.DataFrame(clusters, columns=[\"x0\", \"x1\"])\n",
+    "clusters[\"label\"] = [\"o\", \"+\", \"x\"]\n",
+    "\n",
+    "ax = km_scatter(df, s=100, c=\"0.7\")\n",
+    "km_scatter(clusters, s=200, c=\"red\", ax=ax)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3fe986c",
+   "metadata": {},
+   "source": [
+    "Two variables for us to deal with:\n",
+    "1. clusters: contains location of centroids and a label for them\n",
+    "2. df: contains the actual data points"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cfa1f1aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>x0</th>\n",
+       "      <th>x1</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-3.318190</td>\n",
+       "      <td>3.427192</td>\n",
+       "      <td>o</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2.803704</td>\n",
+       "      <td>2.776817</td>\n",
+       "      <td>+</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.807126</td>\n",
+       "      <td>-2.515565</td>\n",
+       "      <td>x</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         x0        x1 label\n",
+       "0 -3.318190  3.427192     o\n",
+       "1  2.803704  2.776817     +\n",
+       "2  0.807126 -2.515565     x"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clusters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f210c534",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>x0</th>\n",
+       "      <th>x1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8.370099</td>\n",
+       "      <td>7.747045</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-2.701740</td>\n",
+       "      <td>0.395336</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>-3.204128</td>\n",
+       "      <td>-0.407438</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-3.132762</td>\n",
+       "      <td>-1.335692</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.152737</td>\n",
+       "      <td>6.069995</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         x0        x1\n",
+       "0  8.370099  7.747045\n",
+       "1 -2.701740  0.395336\n",
+       "2 -3.204128 -0.407438\n",
+       "3 -3.132762 -1.335692\n",
+       "4  7.152737  6.069995"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a28466ce",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "class KM:\n",
+    "    def __init__(self, df, clusters):\n",
+    "        # We make copies because we are going to keep changing the dataframe to \n",
+    "        # identify better clusters\n",
+    "        self.df = df.copy()\n",
+    "        self.clusters = clusters.copy()\n",
+    "        self.labels = clusters[\"label\"].values\n",
+    "        \n",
+    "    def plot(self):\n",
+    "        ax = km_scatter(self.df, color=\"0.7\", s=100)\n",
+    "        km_scatter(self.clusters, ax=ax, color=\"red\", s=200)\n",
+    "        \n",
+    "    def assign_points(self):\n",
+    "        \"\"\"\n",
+    "        compute Euclidean distance between each point and each centroids\n",
+    "        \"\"\"\n",
+    "        for center in self.clusters.itertuples():\n",
+    "            # Euclidean distance\n",
+    "            x0_diff = df[\"x0\"] - center.x0\n",
+    "            x1_diff = df[\"x1\"] - center.x1\n",
+    "            distances = (x0_diff ** 2 + x1_diff ** 2) ** 0.5\n",
+    "            # add distance to each centroid as a column within the dataframe\n",
+    "            self.df[center.label] = distances\n",
+    "        # get the label of the nearest centroid\n",
+    "        self.df[\"label\"] = self.labels[self.df[self.labels].values.argmin(axis=1)]\n",
+    "    \n",
+    "    def update_centers(self):\n",
+    "        \"\"\"\n",
+    "        update centroids by taking mean of the points that are nearest to that\n",
+    "        particular centroid\n",
+    "        \"\"\"\n",
+    "        for center in self.clusters.itertuples():\n",
+    "            subset_df = self.df[self.df[\"label\"] == center.label]\n",
+    "            if len(subset_df) > 0:\n",
+    "                x0 = subset_df[\"x0\"].mean()\n",
+    "                x1 = subset_df[\"x1\"].mean()\n",
+    "                self.clusters.at[center.Index, \"x0\"] = x0\n",
+    "                self.clusters.at[center.Index, \"x1\"] = x1\n",
+    "\n",
+    "\"\"\"\n",
+    "High-level algorithm:\n",
+    "1. Start with random locations for centroids\n",
+    "2. Iterate over each data point:\n",
+    "    1. Find the distance (Euclidean distance) between current data point and each centroid.\n",
+    "    2. Find the minimum of those distances and the corresponding label.\n",
+    "    3. Assign current data point to the closest cluster centroid label.\n",
+    "4. Once all points are assigned, compute new centroid for each cluster. Iterate over \n",
+    "   each cluster:\n",
+    "    1. Extract subset of data points which got assigned to curr cluster label.\n",
+    "    2. Compute mean of all the assigned data points.\n",
+    "    3. Update cluster centroid.\n",
+    "5. Repeat steps 2 to 4 many times (iterative improvement).\n",
+    "\"\"\"\n",
+    "\n",
+    "# Creating object instance\n",
+    "km = KM(df, clusters)\n",
+    "km.plot()\n",
+    "\n",
+    "# km.assign_points()\n",
+    "# km.plot()\n",
+    "# km.update_centers()\n",
+    "\n",
+    "for i in range(10):\n",
+    "    km.assign_points()\n",
+    "    km.update_centers()\n",
+    "    \n",
+    "km.plot()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "938a6cc5",
+   "metadata": {},
+   "source": [
+    "### `sklearn KMeans`\n",
+    "\n",
+    "- import statement:\n",
+    "```python\n",
+    "from sklearn.cluster import KMeans\n",
+    "```\n",
+    "- documentation: https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html\n",
+    "\n",
+    "**Instantiation:**\n",
+    "`KMeans(n_clusters=<num>, n_init=<num>, max_iter=<num>)`\n",
+    "- `n_clusters`: number of clusters to be formed\n",
+    "- `n_init`: number of initial random seeds to try (to avoid downside of bad initial random choices)\n",
+    "- `max_iter`: maximum number of iterations for a single K-means run (single starting seed)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "caa96a1e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KMeans(n_clusters=3, n_init=320)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KMeans</label><div class=\"sk-toggleable__content\"><pre>KMeans(n_clusters=3, n_init=320)</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "KMeans(n_clusters=3, n_init=320)"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "km_cluster = KMeans(3, n_init = 320)\n",
+    "km_cluster"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ea51243c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>x0</th>\n",
+       "      <th>x1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8.370099</td>\n",
+       "      <td>7.747045</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-2.701740</td>\n",
+       "      <td>0.395336</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>-3.204128</td>\n",
+       "      <td>-0.407438</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-3.132762</td>\n",
+       "      <td>-1.335692</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.152737</td>\n",
+       "      <td>6.069995</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         x0        x1\n",
+       "0  8.370099  7.747045\n",
+       "1 -2.701740  0.395336\n",
+       "2 -3.204128 -0.407438\n",
+       "3 -3.132762 -1.335692\n",
+       "4  7.152737  6.069995"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84e59c4a",
+   "metadata": {},
+   "source": [
+    "**Methods:**\n",
+    "1. `fit`: find good centroids\n",
+    "2. `transform`: give me the distances from each point to each centroid\n",
+    "3. `predict`: give me the chosen group labels\n",
+    "\n",
+    "**Attributes:**\n",
+    "- `<km object>.cluster_centers_`: coordinates of cluster centers\n",
+    "- `<km object>.inertia_`: sum of squared distances of samples to their closest cluster center"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "26be1744",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 0.85985598,  3.98556415],\n",
+       "       [ 7.69751168,  7.9241129 ],\n",
+       "       [-4.41347291,  0.43410278]])"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# `fit`: find good centroids\n",
+    "km_cluster.fit(df)\n",
+    "# coordinates of cluster centers\n",
+    "km_cluster.cluster_centers_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6ce05e61",
+   "metadata": {},
+   "source": [
+    "**Observeration:** 3 rows (because we have 3 clusters), and 2 columns (because the df had 2 columns)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "2df977a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 8.39955315,  0.69550479, 14.72748598],\n",
+       "       [ 5.057144  , 12.83849367,  1.71217188],\n",
+       "       [ 5.984516  , 13.72080475,  1.47333179],\n",
+       "       [ 6.65257594, 14.24916908,  2.18458064],\n",
+       "       [ 6.62911793,  1.93249405, 12.86625407],\n",
+       "       [ 6.42867089, 14.14472291,  1.56004975],\n",
+       "       [ 7.00663718, 14.79157898,  1.29983259],\n",
+       "       [ 7.09747529,  1.56332001, 13.35025948],\n",
+       "       [ 6.1620119 , 13.93648735,  1.20010768],\n",
+       "       [ 1.75079801,  9.23940355,  5.12923462],\n",
+       "       [ 7.45185474, 15.29849451,  1.23053441],\n",
+       "       [ 8.98045036,  1.52459286, 15.3322184 ],\n",
+       "       [10.91386222,  3.37380113, 17.16390523],\n",
+       "       [ 8.05146158,  0.29966036, 14.40658807],\n",
+       "       [ 1.50499677,  6.61820665,  7.66113117],\n",
+       "       [ 5.52922108, 13.2665394 ,  2.37571603],\n",
+       "       [ 8.29635389,  0.53707918, 14.65282383],\n",
+       "       [ 7.93015965,  1.55598141, 14.25952349],\n",
+       "       [ 5.48003982, 13.29440299,  1.90656095],\n",
+       "       [ 7.2343239 , 15.0936722 ,  0.96395695],\n",
+       "       [ 1.41855649,  9.25115661,  4.992096  ],\n",
+       "       [ 1.45498683,  9.33747036,  4.93551825],\n",
+       "       [ 5.44776095, 13.23976135,  2.07379647],\n",
+       "       [ 2.19458147,  9.56765164,  4.91887166],\n",
+       "       [ 6.93266631, 14.81316619,  0.57581927],\n",
+       "       [ 7.17892147,  1.11200436, 13.53348077],\n",
+       "       [ 7.67472596,  2.34433677, 13.93980529],\n",
+       "       [ 1.93352254,  9.20846006,  5.26299436],\n",
+       "       [ 6.70061053, 14.59106753,  0.65237687],\n",
+       "       [ 7.12823278,  1.94521438, 13.32557282],\n",
+       "       [ 0.74526095,  8.30288243,  6.05203173],\n",
+       "       [ 0.40860041,  8.00815579,  6.23474579],\n",
+       "       [ 9.49044337,  1.60009447, 15.83753761],\n",
+       "       [ 6.22489679, 14.10790541,  0.87321819],\n",
+       "       [ 8.435192  ,  1.15378784, 14.72414628],\n",
+       "       [10.2531705 ,  2.38736888, 16.58783267],\n",
+       "       [ 2.27154202,  5.83830901,  8.55105873],\n",
+       "       [ 2.75660235,  5.95202527,  8.78629101],\n",
+       "       [ 2.84287347, 10.1425873 ,  4.54066469],\n",
+       "       [ 7.16356495,  0.93262286, 13.5212101 ],\n",
+       "       [ 9.19576267,  1.30641878, 15.54221673],\n",
+       "       [ 5.34666581,  2.54971515, 11.7015581 ],\n",
+       "       [ 2.54587855, 10.22941308,  4.36721141],\n",
+       "       [ 1.88491159,  8.68824585,  6.14751601],\n",
+       "       [ 7.33668275, 15.17700603,  1.1667762 ],\n",
+       "       [ 5.45233018, 13.30733704,  1.01799729],\n",
+       "       [ 1.7579973 ,  7.49072887,  7.03318297],\n",
+       "       [ 9.86402785, 17.75488558,  3.54826072],\n",
+       "       [ 7.2031497 ,  1.20887179, 13.55443098],\n",
+       "       [ 5.87271591, 13.74675135,  0.51824276],\n",
+       "       [ 2.30838073,  7.10823668,  7.82838283],\n",
+       "       [ 7.80457898,  1.12270374, 14.15307497],\n",
+       "       [ 6.4156169 , 14.24917525,  1.59442989],\n",
+       "       [ 6.6822816 ,  1.3318725 , 13.03994358],\n",
+       "       [ 6.92982586, 14.80507705,  0.59024245],\n",
+       "       [ 8.63436577,  1.42658402, 14.90539467],\n",
+       "       [ 5.41291689, 13.29593667,  1.25147313],\n",
+       "       [ 8.54636085,  1.19827726, 14.89915191],\n",
+       "       [ 0.57780829,  8.14567593,  6.10488957],\n",
+       "       [ 0.77282299,  8.60942142,  5.67744983],\n",
+       "       [ 2.59528033,  6.32091816,  8.49307124],\n",
+       "       [ 5.35252808, 13.23709537,  1.00610963],\n",
+       "       [ 2.26369124,  7.07230771,  7.5990801 ],\n",
+       "       [ 1.26785392,  9.0405774 ,  5.30885047],\n",
+       "       [ 5.99596267, 13.88620068,  0.47948765],\n",
+       "       [ 0.91763133,  8.58111489,  5.77604558],\n",
+       "       [ 6.65464378,  2.06300507, 12.86777741],\n",
+       "       [ 6.39246794, 14.09638583,  1.62566554],\n",
+       "       [ 1.65291205,  8.35369533,  6.38383554],\n",
+       "       [ 7.53920353, 15.42660006,  1.41490518],\n",
+       "       [ 6.17924199, 14.06223865,  0.17931956],\n",
+       "       [ 8.31324068,  0.59836973, 14.67041305],\n",
+       "       [ 1.99362004,  6.00685668,  8.25397394],\n",
+       "       [ 8.34952026, 16.1079315 ,  2.4063456 ],\n",
+       "       [ 0.37645384,  7.86635161,  6.37596316],\n",
+       "       [ 1.26889021,  9.1588198 ,  5.08950884],\n",
+       "       [ 6.67830608, 14.56800175,  0.69981327],\n",
+       "       [ 0.77020788,  8.64186223,  5.59931912],\n",
+       "       [ 7.79244516,  0.28968299, 14.14799736],\n",
+       "       [ 5.12907373, 12.98613124,  1.30572045],\n",
+       "       [ 2.53789955,  5.87809732,  8.68870984],\n",
+       "       [ 2.36585725,  8.24866952,  6.61574395],\n",
+       "       [ 2.12612074,  5.87257865,  8.45067852],\n",
+       "       [ 0.90652387,  7.12826473,  7.11997028],\n",
+       "       [ 7.26336958,  0.71023041, 13.61995075],\n",
+       "       [ 1.15089783,  8.22238495,  6.12509618],\n",
+       "       [ 7.02568051, 14.91475526,  0.95000417],\n",
+       "       [ 6.83520257,  1.30571326, 13.19097587],\n",
+       "       [ 2.02969683,  9.13122664,  5.6933789 ],\n",
+       "       [ 7.27004865,  0.73792958, 13.60223177],\n",
+       "       [ 1.82317591,  6.1130832 ,  8.1696311 ],\n",
+       "       [ 7.42721394,  0.4748222 , 13.7794429 ],\n",
+       "       [10.81513449,  2.92436629, 17.16231237],\n",
+       "       [ 7.03701825, 14.8381987 ,  2.0476452 ],\n",
+       "       [ 7.26300626,  0.79864959, 13.62070697],\n",
+       "       [ 6.25392175, 14.14191977,  0.70491739],\n",
+       "       [ 5.50220436, 13.35168297,  1.00665632],\n",
+       "       [ 0.30480731,  8.16896184,  6.07336225],\n",
+       "       [ 7.63813717,  0.63263536, 13.95950443],\n",
+       "       [ 8.10973138,  1.16783284, 14.38622797]])"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# `transform`: give me the distances from each point to each centroid\n",
+    "km_cluster.transform(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7cd8409e",
+   "metadata": {},
+   "source": [
+    "**Observations**: Each row corresponds to a row in df. 3 columns correspond to 3 distances to the centroids."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "6a65a976",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 2, 2, 2, 1, 2, 2, 1, 2, 0, 2, 1, 1, 1, 0, 2, 1, 1, 2, 2, 0, 0,\n",
+       "       2, 0, 2, 1, 1, 0, 2, 1, 0, 0, 1, 2, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0,\n",
+       "       2, 2, 0, 2, 1, 2, 0, 1, 2, 1, 2, 1, 2, 1, 0, 0, 0, 2, 0, 0, 2, 0,\n",
+       "       1, 2, 0, 2, 2, 1, 0, 2, 0, 0, 2, 0, 1, 2, 0, 0, 0, 0, 1, 0, 2, 1,\n",
+       "       0, 1, 0, 1, 1, 2, 1, 2, 2, 0, 1, 1], dtype=int32)"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# `predict`: give me the chosen group labels\n",
+    "km_cluster.predict(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "240d995a",
+   "metadata": {},
+   "source": [
+    "### How many clusters do we need?\n",
+    "\n",
+    "- metric: `<km object>.inertia_`: sum of squared distances of samples to their closest cluster center"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "8bf73d2c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "260.7196850565891"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "km_cluster.inertia_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57b5ccc4",
+   "metadata": {},
+   "source": [
+    "**Observation**: we want \"inertia\" to be as small as possible."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae70b416",
+   "metadata": {},
+   "source": [
+    "### Elbow plot to determine `n_clusters`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "607a96b0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1     3621.095890\n",
+       "2      927.007644\n",
+       "3      260.719685\n",
+       "4      211.730031\n",
+       "5      180.483456\n",
+       "6      152.850252\n",
+       "7      128.980812\n",
+       "8      109.222545\n",
+       "9       92.946695\n",
+       "10      82.172702\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# create a series with clusters 1 to 10 and corresponding values are equal to intertia \n",
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "s"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "388cd23f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 0, 'Number of clusters')"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eab497cd",
+   "metadata": {},
+   "source": [
+    "**Observation**: there is an \"elbow\" around `n_clusters`=3."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e763d1c",
+   "metadata": {},
+   "source": [
+    "#### Will we always have a clear \"elbow\"?\n",
+    "\n",
+    "- Let's generate uniform random data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "b5ad30ec",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 0, 'Number of clusters')"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df2 = pd.DataFrame(np.random.uniform(0, 10, (100, 2)))\n",
+    "\n",
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df2)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c6decdab-74a3-45b5-a408-e7b54bd992d9",
+   "metadata": {},
+   "source": [
+    "**Observation**: there is an \"elbow\" around `n_clusters`=3."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c6115b0-61df-4660-8355-3cd56bd94080",
+   "metadata": {},
+   "source": [
+    "#### Will we always have a clear \"elbow\"?\n",
+    "\n",
+    "- Let's generate uniform random data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "424743f8-41de-42b8-ab78-07901682ee84",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='0', ylabel='1'>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df2 = pd.DataFrame(np.random.uniform(0, 10, (100, 2)))\n",
+    "df2.plot.scatter(0, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "fba71303-d4c6-46d3-ae8e-f0e863d8e032",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 0, 'Number of clusters')"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df2)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8af299e7",
+   "metadata": {},
+   "source": [
+    "### K-Means use cases:\n",
+    "\n",
+    "1. estimator\n",
+    "2. transformer:\n",
+    "    - sometimes we'll use an unsupervised learning technique (like k-means) to pre-process data, creating better inputs for a supervised learning technique (like logistic regression)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "6b99861d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_data():\n",
+    "    x, y = datasets.make_blobs(n_samples=250, centers=5, random_state=5)\n",
+    "    xcols = [\"x0\", \"x1\"]\n",
+    "    df1 = pd.DataFrame(x, columns=xcols)\n",
+    "    df1[\"y\"] = y > 0\n",
+    "\n",
+    "    df2 = pd.DataFrame(np.random.uniform(-10, 10, size=(250, 2)), columns=[\"x0\", \"x1\"])\n",
+    "    df2[\"y\"] = False\n",
+    "\n",
+    "    return pd.concat((df1, df2))\n",
+    "\n",
+    "train, test = train_test_split(make_data())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "c1a0353f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.rcParams[\"font.size\"] = 16\n",
+    "fig, ax = plt.subplots(ncols=2, figsize=(10,4))\n",
+    "train.plot.scatter(x=\"x0\", y=\"x1\", c=train[\"y\"], vmin=-1, ax=ax[0])\n",
+    "test.plot.scatter(x=\"x0\", y=\"x1\", c=\"red\", ax=ax[1])\n",
+    "ax[0].set_title(\"Training Data\")\n",
+    "ax[1].set_title(\"Test Data\")\n",
+    "plt.subplots_adjust(wspace=0.4)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57800660",
+   "metadata": {},
+   "source": [
+    "#### Objective: use `LogisticRegression` to classify points as \"black\" or \"gray\"."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "cba5b0b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/gurmail.singh/.local/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
+      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
+      "\n",
+      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
+      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
+      "Please also refer to the documentation for alternative solver options:\n",
+      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
+      "  n_iter_i = _check_optimize_result(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "0.768"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"km\", KMeans(10, n_init = 320)),\n",
+    "    (\"lr\", LogisticRegression()),\n",
+    "])\n",
+    "model.fit(train[[\"x0\", \"x1\"]], train[\"y\"])\n",
+    "model.score(test[[\"x0\", \"x1\"]], test[\"y\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "e78a788c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.784"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"km\", KMeans(10, n_init = 320)),\n",
+    "    (\"std\", StandardScaler()),\n",
+    "    (\"lr\", LogisticRegression()),\n",
+    "])\n",
+    "model.fit(train[[\"x0\", \"x1\"]], train[\"y\"])\n",
+    "model.score(test[[\"x0\", \"x1\"]], test[\"y\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0d506007",
+   "metadata": {},
+   "source": [
+    "### `StandardScaler` with `KMeans`\n",
+    "\n",
+    "Recall that `StandardScaler` should always be applied after applying `PolynomialFeatures` (from last lecture)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "1229aad1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='0', ylabel='1'>"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "x = datasets.make_blobs(centers=np.array([(0, 0), (0, 20), (3, 20)]))[0]\n",
+    "df = pd.DataFrame(x)\n",
+    "df.plot.scatter(x=0, y=1, figsize=(6, 4))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "9f21a66d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0,\n",
+       "       1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1,\n",
+       "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1,\n",
+       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0,\n",
+       "       0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0], dtype=int32)"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "km_c = KMeans(2, n_init = 320)\n",
+    "km_c.fit(df)\n",
+    "km_c.predict(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7dc700d4",
+   "metadata": {},
+   "source": [
+    "#### `fit_predict(...)` is a shortcut for `fit` and `predict` method invocations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "7bc1d18d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0,\n",
+       "       1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1,\n",
+       "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1,\n",
+       "       0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0,\n",
+       "       0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0], dtype=int32)"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "KMeans(2, n_init = 320).fit_predict(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "b2dfa6bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='0', ylabel='1'>"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# -1 => white, 0 => gray, 1 => black\n",
+    "df.plot.scatter(x=0, y=1, figsize=(6, 4), c=KMeans(2, n_init = 320).fit_predict(df), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "762f2882",
+   "metadata": {},
+   "source": [
+    "**Observation**: scale for columns are intentionally not specified."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "4f99dfeb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3.244656</td>\n",
+       "      <td>17.882965</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.519742</td>\n",
+       "      <td>-1.214826</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2.055869</td>\n",
+       "      <td>19.481308</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0.863258</td>\n",
+       "      <td>19.307939</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>-0.270818</td>\n",
+       "      <td>19.559756</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95</th>\n",
+       "      <td>-1.352074</td>\n",
+       "      <td>20.421015</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>96</th>\n",
+       "      <td>0.572919</td>\n",
+       "      <td>0.985182</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>97</th>\n",
+       "      <td>3.724053</td>\n",
+       "      <td>20.445860</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>98</th>\n",
+       "      <td>1.663830</td>\n",
+       "      <td>20.743809</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>99</th>\n",
+       "      <td>2.756283</td>\n",
+       "      <td>19.533742</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>100 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           0          1\n",
+       "0   3.244656  17.882965\n",
+       "1   0.519742  -1.214826\n",
+       "2   2.055869  19.481308\n",
+       "3   0.863258  19.307939\n",
+       "4  -0.270818  19.559756\n",
+       "..       ...        ...\n",
+       "95 -1.352074  20.421015\n",
+       "96  0.572919   0.985182\n",
+       "97  3.724053  20.445860\n",
+       "98  1.663830  20.743809\n",
+       "99  2.756283  19.533742\n",
+       "\n",
+       "[100 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d444185c",
+   "metadata": {},
+   "source": [
+    "Let's make a copy of the data. Assuming initial data for both columns is in \"km\", let's convert one column (`0`) into \"meters\". "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "2e437218",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3244.655538</td>\n",
+       "      <td>17.882965</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>519.741624</td>\n",
+       "      <td>-1.214826</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2055.868744</td>\n",
+       "      <td>19.481308</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>863.258081</td>\n",
+       "      <td>19.307939</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>-270.817705</td>\n",
+       "      <td>19.559756</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             0          1\n",
+       "0  3244.655538  17.882965\n",
+       "1   519.741624  -1.214826\n",
+       "2  2055.868744  19.481308\n",
+       "3   863.258081  19.307939\n",
+       "4  -270.817705  19.559756"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2 = df.copy()\n",
+    "df2[0] *= 1000 # km => m\n",
+    "df2.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "c99315a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='0', ylabel='1'>"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df2.plot.scatter(x=0, y=1, figsize=(6,4), c=KMeans(2, n_init = 320).fit_predict(df2), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3966ddd3",
+   "metadata": {},
+   "source": [
+    "**Observations**:\n",
+    "- One would expect to see the same clusters, but that is not happening here. Why?\n",
+    "    - x-axis difference is too high when compared to the y-axis difference\n",
+    "    - That is, KMeans doesn't get that x-axis has scaled data, whereas y-axis doesn't have scaled data\n",
+    "- This is not too far off from realistic datasets. \n",
+    "    - That is, real-world dataset columns might have difference units. \n",
+    "    - For example, one column might be representing temperature data where as another might be representing distance."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b63c9d9b",
+   "metadata": {},
+   "source": [
+    "#### Conclusion: `StandardScaler` should be applied before `KMeans`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "2c81ed04",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='0', ylabel='1'>"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"std\", StandardScaler()),\n",
+    "    (\"km\", KMeans(2, n_init = 320)),\n",
+    "])\n",
+    "\n",
+    "df2.plot.scatter(x=0, y=1, figsize=(6, 4), c=model.fit_predict(df2), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "359dd107",
+   "metadata": {},
+   "source": [
+    "### Wisconsin counties example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "8847306e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>NAME</th>\n",
+       "      <th>POP100</th>\n",
+       "      <th>AREALAND</th>\n",
+       "      <th>HU100</th>\n",
+       "      <th>developed</th>\n",
+       "      <th>forest</th>\n",
+       "      <th>pasture</th>\n",
+       "      <th>crops</th>\n",
+       "      <th>geometry</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Racine County</td>\n",
+       "      <td>195408</td>\n",
+       "      <td>861533739</td>\n",
+       "      <td>82164</td>\n",
+       "      <td>0.230906</td>\n",
+       "      <td>0.100167</td>\n",
+       "      <td>0.072588</td>\n",
+       "      <td>0.482126</td>\n",
+       "      <td>POLYGON ((645313.81834 2212738.58489, 645456.3...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Clark County</td>\n",
+       "      <td>34690</td>\n",
+       "      <td>3133378070</td>\n",
+       "      <td>15076</td>\n",
+       "      <td>0.046476</td>\n",
+       "      <td>0.326691</td>\n",
+       "      <td>0.022979</td>\n",
+       "      <td>0.444642</td>\n",
+       "      <td>POLYGON ((431909.29098 2393751.35940, 433872.5...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Wood County</td>\n",
+       "      <td>74749</td>\n",
+       "      <td>2054044751</td>\n",
+       "      <td>34088</td>\n",
+       "      <td>0.080285</td>\n",
+       "      <td>0.226244</td>\n",
+       "      <td>0.023411</td>\n",
+       "      <td>0.320990</td>\n",
+       "      <td>POLYGON ((498653.94690 2388370.84202, 498647.3...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Rusk County</td>\n",
+       "      <td>14755</td>\n",
+       "      <td>2366092584</td>\n",
+       "      <td>8883</td>\n",
+       "      <td>0.035567</td>\n",
+       "      <td>0.473937</td>\n",
+       "      <td>0.049572</td>\n",
+       "      <td>0.138357</td>\n",
+       "      <td>POLYGON ((397166.23292 2498521.78567, 397167.7...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Ozaukee County</td>\n",
+       "      <td>86395</td>\n",
+       "      <td>603514413</td>\n",
+       "      <td>36267</td>\n",
+       "      <td>0.222642</td>\n",
+       "      <td>0.088609</td>\n",
+       "      <td>0.127867</td>\n",
+       "      <td>0.389109</td>\n",
+       "      <td>POLYGON ((654796.85595 2272096.94081, 654799.8...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             NAME  POP100    AREALAND  HU100  developed    forest   pasture  \\\n",
+       "0   Racine County  195408   861533739  82164   0.230906  0.100167  0.072588   \n",
+       "1    Clark County   34690  3133378070  15076   0.046476  0.326691  0.022979   \n",
+       "2     Wood County   74749  2054044751  34088   0.080285  0.226244  0.023411   \n",
+       "3     Rusk County   14755  2366092584   8883   0.035567  0.473937  0.049572   \n",
+       "4  Ozaukee County   86395   603514413  36267   0.222642  0.088609  0.127867   \n",
+       "\n",
+       "      crops                                           geometry  \n",
+       "0  0.482126  POLYGON ((645313.81834 2212738.58489, 645456.3...  \n",
+       "1  0.444642  POLYGON ((431909.29098 2393751.35940, 433872.5...  \n",
+       "2  0.320990  POLYGON ((498653.94690 2388370.84202, 498647.3...  \n",
+       "3  0.138357  POLYGON ((397166.23292 2498521.78567, 397167.7...  \n",
+       "4  0.389109  POLYGON ((654796.85595 2272096.94081, 654799.8...  "
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = gpd.read_file(\"counties.geojson\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "377e9bb0",
+   "metadata": {},
+   "source": [
+    "#### If we want to use \"POP100\", \"AREALAND\", \"developed\", \"forest\", \"pasture\", \"crops\" for clustering, what transformer should we use? \n",
+    "\n",
+    "- StandardScaler."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15f0b21c",
+   "metadata": {},
+   "source": [
+    "### Goal here: cluster counties based on similar land usage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "55013d0a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: >"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "a199a2af",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: >"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df.plot(column=\"crops\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "8735a7bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: >"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df.plot(column=\"forest\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a42394cb",
+   "metadata": {},
+   "source": [
+    "### KMeans"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "a8b3c831",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.290908515122804\n",
+      "[3 0 0 2 3 0 3 1 2 0 3 3 3 2 0 1 0 0 2 2 0 2 0 3 0 0 0 0 2 3 3 3 2 0 0 0 3\n",
+      " 0 2 3 3 0 0 3 2 2 2 3 0 0 0 3 2 2 2 3 0 0 3 3 2 3 2 2 3 0 2 2 0 2 2 0]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: >"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = KMeans(4, n_init = 320)\n",
+    "# fit\n",
+    "km_c.fit(df[xcols])\n",
+    "# predict\n",
+    "clusters = km_c.predict(df[xcols])\n",
+    "\n",
+    "print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "01189d61",
+   "metadata": {},
+   "source": [
+    "**Observation**: cluster number can be random. That is, if you re-run the above cell twice, you will get different number for each cluster."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1764b5a6",
+   "metadata": {},
+   "source": [
+    "### Agglomerative clustering\n",
+    "\n",
+    "- import statement\n",
+    "```python\n",
+    "from sklearn.cluster import AgglomerativeClustering\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "3d7954a3",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'AgglomerativeClustering' object has no attribute 'predict'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[36], line 8\u001b[0m\n\u001b[1;32m      6\u001b[0m km_c\u001b[38;5;241m.\u001b[39mfit(df[xcols])\n\u001b[1;32m      7\u001b[0m \u001b[38;5;66;03m# predict\u001b[39;00m\n\u001b[0;32m----> 8\u001b[0m clusters \u001b[38;5;241m=\u001b[39m \u001b[43mkm_c\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m(df[xcols])\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28mprint\u001b[39m(km_c\u001b[38;5;241m.\u001b[39minertia_)\n\u001b[1;32m     11\u001b[0m \u001b[38;5;28mprint\u001b[39m(clusters)\n",
+      "\u001b[0;31mAttributeError\u001b[0m: 'AgglomerativeClustering' object has no attribute 'predict'"
+     ]
+    }
+   ],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = AgglomerativeClustering(4)\n",
+    "# fit\n",
+    "km_c.fit(df[xcols])\n",
+    "# predict\n",
+    "clusters = km_c.predict(df[xcols])\n",
+    "\n",
+    "print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6f825891",
+   "metadata": {},
+   "source": [
+    "**Observations**: \n",
+    "- no centroids => no inertia => no elbow plots (how do we pick cluster count?):\n",
+    "    - AttributeError: 'AgglomerativeClustering' object has no attribute 'predict'\n",
+    "- no `predict` method, but there is `fit_predict`:\n",
+    "    - AttributeError: 'AgglomerativeClustering' object has no attribute 'predict'\n",
+    "    - why?\n",
+    "        - because each point could lead to a completely different tree\n",
+    "        - remember unlike KMeans (which is top-down), AgglomerativeClustering is bottom-up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e16c6131",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = AgglomerativeClustering(4)\n",
+    "# fit_predict\n",
+    "clusters = km_c.fit_predict(df[xcols])\n",
+    "\n",
+    "# print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5fc2bf08-a0e3-49a3-b089-af0f99f83613",
+   "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": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/lecture_material/24-clustering/24-clustering_001.ipynb b/lecture_material/24-clustering/24-clustering_001.ipynb
new file mode 100644
index 0000000..1550e87
--- /dev/null
+++ b/lecture_material/24-clustering/24-clustering_001.ipynb
@@ -0,0 +1,916 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "035e9e2c-9781-4b9c-8395-be9e55e4e082",
+   "metadata": {},
+   "source": [
+    "# Clustering"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cbd48a28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import geopandas as gpd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression, LogisticRegression\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.preprocessing import PolynomialFeatures\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "# new import statements\n",
+    "from sklearn.cluster import KMeans, AgglomerativeClustering"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e72ea2f4",
+   "metadata": {},
+   "source": [
+    "# Unsupervised Machine Learning: Clustering\n",
+    "\n",
+    "- In classification (supervised), we try to find boundaries/rules to separate points according to pre-determined labels.\n",
+    "- In clustering, the algorithm chooses the labels.  Goal is to choose labels so that similar rows get labeled the same.\n",
+    "\n",
+    "### K-Means Clustering\n",
+    "\n",
+    "- K: number of clusters:\n",
+    "    - 3-Means => 3 clusters\n",
+    "    - 4-Means => 4 clusters, and so on\n",
+    "- Means: we will find centroids (aka means aka averages) to create clusters\n",
+    "\n",
+    "- import statement:\n",
+    "```python\n",
+    "from sklearn.cluster import KMeans\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a0ad5a5",
+   "metadata": {},
+   "source": [
+    "#### Iterative algorithm for K-Means"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0b83aaf3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generate random data\n",
+    "x, y = datasets.make_blobs(n_samples=100, centers=3, cluster_std=1.2, random_state=3)\n",
+    "df = pd.DataFrame(x, columns=[\"x0\", \"x1\"])\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbced908",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def km_scatter(df, **kwargs):\n",
+    "    \"\"\"\n",
+    "    Produces scatter plot visualizations with x0 on x-axis and y0 on y-axis.\n",
+    "    It can also plot the centroids for clusters.\n",
+    "    Parameters:\n",
+    "        x0 => x-axis\n",
+    "        x1 => y-axis\n",
+    "        cluster => marker type\n",
+    "    \"\"\"\n",
+    "    ax = kwargs.pop(\"ax\", None)\n",
+    "    if not \"label\" in df.columns:\n",
+    "        return df.plot.scatter(x=\"x0\", y=\"x1\", marker=\"$?$\", ax=ax, **kwargs)\n",
+    "\n",
+    "    for marker in set(df[\"label\"]):\n",
+    "        sub_df = df[df[\"label\"] == marker]\n",
+    "        ax = sub_df.plot.scatter(x=\"x0\", y=\"x1\", marker=marker, ax=ax, **kwargs)\n",
+    "    return ax\n",
+    "\n",
+    "ax = km_scatter(df, s=100, c=\"0.7\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "47686eee",
+   "metadata": {},
+   "source": [
+    "### Hard Problem\n",
+    "\n",
+    "Finding the best answer. What is the answer? Determing the centroids of the clusters.\n",
+    "\n",
+    "### Easier Problem\n",
+    "\n",
+    "Taking a random answer and make it a little better. Then repeat!\n",
+    "Downside? If randomization leads to very bad initial choice of centroids, that might lead to bad clustering (fewer clusters)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f8bde9e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clusters = np.random.uniform(-5, 5, size=(3, 2))\n",
+    "clusters = pd.DataFrame(clusters, columns=[\"x0\", \"x1\"])\n",
+    "clusters[\"label\"] = [\"o\", \"+\", \"x\"]\n",
+    "\n",
+    "ax = km_scatter(df, s=100, c=\"0.7\")\n",
+    "km_scatter(clusters, s=200, c=\"red\", ax=ax)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3fe986c",
+   "metadata": {},
+   "source": [
+    "Two variables for us to deal with:\n",
+    "1. clusters: contains location of centroids and a label for them\n",
+    "2. df: contains the actual data points"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cfa1f1aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clusters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f210c534",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a28466ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class KM:\n",
+    "    def __init__(self, df, clusters):\n",
+    "        # We make copies because we are going to keep changing the dataframe to \n",
+    "        # identify better clusters\n",
+    "        self.df = df.copy()\n",
+    "        self.clusters = clusters.copy()\n",
+    "        self.labels = clusters[\"label\"].values\n",
+    "        \n",
+    "    def plot(self):\n",
+    "        ax = km_scatter(self.df, color=\"0.7\", s=100)\n",
+    "        km_scatter(self.clusters, ax=ax, color=\"red\", s=200)\n",
+    "        \n",
+    "    def assign_points(self):\n",
+    "        \"\"\"\n",
+    "        compute Euclidean distance between each point and each centroids\n",
+    "        \"\"\"\n",
+    "        pass\n",
+    "    \n",
+    "    def update_centers(self):\n",
+    "        \"\"\"\n",
+    "        update centroids by taking mean of the points that are nearest to that\n",
+    "        particular centroid\n",
+    "        \"\"\"\n",
+    "        pass\n",
+    "\n",
+    "\"\"\"\n",
+    "High-level algorithm:\n",
+    "1. Start with random locations for centroids\n",
+    "2. Iterate over each data point:\n",
+    "    1. Find the distance (Euclidean distance) between current data point and each centroid.\n",
+    "    2. Find the minimum of those distances and the corresponding label.\n",
+    "    3. Assign current data point to the closest cluster centroid label.\n",
+    "4. Once all points are assigned, compute new centroid for each cluster. Iterate over \n",
+    "   each cluster:\n",
+    "    1. Extract subset of data points which got assigned to curr cluster label.\n",
+    "    2. Compute mean of all the assigned data points.\n",
+    "    3. Update cluster centroid.\n",
+    "5. Repeat steps 2 to 4 many times (iterative improvement).\n",
+    "\"\"\"\n",
+    "\n",
+    "# Creating object instance\n",
+    "km = KM(df, clusters)\n",
+    "km.plot()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "938a6cc5",
+   "metadata": {},
+   "source": [
+    "### `sklearn KMeans`\n",
+    "\n",
+    "- import statement:\n",
+    "```python\n",
+    "from sklearn.cluster import KMeans\n",
+    "```\n",
+    "- documentation: https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html\n",
+    "\n",
+    "**Instantiation:**\n",
+    "`KMeans(n_clusters=<num>, n_init=<num>, max_iter=<num>)`\n",
+    "- `n_clusters`: number of clusters to be formed\n",
+    "- `n_init`: number of initial random seeds to try (to avoid downside of bad initial random choices)\n",
+    "- `max_iter`: maximum number of iterations for a single K-means run (single starting seed)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "caa96a1e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "km_cluster = \n",
+    "km_cluster"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ea51243c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84e59c4a",
+   "metadata": {},
+   "source": [
+    "**Methods:**\n",
+    "1. `fit`: find good centroids\n",
+    "2. `transform`: give me the distances from each point to each centroid\n",
+    "3. `predict`: give me the chosen group labels\n",
+    "\n",
+    "**Attributes:**\n",
+    "- `<km object>.cluster_centers_`: coordinates of cluster centers\n",
+    "- `<km object>.inertia_`: sum of squared distances of samples to their closest cluster center"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "26be1744",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# `fit`: find good centroids\n",
+    "km_cluster.fit(df)\n",
+    "# coordinates of cluster centers\n",
+    "km_cluster.cluster_centers_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6ce05e61",
+   "metadata": {},
+   "source": [
+    "**Observeration:** 3 rows (because we have 3 clusters), and 2 columns (because the df had 2 columns)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2df977a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# `transform`: give me the distances from each point to each centroid\n",
+    "km_cluster.transform(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7cd8409e",
+   "metadata": {},
+   "source": [
+    "**Observations**: Each row corresponds to a row in df. 3 columns correspond to 3 distances to the centroids."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a65a976",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# `predict`: give me the chosen group labels\n",
+    "km_cluster.predict(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "240d995a",
+   "metadata": {},
+   "source": [
+    "### How many clusters do we need?\n",
+    "\n",
+    "- metric: `<km object>.inertia_`: sum of squared distances of samples to their closest cluster center"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bf73d2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "km_cluster.inertia_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57b5ccc4",
+   "metadata": {},
+   "source": [
+    "**Observation**: we want \"inertia\" to be as small as possible."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae70b416",
+   "metadata": {},
+   "source": [
+    "### Elbow plot to determine `n_clusters`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "607a96b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create a series with clusters 1 to 10 and corresponding values are equal to intertia \n",
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "\n",
+    "\n",
+    "s"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "388cd23f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eab497cd",
+   "metadata": {},
+   "source": [
+    "**Observation**: there is an \"elbow\" around `n_clusters`=3."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e763d1c",
+   "metadata": {},
+   "source": [
+    "#### Will we always have a clear \"elbow\"?\n",
+    "\n",
+    "- Let's generate uniform random data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5ad30ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = pd.DataFrame(np.random.uniform(0, 10, (100, 2)))\n",
+    "\n",
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df2)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c6decdab-74a3-45b5-a408-e7b54bd992d9",
+   "metadata": {},
+   "source": [
+    "**Observation**: there is an \"elbow\" around `n_clusters`=3."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c6115b0-61df-4660-8355-3cd56bd94080",
+   "metadata": {},
+   "source": [
+    "#### Will we always have a clear \"elbow\"?\n",
+    "\n",
+    "- Let's generate uniform random data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "424743f8-41de-42b8-ab78-07901682ee84",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = pd.DataFrame(np.random.uniform(0, 10, (100, 2)))\n",
+    "df2.plot.scatter(0, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fba71303-d4c6-46d3-ae8e-f0e863d8e032",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df2)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8af299e7",
+   "metadata": {},
+   "source": [
+    "### K-Means use cases:\n",
+    "\n",
+    "1. estimator\n",
+    "2. transformer:\n",
+    "    - sometimes we'll use an unsupervised learning technique (like k-means) to pre-process data, creating better inputs for a supervised learning technique (like logistic regression)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b99861d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_data():\n",
+    "    x, y = datasets.make_blobs(n_samples=250, centers=5, random_state=5)\n",
+    "    xcols = [\"x0\", \"x1\"]\n",
+    "    df1 = pd.DataFrame(x, columns=xcols)\n",
+    "    df1[\"y\"] = y > 0\n",
+    "\n",
+    "    df2 = pd.DataFrame(np.random.uniform(-10, 10, size=(250, 2)), columns=[\"x0\", \"x1\"])\n",
+    "    df2[\"y\"] = False\n",
+    "\n",
+    "    return pd.concat((df1, df2))\n",
+    "\n",
+    "train, test = train_test_split(make_data())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c1a0353f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.rcParams[\"font.size\"] = 16\n",
+    "fig, ax = plt.subplots(ncols=2, figsize=(10,4))\n",
+    "train.plot.scatter(x=\"x0\", y=\"x1\", c=train[\"y\"], vmin=-1, ax=ax[0])\n",
+    "test.plot.scatter(x=\"x0\", y=\"x1\", c=\"red\", ax=ax[1])\n",
+    "ax[0].set_title(\"Training Data\")\n",
+    "ax[1].set_title(\"Test Data\")\n",
+    "plt.subplots_adjust(wspace=0.4)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57800660",
+   "metadata": {},
+   "source": [
+    "#### Objective: use `LogisticRegression` to classify points as \"black\" or \"gray\"."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cba5b0b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"km\", KMeans(10, n_init = 320)),\n",
+    "    (\"lr\", LogisticRegression()),\n",
+    "])\n",
+    "# TO DO: fit the model with train columns \"x0\", \"x1\" and test column y\n",
+    "\n",
+    "# TO DO: score the model with test columns \"x0\", \"x1\" and test column y\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e78a788c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"km\", KMeans(10, n_init = 320)),\n",
+    "    (\"std\", StandardScaler()),\n",
+    "    (\"lr\", LogisticRegression()),\n",
+    "])\n",
+    "model.fit(train[[\"x0\", \"x1\"]], train[\"y\"])\n",
+    "model.score(test[[\"x0\", \"x1\"]], test[\"y\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0d506007",
+   "metadata": {},
+   "source": [
+    "### `StandardScaler` with `KMeans`\n",
+    "\n",
+    "Recall that `StandardScaler` should always be applied after applying `PolynomialFeatures` (from last lecture)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1229aad1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = datasets.make_blobs(centers=np.array([(0, 0), (0, 20), (3, 20)]))[0]\n",
+    "df = pd.DataFrame(x)\n",
+    "df.plot.scatter(x=0, y=1, figsize=(6, 4))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f21a66d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "km_c = KMeans(2, n_init = 320)\n",
+    "km_c.fit(df)\n",
+    "km_c.predict(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7dc700d4",
+   "metadata": {},
+   "source": [
+    "#### `fit_predict(...)` is a shortcut for `fit` and `predict` method invocations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bc1d18d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "KMeans(2, n_init = 320).fit_predict(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2dfa6bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# -1 => white, 0 => gray, 1 => black\n",
+    "df.plot.scatter(x=0, y=1, figsize=(6, 4), c=KMeans(2, n_init = 320).fit_predict(df), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "762f2882",
+   "metadata": {},
+   "source": [
+    "**Observation**: scale for columns are intentionally not specified."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f99dfeb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d444185c",
+   "metadata": {},
+   "source": [
+    "Let's make a copy of the data. Assuming initial data for both columns is in \"km\", let's convert one column (`0`) into \"meters\". "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e437218",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = df.copy()\n",
+    "df2[0] *= 1000 # km => m\n",
+    "df2.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c99315a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2.plot.scatter(x=0, y=1, figsize=(6,4), c=KMeans(2, n_init = 320).fit_predict(df2), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3966ddd3",
+   "metadata": {},
+   "source": [
+    "**Observations**:\n",
+    "- One would expect to see the same clusters, but that is not happening here. Why?\n",
+    "    - x-axis difference is too high when compared to the y-axis difference\n",
+    "    - That is, KMeans doesn't get that x-axis has scaled data, whereas y-axis doesn't have scaled data\n",
+    "- This is not too far off from realistic datasets. \n",
+    "    - That is, real-world dataset columns might have difference units. \n",
+    "    - For example, one column might be representing temperature data where as another might be representing distance."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b63c9d9b",
+   "metadata": {},
+   "source": [
+    "#### Conclusion: `StandardScaler` should be applied before `KMeans`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2c81ed04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# TO DO: write a pipeline with StandardScaler and KMeans with 2 clusters\n",
+    "\n",
+    "\n",
+    "\n",
+    "df2.plot.scatter(x=0, y=1, figsize=(6, 4), c=model.fit_predict(df2), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "359dd107",
+   "metadata": {},
+   "source": [
+    "### Wisconsin counties example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8847306e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = gpd.read_file(\"counties.geojson\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "377e9bb0",
+   "metadata": {},
+   "source": [
+    "#### If we want to use \"POP100\", \"AREALAND\", \"developed\", \"forest\", \"pasture\", \"crops\" for clustering, what transformer should we use? \n",
+    "\n",
+    "- StandardScaler."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15f0b21c",
+   "metadata": {},
+   "source": [
+    "### Goal here: cluster counties based on similar land usage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55013d0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a199a2af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(column=\"crops\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8735a7bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(column=\"forest\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a42394cb",
+   "metadata": {},
+   "source": [
+    "### KMeans"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a8b3c831",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = KMeans(4, n_init = 320)\n",
+    "# fit\n",
+    "km_c.fit(df[xcols])\n",
+    "# predict\n",
+    "clusters = km_c.predict(df[xcols])\n",
+    "\n",
+    "print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "01189d61",
+   "metadata": {},
+   "source": [
+    "**Observation**: cluster number can be random. That is, if you re-run the above cell twice, you will get different number for each cluster."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1764b5a6",
+   "metadata": {},
+   "source": [
+    "### Agglomerative clustering\n",
+    "\n",
+    "- import statement\n",
+    "```python\n",
+    "from sklearn.cluster import AgglomerativeClustering\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3d7954a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = AgglomerativeClustering(4)\n",
+    "# fit\n",
+    "km_c.fit(df[xcols])\n",
+    "# predict\n",
+    "clusters = km_c.predict(df[xcols])\n",
+    "\n",
+    "print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6f825891",
+   "metadata": {},
+   "source": [
+    "**Observations**: \n",
+    "- no centroids => no inertia => no elbow plots (how do we pick cluster count?):\n",
+    "    - AttributeError: 'AgglomerativeClustering' object has no attribute 'predict'\n",
+    "- no `predict` method, but there is `fit_predict`:\n",
+    "    - AttributeError: 'AgglomerativeClustering' object has no attribute 'predict'\n",
+    "    - why?\n",
+    "        - because each point could lead to a completely different tree\n",
+    "        - remember unlike KMeans (which is top-down), AgglomerativeClustering is bottom-up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e16c6131",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = AgglomerativeClustering(4)\n",
+    "# fit_predict\n",
+    "clusters = km_c.fit_predict(df[xcols])\n",
+    "\n",
+    "# print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5fc2bf08-a0e3-49a3-b089-af0f99f83613",
+   "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": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/lecture_material/24-clustering/24-clustering_002.ipynb b/lecture_material/24-clustering/24-clustering_002.ipynb
new file mode 100644
index 0000000..1550e87
--- /dev/null
+++ b/lecture_material/24-clustering/24-clustering_002.ipynb
@@ -0,0 +1,916 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "035e9e2c-9781-4b9c-8395-be9e55e4e082",
+   "metadata": {},
+   "source": [
+    "# Clustering"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cbd48a28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import geopandas as gpd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression, LogisticRegression\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.preprocessing import PolynomialFeatures\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "# new import statements\n",
+    "from sklearn.cluster import KMeans, AgglomerativeClustering"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e72ea2f4",
+   "metadata": {},
+   "source": [
+    "# Unsupervised Machine Learning: Clustering\n",
+    "\n",
+    "- In classification (supervised), we try to find boundaries/rules to separate points according to pre-determined labels.\n",
+    "- In clustering, the algorithm chooses the labels.  Goal is to choose labels so that similar rows get labeled the same.\n",
+    "\n",
+    "### K-Means Clustering\n",
+    "\n",
+    "- K: number of clusters:\n",
+    "    - 3-Means => 3 clusters\n",
+    "    - 4-Means => 4 clusters, and so on\n",
+    "- Means: we will find centroids (aka means aka averages) to create clusters\n",
+    "\n",
+    "- import statement:\n",
+    "```python\n",
+    "from sklearn.cluster import KMeans\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a0ad5a5",
+   "metadata": {},
+   "source": [
+    "#### Iterative algorithm for K-Means"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0b83aaf3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generate random data\n",
+    "x, y = datasets.make_blobs(n_samples=100, centers=3, cluster_std=1.2, random_state=3)\n",
+    "df = pd.DataFrame(x, columns=[\"x0\", \"x1\"])\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbced908",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def km_scatter(df, **kwargs):\n",
+    "    \"\"\"\n",
+    "    Produces scatter plot visualizations with x0 on x-axis and y0 on y-axis.\n",
+    "    It can also plot the centroids for clusters.\n",
+    "    Parameters:\n",
+    "        x0 => x-axis\n",
+    "        x1 => y-axis\n",
+    "        cluster => marker type\n",
+    "    \"\"\"\n",
+    "    ax = kwargs.pop(\"ax\", None)\n",
+    "    if not \"label\" in df.columns:\n",
+    "        return df.plot.scatter(x=\"x0\", y=\"x1\", marker=\"$?$\", ax=ax, **kwargs)\n",
+    "\n",
+    "    for marker in set(df[\"label\"]):\n",
+    "        sub_df = df[df[\"label\"] == marker]\n",
+    "        ax = sub_df.plot.scatter(x=\"x0\", y=\"x1\", marker=marker, ax=ax, **kwargs)\n",
+    "    return ax\n",
+    "\n",
+    "ax = km_scatter(df, s=100, c=\"0.7\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "47686eee",
+   "metadata": {},
+   "source": [
+    "### Hard Problem\n",
+    "\n",
+    "Finding the best answer. What is the answer? Determing the centroids of the clusters.\n",
+    "\n",
+    "### Easier Problem\n",
+    "\n",
+    "Taking a random answer and make it a little better. Then repeat!\n",
+    "Downside? If randomization leads to very bad initial choice of centroids, that might lead to bad clustering (fewer clusters)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6f8bde9e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clusters = np.random.uniform(-5, 5, size=(3, 2))\n",
+    "clusters = pd.DataFrame(clusters, columns=[\"x0\", \"x1\"])\n",
+    "clusters[\"label\"] = [\"o\", \"+\", \"x\"]\n",
+    "\n",
+    "ax = km_scatter(df, s=100, c=\"0.7\")\n",
+    "km_scatter(clusters, s=200, c=\"red\", ax=ax)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3fe986c",
+   "metadata": {},
+   "source": [
+    "Two variables for us to deal with:\n",
+    "1. clusters: contains location of centroids and a label for them\n",
+    "2. df: contains the actual data points"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cfa1f1aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clusters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f210c534",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a28466ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class KM:\n",
+    "    def __init__(self, df, clusters):\n",
+    "        # We make copies because we are going to keep changing the dataframe to \n",
+    "        # identify better clusters\n",
+    "        self.df = df.copy()\n",
+    "        self.clusters = clusters.copy()\n",
+    "        self.labels = clusters[\"label\"].values\n",
+    "        \n",
+    "    def plot(self):\n",
+    "        ax = km_scatter(self.df, color=\"0.7\", s=100)\n",
+    "        km_scatter(self.clusters, ax=ax, color=\"red\", s=200)\n",
+    "        \n",
+    "    def assign_points(self):\n",
+    "        \"\"\"\n",
+    "        compute Euclidean distance between each point and each centroids\n",
+    "        \"\"\"\n",
+    "        pass\n",
+    "    \n",
+    "    def update_centers(self):\n",
+    "        \"\"\"\n",
+    "        update centroids by taking mean of the points that are nearest to that\n",
+    "        particular centroid\n",
+    "        \"\"\"\n",
+    "        pass\n",
+    "\n",
+    "\"\"\"\n",
+    "High-level algorithm:\n",
+    "1. Start with random locations for centroids\n",
+    "2. Iterate over each data point:\n",
+    "    1. Find the distance (Euclidean distance) between current data point and each centroid.\n",
+    "    2. Find the minimum of those distances and the corresponding label.\n",
+    "    3. Assign current data point to the closest cluster centroid label.\n",
+    "4. Once all points are assigned, compute new centroid for each cluster. Iterate over \n",
+    "   each cluster:\n",
+    "    1. Extract subset of data points which got assigned to curr cluster label.\n",
+    "    2. Compute mean of all the assigned data points.\n",
+    "    3. Update cluster centroid.\n",
+    "5. Repeat steps 2 to 4 many times (iterative improvement).\n",
+    "\"\"\"\n",
+    "\n",
+    "# Creating object instance\n",
+    "km = KM(df, clusters)\n",
+    "km.plot()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "938a6cc5",
+   "metadata": {},
+   "source": [
+    "### `sklearn KMeans`\n",
+    "\n",
+    "- import statement:\n",
+    "```python\n",
+    "from sklearn.cluster import KMeans\n",
+    "```\n",
+    "- documentation: https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html\n",
+    "\n",
+    "**Instantiation:**\n",
+    "`KMeans(n_clusters=<num>, n_init=<num>, max_iter=<num>)`\n",
+    "- `n_clusters`: number of clusters to be formed\n",
+    "- `n_init`: number of initial random seeds to try (to avoid downside of bad initial random choices)\n",
+    "- `max_iter`: maximum number of iterations for a single K-means run (single starting seed)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "caa96a1e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "km_cluster = \n",
+    "km_cluster"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ea51243c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84e59c4a",
+   "metadata": {},
+   "source": [
+    "**Methods:**\n",
+    "1. `fit`: find good centroids\n",
+    "2. `transform`: give me the distances from each point to each centroid\n",
+    "3. `predict`: give me the chosen group labels\n",
+    "\n",
+    "**Attributes:**\n",
+    "- `<km object>.cluster_centers_`: coordinates of cluster centers\n",
+    "- `<km object>.inertia_`: sum of squared distances of samples to their closest cluster center"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "26be1744",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# `fit`: find good centroids\n",
+    "km_cluster.fit(df)\n",
+    "# coordinates of cluster centers\n",
+    "km_cluster.cluster_centers_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6ce05e61",
+   "metadata": {},
+   "source": [
+    "**Observeration:** 3 rows (because we have 3 clusters), and 2 columns (because the df had 2 columns)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2df977a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# `transform`: give me the distances from each point to each centroid\n",
+    "km_cluster.transform(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7cd8409e",
+   "metadata": {},
+   "source": [
+    "**Observations**: Each row corresponds to a row in df. 3 columns correspond to 3 distances to the centroids."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a65a976",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# `predict`: give me the chosen group labels\n",
+    "km_cluster.predict(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "240d995a",
+   "metadata": {},
+   "source": [
+    "### How many clusters do we need?\n",
+    "\n",
+    "- metric: `<km object>.inertia_`: sum of squared distances of samples to their closest cluster center"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bf73d2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "km_cluster.inertia_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57b5ccc4",
+   "metadata": {},
+   "source": [
+    "**Observation**: we want \"inertia\" to be as small as possible."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae70b416",
+   "metadata": {},
+   "source": [
+    "### Elbow plot to determine `n_clusters`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "607a96b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create a series with clusters 1 to 10 and corresponding values are equal to intertia \n",
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "\n",
+    "\n",
+    "s"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "388cd23f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eab497cd",
+   "metadata": {},
+   "source": [
+    "**Observation**: there is an \"elbow\" around `n_clusters`=3."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e763d1c",
+   "metadata": {},
+   "source": [
+    "#### Will we always have a clear \"elbow\"?\n",
+    "\n",
+    "- Let's generate uniform random data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5ad30ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = pd.DataFrame(np.random.uniform(0, 10, (100, 2)))\n",
+    "\n",
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df2)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c6decdab-74a3-45b5-a408-e7b54bd992d9",
+   "metadata": {},
+   "source": [
+    "**Observation**: there is an \"elbow\" around `n_clusters`=3."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c6115b0-61df-4660-8355-3cd56bd94080",
+   "metadata": {},
+   "source": [
+    "#### Will we always have a clear \"elbow\"?\n",
+    "\n",
+    "- Let's generate uniform random data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "424743f8-41de-42b8-ab78-07901682ee84",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = pd.DataFrame(np.random.uniform(0, 10, (100, 2)))\n",
+    "df2.plot.scatter(0, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fba71303-d4c6-46d3-ae8e-f0e863d8e032",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "s = pd.Series(dtype=float)\n",
+    "\n",
+    "for num_clusters in range(1, 11):\n",
+    "    km = KMeans(num_clusters, n_init = 320)\n",
+    "    km.fit(df2)\n",
+    "    s.at[num_clusters] = km.inertia_\n",
+    "\n",
+    "ax = s.plot.line(figsize=(6, 4))\n",
+    "ax.set_ylabel(\"Inertia\")\n",
+    "ax.set_xlabel(\"Number of clusters\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8af299e7",
+   "metadata": {},
+   "source": [
+    "### K-Means use cases:\n",
+    "\n",
+    "1. estimator\n",
+    "2. transformer:\n",
+    "    - sometimes we'll use an unsupervised learning technique (like k-means) to pre-process data, creating better inputs for a supervised learning technique (like logistic regression)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b99861d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_data():\n",
+    "    x, y = datasets.make_blobs(n_samples=250, centers=5, random_state=5)\n",
+    "    xcols = [\"x0\", \"x1\"]\n",
+    "    df1 = pd.DataFrame(x, columns=xcols)\n",
+    "    df1[\"y\"] = y > 0\n",
+    "\n",
+    "    df2 = pd.DataFrame(np.random.uniform(-10, 10, size=(250, 2)), columns=[\"x0\", \"x1\"])\n",
+    "    df2[\"y\"] = False\n",
+    "\n",
+    "    return pd.concat((df1, df2))\n",
+    "\n",
+    "train, test = train_test_split(make_data())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c1a0353f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.rcParams[\"font.size\"] = 16\n",
+    "fig, ax = plt.subplots(ncols=2, figsize=(10,4))\n",
+    "train.plot.scatter(x=\"x0\", y=\"x1\", c=train[\"y\"], vmin=-1, ax=ax[0])\n",
+    "test.plot.scatter(x=\"x0\", y=\"x1\", c=\"red\", ax=ax[1])\n",
+    "ax[0].set_title(\"Training Data\")\n",
+    "ax[1].set_title(\"Test Data\")\n",
+    "plt.subplots_adjust(wspace=0.4)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57800660",
+   "metadata": {},
+   "source": [
+    "#### Objective: use `LogisticRegression` to classify points as \"black\" or \"gray\"."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cba5b0b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"km\", KMeans(10, n_init = 320)),\n",
+    "    (\"lr\", LogisticRegression()),\n",
+    "])\n",
+    "# TO DO: fit the model with train columns \"x0\", \"x1\" and test column y\n",
+    "\n",
+    "# TO DO: score the model with test columns \"x0\", \"x1\" and test column y\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e78a788c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Pipeline([\n",
+    "    (\"km\", KMeans(10, n_init = 320)),\n",
+    "    (\"std\", StandardScaler()),\n",
+    "    (\"lr\", LogisticRegression()),\n",
+    "])\n",
+    "model.fit(train[[\"x0\", \"x1\"]], train[\"y\"])\n",
+    "model.score(test[[\"x0\", \"x1\"]], test[\"y\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0d506007",
+   "metadata": {},
+   "source": [
+    "### `StandardScaler` with `KMeans`\n",
+    "\n",
+    "Recall that `StandardScaler` should always be applied after applying `PolynomialFeatures` (from last lecture)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1229aad1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = datasets.make_blobs(centers=np.array([(0, 0), (0, 20), (3, 20)]))[0]\n",
+    "df = pd.DataFrame(x)\n",
+    "df.plot.scatter(x=0, y=1, figsize=(6, 4))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f21a66d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "km_c = KMeans(2, n_init = 320)\n",
+    "km_c.fit(df)\n",
+    "km_c.predict(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7dc700d4",
+   "metadata": {},
+   "source": [
+    "#### `fit_predict(...)` is a shortcut for `fit` and `predict` method invocations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bc1d18d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "KMeans(2, n_init = 320).fit_predict(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2dfa6bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# -1 => white, 0 => gray, 1 => black\n",
+    "df.plot.scatter(x=0, y=1, figsize=(6, 4), c=KMeans(2, n_init = 320).fit_predict(df), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "762f2882",
+   "metadata": {},
+   "source": [
+    "**Observation**: scale for columns are intentionally not specified."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f99dfeb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d444185c",
+   "metadata": {},
+   "source": [
+    "Let's make a copy of the data. Assuming initial data for both columns is in \"km\", let's convert one column (`0`) into \"meters\". "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e437218",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = df.copy()\n",
+    "df2[0] *= 1000 # km => m\n",
+    "df2.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c99315a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2.plot.scatter(x=0, y=1, figsize=(6,4), c=KMeans(2, n_init = 320).fit_predict(df2), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3966ddd3",
+   "metadata": {},
+   "source": [
+    "**Observations**:\n",
+    "- One would expect to see the same clusters, but that is not happening here. Why?\n",
+    "    - x-axis difference is too high when compared to the y-axis difference\n",
+    "    - That is, KMeans doesn't get that x-axis has scaled data, whereas y-axis doesn't have scaled data\n",
+    "- This is not too far off from realistic datasets. \n",
+    "    - That is, real-world dataset columns might have difference units. \n",
+    "    - For example, one column might be representing temperature data where as another might be representing distance."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b63c9d9b",
+   "metadata": {},
+   "source": [
+    "#### Conclusion: `StandardScaler` should be applied before `KMeans`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2c81ed04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# TO DO: write a pipeline with StandardScaler and KMeans with 2 clusters\n",
+    "\n",
+    "\n",
+    "\n",
+    "df2.plot.scatter(x=0, y=1, figsize=(6, 4), c=model.fit_predict(df2), vmin=-1, vmax=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "359dd107",
+   "metadata": {},
+   "source": [
+    "### Wisconsin counties example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8847306e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = gpd.read_file(\"counties.geojson\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "377e9bb0",
+   "metadata": {},
+   "source": [
+    "#### If we want to use \"POP100\", \"AREALAND\", \"developed\", \"forest\", \"pasture\", \"crops\" for clustering, what transformer should we use? \n",
+    "\n",
+    "- StandardScaler."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15f0b21c",
+   "metadata": {},
+   "source": [
+    "### Goal here: cluster counties based on similar land usage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55013d0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a199a2af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(column=\"crops\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8735a7bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.plot(column=\"forest\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a42394cb",
+   "metadata": {},
+   "source": [
+    "### KMeans"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a8b3c831",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = KMeans(4, n_init = 320)\n",
+    "# fit\n",
+    "km_c.fit(df[xcols])\n",
+    "# predict\n",
+    "clusters = km_c.predict(df[xcols])\n",
+    "\n",
+    "print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "01189d61",
+   "metadata": {},
+   "source": [
+    "**Observation**: cluster number can be random. That is, if you re-run the above cell twice, you will get different number for each cluster."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1764b5a6",
+   "metadata": {},
+   "source": [
+    "### Agglomerative clustering\n",
+    "\n",
+    "- import statement\n",
+    "```python\n",
+    "from sklearn.cluster import AgglomerativeClustering\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3d7954a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = AgglomerativeClustering(4)\n",
+    "# fit\n",
+    "km_c.fit(df[xcols])\n",
+    "# predict\n",
+    "clusters = km_c.predict(df[xcols])\n",
+    "\n",
+    "print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6f825891",
+   "metadata": {},
+   "source": [
+    "**Observations**: \n",
+    "- no centroids => no inertia => no elbow plots (how do we pick cluster count?):\n",
+    "    - AttributeError: 'AgglomerativeClustering' object has no attribute 'predict'\n",
+    "- no `predict` method, but there is `fit_predict`:\n",
+    "    - AttributeError: 'AgglomerativeClustering' object has no attribute 'predict'\n",
+    "    - why?\n",
+    "        - because each point could lead to a completely different tree\n",
+    "        - remember unlike KMeans (which is top-down), AgglomerativeClustering is bottom-up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e16c6131",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xcols = [\"developed\", \"forest\", \"pasture\", \"crops\"]\n",
+    "\n",
+    "# instantiate\n",
+    "km_c = AgglomerativeClustering(4)\n",
+    "# fit_predict\n",
+    "clusters = km_c.fit_predict(df[xcols])\n",
+    "\n",
+    "# print(km_c.inertia_)\n",
+    "print(clusters)\n",
+    "\n",
+    "df.plot(column=clusters, cmap=\"tab10\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5fc2bf08-a0e3-49a3-b089-af0f99f83613",
+   "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": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
-- 
GitLab