{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "7b75e6ad",
   "metadata": {},
   "source": [
    "# Principal Component Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4f98ef84",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:39.547981Z",
     "iopub.status.busy": "2026-10-24T07:02:39.547698Z",
     "iopub.status.idle": "2026-10-24T07:02:40.566095Z",
     "shell.execute_reply": "2026-10-24T07:02:40.565675Z"
    },
    "tags": [
     "hide-input",
     "thebe-init",
     "runnable"
    ]
   },
   "outputs": [],
   "source": [
    "path_data = '../../data/'\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.metrics import silhouette_score\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "67beff6c",
   "metadata": {},
   "source": [
    "```{note}\n",
    "**Optional section.** This section goes beyond the core clustering material in this chapter. The lab and homework do not use it. Read it if you want a tool for looking at data with many columns at once.\n",
    "```\n",
    "\n",
    "In {doc}`1602-k-means-workflow` you clustered the wholesale clients on two spending columns, so you could see every client on one scatter plot. The data have six spending columns, and real customer and product tables often have many more. **Principal component analysis (PCA)** is a way to summarize many correlated columns with a few new ones, so that you can plot the data, see its main patterns, and check what a clustering found."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4356805c",
   "metadata": {},
   "source": [
    "```{contents}\n",
    ":local:\n",
    ":depth: 2\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec3a73d7",
   "metadata": {},
   "source": [
    "## Too Many Columns\n",
    "\n",
    "```{index} dimensionality reduction\n",
    "```\n",
    "\n",
    "```{index} dimensionality\n",
    "```\n",
    "\n",
    "This section uses the wholesale clients again: 440 clients of a Portuguese distributor, from the UCI Machine Learning Repository (dataset 292, CC BY 4.0), as described in {doc}`1602-k-means-workflow`. This time it uses all six spending columns.\n",
    "\n",
    "| Feature | Meaning |\n",
    "|---|---|\n",
    "| `fresh` | Annual spending on fresh food |\n",
    "| `milk` | Annual spending on milk and dairy products |\n",
    "| `grocery` | Annual spending on grocery items |\n",
    "| `frozen` | Annual spending on frozen food |\n",
    "| `detergents_paper` | Annual spending on cleaning products and paper goods |\n",
    "| `delicatessen` | Annual spending on delicatessen items |\n",
    "\n",
    "All amounts are in monetary units per year."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "798c8212",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.567308Z",
     "iopub.status.busy": "2026-10-24T07:02:40.567207Z",
     "iopub.status.idle": "2026-10-24T07:02:40.571887Z",
     "shell.execute_reply": "2026-10-24T07:02:40.571534Z"
    },
    "tags": []
   },
   "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>client_id</th>\n",
       "      <th>channel</th>\n",
       "      <th>region</th>\n",
       "      <th>fresh</th>\n",
       "      <th>milk</th>\n",
       "      <th>grocery</th>\n",
       "      <th>frozen</th>\n",
       "      <th>detergents_paper</th>\n",
       "      <th>delicatessen</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>W001</td>\n",
       "      <td>Retail</td>\n",
       "      <td>Other</td>\n",
       "      <td>12669</td>\n",
       "      <td>9656</td>\n",
       "      <td>7561</td>\n",
       "      <td>214</td>\n",
       "      <td>2674</td>\n",
       "      <td>1338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>W002</td>\n",
       "      <td>Retail</td>\n",
       "      <td>Other</td>\n",
       "      <td>7057</td>\n",
       "      <td>9810</td>\n",
       "      <td>9568</td>\n",
       "      <td>1762</td>\n",
       "      <td>3293</td>\n",
       "      <td>1776</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>W003</td>\n",
       "      <td>Retail</td>\n",
       "      <td>Other</td>\n",
       "      <td>6353</td>\n",
       "      <td>8808</td>\n",
       "      <td>7684</td>\n",
       "      <td>2405</td>\n",
       "      <td>3516</td>\n",
       "      <td>7844</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>W004</td>\n",
       "      <td>HoReCa</td>\n",
       "      <td>Other</td>\n",
       "      <td>13265</td>\n",
       "      <td>1196</td>\n",
       "      <td>4221</td>\n",
       "      <td>6404</td>\n",
       "      <td>507</td>\n",
       "      <td>1788</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>W005</td>\n",
       "      <td>Retail</td>\n",
       "      <td>Other</td>\n",
       "      <td>22615</td>\n",
       "      <td>5410</td>\n",
       "      <td>7198</td>\n",
       "      <td>3915</td>\n",
       "      <td>1777</td>\n",
       "      <td>5185</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  client_id channel region  fresh  milk  grocery  frozen  detergents_paper  \\\n",
       "0      W001  Retail  Other  12669  9656     7561     214              2674   \n",
       "1      W002  Retail  Other   7057  9810     9568    1762              3293   \n",
       "2      W003  Retail  Other   6353  8808     7684    2405              3516   \n",
       "3      W004  HoReCa  Other  13265  1196     4221    6404               507   \n",
       "4      W005  Retail  Other  22615  5410     7198    3915              1777   \n",
       "\n",
       "   delicatessen  \n",
       "0          1338  \n",
       "1          1776  \n",
       "2          7844  \n",
       "3          1788  \n",
       "4          5185  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "clients.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c89f67b6",
   "metadata": {},
   "source": [
    "Each client is now a point in six dimensions. The number of features is the data's **dimensionality**. You cannot draw a six-dimensional scatter plot. You could draw a scatter plot for every pair of features, but six features give 15 pairs, and none of them shows the whole picture.\n",
    "\n",
    "The features also overlap. Clients that buy a lot of groceries tend to buy a lot of cleaning and paper goods too. The correlation table (correlation was introduced in Chapter 12) shows how strongly each pair of features moves together. As in {doc}`1602-k-means-workflow`, take base-10 logarithms of the spending first, because a few very large clients would otherwise dominate the correlations:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "eefe855f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.572901Z",
     "iopub.status.busy": "2026-10-24T07:02:40.572837Z",
     "iopub.status.idle": "2026-10-24T07:02:40.660193Z",
     "shell.execute_reply": "2026-10-24T07:02:40.659827Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 700x550 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "X = np.log10(clients[spend_cols])\n",
    "\n",
    "plt.figure(figsize=(7, 5.5))\n",
    "sns.heatmap(X.corr(), annot=True, fmt='.2f', cmap='RdBu_r', vmin=-1, vmax=1)\n",
    "plt.title('Correlations Between Log Spending Columns')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "40b16b8c",
   "metadata": {},
   "source": [
    "Grocery and detergents and paper have a correlation of 0.80, the highest of the 15 pairs, so they carry much of the same information: knowing a client's spending on one tells you a lot about the other. Milk is also strongly related to both (0.76 with grocery and 0.68 with detergents and paper). Fresh and frozen food are only weakly related to these three, and fresh and frozen food are moderately related to each other (0.38). When columns overlap like this, the data have fewer independent patterns than they have columns.\n",
    "\n",
    "**Dimensionality reduction** means replacing many features with a few new ones that keep most of the information. PCA is the most common method for numeric data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "308d1e43",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.661505Z",
     "iopub.status.busy": "2026-10-24T07:02:40.661404Z",
     "iopub.status.idle": "2026-10-24T07:02:40.664137Z",
     "shell.execute_reply": "2026-10-24T07:02:40.663721Z"
    },
    "tags": [
     "thebe-interactive"
    ]
   },
   "outputs": [],
   "source": [
    "### Exercise: Find the Most Correlated Pair\n",
    "# Use the wholesale clients data with log10 spending.\n",
    "#   1. Take the base-10 logarithm of the six spending columns and compute their correlation table.\n",
    "#   2. Find the correlation between grocery and detergents_paper.\n",
    "#   3. Find the correlation between fresh and frozen.\n",
    "# Print each correlation rounded with round(..., 2).\n",
    "# Print exactly:\n",
    "# grocery vs detergents: 0.8\n",
    "# fresh vs frozen: 0.38\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "### Your code starts here.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "### Your code ends here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "bc378e62",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.665000Z",
     "iopub.status.busy": "2026-10-24T07:02:40.664945Z",
     "iopub.status.idle": "2026-10-24T07:02:40.667673Z",
     "shell.execute_reply": "2026-10-24T07:02:40.667396Z"
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "grocery vs detergents: 0.8\n",
      "fresh vs frozen: 0.38\n"
     ]
    }
   ],
   "source": [
    "### Solution\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "\n",
    "corr = np.log10(ex_clients[ex_spend_cols]).corr()\n",
    "print('grocery vs detergents:', round(corr.loc['grocery', 'detergents_paper'], 2))\n",
    "print('fresh vs frozen:', round(corr.loc['fresh', 'frozen'], 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1f11a32",
   "metadata": {},
   "source": [
    "## Principal Components as New Axes\n",
    "\n",
    "```{index} principal component\n",
    "```\n",
    "\n",
    "```{index} principal component analysis\n",
    "```\n",
    "\n",
    "Start with just two features that move together, grocery and detergents and paper. Put both (after the logarithm) in standard units first (Chapter 12), so that each is measured in standard deviations from its mean, as you did for clustering in the previous section."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f9f3d866",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.668558Z",
     "iopub.status.busy": "2026-10-24T07:02:40.668500Z",
     "iopub.status.idle": "2026-10-24T07:02:40.675566Z",
     "shell.execute_reply": "2026-10-24T07:02:40.675220Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.70710678, 0.70710678])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "two = np.log10(clients[['grocery', 'detergents_paper']])\n",
    "two_su = (two - two.mean()) / two.std(ddof=0)      # standard units\n",
    "\n",
    "pca_two = PCA(n_components=2)\n",
    "pca_two.fit(two_su)\n",
    "\n",
    "direction = pca_two.components_[0]     # direction of the first component\n",
    "direction"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af271a8f",
   "metadata": {},
   "source": [
    "A **principal component** is a new axis through the data. The first principal component, PC1, points in the direction in which the data are most spread out. `components_[0]` holds that direction: it moves about 0.71 standard units in detergents and paper for every 0.71 standard units in grocery, so it runs diagonally through the cloud of points. (The signs of both numbers could be reversed; this comes up again below.) The second component, PC2, is at a right angle to PC1 and picks up the spread that is left over.\n",
    "\n",
    "The plot on the left draws both axes on the scatter plot. The plot on the right shows the same clients measured on the new axes: PCA has simply **rotated the axes** so that the long direction of the cloud lies along the horizontal axis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "954b2cce",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.676562Z",
     "iopub.status.busy": "2026-10-24T07:02:40.676496Z",
     "iopub.status.idle": "2026-10-24T07:02:40.745098Z",
     "shell.execute_reply": "2026-10-24T07:02:40.744786Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1100x450 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "scores_two = pca_two.transform(two_su)     # each client's position on PC1 and PC2\n",
    "\n",
    "fig, axes = plt.subplots(1, 2, figsize=(11, 4.5))\n",
    "\n",
    "axes[0].scatter(two_su['grocery'], two_su['detergents_paper'], alpha=0.5)\n",
    "for i, name in enumerate(['PC1', 'PC2']):\n",
    "    d = pca_two.components_[i] * 2.2\n",
    "    axes[0].annotate('', xy=d, xytext=(0, 0),\n",
    "                     arrowprops=dict(arrowstyle='->', color='crimson', lw=2))\n",
    "    axes[0].text(d[0] * 1.1, d[1] * 1.1, name, color='crimson', fontsize=12)\n",
    "axes[0].set_xlabel('Grocery (log10, standard units)')\n",
    "axes[0].set_ylabel('Detergents and paper (log10, standard units)')\n",
    "axes[0].set_title('Original axes')\n",
    "axes[0].set_xlim(-3.6, 3.6)\n",
    "axes[0].set_ylim(-3.6, 3.6)\n",
    "axes[0].set_aspect('equal')\n",
    "\n",
    "axes[1].scatter(scores_two[:, 0], scores_two[:, 1], alpha=0.5)\n",
    "axes[1].set_xlabel('PC1')\n",
    "axes[1].set_ylabel('PC2')\n",
    "axes[1].set_title('Rotated axes')\n",
    "axes[1].set_aspect('equal')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5583ee07",
   "metadata": {},
   "source": [
    "Most of the spread now runs along PC1, and the points vary only a little along PC2. The model reports how much of the total spread each component captures:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "70c91bf3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.746137Z",
     "iopub.status.busy": "2026-10-24T07:02:40.746075Z",
     "iopub.status.idle": "2026-10-24T07:02:40.747897Z",
     "shell.execute_reply": "2026-10-24T07:02:40.747622Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.89819887, 0.10180113])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pca_two.explained_variance_ratio_"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c9455b17",
   "metadata": {},
   "source": [
    "PC1 captures about 90% of the variation in the two features, and PC2 only about 10%. One number per client, the PC1 score, which you could call \"household-goods spending\", keeps almost all of what grocery and detergents and paper spending tell you. That is the idea of PCA: when features overlap, a few well-chosen directions can replace many columns."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "3c50d52b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.748786Z",
     "iopub.status.busy": "2026-10-24T07:02:40.748735Z",
     "iopub.status.idle": "2026-10-24T07:02:40.751245Z",
     "shell.execute_reply": "2026-10-24T07:02:40.750923Z"
    },
    "tags": [
     "thebe-interactive"
    ]
   },
   "outputs": [],
   "source": [
    "### Exercise: PCA on Two Features\n",
    "# A manager wants one \"fresh and frozen\" measure built from the fresh and frozen columns.\n",
    "#   1. Take log10 of the two columns and put them in standard units.\n",
    "#   2. Fit PCA with 2 components.\n",
    "#   3. Print the share of variation captured by PC1, rounded to 2 decimal places.\n",
    "# Print exactly:\n",
    "# PC1 share: 0.69\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "pair = np.log10(ex_clients[['fresh', 'frozen']])\n",
    "### Your code starts here.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "### Your code ends here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "3ffef2de",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.752024Z",
     "iopub.status.busy": "2026-10-24T07:02:40.751970Z",
     "iopub.status.idle": "2026-10-24T07:02:40.755397Z",
     "shell.execute_reply": "2026-10-24T07:02:40.755084Z"
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PC1 share: 0.69\n"
     ]
    }
   ],
   "source": [
    "### Solution\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "pair = np.log10(ex_clients[['fresh', 'frozen']])\n",
    "\n",
    "pair_su = (pair - pair.mean()) / pair.std(ddof=0)\n",
    "pca_pair = PCA(n_components=2).fit(pair_su)\n",
    "print('PC1 share:', round(pca_pair.explained_variance_ratio_[0], 2))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6c30f289",
   "metadata": {},
   "source": [
    "## Standardize, Then Fit PCA\n",
    "\n",
    "```{index} explained variance ratio\n",
    "```\n",
    "\n",
    "```{index} scree plot\n",
    "```\n",
    "\n",
    "PCA looks for the directions with the most spread, so, like k-means, it depends on the units and the skew of the features. In monetary units, the standard deviation of fresh spending is about 12,600, while that of delicatessen is about 2,800, and a few clients spend many times the typical amount. Here is PCA on the raw features:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "bd27c0c4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.756239Z",
     "iopub.status.busy": "2026-10-24T07:02:40.756179Z",
     "iopub.status.idle": "2026-10-24T07:02:40.759067Z",
     "shell.execute_reply": "2026-10-24T07:02:40.758714Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "fresh               0.977\n",
       "milk                0.121\n",
       "grocery             0.062\n",
       "frozen              0.152\n",
       "detergents_paper   -0.007\n",
       "delicatessen        0.068\n",
       "dtype: float64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pca_raw = PCA().fit(clients[spend_cols])\n",
    "pd.Series(pca_raw.components_[0], index=spend_cols).round(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "0a8c50ab",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.759877Z",
     "iopub.status.busy": "2026-10-24T07:02:40.759825Z",
     "iopub.status.idle": "2026-10-24T07:02:40.761530Z",
     "shell.execute_reply": "2026-10-24T07:02:40.761238Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.float64(0.45961361681363927)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pca_raw.explained_variance_ratio_[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "99690a1f",
   "metadata": {},
   "source": [
    "On the raw features, PC1 is almost exactly `fresh` (weight about 0.98, the others 0.15 or less) and claims about 46% of the variation, only because fresh spending has the largest numbers. As with k-means, take logarithms and put the features in standard units, so that each feature starts with the same spread:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "6a217a7e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.762340Z",
     "iopub.status.busy": "2026-10-24T07:02:40.762290Z",
     "iopub.status.idle": "2026-10-24T07:02:40.765387Z",
     "shell.execute_reply": "2026-10-24T07:02:40.765153Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.44 , 0.271, 0.108, 0.101, 0.049, 0.031])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_scaled = pd.DataFrame(StandardScaler().fit_transform(X), columns=spend_cols)   # standard units\n",
    "\n",
    "pca = PCA()            # keep all 6 components for now\n",
    "pca.fit(X_scaled)\n",
    "\n",
    "pca.explained_variance_ratio_.round(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "155baadc",
   "metadata": {},
   "source": [
    "The **explained variance ratio** of a component is the share of the total variation in the scaled data that the component captures. The ratios are in order from largest to smallest and add up to 1. A **scree plot** shows them as bars, often with the running (cumulative) total as a line:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "bfa238c1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.766371Z",
     "iopub.status.busy": "2026-10-24T07:02:40.766314Z",
     "iopub.status.idle": "2026-10-24T07:02:40.801987Z",
     "shell.execute_reply": "2026-10-24T07:02:40.801652Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 700x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ratios = pca.explained_variance_ratio_\n",
    "pcs = [f'PC{i}' for i in range(1, len(ratios) + 1)]\n",
    "\n",
    "plt.figure(figsize=(7, 4))\n",
    "plt.bar(pcs, ratios, color='steelblue', label='Each component')\n",
    "plt.plot(pcs, ratios.cumsum(), color='crimson', marker='o', label='Cumulative')\n",
    "plt.axhline(0.9, color='gray', linestyle='--', linewidth=1)\n",
    "plt.ylim(0, 1.05)\n",
    "plt.ylabel('Explained variance ratio')\n",
    "plt.title('Scree Plot for Wholesale Clients')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "03a72e2f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.802903Z",
     "iopub.status.busy": "2026-10-24T07:02:40.802852Z",
     "iopub.status.idle": "2026-10-24T07:02:40.805629Z",
     "shell.execute_reply": "2026-10-24T07:02:40.805346Z"
    },
    "tags": []
   },
   "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>component</th>\n",
       "      <th>explained</th>\n",
       "      <th>cumulative</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>PC1</td>\n",
       "      <td>0.440</td>\n",
       "      <td>0.440</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>PC2</td>\n",
       "      <td>0.271</td>\n",
       "      <td>0.711</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>PC3</td>\n",
       "      <td>0.108</td>\n",
       "      <td>0.819</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>PC4</td>\n",
       "      <td>0.101</td>\n",
       "      <td>0.920</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>PC5</td>\n",
       "      <td>0.049</td>\n",
       "      <td>0.969</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>PC6</td>\n",
       "      <td>0.031</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  component  explained  cumulative\n",
       "0       PC1      0.440       0.440\n",
       "1       PC2      0.271       0.711\n",
       "2       PC3      0.108       0.819\n",
       "3       PC4      0.101       0.920\n",
       "4       PC5      0.049       0.969\n",
       "5       PC6      0.031       1.000"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame({'component': pcs,\n",
    "              'explained': ratios.round(3),\n",
    "              'cumulative': ratios.cumsum().round(3)})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d473ec1",
   "metadata": {},
   "source": [
    "**Choosing how many components to keep.** PC1 captures about 44% of the variation, PC2 about 27%, and PC3 about 11%. After PC2 the bars drop and then shrink slowly: PC3 and PC4 hold about 11% and 10%, and PC5 and PC6 together hold about 8%. Three common rules of thumb:\n",
    "\n",
    "- Keep the components before the scree plot levels off (the \"elbow\", as with choosing k in the previous section). Here the bars drop steeply after PC1 and again after PC2, then nearly level off (PC3 and PC4 are about equal), so the elbow suggests two, though it is not sharp.\n",
    "- Keep enough components to reach a target share, such as 80% or 90%. Here, three components reach about 82% and four reach about 92%.\n",
    "- For a picture, keep two. PC1 and PC2 together hold about 71% of the variation, enough to show the main patterns on one scatter plot.\n",
    "\n",
    "As with choosing k, these are guides. The right number depends on what the components will be used for. Six columns do not shrink as much as a table with dozens of overlapping columns would, because these six are only partly correlated."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "65eeb0cd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.806568Z",
     "iopub.status.busy": "2026-10-24T07:02:40.806515Z",
     "iopub.status.idle": "2026-10-24T07:02:40.809589Z",
     "shell.execute_reply": "2026-10-24T07:02:40.809268Z"
    },
    "tags": [
     "thebe-interactive"
    ]
   },
   "outputs": [],
   "source": [
    "### Exercise: How Many Components?\n",
    "# Use ex_X_scaled, the six wholesale spending columns after log10 and standardizing.\n",
    "#   1. Fit PCA with all components.\n",
    "#   2. Compute the cumulative explained variance ratio.\n",
    "#   3. Find the smallest number of components whose cumulative share is at least 0.85.\n",
    "# Print exactly:\n",
    "# Components needed: 4\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "ex_X = np.log10(ex_clients[ex_spend_cols])\n",
    "ex_X_scaled = (ex_X - ex_X.mean()) / ex_X.std(ddof=0)\n",
    "### Your code starts here.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "### Your code ends here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6be6d484",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.810424Z",
     "iopub.status.busy": "2026-10-24T07:02:40.810366Z",
     "iopub.status.idle": "2026-10-24T07:02:40.814077Z",
     "shell.execute_reply": "2026-10-24T07:02:40.813790Z"
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Components needed: 4\n"
     ]
    }
   ],
   "source": [
    "### Solution\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "ex_X = np.log10(ex_clients[ex_spend_cols])\n",
    "ex_X_scaled = (ex_X - ex_X.mean()) / ex_X.std(ddof=0)\n",
    "\n",
    "cumulative = PCA().fit(ex_X_scaled).explained_variance_ratio_.cumsum()\n",
    "needed = int(np.argmax(cumulative >= 0.85)) + 1     # first position that reaches 0.85\n",
    "print('Components needed:', needed)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c1e9b47",
   "metadata": {},
   "source": [
    "## Reading the Loadings\n",
    "\n",
    "```{index} loading\n",
    "```\n",
    "\n",
    "A component is a weighted combination of the original features. The weights are called **loadings**, and they are stored in `components_`, one row per component. A large positive loading means the feature rises with the component; a large negative loading means it falls; a loading near 0 means the feature has little to do with that component."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "79d49150",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.815009Z",
     "iopub.status.busy": "2026-10-24T07:02:40.814958Z",
     "iopub.status.idle": "2026-10-24T07:02:40.817791Z",
     "shell.execute_reply": "2026-10-24T07:02:40.817341Z"
    },
    "tags": []
   },
   "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>PC1</th>\n",
       "      <th>PC2</th>\n",
       "      <th>PC3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fresh</th>\n",
       "      <td>-0.10</td>\n",
       "      <td>0.59</td>\n",
       "      <td>-0.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>milk</th>\n",
       "      <td>0.54</td>\n",
       "      <td>0.13</td>\n",
       "      <td>-0.08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>grocery</th>\n",
       "      <td>0.57</td>\n",
       "      <td>-0.01</td>\n",
       "      <td>-0.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>frozen</th>\n",
       "      <td>-0.14</td>\n",
       "      <td>0.59</td>\n",
       "      <td>-0.03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>detergents_paper</th>\n",
       "      <td>0.55</td>\n",
       "      <td>-0.07</td>\n",
       "      <td>-0.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>delicatessen</th>\n",
       "      <td>0.21</td>\n",
       "      <td>0.53</td>\n",
       "      <td>0.73</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   PC1   PC2   PC3\n",
       "fresh            -0.10  0.59 -0.63\n",
       "milk              0.54  0.13 -0.08\n",
       "grocery           0.57 -0.01 -0.13\n",
       "frozen           -0.14  0.59 -0.03\n",
       "detergents_paper  0.55 -0.07 -0.20\n",
       "delicatessen      0.21  0.53  0.73"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loadings = pd.DataFrame(pca.components_[:3].T, index=spend_cols,\n",
    "                        columns=['PC1', 'PC2', 'PC3'])\n",
    "loadings.round(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "98d48205",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.818656Z",
     "iopub.status.busy": "2026-10-24T07:02:40.818598Z",
     "iopub.status.idle": "2026-10-24T07:02:40.884120Z",
     "shell.execute_reply": "2026-10-24T07:02:40.883787Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1100x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 2, figsize=(11, 4), sharey=True)\n",
    "for ax, pc in zip(axes, ['PC1', 'PC2']):\n",
    "    sns.barplot(x=loadings[pc], y=loadings.index, ax=ax, color='steelblue')\n",
    "    ax.axvline(0, color='black', linewidth=0.8)\n",
    "    ax.set_title(f'Loadings on {pc}')\n",
    "    ax.set_xlabel('Loading')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9bb0a25f",
   "metadata": {},
   "source": [
    "Read each component by looking for the features with the largest loadings, positive and negative:\n",
    "\n",
    "- **PC1**: grocery (0.57), detergents and paper (0.55), and milk (0.54) are high, and fresh (-0.10) and frozen (-0.14) are slightly negative. A client scores high on PC1 by spending a lot on packaged household goods. You might name PC1 **household and packaged goods**.\n",
    "- **PC2**: fresh (0.59), frozen (0.59), and delicatessen (0.53) are high, while milk (0.13), grocery (-0.01), and detergents and paper (-0.07) are near zero. A client scores high on PC2 by spending a lot on fresh, frozen, and delicatessen food. You might name PC2 **fresh and prepared food**.\n",
    "- **PC3** contrasts delicatessen (0.73) with fresh food (-0.63): a client scores high by spending more on delicatessen than on fresh food. It holds a smaller share of the variation than the first two.\n",
    "\n",
    "PC1 and PC2 describe two different kinds of buying, and the fact that they are separate is the point: spending on household goods and spending on food are close to independent across the distributor's clients.\n",
    "\n",
    "```{caution}\n",
    "The names are an interpretation, not something PCA computes. Two analysts can read the same loadings and choose different names. The sign of a component is also arbitrary: another version of scikit-learn could flip PC1 so that all its loadings change sign, which would turn \"high on household goods\" into \"low on household goods\" without changing anything about the data. Always check the loadings before you name a component, and say which features drive it when you present it.\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c0b211c4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.885060Z",
     "iopub.status.busy": "2026-10-24T07:02:40.884995Z",
     "iopub.status.idle": "2026-10-24T07:02:40.888351Z",
     "shell.execute_reply": "2026-10-24T07:02:40.887996Z"
    },
    "tags": [
     "thebe-interactive"
    ]
   },
   "outputs": [],
   "source": [
    "### Exercise: Read the Loadings\n",
    "# Use the loadings table for the six scaled spending columns.\n",
    "#   1. Fit PCA with 3 components on ex_X_scaled and build a table of loadings (features as rows).\n",
    "#   2. Find the feature with the largest absolute loading on PC3.\n",
    "# Print exactly:\n",
    "# Largest PC3 loading: delicatessen\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "ex_X = np.log10(ex_clients[ex_spend_cols])\n",
    "ex_X_scaled = (ex_X - ex_X.mean()) / ex_X.std(ddof=0)\n",
    "### Your code starts here.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "### Your code ends here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "f4df237e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.889316Z",
     "iopub.status.busy": "2026-10-24T07:02:40.889259Z",
     "iopub.status.idle": "2026-10-24T07:02:40.893012Z",
     "shell.execute_reply": "2026-10-24T07:02:40.892706Z"
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Largest PC3 loading: delicatessen\n"
     ]
    }
   ],
   "source": [
    "### Solution\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "ex_X = np.log10(ex_clients[ex_spend_cols])\n",
    "ex_X_scaled = (ex_X - ex_X.mean()) / ex_X.std(ddof=0)\n",
    "\n",
    "pca_fit = PCA(n_components=3).fit(ex_X_scaled)\n",
    "ex_loadings = pd.DataFrame(pca_fit.components_.T, index=ex_X.columns, columns=['PC1', 'PC2', 'PC3'])\n",
    "print('Largest PC3 loading:', ex_loadings['PC3'].abs().idxmax())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e8583134",
   "metadata": {},
   "source": [
    "## PCA with Clustering\n",
    "\n",
    "```{index} PCA; with clustering\n",
    "```\n",
    "\n",
    "PCA and k-means work well together. Cluster the clients on all six scaled features, exactly as in the previous section, and then use PCA to draw the result. First, a quick silhouette check for the number of clusters:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "81e8bd33",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.893977Z",
     "iopub.status.busy": "2026-10-24T07:02:40.893882Z",
     "iopub.status.idle": "2026-10-24T07:02:40.968113Z",
     "shell.execute_reply": "2026-10-24T07:02:40.967708Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2 0.29\n",
      "3 0.258\n",
      "4 0.188\n",
      "5 0.196\n",
      "6 0.199\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7 0.184\n"
     ]
    }
   ],
   "source": [
    "for k in range(2, 8):\n",
    "    labels = KMeans(n_clusters=k, n_init=10, random_state=101).fit_predict(X_scaled)\n",
    "    print(k, round(silhouette_score(X_scaled, labels), 3))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6e61c40a",
   "metadata": {},
   "source": [
    "As in the previous section, the silhouette score is highest at k = 2 (about 0.29) and about the same, 0.18 to 0.20, for k = 4 to 7. No `k` stands out, so keep the choice of k = 4 from the previous section. Fit k-means with 4 clusters and plot each client at its PC1 and PC2 scores, colored by cluster:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ec5e48a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:40.969647Z",
     "iopub.status.busy": "2026-10-24T07:02:40.969559Z",
     "iopub.status.idle": "2026-10-24T07:02:41.025190Z",
     "shell.execute_reply": "2026-10-24T07:02:41.024750Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kmeans = KMeans(n_clusters=4, n_init=10, random_state=101)\n",
    "clients['cluster'] = kmeans.fit_predict(X_scaled)\n",
    "\n",
    "scores = pca.transform(X_scaled)          # PC scores for every client\n",
    "clients['PC1'] = scores[:, 0]\n",
    "clients['PC2'] = scores[:, 1]\n",
    "\n",
    "sns.scatterplot(data=clients, x='PC1', y='PC2', hue='cluster', palette='tab10')\n",
    "plt.xlabel('PC1: household and packaged goods')\n",
    "plt.ylabel('PC2: fresh and prepared food')\n",
    "plt.title('Wholesale Segments on the First Two Components')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6485ecf5",
   "metadata": {},
   "source": [
    "Six features are now one picture. The four segments occupy different regions of the plot, though they touch where the clients are in between: the clients form a continuous cloud, as the silhouette scores showed. The axis names come from the loadings, so the picture already suggests what each segment is: high or low on household goods, high or low on fresh and prepared food. To describe the segments, though, go back to the original units, as in the previous section. A manager can act on monetary units, not on PC scores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "c8e42924",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:41.026517Z",
     "iopub.status.busy": "2026-10-24T07:02:41.026434Z",
     "iopub.status.idle": "2026-10-24T07:02:41.031463Z",
     "shell.execute_reply": "2026-10-24T07:02:41.030966Z"
    },
    "tags": []
   },
   "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>fresh</th>\n",
       "      <th>milk</th>\n",
       "      <th>grocery</th>\n",
       "      <th>frozen</th>\n",
       "      <th>detergents_paper</th>\n",
       "      <th>delicatessen</th>\n",
       "      <th>clients</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cluster</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7842.0</td>\n",
       "      <td>8384.0</td>\n",
       "      <td>12311.0</td>\n",
       "      <td>1365.0</td>\n",
       "      <td>4621.0</td>\n",
       "      <td>1682.0</td>\n",
       "      <td>119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7814.0</td>\n",
       "      <td>1112.0</td>\n",
       "      <td>1820.0</td>\n",
       "      <td>1386.0</td>\n",
       "      <td>224.0</td>\n",
       "      <td>432.0</td>\n",
       "      <td>130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>16978.0</td>\n",
       "      <td>3122.0</td>\n",
       "      <td>3430.0</td>\n",
       "      <td>4324.0</td>\n",
       "      <td>515.0</td>\n",
       "      <td>1374.0</td>\n",
       "      <td>130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1073.0</td>\n",
       "      <td>6964.0</td>\n",
       "      <td>10518.0</td>\n",
       "      <td>340.0</td>\n",
       "      <td>4508.0</td>\n",
       "      <td>295.0</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           fresh    milk  grocery  frozen  detergents_paper  delicatessen  \\\n",
       "cluster                                                                     \n",
       "0         7842.0  8384.0  12311.0  1365.0            4621.0        1682.0   \n",
       "1         7814.0  1112.0   1820.0  1386.0             224.0         432.0   \n",
       "2        16978.0  3122.0   3430.0  4324.0             515.0        1374.0   \n",
       "3         1073.0  6964.0  10518.0   340.0            4508.0         295.0   \n",
       "\n",
       "         clients  \n",
       "cluster           \n",
       "0            119  \n",
       "1            130  \n",
       "2            130  \n",
       "3             61  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "profile = clients.groupby('cluster')[spend_cols].median().round(0)\n",
    "profile['clients'] = clients['cluster'].value_counts().sort_index()\n",
    "profile"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af9fec66",
   "metadata": {},
   "source": [
    "The profiles match the picture, and they are the same four segments as in the previous section. One cluster buys a lot of milk, grocery, and detergents and paper (household-goods retailers, high on PC1). One buys little milk, grocery, or cleaning goods (small accounts, low on PC1). One buys the most fresh and frozen food (fresh and frozen food service, high on PC2). One buys household goods but almost no fresh or frozen food (packaged-goods shops, high on PC1 and low on PC2). As before, the cluster numbers themselves are arbitrary.\n",
    "\n",
    "**PCA for visualization vs. PCA before clustering.** Above, k-means used all six features, and PCA only drew the result. Another option is to reduce the data first and cluster the PC scores. This can help when there are many noisy or overlapping features, and it makes the clusters easier to plot. But the clusters then ignore whatever the dropped components held; here, clustering only PC1 and PC2 would ignore the 29% of the variation in PC3 to PC6, including the contrast between delicatessen and fresh food. Compare the two:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "f4493bd9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:41.032679Z",
     "iopub.status.busy": "2026-10-24T07:02:41.032619Z",
     "iopub.status.idle": "2026-10-24T07:02:41.046336Z",
     "shell.execute_reply": "2026-10-24T07:02:41.045879Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "first 2 PCs      0    1    2    3\n",
      "all 6 features                   \n",
      "0                7    0    5  107\n",
      "1                1  127    2    0\n",
      "2                0    2  126    2\n",
      "3               61    0    0    0\n",
      "Clients grouped the same way, ignoring the names: 421 of 440\n"
     ]
    }
   ],
   "source": [
    "labels_2pc = KMeans(n_clusters=4, n_init=10, random_state=101).fit_predict(scores[:, :2])\n",
    "table = pd.crosstab(clients['cluster'], labels_2pc, rownames=['all 6 features'], colnames=['first 2 PCs'])\n",
    "print(table)\n",
    "\n",
    "same = table.max(axis=1).sum()      # clients in the best-matching group of each row\n",
    "print('Clients grouped the same way, ignoring the names:', same, 'of', len(clients))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0c57f989",
   "metadata": {},
   "source": [
    "Each row has one large count, so the two approaches put most clients in the same group (the cluster numbers differ, but the groups largely agree). They agree on 421 of 440 clients (96%), and the 19 that differ sit between groups. That is because the first two components hold most of the variation, and the segments differ mostly on household goods and on fresh and frozen food. With more columns or more complex data the two approaches often disagree more, so report which one you used."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "937d2b69",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:41.047452Z",
     "iopub.status.busy": "2026-10-24T07:02:41.047394Z",
     "iopub.status.idle": "2026-10-24T07:02:41.050973Z",
     "shell.execute_reply": "2026-10-24T07:02:41.050541Z"
    },
    "tags": [
     "thebe-interactive"
    ]
   },
   "outputs": [],
   "source": [
    "### Exercise: Cluster the PC Scores\n",
    "# Use the PC scores of the six scaled wholesale spending columns.\n",
    "#   1. Fit PCA on ex_X_scaled and keep the first 3 components' scores.\n",
    "#   2. Fit KMeans with 4 clusters (n_init=10, random_state=101) on those scores.\n",
    "#   3. Print the cluster sizes sorted from smallest to largest, as a list.\n",
    "# Print exactly:\n",
    "# Cluster sizes: [69, 110, 116, 145]\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.cluster import KMeans\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "ex_X = np.log10(ex_clients[ex_spend_cols])\n",
    "ex_X_scaled = (ex_X - ex_X.mean()) / ex_X.std(ddof=0)\n",
    "### Your code starts here.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "### Your code ends here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "e0605585",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-10-24T07:02:41.052121Z",
     "iopub.status.busy": "2026-10-24T07:02:41.052067Z",
     "iopub.status.idle": "2026-10-24T07:02:41.062075Z",
     "shell.execute_reply": "2026-10-24T07:02:41.061798Z"
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cluster sizes: [69, 110, 116, 145]\n"
     ]
    }
   ],
   "source": [
    "### Solution\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.cluster import KMeans\n",
    "\n",
    "ex_clients = pd.read_csv(path_data + 'wholesale_customers.csv')\n",
    "ex_spend_cols = ['fresh', 'milk', 'grocery', 'frozen', 'detergents_paper', 'delicatessen']\n",
    "ex_X = np.log10(ex_clients[ex_spend_cols])\n",
    "ex_X_scaled = (ex_X - ex_X.mean()) / ex_X.std(ddof=0)\n",
    "\n",
    "scores3 = PCA(n_components=3).fit_transform(ex_X_scaled)\n",
    "ex_labels = KMeans(n_clusters=4, n_init=10, random_state=101).fit_predict(scores3)\n",
    "print('Cluster sizes:', sorted(np.bincount(ex_labels).tolist()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "def9a5b9",
   "metadata": {},
   "source": [
    "## Limits of PCA\n",
    "\n",
    "```{index} PCA; limits\n",
    "```\n",
    "\n",
    "PCA is a useful first look at data with many columns, but keep its limits in mind:\n",
    "\n",
    "- **Linear only.** Each component is a straight-line direction, a weighted sum of the features. Curved or more complex patterns may not show up in the first few components.\n",
    "- **Sensitive to scaling.** As you saw, PCA on raw features is dominated by whichever feature has the biggest numbers, here fresh food. Standardize first unless the features already share a unit, and take logarithms when a few very large values stretch a column.\n",
    "- **Harder to explain.** \"PC1 score of 1.8\" means nothing to a manager until you translate it into the features that drive it. Original columns such as grocery and fresh are easier to explain, so present results in the original units and use components as a summary or a map.\n",
    "- **Spread is not importance.** PCA keeps the directions with the most variation, which are not always the ones that matter for a decision. A small component can still hold the signal that predicts churn or profit.\n",
    "- **Numeric features.** PCA works with numeric columns. Categories such as channel or region need other methods."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.13.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}
