From df28f7edaf6adfef499a767ce15c852ccf66d11a Mon Sep 17 00:00:00 2001
From: Jake Walker <jacob.walker@qinetiq.com>
Date: Thu, 22 Feb 2024 16:59:37 +0000
Subject: [PATCH] Add breast cancer data exploration

---
 PCA Clustering.ipynb | 642 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 641 insertions(+), 1 deletion(-)

diff --git a/PCA Clustering.ipynb b/PCA Clustering.ipynb
index 78e4816..3140b67 100644
--- a/PCA Clustering.ipynb	
+++ b/PCA Clustering.ipynb	
@@ -10,11 +10,651 @@
     "\n",
     "From: <https://www.datacamp.com/tutorial/principal-component-analysis-in-python>"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Breast Cancer Data Exploration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.datasets import load_breast_cancer\n",
+    "\n",
+    "breast = load_breast_cancer()\n",
+    "breast_data = breast.data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(569, 30)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "breast_data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(569,)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "breast_labels = breast.target\n",
+    "breast_labels.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels = np.reshape(breast_labels, (569, 1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(569, 31)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "final_breast_data = np.concatenate([breast_data, labels], axis=1)\n",
+    "final_breast_data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "breast_dataset = pd.DataFrame(final_breast_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',\n",
+       "       'mean smoothness', 'mean compactness', 'mean concavity',\n",
+       "       'mean concave points', 'mean symmetry', 'mean fractal dimension',\n",
+       "       'radius error', 'texture error', 'perimeter error', 'area error',\n",
+       "       'smoothness error', 'compactness error', 'concavity error',\n",
+       "       'concave points error', 'symmetry error',\n",
+       "       'fractal dimension error', 'worst radius', 'worst texture',\n",
+       "       'worst perimeter', 'worst area', 'worst smoothness',\n",
+       "       'worst compactness', 'worst concavity', 'worst concave points',\n",
+       "       'worst symmetry', 'worst fractal dimension'], dtype='<U23')"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "features = breast.feature_names\n",
+    "features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features_labels = np.append(features, \"label\")\n",
+    "breast_dataset.columns = features_labels"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "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>mean radius</th>\n",
+       "      <th>mean texture</th>\n",
+       "      <th>mean perimeter</th>\n",
+       "      <th>mean area</th>\n",
+       "      <th>mean smoothness</th>\n",
+       "      <th>mean compactness</th>\n",
+       "      <th>mean concavity</th>\n",
+       "      <th>mean concave points</th>\n",
+       "      <th>mean symmetry</th>\n",
+       "      <th>mean fractal dimension</th>\n",
+       "      <th>...</th>\n",
+       "      <th>worst texture</th>\n",
+       "      <th>worst perimeter</th>\n",
+       "      <th>worst area</th>\n",
+       "      <th>worst smoothness</th>\n",
+       "      <th>worst compactness</th>\n",
+       "      <th>worst concavity</th>\n",
+       "      <th>worst concave points</th>\n",
+       "      <th>worst symmetry</th>\n",
+       "      <th>worst fractal dimension</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>17.99</td>\n",
+       "      <td>10.38</td>\n",
+       "      <td>122.80</td>\n",
+       "      <td>1001.0</td>\n",
+       "      <td>0.11840</td>\n",
+       "      <td>0.27760</td>\n",
+       "      <td>0.3001</td>\n",
+       "      <td>0.14710</td>\n",
+       "      <td>0.2419</td>\n",
+       "      <td>0.07871</td>\n",
+       "      <td>...</td>\n",
+       "      <td>17.33</td>\n",
+       "      <td>184.60</td>\n",
+       "      <td>2019.0</td>\n",
+       "      <td>0.1622</td>\n",
+       "      <td>0.6656</td>\n",
+       "      <td>0.7119</td>\n",
+       "      <td>0.2654</td>\n",
+       "      <td>0.4601</td>\n",
+       "      <td>0.11890</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>20.57</td>\n",
+       "      <td>17.77</td>\n",
+       "      <td>132.90</td>\n",
+       "      <td>1326.0</td>\n",
+       "      <td>0.08474</td>\n",
+       "      <td>0.07864</td>\n",
+       "      <td>0.0869</td>\n",
+       "      <td>0.07017</td>\n",
+       "      <td>0.1812</td>\n",
+       "      <td>0.05667</td>\n",
+       "      <td>...</td>\n",
+       "      <td>23.41</td>\n",
+       "      <td>158.80</td>\n",
+       "      <td>1956.0</td>\n",
+       "      <td>0.1238</td>\n",
+       "      <td>0.1866</td>\n",
+       "      <td>0.2416</td>\n",
+       "      <td>0.1860</td>\n",
+       "      <td>0.2750</td>\n",
+       "      <td>0.08902</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>19.69</td>\n",
+       "      <td>21.25</td>\n",
+       "      <td>130.00</td>\n",
+       "      <td>1203.0</td>\n",
+       "      <td>0.10960</td>\n",
+       "      <td>0.15990</td>\n",
+       "      <td>0.1974</td>\n",
+       "      <td>0.12790</td>\n",
+       "      <td>0.2069</td>\n",
+       "      <td>0.05999</td>\n",
+       "      <td>...</td>\n",
+       "      <td>25.53</td>\n",
+       "      <td>152.50</td>\n",
+       "      <td>1709.0</td>\n",
+       "      <td>0.1444</td>\n",
+       "      <td>0.4245</td>\n",
+       "      <td>0.4504</td>\n",
+       "      <td>0.2430</td>\n",
+       "      <td>0.3613</td>\n",
+       "      <td>0.08758</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>11.42</td>\n",
+       "      <td>20.38</td>\n",
+       "      <td>77.58</td>\n",
+       "      <td>386.1</td>\n",
+       "      <td>0.14250</td>\n",
+       "      <td>0.28390</td>\n",
+       "      <td>0.2414</td>\n",
+       "      <td>0.10520</td>\n",
+       "      <td>0.2597</td>\n",
+       "      <td>0.09744</td>\n",
+       "      <td>...</td>\n",
+       "      <td>26.50</td>\n",
+       "      <td>98.87</td>\n",
+       "      <td>567.7</td>\n",
+       "      <td>0.2098</td>\n",
+       "      <td>0.8663</td>\n",
+       "      <td>0.6869</td>\n",
+       "      <td>0.2575</td>\n",
+       "      <td>0.6638</td>\n",
+       "      <td>0.17300</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>20.29</td>\n",
+       "      <td>14.34</td>\n",
+       "      <td>135.10</td>\n",
+       "      <td>1297.0</td>\n",
+       "      <td>0.10030</td>\n",
+       "      <td>0.13280</td>\n",
+       "      <td>0.1980</td>\n",
+       "      <td>0.10430</td>\n",
+       "      <td>0.1809</td>\n",
+       "      <td>0.05883</td>\n",
+       "      <td>...</td>\n",
+       "      <td>16.67</td>\n",
+       "      <td>152.20</td>\n",
+       "      <td>1575.0</td>\n",
+       "      <td>0.1374</td>\n",
+       "      <td>0.2050</td>\n",
+       "      <td>0.4000</td>\n",
+       "      <td>0.1625</td>\n",
+       "      <td>0.2364</td>\n",
+       "      <td>0.07678</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 31 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
+       "0        17.99         10.38          122.80     1001.0          0.11840   \n",
+       "1        20.57         17.77          132.90     1326.0          0.08474   \n",
+       "2        19.69         21.25          130.00     1203.0          0.10960   \n",
+       "3        11.42         20.38           77.58      386.1          0.14250   \n",
+       "4        20.29         14.34          135.10     1297.0          0.10030   \n",
+       "\n",
+       "   mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
+       "0           0.27760          0.3001              0.14710         0.2419   \n",
+       "1           0.07864          0.0869              0.07017         0.1812   \n",
+       "2           0.15990          0.1974              0.12790         0.2069   \n",
+       "3           0.28390          0.2414              0.10520         0.2597   \n",
+       "4           0.13280          0.1980              0.10430         0.1809   \n",
+       "\n",
+       "   mean fractal dimension  ...  worst texture  worst perimeter  worst area  \\\n",
+       "0                 0.07871  ...          17.33           184.60      2019.0   \n",
+       "1                 0.05667  ...          23.41           158.80      1956.0   \n",
+       "2                 0.05999  ...          25.53           152.50      1709.0   \n",
+       "3                 0.09744  ...          26.50            98.87       567.7   \n",
+       "4                 0.05883  ...          16.67           152.20      1575.0   \n",
+       "\n",
+       "   worst smoothness  worst compactness  worst concavity  worst concave points  \\\n",
+       "0            0.1622             0.6656           0.7119                0.2654   \n",
+       "1            0.1238             0.1866           0.2416                0.1860   \n",
+       "2            0.1444             0.4245           0.4504                0.2430   \n",
+       "3            0.2098             0.8663           0.6869                0.2575   \n",
+       "4            0.1374             0.2050           0.4000                0.1625   \n",
+       "\n",
+       "   worst symmetry  worst fractal dimension  label  \n",
+       "0          0.4601                  0.11890    0.0  \n",
+       "1          0.2750                  0.08902    0.0  \n",
+       "2          0.3613                  0.08758    0.0  \n",
+       "3          0.6638                  0.17300    0.0  \n",
+       "4          0.2364                  0.07678    0.0  \n",
+       "\n",
+       "[5 rows x 31 columns]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "breast_dataset.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\JakeWalker\\AppData\\Local\\Temp\\ipykernel_17096\\3450579118.py:1: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
+      "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
+      "\n",
+      "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
+      "\n",
+      "\n",
+      "  breast_dataset[\"label\"].replace(0, \"Benign\", inplace=True)\n"
+     ]
+    }
+   ],
+   "source": [
+    "breast_dataset[\"label\"].replace(0, \"Benign\", inplace=True)\n",
+    "breast_dataset[\"label\"].replace(1, \"Malignant\", inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "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>mean radius</th>\n",
+       "      <th>mean texture</th>\n",
+       "      <th>mean perimeter</th>\n",
+       "      <th>mean area</th>\n",
+       "      <th>mean smoothness</th>\n",
+       "      <th>mean compactness</th>\n",
+       "      <th>mean concavity</th>\n",
+       "      <th>mean concave points</th>\n",
+       "      <th>mean symmetry</th>\n",
+       "      <th>mean fractal dimension</th>\n",
+       "      <th>...</th>\n",
+       "      <th>worst texture</th>\n",
+       "      <th>worst perimeter</th>\n",
+       "      <th>worst area</th>\n",
+       "      <th>worst smoothness</th>\n",
+       "      <th>worst compactness</th>\n",
+       "      <th>worst concavity</th>\n",
+       "      <th>worst concave points</th>\n",
+       "      <th>worst symmetry</th>\n",
+       "      <th>worst fractal dimension</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>564</th>\n",
+       "      <td>21.56</td>\n",
+       "      <td>22.39</td>\n",
+       "      <td>142.00</td>\n",
+       "      <td>1479.0</td>\n",
+       "      <td>0.11100</td>\n",
+       "      <td>0.11590</td>\n",
+       "      <td>0.24390</td>\n",
+       "      <td>0.13890</td>\n",
+       "      <td>0.1726</td>\n",
+       "      <td>0.05623</td>\n",
+       "      <td>...</td>\n",
+       "      <td>26.40</td>\n",
+       "      <td>166.10</td>\n",
+       "      <td>2027.0</td>\n",
+       "      <td>0.14100</td>\n",
+       "      <td>0.21130</td>\n",
+       "      <td>0.4107</td>\n",
+       "      <td>0.2216</td>\n",
+       "      <td>0.2060</td>\n",
+       "      <td>0.07115</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>565</th>\n",
+       "      <td>20.13</td>\n",
+       "      <td>28.25</td>\n",
+       "      <td>131.20</td>\n",
+       "      <td>1261.0</td>\n",
+       "      <td>0.09780</td>\n",
+       "      <td>0.10340</td>\n",
+       "      <td>0.14400</td>\n",
+       "      <td>0.09791</td>\n",
+       "      <td>0.1752</td>\n",
+       "      <td>0.05533</td>\n",
+       "      <td>...</td>\n",
+       "      <td>38.25</td>\n",
+       "      <td>155.00</td>\n",
+       "      <td>1731.0</td>\n",
+       "      <td>0.11660</td>\n",
+       "      <td>0.19220</td>\n",
+       "      <td>0.3215</td>\n",
+       "      <td>0.1628</td>\n",
+       "      <td>0.2572</td>\n",
+       "      <td>0.06637</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>566</th>\n",
+       "      <td>16.60</td>\n",
+       "      <td>28.08</td>\n",
+       "      <td>108.30</td>\n",
+       "      <td>858.1</td>\n",
+       "      <td>0.08455</td>\n",
+       "      <td>0.10230</td>\n",
+       "      <td>0.09251</td>\n",
+       "      <td>0.05302</td>\n",
+       "      <td>0.1590</td>\n",
+       "      <td>0.05648</td>\n",
+       "      <td>...</td>\n",
+       "      <td>34.12</td>\n",
+       "      <td>126.70</td>\n",
+       "      <td>1124.0</td>\n",
+       "      <td>0.11390</td>\n",
+       "      <td>0.30940</td>\n",
+       "      <td>0.3403</td>\n",
+       "      <td>0.1418</td>\n",
+       "      <td>0.2218</td>\n",
+       "      <td>0.07820</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>567</th>\n",
+       "      <td>20.60</td>\n",
+       "      <td>29.33</td>\n",
+       "      <td>140.10</td>\n",
+       "      <td>1265.0</td>\n",
+       "      <td>0.11780</td>\n",
+       "      <td>0.27700</td>\n",
+       "      <td>0.35140</td>\n",
+       "      <td>0.15200</td>\n",
+       "      <td>0.2397</td>\n",
+       "      <td>0.07016</td>\n",
+       "      <td>...</td>\n",
+       "      <td>39.42</td>\n",
+       "      <td>184.60</td>\n",
+       "      <td>1821.0</td>\n",
+       "      <td>0.16500</td>\n",
+       "      <td>0.86810</td>\n",
+       "      <td>0.9387</td>\n",
+       "      <td>0.2650</td>\n",
+       "      <td>0.4087</td>\n",
+       "      <td>0.12400</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>568</th>\n",
+       "      <td>7.76</td>\n",
+       "      <td>24.54</td>\n",
+       "      <td>47.92</td>\n",
+       "      <td>181.0</td>\n",
+       "      <td>0.05263</td>\n",
+       "      <td>0.04362</td>\n",
+       "      <td>0.00000</td>\n",
+       "      <td>0.00000</td>\n",
+       "      <td>0.1587</td>\n",
+       "      <td>0.05884</td>\n",
+       "      <td>...</td>\n",
+       "      <td>30.37</td>\n",
+       "      <td>59.16</td>\n",
+       "      <td>268.6</td>\n",
+       "      <td>0.08996</td>\n",
+       "      <td>0.06444</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.2871</td>\n",
+       "      <td>0.07039</td>\n",
+       "      <td>Malignant</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 31 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
+       "564        21.56         22.39          142.00     1479.0          0.11100   \n",
+       "565        20.13         28.25          131.20     1261.0          0.09780   \n",
+       "566        16.60         28.08          108.30      858.1          0.08455   \n",
+       "567        20.60         29.33          140.10     1265.0          0.11780   \n",
+       "568         7.76         24.54           47.92      181.0          0.05263   \n",
+       "\n",
+       "     mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
+       "564           0.11590         0.24390              0.13890         0.1726   \n",
+       "565           0.10340         0.14400              0.09791         0.1752   \n",
+       "566           0.10230         0.09251              0.05302         0.1590   \n",
+       "567           0.27700         0.35140              0.15200         0.2397   \n",
+       "568           0.04362         0.00000              0.00000         0.1587   \n",
+       "\n",
+       "     mean fractal dimension  ...  worst texture  worst perimeter  worst area  \\\n",
+       "564                 0.05623  ...          26.40           166.10      2027.0   \n",
+       "565                 0.05533  ...          38.25           155.00      1731.0   \n",
+       "566                 0.05648  ...          34.12           126.70      1124.0   \n",
+       "567                 0.07016  ...          39.42           184.60      1821.0   \n",
+       "568                 0.05884  ...          30.37            59.16       268.6   \n",
+       "\n",
+       "     worst smoothness  worst compactness  worst concavity  \\\n",
+       "564           0.14100            0.21130           0.4107   \n",
+       "565           0.11660            0.19220           0.3215   \n",
+       "566           0.11390            0.30940           0.3403   \n",
+       "567           0.16500            0.86810           0.9387   \n",
+       "568           0.08996            0.06444           0.0000   \n",
+       "\n",
+       "     worst concave points  worst symmetry  worst fractal dimension      label  \n",
+       "564                0.2216          0.2060                  0.07115     Benign  \n",
+       "565                0.1628          0.2572                  0.06637     Benign  \n",
+       "566                0.1418          0.2218                  0.07820     Benign  \n",
+       "567                0.2650          0.4087                  0.12400     Benign  \n",
+       "568                0.0000          0.2871                  0.07039  Malignant  \n",
+       "\n",
+       "[5 rows x 31 columns]"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "breast_dataset.tail()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## CIFAR-10 Data Exploration"
+   ]
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "data-science-research-W2__OPFf-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,