└── Dendrogram_linkage.ipynb


/Dendrogram_linkage.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "provenance": [],
  7 |       "authorship_tag": "ABX9TyMcNO2yUmh/RFX/M4tqhRYy",
  8 |       "include_colab_link": true
  9 |     },
 10 |     "kernelspec": {
 11 |       "name": "python3",
 12 |       "display_name": "Python 3"
 13 |     },
 14 |     "language_info": {
 15 |       "name": "python"
 16 |     }
 17 |   },
 18 |   "cells": [
 19 |     {
 20 |       "cell_type": "markdown",
 21 |       "metadata": {
 22 |         "id": "view-in-github",
 23 |         "colab_type": "text"
 24 |       },
 25 |       "source": [
 26 |         "<a href=\"https://colab.research.google.com/github/NandhanaRameshkumar/Dendrogram_linkage/blob/main/Dendrogram_linkage.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
 27 |       ]
 28 |     },
 29 |     {
 30 |       "cell_type": "code",
 31 |       "execution_count": null,
 32 |       "metadata": {
 33 |         "id": "BePFV0-xpKYW"
 34 |       },
 35 |       "outputs": [],
 36 |       "source": [
 37 |         "import pandas as pd\n",
 38 |         "from scipy.cluster.hierarchy import dendrogram, linkage\n",
 39 |         "from sklearn.preprocessing import OneHotEncoder\n",
 40 |         "import matplotlib.pyplot as plt  # Import for plotting\n",
 41 |         "from tqdm import tqdm  # Import for progress bar"
 42 |       ]
 43 |     },
 44 |     {
 45 |       "cell_type": "code",
 46 |       "source": [
 47 |         "data = pd.read_csv('IPL_Ball_by_Ball_2008_2022.csv')"
 48 |       ],
 49 |       "metadata": {
 50 |         "id": "QOzZBzqZqMDd"
 51 |       },
 52 |       "execution_count": null,
 53 |       "outputs": []
 54 |     },
 55 |     {
 56 |       "cell_type": "code",
 57 |       "source": [
 58 |         "print(data.columns.tolist())"
 59 |       ],
 60 |       "metadata": {
 61 |         "colab": {
 62 |           "base_uri": "https://localhost:8080/"
 63 |         },
 64 |         "id": "1uGFVwUhsoQy",
 65 |         "outputId": "d119421f-aa46-4187-c815-3dbf7010753a"
 66 |       },
 67 |       "execution_count": null,
 68 |       "outputs": [
 69 |         {
 70 |           "output_type": "stream",
 71 |           "name": "stdout",
 72 |           "text": [
 73 |             "['ID', 'innings', 'overs', 'ballnumber', 'batter', 'bowler', 'non-striker', 'extra_type', 'batsman_run', 'extras_run', 'total_run', 'non_boundary', 'isWicketDelivery', 'player_out', 'kind', 'fielders_involved', 'BattingTeam']\n"
 74 |           ]
 75 |         }
 76 |       ]
 77 |     },
 78 |     {
 79 |       "cell_type": "code",
 80 |       "source": [
 81 |         "# Select relevant features for clustering\n",
 82 |         "features = ['batsman_run', 'extras_run', 'total_run', 'non_boundary', 'isWicketDelivery']"
 83 |       ],
 84 |       "metadata": {
 85 |         "id": "L-_LMKCosTSS"
 86 |       },
 87 |       "execution_count": null,
 88 |       "outputs": []
 89 |     },
 90 |     {
 91 |       "cell_type": "code",
 92 |       "source": [
 93 |         "# Check data type of 'isWicketDelivery' (optional)\n",
 94 |         "print(data['isWicketDelivery'].dtype)  # Check if it's already numerical"
 95 |       ],
 96 |       "metadata": {
 97 |         "colab": {
 98 |           "base_uri": "https://localhost:8080/"
 99 |         },
100 |         "id": "5NibnoCK4t_I",
101 |         "outputId": "f36d55f7-73ea-4de6-fea0-b3ad6abd1764"
102 |       },
103 |       "execution_count": null,
104 |       "outputs": [
105 |         {
106 |           "output_type": "stream",
107 |           "name": "stdout",
108 |           "text": [
109 |             "int64\n"
110 |           ]
111 |         }
112 |       ]
113 |     },
114 |     {
115 |       "cell_type": "code",
116 |       "source": [
117 |         "# One-hot encoding (if necessary)\n",
118 |         "categorical_feature = ['isWicketDelivery']  # Assuming 'isWicketDelivery' is categorical\n",
119 |         "if pd.api.types.is_string_dtype(data[categorical_feature]):  # Check if string type\n",
120 |         "    encoder = OneHotEncoder(sparse=False)  # Consider sparse=True for large datasets\n",
121 |         "    data[categorical_feature] = encoder.fit_transform(data[categorical_feature])"
122 |       ],
123 |       "metadata": {
124 |         "id": "1Of7ZUqCw-6I"
125 |       },
126 |       "execution_count": null,
127 |       "outputs": []
128 |     },
129 |     {
130 |       "cell_type": "code",
131 |       "source": [
132 |         "# Select data for clustering\n",
133 |         "X = data[features]"
134 |       ],
135 |       "metadata": {
136 |         "id": "cRt0JAswuZ2h"
137 |       },
138 |       "execution_count": null,
139 |       "outputs": []
140 |     },
141 |     {
142 |       "cell_type": "code",
143 |       "source": [
144 |         "# Choose distance metric (consider data types)\n",
145 |         "# Options: 'euclidean', 'manhattan', 'cosine' (for normalized data)\n",
146 |         "distance_metric = 'euclidean'"
147 |       ],
148 |       "metadata": {
149 |         "id": "5R_QYEHHum_P"
150 |       },
151 |       "execution_count": null,
152 |       "outputs": []
153 |     },
154 |     {
155 |       "cell_type": "code",
156 |       "source": [
157 |         "from tqdm import tqdm\n",
158 |         "from scipy.spatial.distance import pdist"
159 |       ],
160 |       "metadata": {
161 |         "id": "OPqzm-Ga6IRk"
162 |       },
163 |       "execution_count": null,
164 |       "outputs": []
165 |     },
166 |     {
167 |       "cell_type": "code",
168 |       "source": [
169 |         "!pip install scipy\n",
170 |         "import numpy as np\n",
171 |         "from scipy.spatial.distance import pdist\n",
172 |         "\n",
173 |         "def calculate_distance_matrix(X, metric):\n",
174 |         "    distance_matrix = []\n",
175 |         "    features = range(X.shape[1])\n",
176 |         "    for i in features:\n",
177 |         "        for j in features:\n",
178 |         "            if i != j:\n",
179 |         "                # Combine data points into a single argument\n",
180 |         "                data_point = np.array([X[i], X[j]])\n",
181 |         "                # Pass only the combined data point and metric\n",
182 |         "                distance_matrix.append(pdist(data_point, metric))\n",
183 |         "    return np.asarray(distance_matrix)"
184 |       ],
185 |       "metadata": {
186 |         "colab": {
187 |           "base_uri": "https://localhost:8080/"
188 |         },
189 |         "id": "2gcLO9XPu6ue",
190 |         "outputId": "1de4c378-0c55-4b64-f2b5-266498db5e82"
191 |       },
192 |       "execution_count": null,
193 |       "outputs": [
194 |         {
195 |           "output_type": "stream",
196 |           "name": "stdout",
197 |           "text": [
198 |             "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (1.11.4)\n",
199 |             "Requirement already satisfied: numpy<1.28.0,>=1.21.6 in /usr/local/lib/python3.10/dist-packages (from scipy) (1.25.2)\n"
200 |           ]
201 |         }
202 |       ]
203 |     },
204 |     {
205 |       "cell_type": "code",
206 |       "source": [
207 |         "!pip install scipy\n",
208 |         "import scipy.spatial.distance as distance"
209 |       ],
210 |       "metadata": {
211 |         "colab": {
212 |           "base_uri": "https://localhost:8080/"
213 |         },
214 |         "id": "J--HRkDe98gL",
215 |         "outputId": "fcbeea6f-8fca-44f2-848b-27174dbea8a5"
216 |       },
217 |       "execution_count": null,
218 |       "outputs": [
219 |         {
220 |           "output_type": "stream",
221 |           "name": "stdout",
222 |           "text": [
223 |             "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (1.11.4)\n",
224 |             "Requirement already satisfied: numpy<1.28.0,>=1.21.6 in /usr/local/lib/python3.10/dist-packages (from scipy) (1.25.2)\n"
225 |           ]
226 |         }
227 |       ]
228 |     },
229 |     {
230 |       "cell_type": "code",
231 |       "source": [
232 |         "import numpy as np\n",
233 |         "# Define the data points (replace with your actual data)\n",
234 |         "X = np.array([[1, 2], [3, 4], [5, 6]])\n",
235 |         "\n",
236 |         "# Define the distance metric (replace with your desired metric)\n",
237 |         "distance_metric = 'euclidean'\n",
238 |         "\n",
239 |         "# Calculate the distance matrix\n",
240 |         "distance_matrix = distance.cdist(X, X, metric=distance_metric)\n",
241 |         "\n",
242 |         "# Perform hierarchical clustering (Ward's method)\n",
243 |         "Z = linkage(distance_matrix, method='ward')\n"
244 |       ],
245 |       "metadata": {
246 |         "colab": {
247 |           "base_uri": "https://localhost:8080/"
248 |         },
249 |         "id": "Il9uo0W70gaW",
250 |         "outputId": "40a775fb-7024-4bb2-81af-c4ce804eae42"
251 |       },
252 |       "execution_count": null,
253 |       "outputs": [
254 |         {
255 |           "output_type": "stream",
256 |           "name": "stderr",
257 |           "text": [
258 |             "<ipython-input-25-f6af1f6e92c7>:12: ClusterWarning: scipy.cluster: The symmetric non-negative hollow observation matrix looks suspiciously like an uncondensed distance matrix\n",
259 |             "  Z = linkage(distance_matrix, method='ward')\n"
260 |           ]
261 |         }
262 |       ]
263 |     },
264 |     {
265 |       "cell_type": "code",
266 |       "source": [
267 |         "import matplotlib.pyplot as plt\n",
268 |         "from scipy.cluster.hierarchy import dendrogram, linkage\n",
269 |         "print(Z)"
270 |       ],
271 |       "metadata": {
272 |         "colab": {
273 |           "base_uri": "https://localhost:8080/"
274 |         },
275 |         "id": "9XiRJy3i-eK9",
276 |         "outputId": "255063ee-99c1-4ba3-8d7e-27f7b7dead14"
277 |       },
278 |       "execution_count": null,
279 |       "outputs": [
280 |         {
281 |           "output_type": "stream",
282 |           "name": "stdout",
283 |           "text": [
284 |             "[[0.         1.         4.89897949 2.        ]\n",
285 |             " [2.         3.         7.11805217 3.        ]]\n"
286 |           ]
287 |         }
288 |       ]
289 |     },
290 |     {
291 |       "cell_type": "code",
292 |       "source": [
293 |         "print(data.head())"
294 |       ],
295 |       "metadata": {
296 |         "colab": {
297 |           "base_uri": "https://localhost:8080/"
298 |         },
299 |         "id": "wyIGmcwX-lRw",
300 |         "outputId": "97d303c4-9c2a-43dd-99e5-3681a4fb0212"
301 |       },
302 |       "execution_count": null,
303 |       "outputs": [
304 |         {
305 |           "output_type": "stream",
306 |           "name": "stdout",
307 |           "text": [
308 |             "        ID  innings  overs  ballnumber       batter          bowler  \\\n",
309 |             "0  1312200        1      0           1  YBK Jaiswal  Mohammed Shami   \n",
310 |             "1  1312200        1      0           2  YBK Jaiswal  Mohammed Shami   \n",
311 |             "2  1312200        1      0           3   JC Buttler  Mohammed Shami   \n",
312 |             "3  1312200        1      0           4  YBK Jaiswal  Mohammed Shami   \n",
313 |             "4  1312200        1      0           5  YBK Jaiswal  Mohammed Shami   \n",
314 |             "\n",
315 |             "   non-striker extra_type  batsman_run  extras_run  total_run  non_boundary  \\\n",
316 |             "0   JC Buttler        NaN            0           0          0             0   \n",
317 |             "1   JC Buttler    legbyes            0           1          1             0   \n",
318 |             "2  YBK Jaiswal        NaN            1           0          1             0   \n",
319 |             "3   JC Buttler        NaN            0           0          0             0   \n",
320 |             "4   JC Buttler        NaN            0           0          0             0   \n",
321 |             "\n",
322 |             "   isWicketDelivery player_out kind fielders_involved       BattingTeam  \n",
323 |             "0                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
324 |             "1                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
325 |             "2                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
326 |             "3                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
327 |             "4                 0        NaN  NaN               NaN  Rajasthan Royals  \n"
328 |           ]
329 |         }
330 |       ]
331 |     },
332 |     {
333 |       "cell_type": "code",
334 |       "source": [
335 |         "print(Z.shape)\n",
336 |         "print(data['BattingTeam'].shape)"
337 |       ],
338 |       "metadata": {
339 |         "colab": {
340 |           "base_uri": "https://localhost:8080/"
341 |         },
342 |         "id": "E3pyH8-t-1dT",
343 |         "outputId": "2bc4003f-79b2-4307-82e0-21afaf3d1238"
344 |       },
345 |       "execution_count": null,
346 |       "outputs": [
347 |         {
348 |           "output_type": "stream",
349 |           "name": "stdout",
350 |           "text": [
351 |             "(2, 4)\n",
352 |             "(225954,)\n"
353 |           ]
354 |         }
355 |       ]
356 |     },
357 |     {
358 |       "cell_type": "code",
359 |       "source": [
360 |         "print(Z.shape[0])\n",
361 |         "print(data['BattingTeam'].shape[0])"
362 |       ],
363 |       "metadata": {
364 |         "colab": {
365 |           "base_uri": "https://localhost:8080/"
366 |         },
367 |         "id": "_YMNJakO_x0F",
368 |         "outputId": "9b8a8ff4-a65a-43ad-9a48-f1e5f01c5057"
369 |       },
370 |       "execution_count": null,
371 |       "outputs": [
372 |         {
373 |           "output_type": "stream",
374 |           "name": "stdout",
375 |           "text": [
376 |             "2\n",
377 |             "225954\n"
378 |           ]
379 |         }
380 |       ]
381 |     },
382 |     {
383 |       "cell_type": "code",
384 |       "source": [
385 |         "# Check if there are any missing values in data['BattingTeam']\n",
386 |         "missing_values = data['BattingTeam'].isnull().sum()\n",
387 |         "if missing_values > 0:\n",
388 |         "    print(\"There are missing values in data['BattingTeam'].\")"
389 |       ],
390 |       "metadata": {
391 |         "id": "H0YL_2bN_K0E"
392 |       },
393 |       "execution_count": null,
394 |       "outputs": []
395 |     },
396 |     {
397 |       "cell_type": "code",
398 |       "source": [
399 |         "import pandas as pd\n",
400 |         "import numpy as np"
401 |       ],
402 |       "metadata": {
403 |         "id": "M1ApY2EWAIFL"
404 |       },
405 |       "execution_count": null,
406 |       "outputs": []
407 |     },
408 |     {
409 |       "cell_type": "code",
410 |       "source": [
411 |         "data.head()"
412 |       ],
413 |       "metadata": {
414 |         "colab": {
415 |           "base_uri": "https://localhost:8080/",
416 |           "height": 330
417 |         },
418 |         "id": "w14i0V1FADhB",
419 |         "outputId": "f53aa06c-ed7b-4f9f-e1d9-0d21bff7173b"
420 |       },
421 |       "execution_count": null,
422 |       "outputs": [
423 |         {
424 |           "output_type": "execute_result",
425 |           "data": {
426 |             "text/plain": [
427 |               "        ID  innings  overs  ballnumber       batter          bowler  \\\n",
428 |               "0  1312200        1      0           1  YBK Jaiswal  Mohammed Shami   \n",
429 |               "1  1312200        1      0           2  YBK Jaiswal  Mohammed Shami   \n",
430 |               "2  1312200        1      0           3   JC Buttler  Mohammed Shami   \n",
431 |               "3  1312200        1      0           4  YBK Jaiswal  Mohammed Shami   \n",
432 |               "4  1312200        1      0           5  YBK Jaiswal  Mohammed Shami   \n",
433 |               "\n",
434 |               "   non-striker extra_type  batsman_run  extras_run  total_run  non_boundary  \\\n",
435 |               "0   JC Buttler        NaN            0           0          0             0   \n",
436 |               "1   JC Buttler    legbyes            0           1          1             0   \n",
437 |               "2  YBK Jaiswal        NaN            1           0          1             0   \n",
438 |               "3   JC Buttler        NaN            0           0          0             0   \n",
439 |               "4   JC Buttler        NaN            0           0          0             0   \n",
440 |               "\n",
441 |               "   isWicketDelivery player_out kind fielders_involved       BattingTeam  \n",
442 |               "0                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
443 |               "1                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
444 |               "2                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
445 |               "3                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
446 |               "4                 0        NaN  NaN               NaN  Rajasthan Royals  "
447 |             ],
448 |             "text/html": [
449 |               "\n",
450 |               "  <div id=\"df-0a5afb5f-f871-4ee5-974d-ec3a557db427\" class=\"colab-df-container\">\n",
451 |               "    <div>\n",
452 |               "<style scoped>\n",
453 |               "    .dataframe tbody tr th:only-of-type {\n",
454 |               "        vertical-align: middle;\n",
455 |               "    }\n",
456 |               "\n",
457 |               "    .dataframe tbody tr th {\n",
458 |               "        vertical-align: top;\n",
459 |               "    }\n",
460 |               "\n",
461 |               "    .dataframe thead th {\n",
462 |               "        text-align: right;\n",
463 |               "    }\n",
464 |               "</style>\n",
465 |               "<table border=\"1\" class=\"dataframe\">\n",
466 |               "  <thead>\n",
467 |               "    <tr style=\"text-align: right;\">\n",
468 |               "      <th></th>\n",
469 |               "      <th>ID</th>\n",
470 |               "      <th>innings</th>\n",
471 |               "      <th>overs</th>\n",
472 |               "      <th>ballnumber</th>\n",
473 |               "      <th>batter</th>\n",
474 |               "      <th>bowler</th>\n",
475 |               "      <th>non-striker</th>\n",
476 |               "      <th>extra_type</th>\n",
477 |               "      <th>batsman_run</th>\n",
478 |               "      <th>extras_run</th>\n",
479 |               "      <th>total_run</th>\n",
480 |               "      <th>non_boundary</th>\n",
481 |               "      <th>isWicketDelivery</th>\n",
482 |               "      <th>player_out</th>\n",
483 |               "      <th>kind</th>\n",
484 |               "      <th>fielders_involved</th>\n",
485 |               "      <th>BattingTeam</th>\n",
486 |               "    </tr>\n",
487 |               "  </thead>\n",
488 |               "  <tbody>\n",
489 |               "    <tr>\n",
490 |               "      <th>0</th>\n",
491 |               "      <td>1312200</td>\n",
492 |               "      <td>1</td>\n",
493 |               "      <td>0</td>\n",
494 |               "      <td>1</td>\n",
495 |               "      <td>YBK Jaiswal</td>\n",
496 |               "      <td>Mohammed Shami</td>\n",
497 |               "      <td>JC Buttler</td>\n",
498 |               "      <td>NaN</td>\n",
499 |               "      <td>0</td>\n",
500 |               "      <td>0</td>\n",
501 |               "      <td>0</td>\n",
502 |               "      <td>0</td>\n",
503 |               "      <td>0</td>\n",
504 |               "      <td>NaN</td>\n",
505 |               "      <td>NaN</td>\n",
506 |               "      <td>NaN</td>\n",
507 |               "      <td>Rajasthan Royals</td>\n",
508 |               "    </tr>\n",
509 |               "    <tr>\n",
510 |               "      <th>1</th>\n",
511 |               "      <td>1312200</td>\n",
512 |               "      <td>1</td>\n",
513 |               "      <td>0</td>\n",
514 |               "      <td>2</td>\n",
515 |               "      <td>YBK Jaiswal</td>\n",
516 |               "      <td>Mohammed Shami</td>\n",
517 |               "      <td>JC Buttler</td>\n",
518 |               "      <td>legbyes</td>\n",
519 |               "      <td>0</td>\n",
520 |               "      <td>1</td>\n",
521 |               "      <td>1</td>\n",
522 |               "      <td>0</td>\n",
523 |               "      <td>0</td>\n",
524 |               "      <td>NaN</td>\n",
525 |               "      <td>NaN</td>\n",
526 |               "      <td>NaN</td>\n",
527 |               "      <td>Rajasthan Royals</td>\n",
528 |               "    </tr>\n",
529 |               "    <tr>\n",
530 |               "      <th>2</th>\n",
531 |               "      <td>1312200</td>\n",
532 |               "      <td>1</td>\n",
533 |               "      <td>0</td>\n",
534 |               "      <td>3</td>\n",
535 |               "      <td>JC Buttler</td>\n",
536 |               "      <td>Mohammed Shami</td>\n",
537 |               "      <td>YBK Jaiswal</td>\n",
538 |               "      <td>NaN</td>\n",
539 |               "      <td>1</td>\n",
540 |               "      <td>0</td>\n",
541 |               "      <td>1</td>\n",
542 |               "      <td>0</td>\n",
543 |               "      <td>0</td>\n",
544 |               "      <td>NaN</td>\n",
545 |               "      <td>NaN</td>\n",
546 |               "      <td>NaN</td>\n",
547 |               "      <td>Rajasthan Royals</td>\n",
548 |               "    </tr>\n",
549 |               "    <tr>\n",
550 |               "      <th>3</th>\n",
551 |               "      <td>1312200</td>\n",
552 |               "      <td>1</td>\n",
553 |               "      <td>0</td>\n",
554 |               "      <td>4</td>\n",
555 |               "      <td>YBK Jaiswal</td>\n",
556 |               "      <td>Mohammed Shami</td>\n",
557 |               "      <td>JC Buttler</td>\n",
558 |               "      <td>NaN</td>\n",
559 |               "      <td>0</td>\n",
560 |               "      <td>0</td>\n",
561 |               "      <td>0</td>\n",
562 |               "      <td>0</td>\n",
563 |               "      <td>0</td>\n",
564 |               "      <td>NaN</td>\n",
565 |               "      <td>NaN</td>\n",
566 |               "      <td>NaN</td>\n",
567 |               "      <td>Rajasthan Royals</td>\n",
568 |               "    </tr>\n",
569 |               "    <tr>\n",
570 |               "      <th>4</th>\n",
571 |               "      <td>1312200</td>\n",
572 |               "      <td>1</td>\n",
573 |               "      <td>0</td>\n",
574 |               "      <td>5</td>\n",
575 |               "      <td>YBK Jaiswal</td>\n",
576 |               "      <td>Mohammed Shami</td>\n",
577 |               "      <td>JC Buttler</td>\n",
578 |               "      <td>NaN</td>\n",
579 |               "      <td>0</td>\n",
580 |               "      <td>0</td>\n",
581 |               "      <td>0</td>\n",
582 |               "      <td>0</td>\n",
583 |               "      <td>0</td>\n",
584 |               "      <td>NaN</td>\n",
585 |               "      <td>NaN</td>\n",
586 |               "      <td>NaN</td>\n",
587 |               "      <td>Rajasthan Royals</td>\n",
588 |               "    </tr>\n",
589 |               "  </tbody>\n",
590 |               "</table>\n",
591 |               "</div>\n",
592 |               "    <div class=\"colab-df-buttons\">\n",
593 |               "\n",
594 |               "  <div class=\"colab-df-container\">\n",
595 |               "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0a5afb5f-f871-4ee5-974d-ec3a557db427')\"\n",
596 |               "            title=\"Convert this dataframe to an interactive table.\"\n",
597 |               "            style=\"display:none;\">\n",
598 |               "\n",
599 |               "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
600 |               "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
601 |               "  </svg>\n",
602 |               "    </button>\n",
603 |               "\n",
604 |               "  <style>\n",
605 |               "    .colab-df-container {\n",
606 |               "      display:flex;\n",
607 |               "      gap: 12px;\n",
608 |               "    }\n",
609 |               "\n",
610 |               "    .colab-df-convert {\n",
611 |               "      background-color: #E8F0FE;\n",
612 |               "      border: none;\n",
613 |               "      border-radius: 50%;\n",
614 |               "      cursor: pointer;\n",
615 |               "      display: none;\n",
616 |               "      fill: #1967D2;\n",
617 |               "      height: 32px;\n",
618 |               "      padding: 0 0 0 0;\n",
619 |               "      width: 32px;\n",
620 |               "    }\n",
621 |               "\n",
622 |               "    .colab-df-convert:hover {\n",
623 |               "      background-color: #E2EBFA;\n",
624 |               "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
625 |               "      fill: #174EA6;\n",
626 |               "    }\n",
627 |               "\n",
628 |               "    .colab-df-buttons div {\n",
629 |               "      margin-bottom: 4px;\n",
630 |               "    }\n",
631 |               "\n",
632 |               "    [theme=dark] .colab-df-convert {\n",
633 |               "      background-color: #3B4455;\n",
634 |               "      fill: #D2E3FC;\n",
635 |               "    }\n",
636 |               "\n",
637 |               "    [theme=dark] .colab-df-convert:hover {\n",
638 |               "      background-color: #434B5C;\n",
639 |               "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
640 |               "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
641 |               "      fill: #FFFFFF;\n",
642 |               "    }\n",
643 |               "  </style>\n",
644 |               "\n",
645 |               "    <script>\n",
646 |               "      const buttonEl =\n",
647 |               "        document.querySelector('#df-0a5afb5f-f871-4ee5-974d-ec3a557db427 button.colab-df-convert');\n",
648 |               "      buttonEl.style.display =\n",
649 |               "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
650 |               "\n",
651 |               "      async function convertToInteractive(key) {\n",
652 |               "        const element = document.querySelector('#df-0a5afb5f-f871-4ee5-974d-ec3a557db427');\n",
653 |               "        const dataTable =\n",
654 |               "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
655 |               "                                                    [key], {});\n",
656 |               "        if (!dataTable) return;\n",
657 |               "\n",
658 |               "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
659 |               "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
660 |               "          + ' to learn more about interactive tables.';\n",
661 |               "        element.innerHTML = '';\n",
662 |               "        dataTable['output_type'] = 'display_data';\n",
663 |               "        await google.colab.output.renderOutput(dataTable, element);\n",
664 |               "        const docLink = document.createElement('div');\n",
665 |               "        docLink.innerHTML = docLinkHtml;\n",
666 |               "        element.appendChild(docLink);\n",
667 |               "      }\n",
668 |               "    </script>\n",
669 |               "  </div>\n",
670 |               "\n",
671 |               "\n",
672 |               "<div id=\"df-9ff8bb37-105e-4796-b7f1-2c8d2991397d\">\n",
673 |               "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-9ff8bb37-105e-4796-b7f1-2c8d2991397d')\"\n",
674 |               "            title=\"Suggest charts\"\n",
675 |               "            style=\"display:none;\">\n",
676 |               "\n",
677 |               "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
678 |               "     width=\"24px\">\n",
679 |               "    <g>\n",
680 |               "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
681 |               "    </g>\n",
682 |               "</svg>\n",
683 |               "  </button>\n",
684 |               "\n",
685 |               "<style>\n",
686 |               "  .colab-df-quickchart {\n",
687 |               "      --bg-color: #E8F0FE;\n",
688 |               "      --fill-color: #1967D2;\n",
689 |               "      --hover-bg-color: #E2EBFA;\n",
690 |               "      --hover-fill-color: #174EA6;\n",
691 |               "      --disabled-fill-color: #AAA;\n",
692 |               "      --disabled-bg-color: #DDD;\n",
693 |               "  }\n",
694 |               "\n",
695 |               "  [theme=dark] .colab-df-quickchart {\n",
696 |               "      --bg-color: #3B4455;\n",
697 |               "      --fill-color: #D2E3FC;\n",
698 |               "      --hover-bg-color: #434B5C;\n",
699 |               "      --hover-fill-color: #FFFFFF;\n",
700 |               "      --disabled-bg-color: #3B4455;\n",
701 |               "      --disabled-fill-color: #666;\n",
702 |               "  }\n",
703 |               "\n",
704 |               "  .colab-df-quickchart {\n",
705 |               "    background-color: var(--bg-color);\n",
706 |               "    border: none;\n",
707 |               "    border-radius: 50%;\n",
708 |               "    cursor: pointer;\n",
709 |               "    display: none;\n",
710 |               "    fill: var(--fill-color);\n",
711 |               "    height: 32px;\n",
712 |               "    padding: 0;\n",
713 |               "    width: 32px;\n",
714 |               "  }\n",
715 |               "\n",
716 |               "  .colab-df-quickchart:hover {\n",
717 |               "    background-color: var(--hover-bg-color);\n",
718 |               "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
719 |               "    fill: var(--button-hover-fill-color);\n",
720 |               "  }\n",
721 |               "\n",
722 |               "  .colab-df-quickchart-complete:disabled,\n",
723 |               "  .colab-df-quickchart-complete:disabled:hover {\n",
724 |               "    background-color: var(--disabled-bg-color);\n",
725 |               "    fill: var(--disabled-fill-color);\n",
726 |               "    box-shadow: none;\n",
727 |               "  }\n",
728 |               "\n",
729 |               "  .colab-df-spinner {\n",
730 |               "    border: 2px solid var(--fill-color);\n",
731 |               "    border-color: transparent;\n",
732 |               "    border-bottom-color: var(--fill-color);\n",
733 |               "    animation:\n",
734 |               "      spin 1s steps(1) infinite;\n",
735 |               "  }\n",
736 |               "\n",
737 |               "  @keyframes spin {\n",
738 |               "    0% {\n",
739 |               "      border-color: transparent;\n",
740 |               "      border-bottom-color: var(--fill-color);\n",
741 |               "      border-left-color: var(--fill-color);\n",
742 |               "    }\n",
743 |               "    20% {\n",
744 |               "      border-color: transparent;\n",
745 |               "      border-left-color: var(--fill-color);\n",
746 |               "      border-top-color: var(--fill-color);\n",
747 |               "    }\n",
748 |               "    30% {\n",
749 |               "      border-color: transparent;\n",
750 |               "      border-left-color: var(--fill-color);\n",
751 |               "      border-top-color: var(--fill-color);\n",
752 |               "      border-right-color: var(--fill-color);\n",
753 |               "    }\n",
754 |               "    40% {\n",
755 |               "      border-color: transparent;\n",
756 |               "      border-right-color: var(--fill-color);\n",
757 |               "      border-top-color: var(--fill-color);\n",
758 |               "    }\n",
759 |               "    60% {\n",
760 |               "      border-color: transparent;\n",
761 |               "      border-right-color: var(--fill-color);\n",
762 |               "    }\n",
763 |               "    80% {\n",
764 |               "      border-color: transparent;\n",
765 |               "      border-right-color: var(--fill-color);\n",
766 |               "      border-bottom-color: var(--fill-color);\n",
767 |               "    }\n",
768 |               "    90% {\n",
769 |               "      border-color: transparent;\n",
770 |               "      border-bottom-color: var(--fill-color);\n",
771 |               "    }\n",
772 |               "  }\n",
773 |               "</style>\n",
774 |               "\n",
775 |               "  <script>\n",
776 |               "    async function quickchart(key) {\n",
777 |               "      const quickchartButtonEl =\n",
778 |               "        document.querySelector('#' + key + ' button');\n",
779 |               "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
780 |               "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
781 |               "      try {\n",
782 |               "        const charts = await google.colab.kernel.invokeFunction(\n",
783 |               "            'suggestCharts', [key], {});\n",
784 |               "      } catch (error) {\n",
785 |               "        console.error('Error during call to suggestCharts:', error);\n",
786 |               "      }\n",
787 |               "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
788 |               "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
789 |               "    }\n",
790 |               "    (() => {\n",
791 |               "      let quickchartButtonEl =\n",
792 |               "        document.querySelector('#df-9ff8bb37-105e-4796-b7f1-2c8d2991397d button');\n",
793 |               "      quickchartButtonEl.style.display =\n",
794 |               "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
795 |               "    })();\n",
796 |               "  </script>\n",
797 |               "</div>\n",
798 |               "\n",
799 |               "    </div>\n",
800 |               "  </div>\n"
801 |             ],
802 |             "application/vnd.google.colaboratory.intrinsic+json": {
803 |               "type": "dataframe",
804 |               "variable_name": "data"
805 |             }
806 |           },
807 |           "metadata": {},
808 |           "execution_count": 40
809 |         }
810 |       ]
811 |     },
812 |     {
813 |       "cell_type": "code",
814 |       "source": [
815 |         "'Cluster' in data.columns"
816 |       ],
817 |       "metadata": {
818 |         "colab": {
819 |           "base_uri": "https://localhost:8080/"
820 |         },
821 |         "id": "Lex6BdRWACnE",
822 |         "outputId": "34b31cde-e9a7-4e7c-f301-b6d2f72e945b"
823 |       },
824 |       "execution_count": null,
825 |       "outputs": [
826 |         {
827 |           "output_type": "execute_result",
828 |           "data": {
829 |             "text/plain": [
830 |               "False"
831 |             ]
832 |           },
833 |           "metadata": {},
834 |           "execution_count": 41
835 |         }
836 |       ]
837 |     },
838 |     {
839 |       "cell_type": "code",
840 |       "source": [
841 |         "import pandas as pd\n",
842 |         "import matplotlib.pyplot as plt\n",
843 |         "from scipy.cluster.hierarchy import dendrogram"
844 |       ],
845 |       "metadata": {
846 |         "id": "4HBLNb_DAaF_"
847 |       },
848 |       "execution_count": null,
849 |       "outputs": []
850 |     },
851 |     {
852 |       "cell_type": "code",
853 |       "source": [
854 |         "print(Z.shape)\n",
855 |         "print(data['BattingTeam'].shape)"
856 |       ],
857 |       "metadata": {
858 |         "colab": {
859 |           "base_uri": "https://localhost:8080/"
860 |         },
861 |         "id": "a1pMGsNyAeMo",
862 |         "outputId": "c976082f-8bb3-4dfe-e21f-8a137aaf5702"
863 |       },
864 |       "execution_count": null,
865 |       "outputs": [
866 |         {
867 |           "output_type": "stream",
868 |           "name": "stdout",
869 |           "text": [
870 |             "(2, 4)\n",
871 |             "(225954,)\n"
872 |           ]
873 |         }
874 |       ]
875 |     },
876 |     {
877 |       "cell_type": "code",
878 |       "source": [
879 |         "print(data.head())"
880 |       ],
881 |       "metadata": {
882 |         "colab": {
883 |           "base_uri": "https://localhost:8080/"
884 |         },
885 |         "id": "EjuvD3oiBBOD",
886 |         "outputId": "6d43b612-051a-4509-fa4c-6d90690198b5"
887 |       },
888 |       "execution_count": null,
889 |       "outputs": [
890 |         {
891 |           "output_type": "stream",
892 |           "name": "stdout",
893 |           "text": [
894 |             "        ID  innings  overs  ballnumber       batter          bowler  \\\n",
895 |             "0  1312200        1      0           1  YBK Jaiswal  Mohammed Shami   \n",
896 |             "1  1312200        1      0           2  YBK Jaiswal  Mohammed Shami   \n",
897 |             "2  1312200        1      0           3   JC Buttler  Mohammed Shami   \n",
898 |             "3  1312200        1      0           4  YBK Jaiswal  Mohammed Shami   \n",
899 |             "4  1312200        1      0           5  YBK Jaiswal  Mohammed Shami   \n",
900 |             "\n",
901 |             "   non-striker extra_type  batsman_run  extras_run  total_run  non_boundary  \\\n",
902 |             "0   JC Buttler        NaN            0           0          0             0   \n",
903 |             "1   JC Buttler    legbyes            0           1          1             0   \n",
904 |             "2  YBK Jaiswal        NaN            1           0          1             0   \n",
905 |             "3   JC Buttler        NaN            0           0          0             0   \n",
906 |             "4   JC Buttler        NaN            0           0          0             0   \n",
907 |             "\n",
908 |             "   isWicketDelivery player_out kind fielders_involved       BattingTeam  \n",
909 |             "0                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
910 |             "1                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
911 |             "2                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
912 |             "3                 0        NaN  NaN               NaN  Rajasthan Royals  \n",
913 |             "4                 0        NaN  NaN               NaN  Rajasthan Royals  \n"
914 |           ]
915 |         }
916 |       ]
917 |     },
918 |     {
919 |       "cell_type": "code",
920 |       "source": [
921 |         "print(f\"Shape of Z: {Z.shape}\")\n",
922 |         "print(f\"Shape of labels: {data['BattingTeam'][:-1].shape}\")"
923 |       ],
924 |       "metadata": {
925 |         "colab": {
926 |           "base_uri": "https://localhost:8080/"
927 |         },
928 |         "id": "pWpv7P8YBPF6",
929 |         "outputId": "80127805-146b-48f0-cc8f-e9437c8c03a5"
930 |       },
931 |       "execution_count": null,
932 |       "outputs": [
933 |         {
934 |           "output_type": "stream",
935 |           "name": "stdout",
936 |           "text": [
937 |             "Shape of Z: (2, 4)\n",
938 |             "Shape of labels: (225953,)\n"
939 |           ]
940 |         }
941 |       ]
942 |     },
943 |     {
944 |       "cell_type": "code",
945 |       "source": [
946 |         "# Assuming you have the distance matrix ('distance_matrix') and linkage matrix ('Z') calculated\n",
947 |         "\n",
948 |         "# Check if distance_matrix and Z are not empty\n",
949 |         "if distance_matrix.size > 0 and Z.size > 0:\n",
950 |         "\n",
951 |         "  # Ensure data['BattingTeam'] has the same length as the number of data points\n",
952 |         "  if len(data) == Z.shape[0]:  # Check data length vs. linkage matrix size\n",
953 |         "    plt.figure(figsize=(10, 6))\n",
954 |         "    dendrogram(Z, labels=data['BattingTeam'])  # Assuming 'BattingTeam' is the team name column\n",
955 |         "    plt.title('IPL Match Clustering (Ward\\'s Method)')\n",
956 |         "    plt.show()\n",
957 |         "  else:\n",
958 |         "    print(\"Error: Data size and linkage matrix size don't match. Check data selection.\")\n",
959 |         "else:\n",
960 |         "  print(\"Error: Distance matrix or linkage matrix is empty. Check data and calculations.\")\n"
961 |       ],
962 |       "metadata": {
963 |         "colab": {
964 |           "base_uri": "https://localhost:8080/"
965 |         },
966 |         "id": "JwHA8cZmAhHo",
967 |         "outputId": "a32004f8-6fcf-4ce6-f7e8-0f0fe2bc4a26"
968 |       },
969 |       "execution_count": null,
970 |       "outputs": [
971 |         {
972 |           "output_type": "stream",
973 |           "name": "stdout",
974 |           "text": [
975 |             "Error: Data size and linkage matrix size don't match. Check data selection.\n"
976 |           ]
977 |         }
978 |       ]
979 |     }
980 |   ]
981 | }


--------------------------------------------------------------------------------