├── README.md
├── dataset_training.ipynb
└── .ipynb_checkpoints
    └── dataset_training-checkpoint.ipynb


/README.md:
--------------------------------------------------------------------------------
1 | # Intel O-Level Certification Program Task
2 | 
3 | Dataset training.
4 | 


--------------------------------------------------------------------------------
/dataset_training.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "0bb88562",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "application/javascript": [
 12 |        "\n",
 13 |        "            setTimeout(function() {\n",
 14 |        "                var nbb_cell_id = 1;\n",
 15 |        "                var nbb_unformatted_code = \"%load_ext nb_black\";\n",
 16 |        "                var nbb_formatted_code = \"%load_ext nb_black\";\n",
 17 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
 18 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
 19 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
 20 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
 21 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
 22 |        "                        }\n",
 23 |        "                        break;\n",
 24 |        "                    }\n",
 25 |        "                }\n",
 26 |        "            }, 500);\n",
 27 |        "            "
 28 |       ],
 29 |       "text/plain": [
 30 |        "<IPython.core.display.Javascript object>"
 31 |       ]
 32 |      },
 33 |      "metadata": {},
 34 |      "output_type": "display_data"
 35 |     }
 36 |    ],
 37 |    "source": [
 38 |     "%load_ext nb_black"
 39 |    ]
 40 |   },
 41 |   {
 42 |    "cell_type": "code",
 43 |    "execution_count": 47,
 44 |    "id": "fce3217b",
 45 |    "metadata": {},
 46 |    "outputs": [
 47 |     {
 48 |      "data": {
 49 |       "text/html": [
 50 |        "<div>\n",
 51 |        "<style scoped>\n",
 52 |        "    .dataframe tbody tr th:only-of-type {\n",
 53 |        "        vertical-align: middle;\n",
 54 |        "    }\n",
 55 |        "\n",
 56 |        "    .dataframe tbody tr th {\n",
 57 |        "        vertical-align: top;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe thead th {\n",
 61 |        "        text-align: right;\n",
 62 |        "    }\n",
 63 |        "</style>\n",
 64 |        "<table border=\"1\" class=\"dataframe\">\n",
 65 |        "  <thead>\n",
 66 |        "    <tr style=\"text-align: right;\">\n",
 67 |        "      <th></th>\n",
 68 |        "      <th>ram(GB)</th>\n",
 69 |        "      <th>price(¢)</th>\n",
 70 |        "    </tr>\n",
 71 |        "  </thead>\n",
 72 |        "  <tbody>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>0</th>\n",
 75 |        "      <td>8.0</td>\n",
 76 |        "      <td>2450.0</td>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>1</th>\n",
 80 |        "      <td>12.0</td>\n",
 81 |        "      <td>5000.0</td>\n",
 82 |        "    </tr>\n",
 83 |        "    <tr>\n",
 84 |        "      <th>2</th>\n",
 85 |        "      <td>8.0</td>\n",
 86 |        "      <td>3000.0</td>\n",
 87 |        "    </tr>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>3</th>\n",
 90 |        "      <td>8.0</td>\n",
 91 |        "      <td>1900.0</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>4</th>\n",
 95 |        "      <td>12.0</td>\n",
 96 |        "      <td>5750.0</td>\n",
 97 |        "    </tr>\n",
 98 |        "    <tr>\n",
 99 |        "      <th>...</th>\n",
100 |        "      <td>...</td>\n",
101 |        "      <td>...</td>\n",
102 |        "    </tr>\n",
103 |        "    <tr>\n",
104 |        "      <th>3595</th>\n",
105 |        "      <td>0.0</td>\n",
106 |        "      <td>2850.0</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>3596</th>\n",
110 |        "      <td>8.0</td>\n",
111 |        "      <td>1060.0</td>\n",
112 |        "    </tr>\n",
113 |        "    <tr>\n",
114 |        "      <th>3597</th>\n",
115 |        "      <td>2.0</td>\n",
116 |        "      <td>880.0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>3598</th>\n",
120 |        "      <td>0.0</td>\n",
121 |        "      <td>299.0</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>3599</th>\n",
125 |        "      <td>16.0</td>\n",
126 |        "      <td>11500.0</td>\n",
127 |        "    </tr>\n",
128 |        "  </tbody>\n",
129 |        "</table>\n",
130 |        "<p>3600 rows × 2 columns</p>\n",
131 |        "</div>"
132 |       ],
133 |       "text/plain": [
134 |        "      ram(GB)  price(¢)\n",
135 |        "0         8.0    2450.0\n",
136 |        "1        12.0    5000.0\n",
137 |        "2         8.0    3000.0\n",
138 |        "3         8.0    1900.0\n",
139 |        "4        12.0    5750.0\n",
140 |        "...       ...       ...\n",
141 |        "3595      0.0    2850.0\n",
142 |        "3596      8.0    1060.0\n",
143 |        "3597      2.0     880.0\n",
144 |        "3598      0.0     299.0\n",
145 |        "3599     16.0   11500.0\n",
146 |        "\n",
147 |        "[3600 rows x 2 columns]"
148 |       ]
149 |      },
150 |      "execution_count": 47,
151 |      "metadata": {},
152 |      "output_type": "execute_result"
153 |     },
154 |     {
155 |      "data": {
156 |       "application/javascript": [
157 |        "\n",
158 |        "            setTimeout(function() {\n",
159 |        "                var nbb_cell_id = 47;\n",
160 |        "                var nbb_unformatted_code = \"import pandas as pd\\n\\ndata = pd.read_csv(\\\"./Mobile-Phones.csv\\\")\\ndata.drop(\\n    [\\n        \\\"main_camera\\\",\\n        \\\"resolution\\\",\\n        \\\"battery(mAh)\\\",\\n        \\\"storage(GB)\\\",\\n        \\\"selfie_camera(MP)\\\",\\n        \\\"sim_card\\\",\\n        \\\"sd_card\\\",\\n        \\\"region\\\",\\n        \\\"location\\\",\\n        \\\"screen_size(inch)\\\",\\n        \\\"color\\\",\\n        \\\"brand\\\",\\n        \\\"model\\\",\\n        \\\"display\\\",\\n        \\\"os\\\",\\n    ],\\n    axis=1,\\n    inplace=True,\\n)\\ndata.fillna(0, inplace=True)\\ndata\";\n",
161 |        "                var nbb_formatted_code = \"import pandas as pd\\n\\ndata = pd.read_csv(\\\"./Mobile-Phones.csv\\\")\\ndata.drop(\\n    [\\n        \\\"main_camera\\\",\\n        \\\"resolution\\\",\\n        \\\"battery(mAh)\\\",\\n        \\\"storage(GB)\\\",\\n        \\\"selfie_camera(MP)\\\",\\n        \\\"sim_card\\\",\\n        \\\"sd_card\\\",\\n        \\\"region\\\",\\n        \\\"location\\\",\\n        \\\"screen_size(inch)\\\",\\n        \\\"color\\\",\\n        \\\"brand\\\",\\n        \\\"model\\\",\\n        \\\"display\\\",\\n        \\\"os\\\",\\n    ],\\n    axis=1,\\n    inplace=True,\\n)\\ndata.fillna(0, inplace=True)\\ndata\";\n",
162 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
163 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
164 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
165 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
166 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
167 |        "                        }\n",
168 |        "                        break;\n",
169 |        "                    }\n",
170 |        "                }\n",
171 |        "            }, 500);\n",
172 |        "            "
173 |       ],
174 |       "text/plain": [
175 |        "<IPython.core.display.Javascript object>"
176 |       ]
177 |      },
178 |      "metadata": {},
179 |      "output_type": "display_data"
180 |     }
181 |    ],
182 |    "source": [
183 |     "import pandas as pd\n",
184 |     "\n",
185 |     "data = pd.read_csv(\"./Mobile-Phones.csv\")\n",
186 |     "data.drop(\n",
187 |     "    [\n",
188 |     "        \"main_camera\",\n",
189 |     "        \"resolution\",\n",
190 |     "        \"battery(mAh)\",\n",
191 |     "        \"storage(GB)\",\n",
192 |     "        \"selfie_camera(MP)\",\n",
193 |     "        \"sim_card\",\n",
194 |     "        \"sd_card\",\n",
195 |     "        \"region\",\n",
196 |     "        \"location\",\n",
197 |     "        \"screen_size(inch)\",\n",
198 |     "        \"color\",\n",
199 |     "        \"brand\",\n",
200 |     "        \"model\",\n",
201 |     "        \"display\",\n",
202 |     "        \"os\",\n",
203 |     "    ],\n",
204 |     "    axis=1,\n",
205 |     "    inplace=True,\n",
206 |     ")\n",
207 |     "data.fillna(0, inplace=True)\n",
208 |     "data"
209 |    ]
210 |   },
211 |   {
212 |    "cell_type": "code",
213 |    "execution_count": 48,
214 |    "id": "0a7cc21f",
215 |    "metadata": {},
216 |    "outputs": [
217 |     {
218 |      "data": {
219 |       "application/javascript": [
220 |        "\n",
221 |        "            setTimeout(function() {\n",
222 |        "                var nbb_cell_id = 48;\n",
223 |        "                var nbb_unformatted_code = \"x_cols = [x for x in data.columns if x != \\\"price(\\u00a2)\\\"]\\n\\nX_data = data[x_cols]\\ny_data = data[\\\"price(\\u00a2)\\\"]\";\n",
224 |        "                var nbb_formatted_code = \"x_cols = [x for x in data.columns if x != \\\"price(\\u00a2)\\\"]\\n\\nX_data = data[x_cols]\\ny_data = data[\\\"price(\\u00a2)\\\"]\";\n",
225 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
226 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
227 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
228 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
229 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
230 |        "                        }\n",
231 |        "                        break;\n",
232 |        "                    }\n",
233 |        "                }\n",
234 |        "            }, 500);\n",
235 |        "            "
236 |       ],
237 |       "text/plain": [
238 |        "<IPython.core.display.Javascript object>"
239 |       ]
240 |      },
241 |      "metadata": {},
242 |      "output_type": "display_data"
243 |     }
244 |    ],
245 |    "source": [
246 |     "x_cols = [x for x in data.columns if x != \"price(¢)\"]\n",
247 |     "\n",
248 |     "X_data = data[x_cols]\n",
249 |     "y_data = data[\"price(¢)\"]"
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": 49,
255 |    "id": "700973e8",
256 |    "metadata": {},
257 |    "outputs": [
258 |     {
259 |      "data": {
260 |       "application/javascript": [
261 |        "\n",
262 |        "            setTimeout(function() {\n",
263 |        "                var nbb_cell_id = 49;\n",
264 |        "                var nbb_unformatted_code = \"from sklearn.neighbors import KNeighborsClassifier\\n\\nknn = KNeighborsClassifier(n_neighbors=3)\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\";\n",
265 |        "                var nbb_formatted_code = \"from sklearn.neighbors import KNeighborsClassifier\\n\\nknn = KNeighborsClassifier(n_neighbors=3)\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\";\n",
266 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
267 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
268 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
269 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
270 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
271 |        "                        }\n",
272 |        "                        break;\n",
273 |        "                    }\n",
274 |        "                }\n",
275 |        "            }, 500);\n",
276 |        "            "
277 |       ],
278 |       "text/plain": [
279 |        "<IPython.core.display.Javascript object>"
280 |       ]
281 |      },
282 |      "metadata": {},
283 |      "output_type": "display_data"
284 |     }
285 |    ],
286 |    "source": [
287 |     "from sklearn.neighbors import KNeighborsClassifier\n",
288 |     "\n",
289 |     "knn = KNeighborsClassifier(n_neighbors=3)\n",
290 |     "\n",
291 |     "knn = knn.fit(X_data, y_data)\n",
292 |     "\n",
293 |     "y_pred = knn.predict(X_data)"
294 |    ]
295 |   },
296 |   {
297 |    "cell_type": "code",
298 |    "execution_count": 50,
299 |    "id": "807bdc8b",
300 |    "metadata": {},
301 |    "outputs": [
302 |     {
303 |      "data": {
304 |       "application/javascript": [
305 |        "\n",
306 |        "            setTimeout(function() {\n",
307 |        "                var nbb_cell_id = 50;\n",
308 |        "                var nbb_unformatted_code = \"def accuracy(real, predict):\\n    return sum(y_data == y_pred) / float(real.shape[0])\";\n",
309 |        "                var nbb_formatted_code = \"def accuracy(real, predict):\\n    return sum(y_data == y_pred) / float(real.shape[0])\";\n",
310 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
311 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
312 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
313 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
314 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
315 |        "                        }\n",
316 |        "                        break;\n",
317 |        "                    }\n",
318 |        "                }\n",
319 |        "            }, 500);\n",
320 |        "            "
321 |       ],
322 |       "text/plain": [
323 |        "<IPython.core.display.Javascript object>"
324 |       ]
325 |      },
326 |      "metadata": {},
327 |      "output_type": "display_data"
328 |     }
329 |    ],
330 |    "source": [
331 |     "def accuracy(real, predict):\n",
332 |     "    return sum(y_data == y_pred) / float(real.shape[0])"
333 |    ]
334 |   },
335 |   {
336 |    "cell_type": "code",
337 |    "execution_count": 51,
338 |    "id": "0c7b5f8a",
339 |    "metadata": {},
340 |    "outputs": [
341 |     {
342 |      "name": "stdout",
343 |      "output_type": "stream",
344 |      "text": [
345 |       "0.016944444444444446\n"
346 |      ]
347 |     },
348 |     {
349 |      "data": {
350 |       "application/javascript": [
351 |        "\n",
352 |        "            setTimeout(function() {\n",
353 |        "                var nbb_cell_id = 51;\n",
354 |        "                var nbb_unformatted_code = \"print(accuracy(y_data, y_pred))\";\n",
355 |        "                var nbb_formatted_code = \"print(accuracy(y_data, y_pred))\";\n",
356 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
357 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
358 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
359 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
360 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
361 |        "                        }\n",
362 |        "                        break;\n",
363 |        "                    }\n",
364 |        "                }\n",
365 |        "            }, 500);\n",
366 |        "            "
367 |       ],
368 |       "text/plain": [
369 |        "<IPython.core.display.Javascript object>"
370 |       ]
371 |      },
372 |      "metadata": {},
373 |      "output_type": "display_data"
374 |     }
375 |    ],
376 |    "source": [
377 |     "print(accuracy(y_data, y_pred))"
378 |    ]
379 |   },
380 |   {
381 |    "cell_type": "code",
382 |    "execution_count": 52,
383 |    "id": "6d74db71",
384 |    "metadata": {},
385 |    "outputs": [
386 |     {
387 |      "name": "stdout",
388 |      "output_type": "stream",
389 |      "text": [
390 |       "0.015277777777777777\n"
391 |      ]
392 |     },
393 |     {
394 |      "data": {
395 |       "application/javascript": [
396 |        "\n",
397 |        "            setTimeout(function() {\n",
398 |        "                var nbb_cell_id = 52;\n",
399 |        "                var nbb_unformatted_code = \"knn = KNeighborsClassifier(n_neighbors=5, weights=\\\"distance\\\")\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\\n\\nprint(accuracy(y_data, y_pred))\";\n",
400 |        "                var nbb_formatted_code = \"knn = KNeighborsClassifier(n_neighbors=5, weights=\\\"distance\\\")\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\\n\\nprint(accuracy(y_data, y_pred))\";\n",
401 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
402 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
403 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
404 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
405 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
406 |        "                        }\n",
407 |        "                        break;\n",
408 |        "                    }\n",
409 |        "                }\n",
410 |        "            }, 500);\n",
411 |        "            "
412 |       ],
413 |       "text/plain": [
414 |        "<IPython.core.display.Javascript object>"
415 |       ]
416 |      },
417 |      "metadata": {},
418 |      "output_type": "display_data"
419 |     }
420 |    ],
421 |    "source": [
422 |     "knn = KNeighborsClassifier(n_neighbors=5, weights=\"distance\")\n",
423 |     "\n",
424 |     "knn = knn.fit(X_data, y_data)\n",
425 |     "\n",
426 |     "y_pred = knn.predict(X_data)\n",
427 |     "\n",
428 |     "print(accuracy(y_data, y_pred))"
429 |    ]
430 |   },
431 |   {
432 |    "cell_type": "code",
433 |    "execution_count": null,
434 |    "id": "d2055163",
435 |    "metadata": {},
436 |    "outputs": [],
437 |    "source": []
438 |   }
439 |  ],
440 |  "metadata": {
441 |   "kernelspec": {
442 |    "display_name": "Python 3 (ipykernel)",
443 |    "language": "python",
444 |    "name": "python3"
445 |   },
446 |   "language_info": {
447 |    "codemirror_mode": {
448 |     "name": "ipython",
449 |     "version": 3
450 |    },
451 |    "file_extension": ".py",
452 |    "mimetype": "text/x-python",
453 |    "name": "python",
454 |    "nbconvert_exporter": "python",
455 |    "pygments_lexer": "ipython3",
456 |    "version": "3.9.16"
457 |   }
458 |  },
459 |  "nbformat": 4,
460 |  "nbformat_minor": 5
461 | }
462 | 


--------------------------------------------------------------------------------
/.ipynb_checkpoints/dataset_training-checkpoint.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "0bb88562",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "data": {
 11 |       "application/javascript": [
 12 |        "\n",
 13 |        "            setTimeout(function() {\n",
 14 |        "                var nbb_cell_id = 1;\n",
 15 |        "                var nbb_unformatted_code = \"%load_ext nb_black\";\n",
 16 |        "                var nbb_formatted_code = \"%load_ext nb_black\";\n",
 17 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
 18 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
 19 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
 20 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
 21 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
 22 |        "                        }\n",
 23 |        "                        break;\n",
 24 |        "                    }\n",
 25 |        "                }\n",
 26 |        "            }, 500);\n",
 27 |        "            "
 28 |       ],
 29 |       "text/plain": [
 30 |        "<IPython.core.display.Javascript object>"
 31 |       ]
 32 |      },
 33 |      "metadata": {},
 34 |      "output_type": "display_data"
 35 |     }
 36 |    ],
 37 |    "source": [
 38 |     "%load_ext nb_black"
 39 |    ]
 40 |   },
 41 |   {
 42 |    "cell_type": "code",
 43 |    "execution_count": 47,
 44 |    "id": "fce3217b",
 45 |    "metadata": {},
 46 |    "outputs": [
 47 |     {
 48 |      "data": {
 49 |       "text/html": [
 50 |        "<div>\n",
 51 |        "<style scoped>\n",
 52 |        "    .dataframe tbody tr th:only-of-type {\n",
 53 |        "        vertical-align: middle;\n",
 54 |        "    }\n",
 55 |        "\n",
 56 |        "    .dataframe tbody tr th {\n",
 57 |        "        vertical-align: top;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe thead th {\n",
 61 |        "        text-align: right;\n",
 62 |        "    }\n",
 63 |        "</style>\n",
 64 |        "<table border=\"1\" class=\"dataframe\">\n",
 65 |        "  <thead>\n",
 66 |        "    <tr style=\"text-align: right;\">\n",
 67 |        "      <th></th>\n",
 68 |        "      <th>ram(GB)</th>\n",
 69 |        "      <th>price(¢)</th>\n",
 70 |        "    </tr>\n",
 71 |        "  </thead>\n",
 72 |        "  <tbody>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>0</th>\n",
 75 |        "      <td>8.0</td>\n",
 76 |        "      <td>2450.0</td>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>1</th>\n",
 80 |        "      <td>12.0</td>\n",
 81 |        "      <td>5000.0</td>\n",
 82 |        "    </tr>\n",
 83 |        "    <tr>\n",
 84 |        "      <th>2</th>\n",
 85 |        "      <td>8.0</td>\n",
 86 |        "      <td>3000.0</td>\n",
 87 |        "    </tr>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>3</th>\n",
 90 |        "      <td>8.0</td>\n",
 91 |        "      <td>1900.0</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>4</th>\n",
 95 |        "      <td>12.0</td>\n",
 96 |        "      <td>5750.0</td>\n",
 97 |        "    </tr>\n",
 98 |        "    <tr>\n",
 99 |        "      <th>...</th>\n",
100 |        "      <td>...</td>\n",
101 |        "      <td>...</td>\n",
102 |        "    </tr>\n",
103 |        "    <tr>\n",
104 |        "      <th>3595</th>\n",
105 |        "      <td>0.0</td>\n",
106 |        "      <td>2850.0</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>3596</th>\n",
110 |        "      <td>8.0</td>\n",
111 |        "      <td>1060.0</td>\n",
112 |        "    </tr>\n",
113 |        "    <tr>\n",
114 |        "      <th>3597</th>\n",
115 |        "      <td>2.0</td>\n",
116 |        "      <td>880.0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>3598</th>\n",
120 |        "      <td>0.0</td>\n",
121 |        "      <td>299.0</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>3599</th>\n",
125 |        "      <td>16.0</td>\n",
126 |        "      <td>11500.0</td>\n",
127 |        "    </tr>\n",
128 |        "  </tbody>\n",
129 |        "</table>\n",
130 |        "<p>3600 rows × 2 columns</p>\n",
131 |        "</div>"
132 |       ],
133 |       "text/plain": [
134 |        "      ram(GB)  price(¢)\n",
135 |        "0         8.0    2450.0\n",
136 |        "1        12.0    5000.0\n",
137 |        "2         8.0    3000.0\n",
138 |        "3         8.0    1900.0\n",
139 |        "4        12.0    5750.0\n",
140 |        "...       ...       ...\n",
141 |        "3595      0.0    2850.0\n",
142 |        "3596      8.0    1060.0\n",
143 |        "3597      2.0     880.0\n",
144 |        "3598      0.0     299.0\n",
145 |        "3599     16.0   11500.0\n",
146 |        "\n",
147 |        "[3600 rows x 2 columns]"
148 |       ]
149 |      },
150 |      "execution_count": 47,
151 |      "metadata": {},
152 |      "output_type": "execute_result"
153 |     },
154 |     {
155 |      "data": {
156 |       "application/javascript": [
157 |        "\n",
158 |        "            setTimeout(function() {\n",
159 |        "                var nbb_cell_id = 47;\n",
160 |        "                var nbb_unformatted_code = \"import pandas as pd\\n\\ndata = pd.read_csv(\\\"./Mobile-Phones.csv\\\")\\ndata.drop(\\n    [\\n        \\\"main_camera\\\",\\n        \\\"resolution\\\",\\n        \\\"battery(mAh)\\\",\\n        \\\"storage(GB)\\\",\\n        \\\"selfie_camera(MP)\\\",\\n        \\\"sim_card\\\",\\n        \\\"sd_card\\\",\\n        \\\"region\\\",\\n        \\\"location\\\",\\n        \\\"screen_size(inch)\\\",\\n        \\\"color\\\",\\n        \\\"brand\\\",\\n        \\\"model\\\",\\n        \\\"display\\\",\\n        \\\"os\\\",\\n    ],\\n    axis=1,\\n    inplace=True,\\n)\\ndata.fillna(0, inplace=True)\\ndata\";\n",
161 |        "                var nbb_formatted_code = \"import pandas as pd\\n\\ndata = pd.read_csv(\\\"./Mobile-Phones.csv\\\")\\ndata.drop(\\n    [\\n        \\\"main_camera\\\",\\n        \\\"resolution\\\",\\n        \\\"battery(mAh)\\\",\\n        \\\"storage(GB)\\\",\\n        \\\"selfie_camera(MP)\\\",\\n        \\\"sim_card\\\",\\n        \\\"sd_card\\\",\\n        \\\"region\\\",\\n        \\\"location\\\",\\n        \\\"screen_size(inch)\\\",\\n        \\\"color\\\",\\n        \\\"brand\\\",\\n        \\\"model\\\",\\n        \\\"display\\\",\\n        \\\"os\\\",\\n    ],\\n    axis=1,\\n    inplace=True,\\n)\\ndata.fillna(0, inplace=True)\\ndata\";\n",
162 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
163 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
164 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
165 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
166 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
167 |        "                        }\n",
168 |        "                        break;\n",
169 |        "                    }\n",
170 |        "                }\n",
171 |        "            }, 500);\n",
172 |        "            "
173 |       ],
174 |       "text/plain": [
175 |        "<IPython.core.display.Javascript object>"
176 |       ]
177 |      },
178 |      "metadata": {},
179 |      "output_type": "display_data"
180 |     }
181 |    ],
182 |    "source": [
183 |     "import pandas as pd\n",
184 |     "\n",
185 |     "data = pd.read_csv(\"./Mobile-Phones.csv\")\n",
186 |     "data.drop(\n",
187 |     "    [\n",
188 |     "        \"main_camera\",\n",
189 |     "        \"resolution\",\n",
190 |     "        \"battery(mAh)\",\n",
191 |     "        \"storage(GB)\",\n",
192 |     "        \"selfie_camera(MP)\",\n",
193 |     "        \"sim_card\",\n",
194 |     "        \"sd_card\",\n",
195 |     "        \"region\",\n",
196 |     "        \"location\",\n",
197 |     "        \"screen_size(inch)\",\n",
198 |     "        \"color\",\n",
199 |     "        \"brand\",\n",
200 |     "        \"model\",\n",
201 |     "        \"display\",\n",
202 |     "        \"os\",\n",
203 |     "    ],\n",
204 |     "    axis=1,\n",
205 |     "    inplace=True,\n",
206 |     ")\n",
207 |     "data.fillna(0, inplace=True)\n",
208 |     "data"
209 |    ]
210 |   },
211 |   {
212 |    "cell_type": "code",
213 |    "execution_count": 48,
214 |    "id": "0a7cc21f",
215 |    "metadata": {},
216 |    "outputs": [
217 |     {
218 |      "data": {
219 |       "application/javascript": [
220 |        "\n",
221 |        "            setTimeout(function() {\n",
222 |        "                var nbb_cell_id = 48;\n",
223 |        "                var nbb_unformatted_code = \"x_cols = [x for x in data.columns if x != \\\"price(\\u00a2)\\\"]\\n\\nX_data = data[x_cols]\\ny_data = data[\\\"price(\\u00a2)\\\"]\";\n",
224 |        "                var nbb_formatted_code = \"x_cols = [x for x in data.columns if x != \\\"price(\\u00a2)\\\"]\\n\\nX_data = data[x_cols]\\ny_data = data[\\\"price(\\u00a2)\\\"]\";\n",
225 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
226 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
227 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
228 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
229 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
230 |        "                        }\n",
231 |        "                        break;\n",
232 |        "                    }\n",
233 |        "                }\n",
234 |        "            }, 500);\n",
235 |        "            "
236 |       ],
237 |       "text/plain": [
238 |        "<IPython.core.display.Javascript object>"
239 |       ]
240 |      },
241 |      "metadata": {},
242 |      "output_type": "display_data"
243 |     }
244 |    ],
245 |    "source": [
246 |     "x_cols = [x for x in data.columns if x != \"price(¢)\"]\n",
247 |     "\n",
248 |     "X_data = data[x_cols]\n",
249 |     "y_data = data[\"price(¢)\"]"
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": 49,
255 |    "id": "700973e8",
256 |    "metadata": {},
257 |    "outputs": [
258 |     {
259 |      "data": {
260 |       "application/javascript": [
261 |        "\n",
262 |        "            setTimeout(function() {\n",
263 |        "                var nbb_cell_id = 49;\n",
264 |        "                var nbb_unformatted_code = \"from sklearn.neighbors import KNeighborsClassifier\\n\\nknn = KNeighborsClassifier(n_neighbors=3)\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\";\n",
265 |        "                var nbb_formatted_code = \"from sklearn.neighbors import KNeighborsClassifier\\n\\nknn = KNeighborsClassifier(n_neighbors=3)\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\";\n",
266 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
267 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
268 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
269 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
270 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
271 |        "                        }\n",
272 |        "                        break;\n",
273 |        "                    }\n",
274 |        "                }\n",
275 |        "            }, 500);\n",
276 |        "            "
277 |       ],
278 |       "text/plain": [
279 |        "<IPython.core.display.Javascript object>"
280 |       ]
281 |      },
282 |      "metadata": {},
283 |      "output_type": "display_data"
284 |     }
285 |    ],
286 |    "source": [
287 |     "from sklearn.neighbors import KNeighborsClassifier\n",
288 |     "\n",
289 |     "knn = KNeighborsClassifier(n_neighbors=3)\n",
290 |     "\n",
291 |     "knn = knn.fit(X_data, y_data)\n",
292 |     "\n",
293 |     "y_pred = knn.predict(X_data)"
294 |    ]
295 |   },
296 |   {
297 |    "cell_type": "code",
298 |    "execution_count": 50,
299 |    "id": "807bdc8b",
300 |    "metadata": {},
301 |    "outputs": [
302 |     {
303 |      "data": {
304 |       "application/javascript": [
305 |        "\n",
306 |        "            setTimeout(function() {\n",
307 |        "                var nbb_cell_id = 50;\n",
308 |        "                var nbb_unformatted_code = \"def accuracy(real, predict):\\n    return sum(y_data == y_pred) / float(real.shape[0])\";\n",
309 |        "                var nbb_formatted_code = \"def accuracy(real, predict):\\n    return sum(y_data == y_pred) / float(real.shape[0])\";\n",
310 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
311 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
312 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
313 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
314 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
315 |        "                        }\n",
316 |        "                        break;\n",
317 |        "                    }\n",
318 |        "                }\n",
319 |        "            }, 500);\n",
320 |        "            "
321 |       ],
322 |       "text/plain": [
323 |        "<IPython.core.display.Javascript object>"
324 |       ]
325 |      },
326 |      "metadata": {},
327 |      "output_type": "display_data"
328 |     }
329 |    ],
330 |    "source": [
331 |     "def accuracy(real, predict):\n",
332 |     "    return sum(y_data == y_pred) / float(real.shape[0])"
333 |    ]
334 |   },
335 |   {
336 |    "cell_type": "code",
337 |    "execution_count": 51,
338 |    "id": "0c7b5f8a",
339 |    "metadata": {},
340 |    "outputs": [
341 |     {
342 |      "name": "stdout",
343 |      "output_type": "stream",
344 |      "text": [
345 |       "0.016944444444444446\n"
346 |      ]
347 |     },
348 |     {
349 |      "data": {
350 |       "application/javascript": [
351 |        "\n",
352 |        "            setTimeout(function() {\n",
353 |        "                var nbb_cell_id = 51;\n",
354 |        "                var nbb_unformatted_code = \"print(accuracy(y_data, y_pred))\";\n",
355 |        "                var nbb_formatted_code = \"print(accuracy(y_data, y_pred))\";\n",
356 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
357 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
358 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
359 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
360 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
361 |        "                        }\n",
362 |        "                        break;\n",
363 |        "                    }\n",
364 |        "                }\n",
365 |        "            }, 500);\n",
366 |        "            "
367 |       ],
368 |       "text/plain": [
369 |        "<IPython.core.display.Javascript object>"
370 |       ]
371 |      },
372 |      "metadata": {},
373 |      "output_type": "display_data"
374 |     }
375 |    ],
376 |    "source": [
377 |     "print(accuracy(y_data, y_pred))"
378 |    ]
379 |   },
380 |   {
381 |    "cell_type": "code",
382 |    "execution_count": 52,
383 |    "id": "6d74db71",
384 |    "metadata": {},
385 |    "outputs": [
386 |     {
387 |      "name": "stdout",
388 |      "output_type": "stream",
389 |      "text": [
390 |       "0.015277777777777777\n"
391 |      ]
392 |     },
393 |     {
394 |      "data": {
395 |       "application/javascript": [
396 |        "\n",
397 |        "            setTimeout(function() {\n",
398 |        "                var nbb_cell_id = 52;\n",
399 |        "                var nbb_unformatted_code = \"knn = KNeighborsClassifier(n_neighbors=5, weights=\\\"distance\\\")\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\\n\\nprint(accuracy(y_data, y_pred))\";\n",
400 |        "                var nbb_formatted_code = \"knn = KNeighborsClassifier(n_neighbors=5, weights=\\\"distance\\\")\\n\\nknn = knn.fit(X_data, y_data)\\n\\ny_pred = knn.predict(X_data)\\n\\nprint(accuracy(y_data, y_pred))\";\n",
401 |        "                var nbb_cells = Jupyter.notebook.get_cells();\n",
402 |        "                for (var i = 0; i < nbb_cells.length; ++i) {\n",
403 |        "                    if (nbb_cells[i].input_prompt_number == nbb_cell_id) {\n",
404 |        "                        if (nbb_cells[i].get_text() == nbb_unformatted_code) {\n",
405 |        "                             nbb_cells[i].set_text(nbb_formatted_code);\n",
406 |        "                        }\n",
407 |        "                        break;\n",
408 |        "                    }\n",
409 |        "                }\n",
410 |        "            }, 500);\n",
411 |        "            "
412 |       ],
413 |       "text/plain": [
414 |        "<IPython.core.display.Javascript object>"
415 |       ]
416 |      },
417 |      "metadata": {},
418 |      "output_type": "display_data"
419 |     }
420 |    ],
421 |    "source": [
422 |     "knn = KNeighborsClassifier(n_neighbors=5, weights=\"distance\")\n",
423 |     "\n",
424 |     "knn = knn.fit(X_data, y_data)\n",
425 |     "\n",
426 |     "y_pred = knn.predict(X_data)\n",
427 |     "\n",
428 |     "print(accuracy(y_data, y_pred))"
429 |    ]
430 |   },
431 |   {
432 |    "cell_type": "code",
433 |    "execution_count": null,
434 |    "id": "d2055163",
435 |    "metadata": {},
436 |    "outputs": [],
437 |    "source": []
438 |   }
439 |  ],
440 |  "metadata": {
441 |   "kernelspec": {
442 |    "display_name": "Python 3 (ipykernel)",
443 |    "language": "python",
444 |    "name": "python3"
445 |   },
446 |   "language_info": {
447 |    "codemirror_mode": {
448 |     "name": "ipython",
449 |     "version": 3
450 |    },
451 |    "file_extension": ".py",
452 |    "mimetype": "text/x-python",
453 |    "name": "python",
454 |    "nbconvert_exporter": "python",
455 |    "pygments_lexer": "ipython3",
456 |    "version": "3.9.16"
457 |   }
458 |  },
459 |  "nbformat": 4,
460 |  "nbformat_minor": 5
461 | }
462 | 


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