Upload sklearn_practice.ipynb

in machine learning, model validation is referred to as the process where a trained model is evaluated with a testing data set.

sklearn_practice.ipynb

@@ -0,0 +1,633 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "6452ab53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "df=pd.read_csv(\"Advertising.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5533bf4b",
+   "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>Unnamed: 0</th>\n",
+       "      <th>TV</th>\n",
+       "      <th>radio</th>\n",
+       "      <th>newspaper</th>\n",
+       "      <th>sales</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>230.1</td>\n",
+       "      <td>37.8</td>\n",
+       "      <td>69.2</td>\n",
+       "      <td>22.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>44.5</td>\n",
+       "      <td>39.3</td>\n",
+       "      <td>45.1</td>\n",
+       "      <td>10.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>17.2</td>\n",
+       "      <td>45.9</td>\n",
+       "      <td>69.3</td>\n",
+       "      <td>9.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>151.5</td>\n",
+       "      <td>41.3</td>\n",
+       "      <td>58.5</td>\n",
+       "      <td>18.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>180.8</td>\n",
+       "      <td>10.8</td>\n",
+       "      <td>58.4</td>\n",
+       "      <td>12.9</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Unnamed: 0     TV  radio  newspaper  sales\n",
+       "0           1  230.1   37.8       69.2   22.1\n",
+       "1           2   44.5   39.3       45.1   10.4\n",
+       "2           3   17.2   45.9       69.3    9.3\n",
+       "3           4  151.5   41.3       58.5   18.5\n",
+       "4           5  180.8   10.8       58.4   12.9"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "5f2f38b5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Unnamed: 0    0\n",
+       "TV            0\n",
+       "radio         0\n",
+       "newspaper     0\n",
+       "sales         0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a3c652b1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(200, 5)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c80ca9d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.tree import DecisionTreeRegressor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "64f6ec0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_features=df.columns\n",
+    "y=df.sales\n",
+    "X=df[df_features]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f863cb72",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Index(['Unnamed: 0', 'TV', 'radio', 'newspaper', 'sales'], dtype='object')\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_features)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "6cbf836d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0      22.1\n",
+      "1      10.4\n",
+      "2       9.3\n",
+      "3      18.5\n",
+      "4      12.9\n",
+      "       ... \n",
+      "195     7.6\n",
+      "196     9.7\n",
+      "197    12.8\n",
+      "198    25.5\n",
+      "199    13.4\n",
+      "Name: sales, Length: 200, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "889e08ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     Unnamed: 0     TV  radio  newspaper  sales\n",
+      "0             1  230.1   37.8       69.2   22.1\n",
+      "1             2   44.5   39.3       45.1   10.4\n",
+      "2             3   17.2   45.9       69.3    9.3\n",
+      "3             4  151.5   41.3       58.5   18.5\n",
+      "4             5  180.8   10.8       58.4   12.9\n",
+      "..          ...    ...    ...        ...    ...\n",
+      "195         196   38.2    3.7       13.8    7.6\n",
+      "196         197   94.2    4.9        8.1    9.7\n",
+      "197         198  177.0    9.3        6.4   12.8\n",
+      "198         199  283.6   42.0       66.2   25.5\n",
+      "199         200  232.1    8.6        8.7   13.4\n",
+      "\n",
+      "[200 rows x 5 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e486a41a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#model cretaed\n",
+    "df_model=DecisionTreeRegressor()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "c7070799",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "DecisionTreeRegressor()"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "b796e14e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "DecisionTreeRegressor()"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#fit model\n",
+    "df_model.fit(X,y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "650afd98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#calculateing the MAE\n",
+    "from sklearn.metrics import mean_absolute_error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "b8292980",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predicted_sales=df_model.predict(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "776ea1bb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([22.1, 10.4,  9.3, 18.5, 12.9,  7.2, 11.8, 13.2,  4.8, 10.6,  8.6,\n",
+       "       17.4,  9.2,  9.7, 19. , 22.4, 12.5, 24.4, 11.3, 14.6, 18. , 12.5,\n",
+       "        5.6, 15.5,  9.7, 12. , 15. , 15.9, 18.9, 10.5, 21.4, 11.9,  9.6,\n",
+       "       17.4,  9.5, 12.8, 25.4, 14.7, 10.1, 21.5, 16.6, 17.1, 20.7, 12.9,\n",
+       "        8.5, 14.9, 10.6, 23.2, 14.8,  9.7, 11.4, 10.7, 22.6, 21.2, 20.2,\n",
+       "       23.7,  5.5, 13.2, 23.8, 18.4,  8.1, 24.2, 15.7, 14. , 18. ,  9.3,\n",
+       "        9.5, 13.4, 18.9, 22.3, 18.3, 12.4,  8.8, 11. , 17. ,  8.7,  6.9,\n",
+       "       14.2,  5.3, 11. , 11.8, 12.3, 11.3, 13.6, 21.7, 15.2, 12. , 16. ,\n",
+       "       12.9, 16.7, 11.2,  7.3, 19.4, 22.2, 11.5, 16.9, 11.7, 15.5, 25.4,\n",
+       "       17.2, 11.7, 23.8, 14.8, 14.7, 20.7, 19.2,  7.2,  8.7,  5.3, 19.8,\n",
+       "       13.4, 21.8, 14.1, 15.9, 14.6, 12.6, 12.2,  9.4, 15.9,  6.6, 15.5,\n",
+       "        7. , 11.6, 15.2, 19.7, 10.6,  6.6,  8.8, 24.7,  9.7,  1.6, 12.7,\n",
+       "        5.7, 19.6, 10.8, 11.6,  9.5, 20.8,  9.6, 20.7, 10.9, 19.2, 20.1,\n",
+       "       10.4, 11.4, 10.3, 13.2, 25.4, 10.9, 10.1, 16.1, 11.6, 16.6, 19. ,\n",
+       "       15.6,  3.2, 15.3, 10.1,  7.3, 12.9, 14.4, 13.3, 14.9, 18. , 11.9,\n",
+       "       11.9,  8. , 12.2, 17.1, 15. ,  8.4, 14.5,  7.6, 11.7, 11.5, 27. ,\n",
+       "       20.2, 11.7, 11.8, 12.6, 10.5, 12.2,  8.7, 26.2, 17.6, 22.6, 10.3,\n",
+       "       17.3, 15.9,  6.7, 10.8,  9.9,  5.9, 19.6, 17.3,  7.6,  9.7, 12.8,\n",
+       "       25.5, 13.4])"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predicted_sales"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "785db183",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "5.329070518200751e-17"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_absolute_error(y,predicted_sales)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7c56805f",
+   "metadata": {},
+   "source": [
+    "# splitting the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "c9a97954",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "592afda8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#split the data and make ordiction on the slaes\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "train_X, value_X, train_y, value_y = train_test_split(X,y,random_state=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "9b16c96b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     Unnamed: 0     TV  radio  newspaper  sales\n",
+      "71           72  109.8   14.3       31.7   12.4\n",
+      "124         125  229.5   32.3       74.2   19.7\n",
+      "184         185  253.8   21.3       30.0   17.6\n",
+      "97           98  184.9   21.0       22.0   15.5\n",
+      "149         150   44.7   25.8       20.6   10.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "#model defining for the splitted data\n",
+    "print(train_X.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "ccb49d15",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "     Unnamed: 0     TV  radio  newspaper  sales\n",
+      "18           19   69.2   20.5       18.3   11.3\n",
+      "170         171   50.0   11.6       18.4    8.4\n",
+      "107         108   90.4    0.3       23.2    8.7\n",
+      "98           99  289.7   42.3       51.2   25.4\n",
+      "177         178  170.2    7.8       35.2   11.7\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(value_X.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "1cf49a81",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "71     12.4\n",
+      "124    19.7\n",
+      "184    17.6\n",
+      "97     15.5\n",
+      "149    10.1\n",
+      "Name: sales, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(train_y.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "2a43ddbe",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "18     11.3\n",
+      "170     8.4\n",
+      "107     8.7\n",
+      "98     25.4\n",
+      "177    11.7\n",
+      "Name: sales, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(value_y.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "1d693cd4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_df2=DecisionTreeRegressor()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "1c9fa0e3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "DecisionTreeRegressor()"
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model_df2.fit(train_X,train_y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "281c1e58",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2_predict=model_df2.predict(value_X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "91b05122",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([11.3,  8.6,  8.6, 25.5, 11.7,  8.6,  7.3, 13.4,  9.3, 16.9, 24.4,\n",
+       "       10.9, 11. , 15.7, 11.8, 13.2, 17.6,  3.2, 14.7, 16.7, 25.4, 10.3,\n",
+       "       15.2, 12.9,  8.6, 15.3, 12.5, 22.6, 11.6,  8.6, 12.6, 23.8, 15.9,\n",
+       "       21.5,  5.5,  6.6,  9.7, 12.9, 13.2,  7.3, 10.9,  9.5, 15.2, 15.9,\n",
+       "       17.4, 14.2,  5.3,  8. , 16. , 11. ])"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2_predict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "22a076e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mae=mean_absolute_error(value_y,df2_predict)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "4584d26d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.20800000000000002"
+      ]
+     },
+     "execution_count": 52,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mae"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}