diff --git a/Diabetes Classification/.ipynb_checkpoints/diabetesclassification-checkpoint.ipynb b/Diabetes Classification/.ipynb_checkpoints/diabetesclassification-checkpoint.ipynb
index d4d68ed..0f854e2 100644
--- a/Diabetes Classification/.ipynb_checkpoints/diabetesclassification-checkpoint.ipynb	
+++ b/Diabetes Classification/.ipynb_checkpoints/diabetesclassification-checkpoint.ipynb	
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 166,
+   "execution_count": 36,
    "id": "312c95a1",
    "metadata": {},
    "outputs": [],
@@ -29,7 +29,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 167,
+   "execution_count": 37,
    "id": "aea1b45b",
    "metadata": {},
    "outputs": [],
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 168,
+   "execution_count": 38,
    "id": "2ac5c17b",
    "metadata": {},
    "outputs": [
@@ -275,7 +275,7 @@
        "[5132 rows x 11 columns]"
       ]
      },
-     "execution_count": 168,
+     "execution_count": 38,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -286,7 +286,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 169,
+   "execution_count": 39,
    "id": "c4484360",
    "metadata": {},
    "outputs": [
@@ -408,7 +408,7 @@
        "4           4   50      F   24   3.6  1.3  0.9  2.1  50.0  2.0          0"
       ]
      },
-     "execution_count": 169,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -427,7 +427,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 170,
+   "execution_count": 40,
    "id": "ea7c6dcb",
    "metadata": {},
    "outputs": [
@@ -437,7 +437,7 @@
        "(5132, 11)"
       ]
      },
-     "execution_count": 170,
+     "execution_count": 40,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -456,7 +456,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 171,
+   "execution_count": 41,
    "id": "a3c2ff78",
    "metadata": {},
    "outputs": [
@@ -499,7 +499,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 172,
+   "execution_count": 42,
    "id": "a9cc7614",
    "metadata": {},
    "outputs": [],
@@ -510,7 +510,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 173,
+   "execution_count": 43,
    "id": "cdee3c52",
    "metadata": {
     "scrolled": true
@@ -554,7 +554,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 174,
+   "execution_count": 44,
    "id": "2f353609",
    "metadata": {},
    "outputs": [
@@ -572,7 +572,7 @@
        "Name: Age, dtype: float64"
       ]
      },
-     "execution_count": 174,
+     "execution_count": 44,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -583,7 +583,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 175,
+   "execution_count": 45,
    "id": "b7887949",
    "metadata": {},
    "outputs": [
@@ -601,7 +601,7 @@
        "Name: BMI, dtype: float64"
       ]
      },
-     "execution_count": 175,
+     "execution_count": 45,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -612,7 +612,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 176,
+   "execution_count": 46,
    "id": "fdf468b3",
    "metadata": {},
    "outputs": [
@@ -630,7 +630,7 @@
        "Name: Chol, dtype: float64"
       ]
      },
-     "execution_count": 176,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -641,7 +641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 177,
+   "execution_count": 47,
    "id": "7877549d",
    "metadata": {},
    "outputs": [
@@ -659,7 +659,7 @@
        "Name: TG, dtype: float64"
       ]
      },
-     "execution_count": 177,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -670,7 +670,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 178,
+   "execution_count": 48,
    "id": "71ec5fcb",
    "metadata": {},
    "outputs": [
@@ -688,7 +688,7 @@
        "Name: HDL, dtype: float64"
       ]
      },
-     "execution_count": 178,
+     "execution_count": 48,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -699,7 +699,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 179,
+   "execution_count": 49,
    "id": "bbd3682c",
    "metadata": {},
    "outputs": [
@@ -717,7 +717,7 @@
        "Name: LDL, dtype: float64"
       ]
      },
-     "execution_count": 179,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -728,7 +728,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 180,
+   "execution_count": 50,
    "id": "c4603e52",
    "metadata": {},
    "outputs": [
@@ -746,7 +746,7 @@
        "Name: Cr, dtype: float64"
       ]
      },
-     "execution_count": 180,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -757,7 +757,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 181,
+   "execution_count": 51,
    "id": "f98b84c7",
    "metadata": {},
    "outputs": [
@@ -775,7 +775,7 @@
        "Name: BUN, dtype: float64"
       ]
      },
-     "execution_count": 181,
+     "execution_count": 51,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -794,7 +794,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 182,
+   "execution_count": 52,
    "id": "a9add765",
    "metadata": {},
    "outputs": [
@@ -822,7 +822,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 183,
+   "execution_count": 53,
    "id": "752e448c",
    "metadata": {},
    "outputs": [],
@@ -835,7 +835,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 184,
+   "execution_count": 54,
    "id": "a8441035",
    "metadata": {},
    "outputs": [],
@@ -846,7 +846,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 185,
+   "execution_count": 55,
    "id": "378ecf72",
    "metadata": {},
    "outputs": [
@@ -892,7 +892,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 186,
+   "execution_count": 56,
    "id": "39477c2a",
    "metadata": {},
    "outputs": [
@@ -953,7 +953,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 187,
+   "execution_count": 57,
    "id": "651dd699",
    "metadata": {},
    "outputs": [],
@@ -961,24 +961,25 @@
     "from sklearn.preprocessing import LabelEncoder\n",
     "from sklearn.feature_selection import SelectKBest, chi2, f_classif, RFE,SelectKBest\n",
     "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score\n",
+    "from sklearn.metrics import accuracy_score, confusion_matrix\n",
+    "\n",
     "\n",
     "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 188,
+   "execution_count": 58,
    "id": "e1801370",
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_new=data_new.drop(['Gender'],axis=1)\n"
+    "data_new=data_new.drop('Gender',axis=1)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 189,
+   "execution_count": 59,
    "id": "eb6127cc",
    "metadata": {},
    "outputs": [
@@ -1088,7 +1089,7 @@
        "4   50  24.0   3.6  1.3  0.9  2.1  50.0  2.0          0"
       ]
      },
-     "execution_count": 189,
+     "execution_count": 59,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1099,7 +1100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 190,
+   "execution_count": 60,
    "id": "12304d13",
    "metadata": {},
    "outputs": [],
@@ -1110,28 +1111,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 191,
+   "execution_count": 61,
    "id": "dfd08af6",
    "metadata": {},
    "outputs": [],
    "source": [
     "X_f = SelectKBest(f_classif, k=5).fit_transform(X, y)\n",
     "\n",
-    "# Assuming X has feature names and k=5\n",
+    "\n",
     "selector = SelectKBest(f_classif, k=5).fit(X, y)\n",
     "\n",
-    "# Check scikit-learn version (optional)\n",
-    "# import sklearn as skl\n",
-    "# print(f\"scikit-learn version: {skl.__version__}\")\n",
     "\n",
-    "if hasattr(selector, 'support_'):  # For older versions\n",
+    "if hasattr(selector, 'support_'): \n",
     "    support = selector.support_\n",
     "else:\n",
-    "    support = selector.get_support()  # For newer versions\n",
+    "    support = selector.get_support()  \n",
+    "\n",
+    "selected_features = X.columns[support]  \n",
     "\n",
-    "selected_features = X.columns[support]  # List of selected feature names\n",
     "\n",
-    "# Columns to filter out (original features not in selected_features)\n",
     "columns_to_filter = [col for col in X.columns if col not in selected_features]\n",
     "\n"
    ]
@@ -1146,7 +1144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 192,
+   "execution_count": 62,
    "id": "237cd728",
    "metadata": {},
    "outputs": [
@@ -1156,7 +1154,7 @@
        "['Chol', 'Cr', 'BUN']"
       ]
      },
-     "execution_count": 192,
+     "execution_count": 62,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1175,17 +1173,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 193,
+   "execution_count": 63,
    "id": "40e0c236",
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_new=data_new.drop(['Chol','Cr','BUN'],axis=1)"
+    "data_new_kbest=data_new.drop(['Chol','Cr','BUN'],axis=1)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 194,
+   "execution_count": 64,
    "id": "6f5836ec",
    "metadata": {},
    "outputs": [
@@ -1340,13 +1338,13 @@
        "[5132 rows x 6 columns]"
       ]
      },
-     "execution_count": 194,
+     "execution_count": 64,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "data_new"
+    "data_new_kbest"
    ]
   },
   {
@@ -1359,9 +1357,351 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 66,
    "id": "67e27ab3",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8198636806231743\n",
+      "[[536  68]\n",
+      " [117 306]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_f= data_new_kbest['Diagnosis']\n",
+    "X_f=data_new_kbest.drop(['Diagnosis'],axis=1)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_f, y_f, test_size=0.2, random_state=42)\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "rfc = RandomForestClassifier(n_estimators=100)  \n",
+    "rfc.fit(X_train, y_train)\n",
+    "y_pred = rfc.predict(X_test)\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "print(\"Accuracy:\", accuracy)\n",
+    "cm = confusion_matrix(y_test, y_pred)\n",
+    "print(cm)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e6b9595",
+   "metadata": {},
+   "source": [
+    "Applying a random forest classifier on the dataset obtained by using f-statistic in selectkbest, we also bobserve the model accuracy and the confusion matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "f63ffb4d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of selected features: 8\n",
+      "Selected Features: Index(['Age', 'BMI', 'Chol', 'TG', 'HDL', 'LDL', 'Cr', 'BUN'], dtype='object')\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_selection import RFECV\n",
+    "X_rfecv = data_new.drop('Diagnosis', axis=1)\n",
+    "y_rfecv = data_new['Diagnosis']\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_rfecv, y_rfecv, test_size=0.2, random_state=42)\n",
+    "rfecv = RFECV(estimator=RandomForestClassifier(n_estimators=1000), cv=5) \n",
+    "rfecv.fit(X_train, y_train)\n",
+    "print(\"Number of selected features:\", rfecv.n_features_)\n",
+    "selected_features = X.columns[rfecv.support_]\n",
+    "print(\"Selected Features:\", selected_features)\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9ef9701",
+   "metadata": {},
+   "source": [
+    "Applying Recursive Feature Elimination with Cross Validation to filter out features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "22dbb42e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_new_rfecv=data_new\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "d96d1966",
+   "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>Age</th>\n",
+       "      <th>BMI</th>\n",
+       "      <th>Chol</th>\n",
+       "      <th>TG</th>\n",
+       "      <th>HDL</th>\n",
+       "      <th>LDL</th>\n",
+       "      <th>Cr</th>\n",
+       "      <th>BUN</th>\n",
+       "      <th>Diagnosis</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>50</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>4.20</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>2.40</td>\n",
+       "      <td>1.40</td>\n",
+       "      <td>46.0</td>\n",
+       "      <td>4.70</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>26</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>3.70</td>\n",
+       "      <td>1.40</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>2.10</td>\n",
+       "      <td>62.0</td>\n",
+       "      <td>4.50</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>33</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>4.90</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>46.0</td>\n",
+       "      <td>7.10</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>45</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>2.90</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1.50</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>2.30</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>50</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>3.60</td>\n",
+       "      <td>1.30</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>2.10</td>\n",
+       "      <td>50.0</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5127</th>\n",
+       "      <td>54</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>5.00</td>\n",
+       "      <td>1.50</td>\n",
+       "      <td>1.24</td>\n",
+       "      <td>2.98</td>\n",
+       "      <td>77.0</td>\n",
+       "      <td>3.50</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5128</th>\n",
+       "      <td>50</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>4.37</td>\n",
+       "      <td>2.09</td>\n",
+       "      <td>1.37</td>\n",
+       "      <td>2.29</td>\n",
+       "      <td>47.3</td>\n",
+       "      <td>4.40</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5129</th>\n",
+       "      <td>67</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>3.89</td>\n",
+       "      <td>1.38</td>\n",
+       "      <td>1.14</td>\n",
+       "      <td>2.17</td>\n",
+       "      <td>70.6</td>\n",
+       "      <td>4.73</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5130</th>\n",
+       "      <td>60</td>\n",
+       "      <td>29.0</td>\n",
+       "      <td>5.91</td>\n",
+       "      <td>1.29</td>\n",
+       "      <td>1.73</td>\n",
+       "      <td>2.85</td>\n",
+       "      <td>50.2</td>\n",
+       "      <td>7.33</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5131</th>\n",
+       "      <td>37</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>5.42</td>\n",
+       "      <td>2.66</td>\n",
+       "      <td>1.08</td>\n",
+       "      <td>2.87</td>\n",
+       "      <td>75.5</td>\n",
+       "      <td>4.61</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5132 rows × 9 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      Age   BMI  Chol    TG   HDL   LDL    Cr   BUN  Diagnosis\n",
+       "0      50  24.0  4.20  0.90  2.40  1.40  46.0  4.70          0\n",
+       "1      26  23.0  3.70  1.40  1.10  2.10  62.0  4.50          0\n",
+       "2      33  21.0  4.90  1.00  0.80  2.00  46.0  7.10          0\n",
+       "3      45  21.0  2.90  1.00  1.00  1.50  24.0  2.30          0\n",
+       "4      50  24.0  3.60  1.30  0.90  2.10  50.0  2.00          0\n",
+       "...   ...   ...   ...   ...   ...   ...   ...   ...        ...\n",
+       "5127   54  23.0  5.00  1.50  1.24  2.98  77.0  3.50          1\n",
+       "5128   50  22.0  4.37  2.09  1.37  2.29  47.3  4.40          1\n",
+       "5129   67  24.0  3.89  1.38  1.14  2.17  70.6  4.73          1\n",
+       "5130   60  29.0  5.91  1.29  1.73  2.85  50.2  7.33          1\n",
+       "5131   37  34.0  5.42  2.66  1.08  2.87  75.5  4.61          1\n",
+       "\n",
+       "[5132 rows x 9 columns]"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_new_rfecv"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df381a5f",
+   "metadata": {},
+   "source": [
+    "New dataset generated after using RFECV"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "084425a3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.818889970788705\n",
+      "[[539  65]\n",
+      " [121 302]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_rfecv= data_new_rfecv['Diagnosis']\n",
+    "X_rfecv=data_new_rfecv.drop(['Diagnosis'],axis=1)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_rfecv, y_rfecv, test_size=0.2, random_state=42)\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "rfc = RandomForestClassifier(n_estimators=100)  \n",
+    "rfc.fit(X_train, y_train)\n",
+    "y_pred = rfc.predict(X_test)\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "print(\"Accuracy:\", accuracy)\n",
+    "cm = confusion_matrix(y_test, y_pred)\n",
+    "print(cm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a52ed238",
+   "metadata": {},
+   "source": [
+    "Applying a random forest classifier on the dataset obtained by using RFECV, we also bobserve the model accuracy and the confusion matrix"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "59349ad6",
+   "metadata": {},
+   "source": [
+    "Since, we observe that the accuracy score of the model trained on datset generated by selectkbest is slightly higher that that trained by dataset generate by rfecv, hence we will use the 5 features selected by selectkbest as they have the most significant relationship with diagnosis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82916004",
+   "metadata": {},
    "outputs": [],
    "source": []
   }
diff --git a/Diabetes Classification/diabetesclassification.ipynb b/Diabetes Classification/diabetesclassification.ipynb
index d4d68ed..0f854e2 100644
--- a/Diabetes Classification/diabetesclassification.ipynb	
+++ b/Diabetes Classification/diabetesclassification.ipynb	
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 166,
+   "execution_count": 36,
    "id": "312c95a1",
    "metadata": {},
    "outputs": [],
@@ -29,7 +29,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 167,
+   "execution_count": 37,
    "id": "aea1b45b",
    "metadata": {},
    "outputs": [],
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 168,
+   "execution_count": 38,
    "id": "2ac5c17b",
    "metadata": {},
    "outputs": [
@@ -275,7 +275,7 @@
        "[5132 rows x 11 columns]"
       ]
      },
-     "execution_count": 168,
+     "execution_count": 38,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -286,7 +286,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 169,
+   "execution_count": 39,
    "id": "c4484360",
    "metadata": {},
    "outputs": [
@@ -408,7 +408,7 @@
        "4           4   50      F   24   3.6  1.3  0.9  2.1  50.0  2.0          0"
       ]
      },
-     "execution_count": 169,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -427,7 +427,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 170,
+   "execution_count": 40,
    "id": "ea7c6dcb",
    "metadata": {},
    "outputs": [
@@ -437,7 +437,7 @@
        "(5132, 11)"
       ]
      },
-     "execution_count": 170,
+     "execution_count": 40,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -456,7 +456,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 171,
+   "execution_count": 41,
    "id": "a3c2ff78",
    "metadata": {},
    "outputs": [
@@ -499,7 +499,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 172,
+   "execution_count": 42,
    "id": "a9cc7614",
    "metadata": {},
    "outputs": [],
@@ -510,7 +510,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 173,
+   "execution_count": 43,
    "id": "cdee3c52",
    "metadata": {
     "scrolled": true
@@ -554,7 +554,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 174,
+   "execution_count": 44,
    "id": "2f353609",
    "metadata": {},
    "outputs": [
@@ -572,7 +572,7 @@
        "Name: Age, dtype: float64"
       ]
      },
-     "execution_count": 174,
+     "execution_count": 44,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -583,7 +583,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 175,
+   "execution_count": 45,
    "id": "b7887949",
    "metadata": {},
    "outputs": [
@@ -601,7 +601,7 @@
        "Name: BMI, dtype: float64"
       ]
      },
-     "execution_count": 175,
+     "execution_count": 45,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -612,7 +612,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 176,
+   "execution_count": 46,
    "id": "fdf468b3",
    "metadata": {},
    "outputs": [
@@ -630,7 +630,7 @@
        "Name: Chol, dtype: float64"
       ]
      },
-     "execution_count": 176,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -641,7 +641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 177,
+   "execution_count": 47,
    "id": "7877549d",
    "metadata": {},
    "outputs": [
@@ -659,7 +659,7 @@
        "Name: TG, dtype: float64"
       ]
      },
-     "execution_count": 177,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -670,7 +670,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 178,
+   "execution_count": 48,
    "id": "71ec5fcb",
    "metadata": {},
    "outputs": [
@@ -688,7 +688,7 @@
        "Name: HDL, dtype: float64"
       ]
      },
-     "execution_count": 178,
+     "execution_count": 48,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -699,7 +699,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 179,
+   "execution_count": 49,
    "id": "bbd3682c",
    "metadata": {},
    "outputs": [
@@ -717,7 +717,7 @@
        "Name: LDL, dtype: float64"
       ]
      },
-     "execution_count": 179,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -728,7 +728,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 180,
+   "execution_count": 50,
    "id": "c4603e52",
    "metadata": {},
    "outputs": [
@@ -746,7 +746,7 @@
        "Name: Cr, dtype: float64"
       ]
      },
-     "execution_count": 180,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -757,7 +757,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 181,
+   "execution_count": 51,
    "id": "f98b84c7",
    "metadata": {},
    "outputs": [
@@ -775,7 +775,7 @@
        "Name: BUN, dtype: float64"
       ]
      },
-     "execution_count": 181,
+     "execution_count": 51,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -794,7 +794,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 182,
+   "execution_count": 52,
    "id": "a9add765",
    "metadata": {},
    "outputs": [
@@ -822,7 +822,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 183,
+   "execution_count": 53,
    "id": "752e448c",
    "metadata": {},
    "outputs": [],
@@ -835,7 +835,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 184,
+   "execution_count": 54,
    "id": "a8441035",
    "metadata": {},
    "outputs": [],
@@ -846,7 +846,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 185,
+   "execution_count": 55,
    "id": "378ecf72",
    "metadata": {},
    "outputs": [
@@ -892,7 +892,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 186,
+   "execution_count": 56,
    "id": "39477c2a",
    "metadata": {},
    "outputs": [
@@ -953,7 +953,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 187,
+   "execution_count": 57,
    "id": "651dd699",
    "metadata": {},
    "outputs": [],
@@ -961,24 +961,25 @@
     "from sklearn.preprocessing import LabelEncoder\n",
     "from sklearn.feature_selection import SelectKBest, chi2, f_classif, RFE,SelectKBest\n",
     "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score\n",
+    "from sklearn.metrics import accuracy_score, confusion_matrix\n",
+    "\n",
     "\n",
     "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 188,
+   "execution_count": 58,
    "id": "e1801370",
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_new=data_new.drop(['Gender'],axis=1)\n"
+    "data_new=data_new.drop('Gender',axis=1)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 189,
+   "execution_count": 59,
    "id": "eb6127cc",
    "metadata": {},
    "outputs": [
@@ -1088,7 +1089,7 @@
        "4   50  24.0   3.6  1.3  0.9  2.1  50.0  2.0          0"
       ]
      },
-     "execution_count": 189,
+     "execution_count": 59,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1099,7 +1100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 190,
+   "execution_count": 60,
    "id": "12304d13",
    "metadata": {},
    "outputs": [],
@@ -1110,28 +1111,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 191,
+   "execution_count": 61,
    "id": "dfd08af6",
    "metadata": {},
    "outputs": [],
    "source": [
     "X_f = SelectKBest(f_classif, k=5).fit_transform(X, y)\n",
     "\n",
-    "# Assuming X has feature names and k=5\n",
+    "\n",
     "selector = SelectKBest(f_classif, k=5).fit(X, y)\n",
     "\n",
-    "# Check scikit-learn version (optional)\n",
-    "# import sklearn as skl\n",
-    "# print(f\"scikit-learn version: {skl.__version__}\")\n",
     "\n",
-    "if hasattr(selector, 'support_'):  # For older versions\n",
+    "if hasattr(selector, 'support_'): \n",
     "    support = selector.support_\n",
     "else:\n",
-    "    support = selector.get_support()  # For newer versions\n",
+    "    support = selector.get_support()  \n",
+    "\n",
+    "selected_features = X.columns[support]  \n",
     "\n",
-    "selected_features = X.columns[support]  # List of selected feature names\n",
     "\n",
-    "# Columns to filter out (original features not in selected_features)\n",
     "columns_to_filter = [col for col in X.columns if col not in selected_features]\n",
     "\n"
    ]
@@ -1146,7 +1144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 192,
+   "execution_count": 62,
    "id": "237cd728",
    "metadata": {},
    "outputs": [
@@ -1156,7 +1154,7 @@
        "['Chol', 'Cr', 'BUN']"
       ]
      },
-     "execution_count": 192,
+     "execution_count": 62,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1175,17 +1173,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 193,
+   "execution_count": 63,
    "id": "40e0c236",
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_new=data_new.drop(['Chol','Cr','BUN'],axis=1)"
+    "data_new_kbest=data_new.drop(['Chol','Cr','BUN'],axis=1)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 194,
+   "execution_count": 64,
    "id": "6f5836ec",
    "metadata": {},
    "outputs": [
@@ -1340,13 +1338,13 @@
        "[5132 rows x 6 columns]"
       ]
      },
-     "execution_count": 194,
+     "execution_count": 64,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "data_new"
+    "data_new_kbest"
    ]
   },
   {
@@ -1359,9 +1357,351 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 66,
    "id": "67e27ab3",
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8198636806231743\n",
+      "[[536  68]\n",
+      " [117 306]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_f= data_new_kbest['Diagnosis']\n",
+    "X_f=data_new_kbest.drop(['Diagnosis'],axis=1)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_f, y_f, test_size=0.2, random_state=42)\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "rfc = RandomForestClassifier(n_estimators=100)  \n",
+    "rfc.fit(X_train, y_train)\n",
+    "y_pred = rfc.predict(X_test)\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "print(\"Accuracy:\", accuracy)\n",
+    "cm = confusion_matrix(y_test, y_pred)\n",
+    "print(cm)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8e6b9595",
+   "metadata": {},
+   "source": [
+    "Applying a random forest classifier on the dataset obtained by using f-statistic in selectkbest, we also bobserve the model accuracy and the confusion matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "id": "f63ffb4d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of selected features: 8\n",
+      "Selected Features: Index(['Age', 'BMI', 'Chol', 'TG', 'HDL', 'LDL', 'Cr', 'BUN'], dtype='object')\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_selection import RFECV\n",
+    "X_rfecv = data_new.drop('Diagnosis', axis=1)\n",
+    "y_rfecv = data_new['Diagnosis']\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_rfecv, y_rfecv, test_size=0.2, random_state=42)\n",
+    "rfecv = RFECV(estimator=RandomForestClassifier(n_estimators=1000), cv=5) \n",
+    "rfecv.fit(X_train, y_train)\n",
+    "print(\"Number of selected features:\", rfecv.n_features_)\n",
+    "selected_features = X.columns[rfecv.support_]\n",
+    "print(\"Selected Features:\", selected_features)\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9ef9701",
+   "metadata": {},
+   "source": [
+    "Applying Recursive Feature Elimination with Cross Validation to filter out features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "22dbb42e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_new_rfecv=data_new\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "d96d1966",
+   "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>Age</th>\n",
+       "      <th>BMI</th>\n",
+       "      <th>Chol</th>\n",
+       "      <th>TG</th>\n",
+       "      <th>HDL</th>\n",
+       "      <th>LDL</th>\n",
+       "      <th>Cr</th>\n",
+       "      <th>BUN</th>\n",
+       "      <th>Diagnosis</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>50</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>4.20</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>2.40</td>\n",
+       "      <td>1.40</td>\n",
+       "      <td>46.0</td>\n",
+       "      <td>4.70</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>26</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>3.70</td>\n",
+       "      <td>1.40</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>2.10</td>\n",
+       "      <td>62.0</td>\n",
+       "      <td>4.50</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>33</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>4.90</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>46.0</td>\n",
+       "      <td>7.10</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>45</td>\n",
+       "      <td>21.0</td>\n",
+       "      <td>2.90</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1.50</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>2.30</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>50</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>3.60</td>\n",
+       "      <td>1.30</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>2.10</td>\n",
+       "      <td>50.0</td>\n",
+       "      <td>2.00</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5127</th>\n",
+       "      <td>54</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>5.00</td>\n",
+       "      <td>1.50</td>\n",
+       "      <td>1.24</td>\n",
+       "      <td>2.98</td>\n",
+       "      <td>77.0</td>\n",
+       "      <td>3.50</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5128</th>\n",
+       "      <td>50</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>4.37</td>\n",
+       "      <td>2.09</td>\n",
+       "      <td>1.37</td>\n",
+       "      <td>2.29</td>\n",
+       "      <td>47.3</td>\n",
+       "      <td>4.40</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5129</th>\n",
+       "      <td>67</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>3.89</td>\n",
+       "      <td>1.38</td>\n",
+       "      <td>1.14</td>\n",
+       "      <td>2.17</td>\n",
+       "      <td>70.6</td>\n",
+       "      <td>4.73</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5130</th>\n",
+       "      <td>60</td>\n",
+       "      <td>29.0</td>\n",
+       "      <td>5.91</td>\n",
+       "      <td>1.29</td>\n",
+       "      <td>1.73</td>\n",
+       "      <td>2.85</td>\n",
+       "      <td>50.2</td>\n",
+       "      <td>7.33</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5131</th>\n",
+       "      <td>37</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>5.42</td>\n",
+       "      <td>2.66</td>\n",
+       "      <td>1.08</td>\n",
+       "      <td>2.87</td>\n",
+       "      <td>75.5</td>\n",
+       "      <td>4.61</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5132 rows × 9 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      Age   BMI  Chol    TG   HDL   LDL    Cr   BUN  Diagnosis\n",
+       "0      50  24.0  4.20  0.90  2.40  1.40  46.0  4.70          0\n",
+       "1      26  23.0  3.70  1.40  1.10  2.10  62.0  4.50          0\n",
+       "2      33  21.0  4.90  1.00  0.80  2.00  46.0  7.10          0\n",
+       "3      45  21.0  2.90  1.00  1.00  1.50  24.0  2.30          0\n",
+       "4      50  24.0  3.60  1.30  0.90  2.10  50.0  2.00          0\n",
+       "...   ...   ...   ...   ...   ...   ...   ...   ...        ...\n",
+       "5127   54  23.0  5.00  1.50  1.24  2.98  77.0  3.50          1\n",
+       "5128   50  22.0  4.37  2.09  1.37  2.29  47.3  4.40          1\n",
+       "5129   67  24.0  3.89  1.38  1.14  2.17  70.6  4.73          1\n",
+       "5130   60  29.0  5.91  1.29  1.73  2.85  50.2  7.33          1\n",
+       "5131   37  34.0  5.42  2.66  1.08  2.87  75.5  4.61          1\n",
+       "\n",
+       "[5132 rows x 9 columns]"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_new_rfecv"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df381a5f",
+   "metadata": {},
+   "source": [
+    "New dataset generated after using RFECV"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "084425a3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.818889970788705\n",
+      "[[539  65]\n",
+      " [121 302]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_rfecv= data_new_rfecv['Diagnosis']\n",
+    "X_rfecv=data_new_rfecv.drop(['Diagnosis'],axis=1)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_rfecv, y_rfecv, test_size=0.2, random_state=42)\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "rfc = RandomForestClassifier(n_estimators=100)  \n",
+    "rfc.fit(X_train, y_train)\n",
+    "y_pred = rfc.predict(X_test)\n",
+    "accuracy = accuracy_score(y_test, y_pred)\n",
+    "print(\"Accuracy:\", accuracy)\n",
+    "cm = confusion_matrix(y_test, y_pred)\n",
+    "print(cm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a52ed238",
+   "metadata": {},
+   "source": [
+    "Applying a random forest classifier on the dataset obtained by using RFECV, we also bobserve the model accuracy and the confusion matrix"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "59349ad6",
+   "metadata": {},
+   "source": [
+    "Since, we observe that the accuracy score of the model trained on datset generated by selectkbest is slightly higher that that trained by dataset generate by rfecv, hence we will use the 5 features selected by selectkbest as they have the most significant relationship with diagnosis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82916004",
+   "metadata": {},
    "outputs": [],
    "source": []
   }