Spaces:
Sleeping
Sleeping
File size: 12,540 Bytes
93ea505 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | {
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "e7144afc-a75f-4273-934d-0fa7c3c1d511",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Pima shape: (768, 9)\n",
"Frankfurt shape: (2000, 9)\n",
"\n",
"Pima columns: ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome']\n",
"Frankfurt columns: ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome']\n",
"\n",
"Merged shape: (2768, 9)\n",
"\n",
"Missing values after fixing zeros:\n",
"Pregnancies 0\n",
"Glucose 18\n",
"BloodPressure 125\n",
"SkinThickness 800\n",
"Insulin 1330\n",
"BMI 39\n",
"DiabetesPedigreeFunction 0\n",
"Age 0\n",
"Outcome 0\n",
"dtype: int64\n",
"\n",
"Class distribution:\n",
"Outcome\n",
"0 1816\n",
"1 952\n",
"Name: count, dtype: int64\n",
"Outcome\n",
"0 65.6\n",
"1 34.4\n",
"Name: proportion, dtype: float64\n",
"\n",
"Saved to: C:\\Users\\abdul\\Amr senior\\dataset\\diabetes_merged.csv\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\abdul\\AppData\\Local\\Temp\\ipykernel_26020\\6553557.py:31: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"\n",
"\n",
" df[col].fillna(df[col].median(), inplace=True)\n",
"C:\\Users\\abdul\\AppData\\Local\\Temp\\ipykernel_26020\\6553557.py:31: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"\n",
"\n",
" df[col].fillna(df[col].median(), inplace=True)\n",
"C:\\Users\\abdul\\AppData\\Local\\Temp\\ipykernel_26020\\6553557.py:31: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"\n",
"\n",
" df[col].fillna(df[col].median(), inplace=True)\n",
"C:\\Users\\abdul\\AppData\\Local\\Temp\\ipykernel_26020\\6553557.py:31: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"\n",
"\n",
" df[col].fillna(df[col].median(), inplace=True)\n",
"C:\\Users\\abdul\\AppData\\Local\\Temp\\ipykernel_26020\\6553557.py:31: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n",
"The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n",
"\n",
"For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n",
"\n",
"\n",
" df[col].fillna(df[col].median(), inplace=True)\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"# ── Load both datasets ──────────────────────────────────────────\n",
"pima = pd.read_csv(r\"C:\\Users\\abdul\\Amr senior\\dataset\\archive (8)\\diabetes.csv\")\n",
"frankfurt = pd.read_csv(r\"C:\\Users\\abdul\\Amr senior\\dataset\\archive (7)\\diabetes.csv\")\n",
"\n",
"print(\"Pima shape: \", pima.shape)\n",
"print(\"Frankfurt shape: \", frankfurt.shape)\n",
"\n",
"# ── Align columns (in case of any naming differences) ───────────\n",
"print(\"\\nPima columns: \", pima.columns.tolist())\n",
"print(\"Frankfurt columns:\", frankfurt.columns.tolist())\n",
"\n",
"# Rename to match if needed (usually identical)\n",
"frankfurt.columns = pima.columns\n",
"\n",
"# ── Merge ────────────────────────────────────────────────────────\n",
"df = pd.concat([pima, frankfurt], ignore_index=True)\n",
"print(f\"\\nMerged shape: {df.shape}\") # Expected: (2768, 9)\n",
"\n",
"# ── Fix zero values (medically impossible zeros → NaN) ──────────\n",
"zero_invalid_cols = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']\n",
"df[zero_invalid_cols] = df[zero_invalid_cols].replace(0, np.nan)\n",
"\n",
"print(\"\\nMissing values after fixing zeros:\")\n",
"print(df.isnull().sum())\n",
"\n",
"# ── Impute with median ───────────────────────────────────────────\n",
"for col in zero_invalid_cols:\n",
" df[col].fillna(df[col].median(), inplace=True)\n",
"\n",
"# ── Check class balance ──────────────────────────────────────────\n",
"print(\"\\nClass distribution:\")\n",
"print(df['Outcome'].value_counts())\n",
"print(df['Outcome'].value_counts(normalize=True).mul(100).round(1))\n",
"\n",
"# ── Save merged dataset ──────────────────────────────────────────\n",
"save_path = r\"C:\\Users\\abdul\\Amr senior\\dataset\\diabetes_merged.csv\"\n",
"df.to_csv(save_path, index=False)\n",
"print(f\"\\nSaved to: {save_path}\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "9bccf5b9-7f44-4507-84ae-2a9ca5eec9f4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"✅ Missing after imputation:\n",
"0 nulls remaining\n",
"\n",
"✅ Features after engineering: 12 features\n",
"\n",
"✅ Class distribution after SMOTE:\n",
"Outcome\n",
"0 1453\n",
"1 1453\n",
"Name: count, dtype: int64\n",
"\n",
"✅ All files saved and ready for training!\n",
" Train: (2906, 12) | Test: (554, 12)\n"
]
}
],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.experimental import enable_iterative_imputer\n",
"from sklearn.impute import IterativeImputer\n",
"from sklearn.preprocessing import StandardScaler\n",
"from imblearn.over_sampling import SMOTE\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"df = pd.read_csv(r\"C:\\Users\\abdul\\Amr senior\\dataset\\diabetes_merged.csv\")\n",
"\n",
"# ── Step 1: Smart Imputation (KNN-style iterative) ───────────────\n",
"# Much better than median for high-missing columns like Insulin\n",
"imputer = IterativeImputer(max_iter=10, random_state=42)\n",
"cols_to_impute = ['Glucose','BloodPressure','SkinThickness','Insulin','BMI']\n",
"\n",
"df[cols_to_impute] = imputer.fit_transform(df[cols_to_impute])\n",
"\n",
"# Clip negative values that imputer might produce\n",
"df[cols_to_impute] = df[cols_to_impute].clip(lower=0)\n",
"\n",
"print(\"✅ Missing after imputation:\")\n",
"print(df.isnull().sum().sum(), \"nulls remaining\")\n",
"\n",
"# ── Step 2: Feature Engineering ──────────────────────────────────\n",
"df['Glucose_BMI'] = df['Glucose'] * df['BMI']\n",
"df['Age_BMI'] = df['Age'] * df['BMI']\n",
"df['Glucose_squared']= df['Glucose'] ** 2\n",
"df['Insulin_BMI'] = df['Insulin'] * df['BMI']\n",
"\n",
"print(\"\\n✅ Features after engineering:\", df.shape[1] - 1, \"features\")\n",
"\n",
"# ── Step 3: Split BEFORE scaling/SMOTE (prevent data leakage) ────\n",
"X = df.drop('Outcome', axis=1)\n",
"y = df['Outcome']\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(\n",
" X, y, test_size=0.2, random_state=42, stratify=y\n",
")\n",
"\n",
"# ── Step 4: Normalize ─────────────────────────────────────────────\n",
"scaler = StandardScaler()\n",
"X_train_scaled = scaler.fit_transform(X_train) # fit only on train\n",
"X_test_scaled = scaler.transform(X_test) # transform test\n",
"\n",
"# ── Step 5: SMOTE on training set only ───────────────────────────\n",
"smote = SMOTE(random_state=42)\n",
"X_train_bal, y_train_bal = smote.fit_resample(X_train_scaled, y_train)\n",
"\n",
"print(\"\\n✅ Class distribution after SMOTE:\")\n",
"print(pd.Series(y_train_bal).value_counts())\n",
"\n",
"# ── Step 6: Save processed splits ────────────────────────────────\n",
"base = r\"C:\\Users\\abdul\\Amr senior\\dataset\"\n",
"np.save(f\"{base}\\\\X_train.npy\", X_train_bal)\n",
"np.save(f\"{base}\\\\X_test.npy\", X_test_scaled)\n",
"np.save(f\"{base}\\\\y_train.npy\", y_train_bal)\n",
"np.save(f\"{base}\\\\y_test.npy\", y_test.values)\n",
"import joblib\n",
"joblib.dump(scaler, f\"{base}\\\\scaler.pkl\")\n",
"\n",
"print(\"\\n✅ All files saved and ready for training!\")\n",
"print(f\" Train: {X_train_bal.shape} | Test: {X_test_scaled.shape}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8eb333a4-afab-4aae-b6f5-2c9e11cdc69f",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "fa396b1d-2a87-4a4e-af76-d109e20f067c",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.12.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|