325 lines (324 with data), 81.9 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "\n",
    "\n",
    "\n",
    "def load_data(path):\n",
    "    df = pd.read_csv(path)\n",
    "    # arham check this later\n",
    "    # original = pd.read_csv('/kaggle/input/obesity-or-cvd-risk-classifyregressorcluster/ObesityDataSet.csv')\n",
    "    # split to train test\n",
    "    train_df, test_df = train_test_split(df, test_size=0.35, random_state=42)\n",
    "    train_df = train_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n",
    "    test_df = test_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n",
    "    return train_df, test_df\n",
    "\n",
    "def encode_target(train):\n",
    "    target_key = {'Insufficient_Weight': 0, 'Normal_Weight': 1, 'Overweight_Level_I': 2, 'Overweight_Level_II': 3, 'Obesity_Type_I': 4,'Obesity_Type_II' : 5, 'Obesity_Type_III': 6}\n",
    "    train['NObeyesdad'] = train['NObeyesdad'].map(target_key)\n",
    "    return train\n",
    "\n",
    "def decode_target(train):\n",
    "    target_key = {0: 'Insufficient_Weight', 1: 'Normal_Weight', 2: 'Overweight_Level_I', 3: 'Overweight_Level_II', 4: 'Obesity_Type_I', 5: 'Obesity_Type_II', 6: 'Obesity_Type_III'}\n",
    "    train['NObeyesdad'] = train['NObeyesdad'].map(target_key)\n",
    "    return train\n",
    "\n",
    "\"\"\"Univar functions\"\"\"\n",
    "\n",
    "\n",
    "def make_gender_binary(train):\n",
    "    gender_key = { 'Male':0, 'Female':1}\n",
    "    train['Gender'] = train['Gender'].map(gender_key)\n",
    "    return train\n",
    "\n",
    "# let's try three types of solutions:\n",
    "\n",
    "\n",
    "def age_binning(train_df):\n",
    "    # Binning\n",
    "    train_df['Age_Group'] = pd.cut(train_df['Age'], bins=[0, 20, 30, 40, 50, train_df['Age'].max()], labels=['0-20', '21-30', '31-40', '41-50', '50+'],)\n",
    "    return train_df\n",
    "\n",
    "def age_scaling_log(train_df):\n",
    "    train_df['Log_Age'] = np.log1p(train_df['Age'])\n",
    "    return train_df\n",
    "\n",
    "def age_scaling_minmax(train_df):\n",
    "    # scaling\n",
    "    scaler_age = MinMaxScaler()\n",
    "    train_df['Scaled_Age'] = scaler_age.fit_transform(train_df['Age'].values.reshape(-1, 1))\n",
    "    return train_df, scaler_age\n",
    "\n",
    "def height_scaling_log(train_df):\n",
    "    train_df['Log_Height'] = np.log1p(train_df['Height'])\n",
    "    return train_df\n",
    "\n",
    "def weight_scaling_minmax(train_df):\n",
    "    # scaling\n",
    "    scaler_weight = MinMaxScaler()\n",
    "    train_df['Scaled_Height'] = scaler_weight.fit_transform(train_df['Weight'].values.reshape(-1, 1))\n",
    "    return train_df, scaler_weight\n",
    "\n",
    "def height_scaling_log(train_df):\n",
    "    train_df['Log_Weight'] = np.log1p(train_df['Weight'])\n",
    "    return train_df\n",
    "\n",
    "def height_scaling_minmax(train_df):\n",
    "    # scaling\n",
    "    scaler_height = MinMaxScaler()\n",
    "    train_df['Scaled_Weight'] = scaler_height.fit_transform(train_df['Weight'].values.reshape(-1, 1))\n",
    "    return train_df, scaler_height\n",
    "\n",
    "def Other_features(train):\n",
    "    train['BMI'] = train['Weight'] / (train['Height'] ** 2)\n",
    "    train['Age * Gender'] = train['Age'] * train['Gender']   \n",
    "    categorical_features = ['Gender', 'family_history_with_overweight', 'Age group', 'FAVC','CAEC', 'SMOKE','SCC', 'CALC', 'MTRANS']\n",
    "    train = pd.get_dummies(train, columns=categorical_features)\n",
    "    polynomial_features = PolynomialFeatures(degree=2)\n",
    "    X_poly = polynomial_features.fit_transform(train[['Age', 'BMI']])\n",
    "    train = pd.concat([train, pd.DataFrame(X_poly, columns=['Age^2', 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI2', 'Age * BMI3'])], axis=1)\n",
    "\n",
    "path = '/Users/arham/Downloads/Projects/01-Dataset/01-Data-for-model-building/train.csv'\n",
    "train_df,test_df = load_data('/Users/arham/Downloads/Projects/01-Dataset/01-Data-for-model-building/train.csv')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Gender\n",
    "\n",
    "Classes appear to be gender sensitive. \\\n",
    "For e.g. Given a man, probability of obesity type II is 31% which for a women is practically zero "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>Gender</th>\n",
       "      <th>Female</th>\n",
       "      <th>Male</th>\n",
       "      <th>Pr(Class|Female)</th>\n",
       "      <th>Pr(Class|Male)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NObeyesdad</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Insufficient_Weight</th>\n",
       "      <td>1059</td>\n",
       "      <td>574</td>\n",
       "      <td>0.16</td>\n",
       "      <td>0.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Normal_Weight</th>\n",
       "      <td>1056</td>\n",
       "      <td>943</td>\n",
       "      <td>0.16</td>\n",
       "      <td>0.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Obesity_Type_I</th>\n",
       "      <td>842</td>\n",
       "      <td>1077</td>\n",
       "      <td>0.12</td>\n",
       "      <td>0.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Obesity_Type_II</th>\n",
       "      <td>5</td>\n",
       "      <td>2081</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Obesity_Type_III</th>\n",
       "      <td>2639</td>\n",
       "      <td>3</td>\n",
       "      <td>0.39</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Overweight_Level_I</th>\n",
       "      <td>690</td>\n",
       "      <td>890</td>\n",
       "      <td>0.10</td>\n",
       "      <td>0.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Overweight_Level_II</th>\n",
       "      <td>498</td>\n",
       "      <td>1135</td>\n",
       "      <td>0.07</td>\n",
       "      <td>0.17</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Gender               Female  Male  Pr(Class|Female)  Pr(Class|Male)\n",
       "NObeyesdad                                                         \n",
       "Insufficient_Weight    1059   574              0.16            0.09\n",
       "Normal_Weight          1056   943              0.16            0.14\n",
       "Obesity_Type_I          842  1077              0.12            0.16\n",
       "Obesity_Type_II           5  2081              0.00            0.31\n",
       "Obesity_Type_III       2639     3              0.39            0.00\n",
       "Overweight_Level_I      690   890              0.10            0.13\n",
       "Overweight_Level_II     498  1135              0.07            0.17"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# pivot table gender in column, and NObeyesdad in row, value is count\n",
    "pivot = train_df.pivot_table(index='NObeyesdad', columns = 'Gender', values='Age', aggfunc='count')\n",
    "# dataframe\n",
    "pivot = pd.DataFrame(pivot)\n",
    "\n",
    "# probability(class|gender) columns add = row/row total\n",
    "pivot['Pr(Class|Female)'] = round(pivot['Female']/pivot['Female'].sum(),2)\n",
    "pivot['Pr(Class|Male)'] = round(pivot['Male']/pivot['Male'].sum(),2)\n",
    "\n",
    "pivot\n",
    "                                          \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot\n",
    "\n",
    "# Set up the figure and axes\n",
    "fig, axs = plt.subplots(1, 2, figsize=(14, 6))\n",
    "\n",
    "# Boxplot 1: Gender vs. Age\n",
    "sns.boxplot(x=train_df['Gender'], y=train_df['Age'], palette='Set3', linewidth=2.5, width=0.5, fliersize=5, ax=axs[0])\n",
    "axs[0].set_title('Gender vs. Age')\n",
    "\n",
    "# Boxplot 2: Age vs. NObeyesdad\n",
    "sns.boxplot(x=train_df['Age'], y=train_df['NObeyesdad'], palette='Set1', linewidth=2.5, width=0.5, fliersize=5, ax=axs[1])\n",
    "axs[1].set_title('Age vs. NObeyesdad')\n",
    "\n",
    "# Adjust layout\n",
    "plt.tight_layout()\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##---- final"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "DataScience",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}