miRNA_limma_dataset_xgb_described.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "75167b57",
   "metadata": {},
   "outputs": [],
   "source": [
    "## TRAINING  and TEST SET :  miRNA DATA , MODEL: XGBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "f097ad55",
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import RocCurveDisplay\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from imblearn.over_sampling import SMOTE\n",
    "from sklearn.linear_model import Lasso\n",
    "import xgboost as xgb\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "#np.random.seed(7)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "73b6611a",
   "metadata": {},
   "source": [
    "# Data Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "0eeb7a35",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"DS/miRNA_DS_preprocessed_data.csv\") # read the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "6e7836e1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(230, 239)"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "683b63ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.T # transpose the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "2e78017d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Transform the input data\n",
    "df.rename(columns=df.iloc[0], inplace = True)\n",
    "df.drop(df.index[0], inplace = True)\n",
    "df=df.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "4c50c510",
   "metadata": {},
   "outputs": [],
   "source": [
    "metadata = pd.read_csv(\"DS/miRNA_DS_metadata_col_info.csv\") # read the class information"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "6730cf89",
   "metadata": {},
   "outputs": [],
   "source": [
    "df= df.merge(metadata, left_on=\"index\", right_on= \"Unnamed: 0\") # merge the expresison data with class info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "7a8ad8ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['title0'] = df['title0'].replace('(?i)mucosa|normal|healthy', 0, regex=True) # replace the class name \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "a8cf8643",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['title0'] = df['title0'].replace('(?i)Tumor|Cancer|carcinoma', 1, regex=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "f5d203aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[pd.to_numeric(df['title0'], errors='coerce').notnull()]#remove all non-numeric data from the column."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "523bdaa6",
   "metadata": {},
   "outputs": [],
   "source": [
    "df= df.drop(['index', 'Unnamed: 0'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "46a6fb36",
   "metadata": {},
   "outputs": [],
   "source": [
    "df= df.rename(columns={\"title0\": \"index\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "e26f88c5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "index\n",
       "1    119\n",
       "0    119\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['index'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "fbaf2507",
   "metadata": {},
   "outputs": [],
   "source": [
    "df= df.apply(pd.to_numeric)"