diff --git a/Machine Learning/DS_miRNA_limma_dataset_xgb_final-F.ipynb b/Machine Learning/DS_miRNA_limma_dataset_xgb_final-F.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..e19cab4d08e4dff8eb9df8eedce78d1e53ed6add
--- /dev/null
+++ b/Machine Learning/DS_miRNA_limma_dataset_xgb_final-F.ipynb
@@ -0,0 +1,1504 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "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.model_selection import cross_val_score\n",
+ "#from sklearn.metrics import accuracy_score\n",
+ "#import sklearn.metrics as metrics\n",
+ "#from sklearn.metrics import auc\n",
+ "from sklearn.metrics import RocCurveDisplay\n",
+ "#from sklearn.model_selection import KFold\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": 38,
+ "id": "0eeb7a35",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = pd.read_csv(\"DS/miRNA_DS_preprocessed_data.csv\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "id": "6e7836e1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(230, 239)"
+ ]
+ },
+ "execution_count": 40,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "id": "683b63ce",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = df.T"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "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": 43,
+ "id": "1647a959",
+ "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>index</th>\n",
+ " <th>dmr_3</th>\n",
+ " <th>dmr_31a</th>\n",
+ " <th>dmr_6</th>\n",
+ " <th>ebv-miR-BART13</th>\n",
+ " <th>hsa-let-7c</th>\n",
+ " <th>hsa-let-7d-5p</th>\n",
+ " <th>hsa-let-7i-5p</th>\n",
+ " <th>hsa-miR-100-5p</th>\n",
+ " <th>hsa-miR-101-3p</th>\n",
+ " <th>...</th>\n",
+ " <th>hsv2-miR-H24</th>\n",
+ " <th>hsv2-miR-H25</th>\n",
+ " <th>hsv2-miR-H6</th>\n",
+ " <th>hur_1</th>\n",
+ " <th>hur_2</th>\n",
+ " <th>hur_4</th>\n",
+ " <th>hur_5</th>\n",
+ " <th>hur_6</th>\n",
+ " <th>miRNABrightCorner30</th>\n",
+ " <th>mr_1</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>GSM1069774</td>\n",
+ " <td>0.732675</td>\n",
+ " <td>-0.242559</td>\n",
+ " <td>0.577801</td>\n",
+ " <td>-4.469532</td>\n",
+ " <td>1.195899</td>\n",
+ " <td>-0.334742</td>\n",
+ " <td>0.89199</td>\n",
+ " <td>-2.089223</td>\n",
+ " <td>-2.757097</td>\n",
+ " <td>...</td>\n",
+ " <td>-3.956004</td>\n",
+ " <td>-3.936689</td>\n",
+ " <td>-4.099346</td>\n",
+ " <td>6.98856</td>\n",
+ " <td>7.041557</td>\n",
+ " <td>3.822267</td>\n",
+ " <td>-2.268209</td>\n",
+ " <td>5.114399</td>\n",
+ " <td>2.017444</td>\n",
+ " <td>1.640437</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>GSM1069775</td>\n",
+ " <td>0.249772</td>\n",
+ " <td>-0.655514</td>\n",
+ " <td>0.104933</td>\n",
+ " <td>-5.209572</td>\n",
+ " <td>0.498366</td>\n",
+ " <td>-0.194772</td>\n",
+ " <td>0.637863</td>\n",
+ " <td>-2.357572</td>\n",
+ " <td>-2.196884</td>\n",
+ " <td>...</td>\n",
+ " <td>-4.334103</td>\n",
+ " <td>-4.561624</td>\n",
+ " <td>-4.719714</td>\n",
+ " <td>6.774479</td>\n",
+ " <td>6.862654</td>\n",
+ " <td>3.529789</td>\n",
+ " <td>-2.656642</td>\n",
+ " <td>4.327117</td>\n",
+ " <td>2.022346</td>\n",
+ " <td>0.79426</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>GSM1069776</td>\n",
+ " <td>0.400779</td>\n",
+ " <td>-0.597444</td>\n",
+ " <td>0.232702</td>\n",
+ " <td>-4.952808</td>\n",
+ " <td>1.081166</td>\n",
+ " <td>0.249982</td>\n",
+ " <td>1.45018</td>\n",
+ " <td>-1.138559</td>\n",
+ " <td>-1.802774</td>\n",
+ " <td>...</td>\n",
+ " <td>-4.550077</td>\n",
+ " <td>-4.40729</td>\n",
+ " <td>-4.621278</td>\n",
+ " <td>6.808404</td>\n",
+ " <td>6.75867</td>\n",
+ " <td>3.496675</td>\n",
+ " <td>-2.676555</td>\n",
+ " <td>4.616284</td>\n",
+ " <td>1.498011</td>\n",
+ " <td>1.584544</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>GSM1069777</td>\n",
+ " <td>0.380263</td>\n",
+ " <td>-0.900491</td>\n",
+ " <td>0.243207</td>\n",
+ " <td>-4.892073</td>\n",
+ " <td>-0.023958</td>\n",
+ " <td>-0.980435</td>\n",
+ " <td>1.071857</td>\n",
+ " <td>-2.077406</td>\n",
+ " <td>-2.11406</td>\n",
+ " <td>...</td>\n",
+ " <td>-4.018911</td>\n",
+ " <td>-4.203106</td>\n",
+ " <td>-3.938707</td>\n",
+ " <td>6.524773</td>\n",
+ " <td>6.497959</td>\n",
+ " <td>3.541502</td>\n",
+ " <td>-3.073553</td>\n",
+ " <td>4.581648</td>\n",
+ " <td>0.789822</td>\n",
+ " <td>1.255367</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>GSM1069778</td>\n",
+ " <td>0.422207</td>\n",
+ " <td>-0.414831</td>\n",
+ " <td>-0.000781</td>\n",
+ " <td>-5.139127</td>\n",
+ " <td>1.077485</td>\n",
+ " <td>-0.684875</td>\n",
+ " <td>0.724751</td>\n",
+ " <td>-0.689096</td>\n",
+ " <td>-1.182558</td>\n",
+ " <td>...</td>\n",
+ " <td>-3.690971</td>\n",
+ " <td>-4.332452</td>\n",
+ " <td>-4.178727</td>\n",
+ " <td>6.562608</td>\n",
+ " <td>6.529399</td>\n",
+ " <td>3.305132</td>\n",
+ " <td>-2.964948</td>\n",
+ " <td>4.487481</td>\n",
+ " <td>1.219583</td>\n",
+ " <td>0.951615</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",
+ " <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",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>233</th>\n",
+ " <td>GSM1070007</td>\n",
+ " <td>0.98797</td>\n",
+ " <td>-0.118186</td>\n",
+ " <td>0.750199</td>\n",
+ " <td>-4.572984</td>\n",
+ " <td>0.696251</td>\n",
+ " <td>-1.089669</td>\n",
+ " <td>0.826</td>\n",
+ " <td>-1.604393</td>\n",
+ " <td>-2.87334</td>\n",
+ " <td>...</td>\n",
+ " <td>-2.163581</td>\n",
+ " <td>-2.15805</td>\n",
+ " <td>-2.302647</td>\n",
+ " <td>7.093144</td>\n",
+ " <td>7.150126</td>\n",
+ " <td>3.899704</td>\n",
+ " <td>-2.954284</td>\n",
+ " <td>5.505105</td>\n",
+ " <td>2.457963</td>\n",
+ " <td>2.142301</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>234</th>\n",
+ " <td>GSM1070008</td>\n",
+ " <td>-0.194781</td>\n",
+ " <td>-0.710519</td>\n",
+ " <td>-0.700226</td>\n",
+ " <td>-5.651293</td>\n",
+ " <td>0.742722</td>\n",
+ " <td>-0.964527</td>\n",
+ " <td>0.570816</td>\n",
+ " <td>-1.046029</td>\n",
+ " <td>-1.840615</td>\n",
+ " <td>...</td>\n",
+ " <td>-4.507365</td>\n",
+ " <td>-4.23831</td>\n",
+ " <td>-4.63219</td>\n",
+ " <td>6.18658</td>\n",
+ " <td>6.232722</td>\n",
+ " <td>2.788619</td>\n",
+ " <td>-3.103706</td>\n",
+ " <td>4.340513</td>\n",
+ " <td>0.232713</td>\n",
+ " <td>1.067806</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>235</th>\n",
+ " <td>GSM1070009</td>\n",
+ " <td>0.21218</td>\n",
+ " <td>-0.284657</td>\n",
+ " <td>-0.32472</td>\n",
+ " <td>-4.800142</td>\n",
+ " <td>1.0062</td>\n",
+ " <td>-0.141699</td>\n",
+ " <td>0.80704</td>\n",
+ " <td>-0.993146</td>\n",
+ " <td>-0.823621</td>\n",
+ " <td>...</td>\n",
+ " <td>-2.737709</td>\n",
+ " <td>-2.644713</td>\n",
+ " <td>-3.253632</td>\n",
+ " <td>6.505956</td>\n",
+ " <td>6.548781</td>\n",
+ " <td>3.12575</td>\n",
+ " <td>-2.917537</td>\n",
+ " <td>4.838599</td>\n",
+ " <td>0.863574</td>\n",
+ " <td>1.203499</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>236</th>\n",
+ " <td>GSM1070010</td>\n",
+ " <td>0.330997</td>\n",
+ " <td>-0.19446</td>\n",
+ " <td>-0.206405</td>\n",
+ " <td>-4.840442</td>\n",
+ " <td>1.521159</td>\n",
+ " <td>-0.424901</td>\n",
+ " <td>0.886358</td>\n",
+ " <td>-0.031455</td>\n",
+ " <td>-1.584939</td>\n",
+ " <td>...</td>\n",
+ " <td>-3.292034</td>\n",
+ " <td>-2.941633</td>\n",
+ " <td>-3.939222</td>\n",
+ " <td>6.790132</td>\n",
+ " <td>6.829164</td>\n",
+ " <td>3.365475</td>\n",
+ " <td>-2.736411</td>\n",
+ " <td>5.185601</td>\n",
+ " <td>0.846454</td>\n",
+ " <td>1.604729</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>237</th>\n",
+ " <td>GSM1070011</td>\n",
+ " <td>0.474815</td>\n",
+ " <td>0.043697</td>\n",
+ " <td>-0.102511</td>\n",
+ " <td>-4.849285</td>\n",
+ " <td>1.239637</td>\n",
+ " <td>-0.704124</td>\n",
+ " <td>0.698355</td>\n",
+ " <td>-0.414715</td>\n",
+ " <td>-1.721427</td>\n",
+ " <td>...</td>\n",
+ " <td>-3.378909</td>\n",
+ " <td>-2.909732</td>\n",
+ " <td>-3.510667</td>\n",
+ " <td>6.80237</td>\n",
+ " <td>6.784016</td>\n",
+ " <td>3.514036</td>\n",
+ " <td>-2.931018</td>\n",
+ " <td>4.798139</td>\n",
+ " <td>2.08952</td>\n",
+ " <td>1.597958</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>238 rows × 231 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " index dmr_3 dmr_31a dmr_6 ebv-miR-BART13 hsa-let-7c \\\n",
+ "0 GSM1069774 0.732675 -0.242559 0.577801 -4.469532 1.195899 \n",
+ "1 GSM1069775 0.249772 -0.655514 0.104933 -5.209572 0.498366 \n",
+ "2 GSM1069776 0.400779 -0.597444 0.232702 -4.952808 1.081166 \n",
+ "3 GSM1069777 0.380263 -0.900491 0.243207 -4.892073 -0.023958 \n",
+ "4 GSM1069778 0.422207 -0.414831 -0.000781 -5.139127 1.077485 \n",
+ ".. ... ... ... ... ... ... \n",
+ "233 GSM1070007 0.98797 -0.118186 0.750199 -4.572984 0.696251 \n",
+ "234 GSM1070008 -0.194781 -0.710519 -0.700226 -5.651293 0.742722 \n",
+ "235 GSM1070009 0.21218 -0.284657 -0.32472 -4.800142 1.0062 \n",
+ "236 GSM1070010 0.330997 -0.19446 -0.206405 -4.840442 1.521159 \n",
+ "237 GSM1070011 0.474815 0.043697 -0.102511 -4.849285 1.239637 \n",
+ "\n",
+ " hsa-let-7d-5p hsa-let-7i-5p hsa-miR-100-5p hsa-miR-101-3p ... \\\n",
+ "0 -0.334742 0.89199 -2.089223 -2.757097 ... \n",
+ "1 -0.194772 0.637863 -2.357572 -2.196884 ... \n",
+ "2 0.249982 1.45018 -1.138559 -1.802774 ... \n",
+ "3 -0.980435 1.071857 -2.077406 -2.11406 ... \n",
+ "4 -0.684875 0.724751 -0.689096 -1.182558 ... \n",
+ ".. ... ... ... ... ... \n",
+ "233 -1.089669 0.826 -1.604393 -2.87334 ... \n",
+ "234 -0.964527 0.570816 -1.046029 -1.840615 ... \n",
+ "235 -0.141699 0.80704 -0.993146 -0.823621 ... \n",
+ "236 -0.424901 0.886358 -0.031455 -1.584939 ... \n",
+ "237 -0.704124 0.698355 -0.414715 -1.721427 ... \n",
+ "\n",
+ " hsv2-miR-H24 hsv2-miR-H25 hsv2-miR-H6 hur_1 hur_2 hur_4 \\\n",
+ "0 -3.956004 -3.936689 -4.099346 6.98856 7.041557 3.822267 \n",
+ "1 -4.334103 -4.561624 -4.719714 6.774479 6.862654 3.529789 \n",
+ "2 -4.550077 -4.40729 -4.621278 6.808404 6.75867 3.496675 \n",
+ "3 -4.018911 -4.203106 -3.938707 6.524773 6.497959 3.541502 \n",
+ "4 -3.690971 -4.332452 -4.178727 6.562608 6.529399 3.305132 \n",
+ ".. ... ... ... ... ... ... \n",
+ "233 -2.163581 -2.15805 -2.302647 7.093144 7.150126 3.899704 \n",
+ "234 -4.507365 -4.23831 -4.63219 6.18658 6.232722 2.788619 \n",
+ "235 -2.737709 -2.644713 -3.253632 6.505956 6.548781 3.12575 \n",
+ "236 -3.292034 -2.941633 -3.939222 6.790132 6.829164 3.365475 \n",
+ "237 -3.378909 -2.909732 -3.510667 6.80237 6.784016 3.514036 \n",
+ "\n",
+ " hur_5 hur_6 miRNABrightCorner30 mr_1 \n",
+ "0 -2.268209 5.114399 2.017444 1.640437 \n",
+ "1 -2.656642 4.327117 2.022346 0.79426 \n",
+ "2 -2.676555 4.616284 1.498011 1.584544 \n",
+ "3 -3.073553 4.581648 0.789822 1.255367 \n",
+ "4 -2.964948 4.487481 1.219583 0.951615 \n",
+ ".. ... ... ... ... \n",
+ "233 -2.954284 5.505105 2.457963 2.142301 \n",
+ "234 -3.103706 4.340513 0.232713 1.067806 \n",
+ "235 -2.917537 4.838599 0.863574 1.203499 \n",
+ "236 -2.736411 5.185601 0.846454 1.604729 \n",
+ "237 -2.931018 4.798139 2.08952 1.597958 \n",
+ "\n",
+ "[238 rows x 231 columns]"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "id": "4c50c510",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "metadata = pd.read_csv(\"DS/miRNA_DS_metadata_col_info.csv\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "id": "6730cf89",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df= df.merge(metadata, left_on=\"index\", right_on= \"Unnamed: 0\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "id": "7a8ad8ad",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df['title0'] = df['title0'].replace('(?i)mucosa|normal|healthy', 0, regex=True)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "id": "a8cf8643",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df['title0'] = df['title0'].replace('(?i)Tumor|Cancer|carcinoma', 1, regex=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "id": "5c852a3f",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "title0\n",
+ "1 119\n",
+ "0 119\n",
+ "Name: count, dtype: int64"
+ ]
+ },
+ "execution_count": 50,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df['title0'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "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": 53,
+ "id": "523bdaa6",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df= df.drop(['index', 'Unnamed: 0'], axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "id": "46a6fb36",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df= df.rename(columns={\"title0\": \"index\"})"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "id": "e26f88c5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "index\n",
+ "1 119\n",
+ "0 119\n",
+ "Name: count, dtype: int64"
+ ]
+ },
+ "execution_count": 55,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df['index'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "id": "fbaf2507",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df= df.apply(pd.to_numeric)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "id": "f3f7adb5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "index\n",
+ "1 119\n",
+ "0 119\n",
+ "Name: count, dtype: int64"
+ ]
+ },
+ "execution_count": 57,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df['index'].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "id": "6a50f416",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X=df.drop(\"index\",axis=1)\n",
+ "y=df['index']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "id": "e644ab0e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "y=y.astype('int')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "6cee6462",
+ "metadata": {},
+ "source": [
+ "# Test train split"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "id": "1da48142",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# split data into training and testing data-sets\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=7)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 63,
+ "id": "129430e6",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(index\n",
+ " 0 30\n",
+ " 1 30\n",
+ " Name: count, dtype: int64,\n",
+ " index\n",
+ " 0 89\n",
+ " 1 89\n",
+ " Name: count, dtype: int64)"
+ ]
+ },
+ "execution_count": 63,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y_test.value_counts(),y_train.value_counts()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1cfe2a06",
+ "metadata": {},
+ "source": [
+ "# Cross validation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 64,
+ "id": "d3550b5e",
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fitting 5 folds for each of 36 candidates, totalling 180 fits\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.917 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.4s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.3s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.917 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.4s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.944 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.889 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.944 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.889 total time= 0.4s\n",
+ "[CV 3/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.4s\n",
+ "[CV 5/5] END gamma=0.1, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.4s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[CV 3/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.917 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.3s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.917 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.4s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.4s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.917 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.3s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.917 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.944 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.889 total time= 0.4s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.1s\n",
+ "[CV 1/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.944 total time= 0.3s\n",
+ "[CV 2/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.889 total time= 0.4s\n",
+ "[CV 3/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 5/5] END gamma=0.01, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.4s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.1, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.1s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.1s\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[CV 1/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.1, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.1s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.917 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.3s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.01, max_depth=3, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.1s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=1.000 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.917 total time= 0.4s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.4s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.01, max_depth=5, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.4s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.944 total time= 0.3s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.889 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.4s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.4s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.001, max_depth=3, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.3s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.944 total time= 0.2s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.889 total time= 0.2s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.972 total time= 0.2s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.971 total time= 0.2s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=100, subsample=1.0;, score=0.943 total time= 0.2s\n",
+ "[CV 1/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.944 total time= 0.4s\n",
+ "[CV 2/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.889 total time= 0.3s\n",
+ "[CV 3/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.972 total time= 0.3s\n",
+ "[CV 4/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.971 total time= 0.4s\n",
+ "[CV 5/5] END gamma=0.001, learning_rate=0.001, max_depth=5, n_estimators=200, subsample=1.0;, score=0.943 total time= 0.4s\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"â–¸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"â–¾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(estimator=XGBClassifier(base_score=None, booster=None,\n",
+ " callbacks=None, colsample_bylevel=None,\n",
+ " colsample_bynode=None,\n",
+ " colsample_bytree=None,\n",
+ " early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None,\n",
+ " feature_types=None, gamma=None,\n",
+ " gpu_id=None, grow_policy=None,\n",
+ " importance_type=None,\n",
+ " interaction_constraints=None,\n",
+ " learning_rate=None, max_b...\n",
+ " max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None,\n",
+ " max_leaves=None, min_child_weight=None,\n",
+ " missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None,\n",
+ " num_parallel_tree=None, predictor=None,\n",
+ " random_state=42, ...),\n",
+ " param_grid={'gamma': [0.1, 0.01, 0.001],\n",
+ " 'learning_rate': [0.1, 0.01, 0.001],\n",
+ " 'max_depth': [3, 5], 'n_estimators': [100, 200],\n",
+ " 'subsample': [1.0]},\n",
+ " verbose=3)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(estimator=XGBClassifier(base_score=None, booster=None,\n",
+ " callbacks=None, colsample_bylevel=None,\n",
+ " colsample_bynode=None,\n",
+ " colsample_bytree=None,\n",
+ " early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None,\n",
+ " feature_types=None, gamma=None,\n",
+ " gpu_id=None, grow_policy=None,\n",
+ " importance_type=None,\n",
+ " interaction_constraints=None,\n",
+ " learning_rate=None, max_b...\n",
+ " max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None,\n",
+ " max_leaves=None, min_child_weight=None,\n",
+ " missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None,\n",
+ " num_parallel_tree=None, predictor=None,\n",
+ " random_state=42, ...),\n",
+ " param_grid={'gamma': [0.1, 0.01, 0.001],\n",
+ " 'learning_rate': [0.1, 0.01, 0.001],\n",
+ " 'max_depth': [3, 5], 'n_estimators': [100, 200],\n",
+ " 'subsample': [1.0]},\n",
+ " verbose=3)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
+ " predictor=None, random_state=42, ...)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
+ " predictor=None, random_state=42, ...)</pre></div></div></div></div></div></div></div></div></div></div>"
+ ],
+ "text/plain": [
+ "GridSearchCV(estimator=XGBClassifier(base_score=None, booster=None,\n",
+ " callbacks=None, colsample_bylevel=None,\n",
+ " colsample_bynode=None,\n",
+ " colsample_bytree=None,\n",
+ " early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None,\n",
+ " feature_types=None, gamma=None,\n",
+ " gpu_id=None, grow_policy=None,\n",
+ " importance_type=None,\n",
+ " interaction_constraints=None,\n",
+ " learning_rate=None, max_b...\n",
+ " max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None,\n",
+ " max_leaves=None, min_child_weight=None,\n",
+ " missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None,\n",
+ " num_parallel_tree=None, predictor=None,\n",
+ " random_state=42, ...),\n",
+ " param_grid={'gamma': [0.1, 0.01, 0.001],\n",
+ " 'learning_rate': [0.1, 0.01, 0.001],\n",
+ " 'max_depth': [3, 5], 'n_estimators': [100, 200],\n",
+ " 'subsample': [1.0]},\n",
+ " verbose=3)"
+ ]
+ },
+ "execution_count": 64,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "model = xgb.XGBClassifier(random_state=42)\n",
+ "\n",
+ "# Defining parameter range\n",
+ "param_grid = {\n",
+ " 'max_depth': [3,5],\n",
+ " 'learning_rate': [0.1 ,0.01, 0.001],\n",
+ " 'n_estimators': [100,200],\n",
+ " 'gamma': [ 0.1,0.01,0.001],\n",
+ " 'subsample': [1.0]\n",
+ "}\n",
+ "\n",
+ "\n",
+ "grid = GridSearchCV(model, param_grid, refit=True, verbose=3)\n",
+ "\n",
+ "# Fitting the model for grid search\n",
+ "grid.fit(X_train, y_train)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 65,
+ "id": "556e249c",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'gamma': 0.1, 'learning_rate': 0.1, 'max_depth': 3, 'n_estimators': 100, 'subsample': 1.0}\n",
+ "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=0.1, gpu_id=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=3, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
+ " predictor=None, random_state=42, ...)\n"
+ ]
+ }
+ ],
+ "source": [
+ "# print best parameter after tuning\n",
+ "print(grid.best_params_)\n",
+ " \n",
+ "# print how our model looks after hyper-parameter tuning\n",
+ "print(grid.best_estimator_)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "id": "0686e808",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"â–¸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"â–¾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=0.1, gpu_id=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=3, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
+ " predictor=None, random_state=42, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=0.1, gpu_id=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=3, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
+ " predictor=None, random_state=42, ...)</pre></div></div></div></div></div>"
+ ],
+ "text/plain": [
+ "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+ " colsample_bylevel=None, colsample_bynode=None,\n",
+ " colsample_bytree=None, early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None, feature_types=None,\n",
+ " gamma=0.1, gpu_id=None, grow_policy=None, importance_type=None,\n",
+ " interaction_constraints=None, learning_rate=0.1, max_bin=None,\n",
+ " max_cat_threshold=None, max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=3, max_leaves=None,\n",
+ " min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+ " n_estimators=100, n_jobs=None, num_parallel_tree=None,\n",
+ " predictor=None, random_state=42, ...)"
+ ]
+ },
+ "execution_count": 66,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "model_xgb = grid.best_estimator_\n",
+ "model_xgb.fit(X_train,y_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "id": "ac776bef",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "y_proba = model_xgb.fit(X_train, y_train).predict_proba(X_test)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "3ea57532",
+ "metadata": {},
+ "source": [
+ "# classification report"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "id": "18becbe2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.97 0.97 0.97 30\n",
+ " 1 0.97 0.97 0.97 30\n",
+ "\n",
+ " accuracy 0.97 60\n",
+ " macro avg 0.97 0.97 0.97 60\n",
+ "weighted avg 0.97 0.97 0.97 60\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "from sklearn.metrics import classification_report, confusion_matrix\n",
+ "grid_predictions = grid.predict(X_test)\n",
+ "print(classification_report(y_test, grid_predictions))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 69,
+ "id": "c0193b78",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "classes = model_xgb.classes_"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 70,
+ "id": "d723c69f",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([0, 1])"
+ ]
+ },
+ "execution_count": 70,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "classes"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 71,
+ "id": "4643393d",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 640x480 with 2 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "#######CONFUSION MATRIX ###########\n",
+ "from sklearn import metrics\n",
+ "y_test_pred_xgb = model_xgb.predict(X_test)\n",
+ "confusion_matrix_test = metrics.confusion_matrix(y_test, y_test_pred_xgb)\n",
+ "cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix_test)\n",
+ "cm_display.plot()\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 72,
+ "id": "5ad4efb1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Accuracy : 0.9666666666666667\n",
+ "Sensitivity : 0.9666666666666667\n",
+ "Specificity : 0.9666666666666667\n"
+ ]
+ }
+ ],
+ "source": [
+ "total1=sum(sum(confusion_matrix_test))\n",
+ "#####from confusion matrix calculate accuracy\n",
+ "accuracy1=(confusion_matrix_test[0,0]+confusion_matrix_test[1,1])/total1\n",
+ "print ('Accuracy : ', accuracy1)\n",
+ "\n",
+ "sensitivity1 = confusion_matrix_test[0,0]/(confusion_matrix_test[0,0]+confusion_matrix_test[0,1])\n",
+ "print('Sensitivity : ', sensitivity1 )\n",
+ "\n",
+ "specificity1 = confusion_matrix_test[1,1]/(confusion_matrix_test[1,0]+confusion_matrix_test[1,1])\n",
+ "print('Specificity : ', specificity1)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "6603d82c",
+ "metadata": {},
+ "source": [
+ "# ROC curve"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "id": "0e2a2694",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from sklearn.model_selection import StratifiedKFold\n",
+ "from sklearn.feature_selection import SelectKBest, f_classif\n",
+ "from sklearn.metrics import auc\n",
+ "def roc(X_train,y_train,model,label):\n",
+ " cv = StratifiedKFold(n_splits=6)\n",
+ " classifier = model\n",
+ " tprs = []\n",
+ " aucs = []\n",
+ " mean_fpr = np.linspace(0, 1, 100)\n",
+ "\n",
+ " fig, ax = plt.subplots(figsize=(6, 6))\n",
+ " for fold, (train, test) in enumerate(cv.split(X_train, y_train)):\n",
+ " classifier.fit(X_train.iloc[train], y_train.iloc[train])\n",
+ " viz = RocCurveDisplay.from_estimator(\n",
+ " classifier,\n",
+ " X_train.iloc[test],\n",
+ " y_train.iloc[test],\n",
+ " name=f\"ROC fold {fold}\",\n",
+ " alpha=0.3,\n",
+ " lw=1,\n",
+ " ax=ax,\n",
+ " )\n",
+ " interp_tpr = np.interp(mean_fpr, viz.fpr, viz.tpr)\n",
+ " interp_tpr[0] = 0.0\n",
+ " tprs.append(interp_tpr)\n",
+ " aucs.append(viz.roc_auc)\n",
+ " ax.plot([0, 1], [0, 1], \"k--\", label=\"chance level (AUC = 0.5)\")\n",
+ "\n",
+ " mean_tpr = np.mean(tprs, axis=0)\n",
+ " mean_tpr[-1] = 1.0\n",
+ " mean_auc = auc(mean_fpr, mean_tpr)\n",
+ " std_auc = np.std(aucs)\n",
+ " ax.plot(\n",
+ " mean_fpr,\n",
+ " mean_tpr,\n",
+ " color=\"b\",\n",
+ " label=r\"Mean ROC (AUC = %0.2f $\\pm$ %0.2f)\" % (mean_auc, std_auc),\n",
+ " lw=2,\n",
+ " alpha=0.8,\n",
+ " )\n",
+ "\n",
+ " std_tpr = np.std(tprs, axis=0)\n",
+ " tprs_upper = np.minimum(mean_tpr + std_tpr, 1)\n",
+ " tprs_lower = np.maximum(mean_tpr - std_tpr, 0)\n",
+ " ax.fill_between(\n",
+ " mean_fpr,\n",
+ " tprs_lower,\n",
+ " tprs_upper,\n",
+ " color=\"grey\",\n",
+ " alpha=0.2,\n",
+ " label=r\"$\\pm$ 1 std. dev.\",\n",
+ " )\n",
+ "\n",
+ " ax.set(\n",
+ " xlim=[-0.05, 1.05],\n",
+ " ylim=[-0.05, 1.05],\n",
+ " xlabel=\"False Positive Rate\",\n",
+ " ylabel=\"True Positive Rate\",\n",
+ " title=label,\n",
+ " )\n",
+ " ax.axis(\"square\")\n",
+ " ax.legend(loc=\"lower right\")\n",
+ " plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "id": "d4cc8e6d",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 600x600 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "model = model_xgb\n",
+ "label=\"ROC curve of training data\"\n",
+ "roc(X_train,y_train,model,label)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 75,
+ "id": "1199e2e4",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 600x600 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "label=\"ROC curve of testing data\"\n",
+ "roc(X_test,y_test,model,label)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "bee03388",
+ "metadata": {},
+ "source": [
+ "# Feature importance"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 284,
+ "id": "6688e037",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# for important features:\n",
+ "important_feat = model_xgb.feature_importances_\n",
+ "#get indices of those important features\n",
+ "idx = important_feat.argsort(kind= \"quicksort\")\n",
+ "idx= idx[::-1][:50]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 285,
+ "id": "4e6a7ea1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([ 66, 65, 84, 94, 140, 32, 169, 137, 23, 212, 10, 166, 13,\n",
+ " 36, 56, 126, 48, 57, 42, 208, 37, 113, 29, 160, 22, 96,\n",
+ " 162, 229, 189, 101, 104, 127, 135, 21, 79, 78, 77, 76, 75,\n",
+ " 74, 73, 72, 202, 71, 69, 68, 67, 64, 63, 62])"
+ ]
+ },
+ "execution_count": 285,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "idx"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 286,
+ "id": "f2101fe1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df1 = X.T"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 287,
+ "id": "2cbf1166",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "top_met = df1.iloc[idx]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 288,
+ "id": "2370b2df",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index(['hsa-miR-18b-5p', 'hsa-miR-18a-5p', 'hsa-miR-21-5p', 'hsa-miR-25-3p',\n",
+ " 'hsa-miR-424-5p', 'hsa-miR-130b-3p', 'hsa-miR-455-3p', 'hsa-miR-378i',\n",
+ " 'hsa-miR-1268a', 'hsa-miR-93-5p', 'hsa-miR-106b-5p', 'hsa-miR-451a',\n",
+ " 'hsa-miR-10b-5p', 'hsa-miR-140-3p', 'hsa-miR-15b-5p', 'hsa-miR-3651',\n",
+ " 'hsa-miR-150-5p', 'hsa-miR-16-2-3p', 'hsa-miR-145-5p', 'hsa-miR-7-5p',\n",
+ " 'hsa-miR-140-5p', 'hsa-miR-3198', 'hsa-miR-1290', 'hsa-miR-4465',\n",
+ " 'hsa-miR-126-3p', 'hsa-miR-26b-5p', 'hsa-miR-4497', 'mr_1',\n",
+ " 'hsa-miR-497-5p', 'hsa-miR-29c-3p', 'hsa-miR-30a-5p', 'hsa-miR-3656',\n",
+ " 'hsa-miR-378a-3p', 'hsa-miR-125b-5p', 'hsa-miR-200c-3p',\n",
+ " 'hsa-miR-200b-3p', 'hsa-miR-19b-3p', 'hsa-miR-19a-3p',\n",
+ " 'hsa-miR-199a-5p', 'hsa-miR-199a-3p', 'hsa-miR-1973', 'hsa-miR-197-5p',\n",
+ " 'hsa-miR-642a-3p', 'hsa-miR-197-3p', 'hsa-miR-193b-3p',\n",
+ " 'hsa-miR-193a-5p', 'hsa-miR-1915-3p', 'hsa-miR-188-5p',\n",
+ " 'hsa-miR-185-5p', 'hsa-miR-181b-5p'],\n",
+ " dtype='object')"
+ ]
+ },
+ "execution_count": 288,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "top_met.index"
+ ]
+ }
+ ],
+ "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": "3.9.16"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}