{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## 필요한 모듈 import" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from imblearn.pipeline import make_pipeline, Pipeline\n", "from sklearn.preprocessing import MinMaxScaler\n", "from sklearn.model_selection import StratifiedKFold, RandomizedSearchCV, GridSearchCV, train_test_split\n", "from sklearn.decomposition import PCA\n", "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "from sklearn.feature_selection import VarianceThreshold" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "APCFP = pd.read_csv('finalfingerprint_sub_apc.csv')" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
target_name_bintarget_name_tertarget_name_quatersmilesAPC2D1_C_CAPC2D1_C_NAPC2D1_C_OAPC2D1_C_SAPC2D1_C_PAPC2D1_C_F...SubFPC303SubFPC304SubFPC305SubFPC306SubFPC307bond:C=S_carbonyl_thio_genericbond:CN_amine_pri-NH2_aromaticbond:CS_sulfidebond:S=O_sulfonyl_genericring:hetero_[6_6]_O_benzopyrone_(1_4-)
0AAA1Nc1ccccc1610000...0000601000
1AAA1COc1ccc(N)cc1612000...0000601000
2AAA1COP(=S)(OC)SCn1nnc2ccccc2c1=O733100...0000900100
3AAA1CC(C)(c1ccc(O)cc1)c1ccc(O)cc11602000...00001300000
4AAA1CC(C)(C)c1cc(O)ccc1O1002000...0000700000
..................................................................
582BCCCSCCCCN=C=S320300...0000010100
583BCCCCCN=C=S220100...0000010000
584BCCCS(=O)CCCCC#N410200...0000100000
585BCCCSCCCCC#N410200...0000000100
586BCCC=CCSC#N210200...0000100100
\n", "

587 rows × 1096 columns

\n", "
" ], "text/plain": [ " target_name_bin target_name_ter target_name_quater \\\n", "0 A A A1 \n", "1 A A A1 \n", "2 A A A1 \n", "3 A A A1 \n", "4 A A A1 \n", ".. ... ... ... \n", "582 B C C \n", "583 B C C \n", "584 B C C \n", "585 B C C \n", "586 B C C \n", "\n", " smiles APC2D1_C_C APC2D1_C_N APC2D1_C_O \\\n", "0 Nc1ccccc1 6 1 0 \n", "1 COc1ccc(N)cc1 6 1 2 \n", "2 COP(=S)(OC)SCn1nnc2ccccc2c1=O 7 3 3 \n", "3 CC(C)(c1ccc(O)cc1)c1ccc(O)cc1 16 0 2 \n", "4 CC(C)(C)c1cc(O)ccc1O 10 0 2 \n", ".. ... ... ... ... \n", "582 CSCCCCN=C=S 3 2 0 \n", "583 CCCN=C=S 2 2 0 \n", "584 CS(=O)CCCCC#N 4 1 0 \n", "585 CSCCCCC#N 4 1 0 \n", "586 C=CCSC#N 2 1 0 \n", "\n", " APC2D1_C_S APC2D1_C_P APC2D1_C_F ... SubFPC303 SubFPC304 SubFPC305 \\\n", "0 0 0 0 ... 0 0 0 \n", "1 0 0 0 ... 0 0 0 \n", "2 1 0 0 ... 0 0 0 \n", "3 0 0 0 ... 0 0 0 \n", "4 0 0 0 ... 0 0 0 \n", ".. ... ... ... ... ... ... ... \n", "582 3 0 0 ... 0 0 0 \n", "583 1 0 0 ... 0 0 0 \n", "584 2 0 0 ... 0 0 0 \n", "585 2 0 0 ... 0 0 0 \n", "586 2 0 0 ... 0 0 0 \n", "\n", " SubFPC306 SubFPC307 bond:C=S_carbonyl_thio_generic \\\n", "0 0 6 0 \n", "1 0 6 0 \n", "2 0 9 0 \n", "3 0 13 0 \n", "4 0 7 0 \n", ".. ... ... ... \n", "582 0 0 1 \n", "583 0 0 1 \n", "584 0 1 0 \n", "585 0 0 0 \n", "586 0 1 0 \n", "\n", " bond:CN_amine_pri-NH2_aromatic bond:CS_sulfide \\\n", "0 1 0 \n", "1 1 0 \n", "2 0 1 \n", "3 0 0 \n", "4 0 0 \n", ".. ... ... \n", "582 0 1 \n", "583 0 0 \n", "584 0 0 \n", "585 0 1 \n", "586 0 1 \n", "\n", " bond:S=O_sulfonyl_generic ring:hetero_[6_6]_O_benzopyrone_(1_4-) \n", "0 0 0 \n", "1 0 0 \n", "2 0 0 \n", "3 0 0 \n", "4 0 0 \n", ".. ... ... \n", "582 0 0 \n", "583 0 0 \n", "584 0 0 \n", "585 0 0 \n", "586 0 0 \n", "\n", "[587 rows x 1096 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "APCFP" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "target_bin = APCFP.loc[:, 'target_name_bin']" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "target_bin = pd.DataFrame(target_bin)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "target_ter = APCFP.loc[:, 'target_name_ter']" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "target_ter = pd.DataFrame(target_ter)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "target_quater = APCFP.loc[:, 'target_name_quater']\n", "target_quater = pd.DataFrame(target_quater)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
target_name_ter
0A
1A
2A
3A
4A
......
582C
583C
584C
585C
586C
\n", "

587 rows × 1 columns

\n", "
" ], "text/plain": [ " target_name_ter\n", "0 A\n", "1 A\n", "2 A\n", "3 A\n", "4 A\n", ".. ...\n", "582 C\n", "583 C\n", "584 C\n", "585 C\n", "586 C\n", "\n", "[587 rows x 1 columns]" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "target_ter" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
target_name_quater
0A1
1A1
2A1
3A1
4A1
......
582C
583C
584C
585C
586C
\n", "

587 rows × 1 columns

\n", "
" ], "text/plain": [ " target_name_quater\n", "0 A1\n", "1 A1\n", "2 A1\n", "3 A1\n", "4 A1\n", ".. ...\n", "582 C\n", "583 C\n", "584 C\n", "585 C\n", "586 C\n", "\n", "[587 rows x 1 columns]" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "target_quater" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "features = APCFP.loc[:, 'APC2D1_C_C':'ring:hetero_[6_6]_O_benzopyrone_(1_4-)']" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
APC2D1_C_CAPC2D1_C_NAPC2D1_C_OAPC2D1_C_SAPC2D1_C_PAPC2D1_C_FAPC2D1_C_ClAPC2D1_C_BrAPC2D1_C_IAPC2D1_C_B...SubFPC303SubFPC304SubFPC305SubFPC306SubFPC307bond:C=S_carbonyl_thio_genericbond:CN_amine_pri-NH2_aromaticbond:CS_sulfidebond:S=O_sulfonyl_genericring:hetero_[6_6]_O_benzopyrone_(1_4-)
06100000000...0000601000
16120000000...0000601000
27331000000...0000900100
316020000000...00001300000
410020000000...0000700000
..................................................................
5823203000000...0000010100
5832201000000...0000010000
5844102000000...0000100000
5854102000000...0000000100
5862102000000...0000100100
\n", "

587 rows × 1092 columns

\n", "
" ], "text/plain": [ " APC2D1_C_C APC2D1_C_N APC2D1_C_O APC2D1_C_S APC2D1_C_P APC2D1_C_F \\\n", "0 6 1 0 0 0 0 \n", "1 6 1 2 0 0 0 \n", "2 7 3 3 1 0 0 \n", "3 16 0 2 0 0 0 \n", "4 10 0 2 0 0 0 \n", ".. ... ... ... ... ... ... \n", "582 3 2 0 3 0 0 \n", "583 2 2 0 1 0 0 \n", "584 4 1 0 2 0 0 \n", "585 4 1 0 2 0 0 \n", "586 2 1 0 2 0 0 \n", "\n", " APC2D1_C_Cl APC2D1_C_Br APC2D1_C_I APC2D1_C_B ... SubFPC303 \\\n", "0 0 0 0 0 ... 0 \n", "1 0 0 0 0 ... 0 \n", "2 0 0 0 0 ... 0 \n", "3 0 0 0 0 ... 0 \n", "4 0 0 0 0 ... 0 \n", ".. ... ... ... ... ... ... \n", "582 0 0 0 0 ... 0 \n", "583 0 0 0 0 ... 0 \n", "584 0 0 0 0 ... 0 \n", "585 0 0 0 0 ... 0 \n", "586 0 0 0 0 ... 0 \n", "\n", " SubFPC304 SubFPC305 SubFPC306 SubFPC307 \\\n", "0 0 0 0 6 \n", "1 0 0 0 6 \n", "2 0 0 0 9 \n", "3 0 0 0 13 \n", "4 0 0 0 7 \n", ".. ... ... ... ... \n", "582 0 0 0 0 \n", "583 0 0 0 0 \n", "584 0 0 0 1 \n", "585 0 0 0 0 \n", "586 0 0 0 1 \n", "\n", " bond:C=S_carbonyl_thio_generic bond:CN_amine_pri-NH2_aromatic \\\n", "0 0 1 \n", "1 0 1 \n", "2 0 0 \n", "3 0 0 \n", "4 0 0 \n", ".. ... ... \n", "582 1 0 \n", "583 1 0 \n", "584 0 0 \n", "585 0 0 \n", "586 0 0 \n", "\n", " bond:CS_sulfide bond:S=O_sulfonyl_generic \\\n", "0 0 0 \n", "1 0 0 \n", "2 1 0 \n", "3 0 0 \n", "4 0 0 \n", ".. ... ... \n", "582 1 0 \n", "583 0 0 \n", "584 0 0 \n", "585 1 0 \n", "586 1 0 \n", "\n", " ring:hetero_[6_6]_O_benzopyrone_(1_4-) \n", "0 0 \n", "1 0 \n", "2 0 \n", "3 0 \n", "4 0 \n", ".. ... \n", "582 0 \n", "583 0 \n", "584 0 \n", "585 0 \n", "586 0 \n", "\n", "[587 rows x 1092 columns]" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "features" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "from imblearn.over_sampling import *\n", "import joblib\n", "from sklearn.ensemble import VotingClassifier" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# AtomPairCount_Binary" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "seed=28\n", "X_train_bin, X_test_bin, y_train_bin, y_test_bin = train_test_split(features, target_bin, test_size=0.2, random_state=seed, stratify=target_bin)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Hard Voting" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "bin_rf_pca = joblib.load(\"Binary_APC_RF_PCA.pkl\")\n", "bin_xgb_pca = joblib.load(\"Binary_APC_XGB_PCA.pkl\")\n", "bin_ann_lda = joblib.load(\"Binary_APC_ANN_LDA.pkl\")\n", "bin_rf_lda = joblib.load(\"Binary_APC_RF_LDA.pkl\")\n", "\n", "vot_bin = VotingClassifier(estimators=[('rf_pca', bin_rf_pca),\n", " ('xgb_pca', bin_xgb_pca),\n", " ('ann_lda', bin_ann_lda),\n", " ('rf_lda', bin_rf_lda)], voting='hard')" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 11.9s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 43.9s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.7min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.9min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 300 candidates, totalling 1500 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 2.1s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 6.4s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 13.6s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 24.5s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 38.2s\n", "[Parallel(n_jobs=-1)]: Done 1442 tasks | elapsed: 54.3s\n", "[Parallel(n_jobs=-1)]: Done 1500 out of 1500 | elapsed: 56.4s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 25 candidates, totalling 125 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 18.8s\n", "[Parallel(n_jobs=-1)]: Done 125 out of 125 | elapsed: 42.3min finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 5.2s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 33.7s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.3min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.4min finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('rf_pca',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True,\n", " iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " svd...\n", " warm_start=False))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [1,\n", " 2,\n", " 3],\n", " 'classifier__max_depth': [5,\n", " 10,\n", " 20,\n", " 40,\n", " 80],\n", " 'classifier__n_estimators': [200,\n", " 400,\n", " 800,\n", " 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='hard',\n", " weights=None)" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_bin.fit(X_train_bin, y_train_bin.values.ravel())" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "pred_bin = vot_bin.predict(X_test_bin)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.6635\n" ] } ], "source": [ "from sklearn import metrics\n", "testscore_bin = metrics.f1_score(y_test_bin, pred_bin, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_bin))" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[89 8]\n", " [13 8]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_bin, pred_bin))" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Binary_APC_Vot_hard.pkl']" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_bin, \"Binary_APC_Vot_hard.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Soft Voting" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "bin_rf_pca = joblib.load(\"Binary_APC_RF_PCA.pkl\")\n", "bin_xgb_pca = joblib.load(\"Binary_APC_XGB_PCA.pkl\")\n", "bin_ann_lda = joblib.load(\"Binary_APC_ANN_LDA.pkl\")\n", "bin_rf_lda = joblib.load(\"Binary_APC_RF_LDA.pkl\")\n", "\n", "vot_bin_soft = VotingClassifier(estimators=[('rf_pca', bin_rf_pca),\n", " ('xgb_pca', bin_xgb_pca),\n", " ('ann_lda', bin_ann_lda),\n", " ('rf_lda', bin_rf_lda)], voting='soft')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 4.3s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 33.7s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.4min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.5min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 300 candidates, totalling 1500 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 1.0s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 4.9s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 11.3s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 20.2s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 31.8s\n", "[Parallel(n_jobs=-1)]: Done 1442 tasks | elapsed: 46.6s\n", "[Parallel(n_jobs=-1)]: Done 1500 out of 1500 | elapsed: 48.5s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 25 candidates, totalling 125 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 17.9s\n", "[Parallel(n_jobs=-1)]: Done 125 out of 125 | elapsed: 42.1min finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 5.0s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 31.0s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.2min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.4min finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('rf_pca',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True,\n", " iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " svd...\n", " warm_start=False))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [1,\n", " 2,\n", " 3],\n", " 'classifier__max_depth': [5,\n", " 10,\n", " 20,\n", " 40,\n", " 80],\n", " 'classifier__n_estimators': [200,\n", " 400,\n", " 800,\n", " 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='soft',\n", " weights=None)" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_bin_soft.fit(X_train_bin, y_train_bin.values.ravel())" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "pred_bin_soft = vot_bin_soft.predict(X_test_bin)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.5623\n" ] } ], "source": [ "from sklearn import metrics\n", "testscore_bin_soft = metrics.f1_score(y_test_bin, pred_bin_soft, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_bin_soft))" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[75 22]\n", " [13 8]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_bin, pred_bin_soft))" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Binary_APC_Vot_soft.pkl']" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_bin_soft, \"Binary_APC_Vot_soft.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# AtomPairCount_Ternary" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [], "source": [ "X_train_ter, X_test_ter, y_train_ter, y_test_ter = train_test_split(features, target_ter, test_size=0.2, random_state=seed, stratify=target_ter)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Hard Voting" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [], "source": [ "ter_xgb_lda = joblib.load(\"Ternary_APC_XGB_LDA.pkl\")\n", "ter_svm_lda = joblib.load(\"Ternary_APC_SVM_LDA.pkl\")\n", "ter_xgb_pca = joblib.load(\"Ternary_APC_XGB_PCA.pkl\")\n", "ter_rf_lda = joblib.load(\"Ternary_APC_RF_LDA.pkl\")\n", "\n", "vot_ter_hard = VotingClassifier(estimators=[('xgb_lda', ter_xgb_lda),\n", " ('svm_lda', ter_svm_lda),\n", " ('xgb_pca', ter_xgb_pca),\n", " ('rf_lda', ter_rf_lda)], voting='hard')" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 252 candidates, totalling 1260 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 7.8s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 12.9s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 21.0s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 33.3s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 47.1s\n", "[Parallel(n_jobs=-1)]: Done 1260 out of 1260 | elapsed: 56.8s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 288 candidates, totalling 1440 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 0.9s\n", "[Parallel(n_jobs=-1)]: Done 276 tasks | elapsed: 6.2s\n", "[Parallel(n_jobs=-1)]: Done 682 tasks | elapsed: 13.7s\n", "[Parallel(n_jobs=-1)]: Done 1248 tasks | elapsed: 23.9s\n", "[Parallel(n_jobs=-1)]: Done 1440 out of 1440 | elapsed: 27.4s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 192 candidates, totalling 960 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 1.3s\n", "[Parallel(n_jobs=-1)]: Done 276 tasks | elapsed: 9.1s\n", "[Parallel(n_jobs=-1)]: Done 682 tasks | elapsed: 22.3s\n", "[Parallel(n_jobs=-1)]: Done 960 out of 960 | elapsed: 32.9s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 4.3s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 34.0s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.3min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.5min finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('xgb_lda',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('LDA',\n", " LinearDiscriminantAnalysis(n_components=None,\n", " priors=None,\n", " shrinkage=None,\n", " so...\n", " warm_start=False))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [1,\n", " 2,\n", " 3],\n", " 'classifier__max_depth': [5,\n", " 10,\n", " 20,\n", " 40,\n", " 80],\n", " 'classifier__n_estimators': [200,\n", " 400,\n", " 800,\n", " 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='hard',\n", " weights=None)" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_ter_hard.fit(X_train_ter, y_train_ter.values.ravel())" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [], "source": [ "pred_ter_hard = vot_ter_hard.predict(X_test_ter)" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.4862\n" ] } ], "source": [ "testscore_ter_hard = metrics.f1_score(y_test_ter, pred_ter_hard, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_ter_hard))" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[47 15 9]\n", " [12 10 4]\n", " [ 2 10 9]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_ter, pred_ter_hard))" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Ternary_APC_Vot_hard.pkl']" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_ter_hard, \"Ternary_APC_Vot_hard.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Soft Voting" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [], "source": [ "ter_xgb_lda = joblib.load(\"Ternary_APC_XGB_LDA.pkl\")\n", "ter_svm_lda = joblib.load(\"Ternary_APC_SVM_LDA.pkl\")\n", "ter_xgb_pca = joblib.load(\"Ternary_APC_XGB_PCA.pkl\")\n", "ter_rf_lda = joblib.load(\"Ternary_APC_RF_LDA.pkl\")\n", "\n", "vot_ter_soft = VotingClassifier(estimators=[('xgb_lda', ter_xgb_lda),\n", " ('svm_lda', ter_svm_lda),\n", " ('xgb_pca', ter_xgb_pca),\n", " ('rf_lda', ter_rf_lda)], voting='soft')" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 252 candidates, totalling 1260 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 14.1s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 18.9s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 26.9s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 38.5s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 53.3s\n", "[Parallel(n_jobs=-1)]: Done 1260 out of 1260 | elapsed: 1.1min finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 288 candidates, totalling 1440 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 0.8s\n", "[Parallel(n_jobs=-1)]: Done 276 tasks | elapsed: 5.3s\n", "[Parallel(n_jobs=-1)]: Done 682 tasks | elapsed: 12.8s\n", "[Parallel(n_jobs=-1)]: Done 1248 tasks | elapsed: 23.4s\n", "[Parallel(n_jobs=-1)]: Done 1440 out of 1440 | elapsed: 27.0s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 192 candidates, totalling 960 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 1.5s\n", "[Parallel(n_jobs=-1)]: Done 276 tasks | elapsed: 9.6s\n", "[Parallel(n_jobs=-1)]: Done 682 tasks | elapsed: 23.3s\n", "[Parallel(n_jobs=-1)]: Done 960 out of 960 | elapsed: 34.4s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 4.2s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 34.1s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.4min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.5min finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('xgb_lda',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('LDA',\n", " LinearDiscriminantAnalysis(n_components=None,\n", " priors=None,\n", " shrinkage=None,\n", " so...\n", " warm_start=False))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [1,\n", " 2,\n", " 3],\n", " 'classifier__max_depth': [5,\n", " 10,\n", " 20,\n", " 40,\n", " 80],\n", " 'classifier__n_estimators': [200,\n", " 400,\n", " 800,\n", " 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='soft',\n", " weights=None)" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_ter_soft.fit(X_train_ter, y_train_ter.values.ravel())" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [], "source": [ "pred_ter_soft = vot_ter_soft.predict(X_test_ter)" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.4838\n" ] } ], "source": [ "testscore_ter_soft = metrics.f1_score(y_test_ter, pred_ter_soft, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_ter_soft))" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[46 16 9]\n", " [13 9 4]\n", " [ 2 9 10]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_ter, pred_ter_soft))" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Ternary_APC_Vot_soft.pkl']" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_ter_soft, \"Ternary_APC_Vot_soft.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# APC_Quaternary(w/o SMOTE)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "seed=28\n", "X_train_quater, X_test_quater, y_train_quater, y_test_quater = train_test_split(features, target_quater, test_size=0.2, random_state=seed, stratify=target_quater)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Hard Voting" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [], "source": [ "quater_svm_pca_smotx = joblib.load(\"Quaternary_APC_SVM_PCA_smotx.pkl\")\n", "quater_rf_pca_smotx = joblib.load(\"Quaternary_APC_RF_PCA_smotx.pkl\")\n", "quater_ann_pca_smotx = joblib.load(\"Quaternary_APC_ANN_PCA_smotx.pkl\")\n", "quater_ann_lda_smotx = joblib.load(\"Quaternary_APC_ANN_LDA_smotx.pkl\")\n", "\n", "vot_quater_smotx_hard = VotingClassifier(estimators=[('svm_pca', quater_svm_pca_smotx),\n", " ('rf_pca', quater_rf_pca_smotx),\n", " ('ann_pca', quater_ann_pca_smotx),\n", " ('ann_lda', quater_ann_lda_smotx)], voting='hard')" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 288 candidates, totalling 1440 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 0.6s\n", "[Parallel(n_jobs=-1)]: Done 276 tasks | elapsed: 3.9s\n", "[Parallel(n_jobs=-1)]: Done 682 tasks | elapsed: 9.5s\n", "[Parallel(n_jobs=-1)]: Done 1248 tasks | elapsed: 17.2s\n", "[Parallel(n_jobs=-1)]: Done 1440 out of 1440 | elapsed: 20.0s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 3.8s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 30.9s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.3min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.4min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 35 candidates, totalling 175 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 47.4s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 5.1min\n", "[Parallel(n_jobs=-1)]: Done 175 out of 175 | elapsed: 6.5min finished\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:470: ConvergenceWarning: lbfgs failed to converge (status=1):\n", "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n", "\n", "Increase the number of iterations (max_iter) or scale the data as shown in:\n", " https://scikit-learn.org/stable/modules/preprocessing.html\n", " self.n_iter_ = _check_optimize_result(\"lbfgs\", opt_res, self.max_iter)\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 35 candidates, totalling 175 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 3.7s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 20.5s\n", "[Parallel(n_jobs=-1)]: Done 175 out of 175 | elapsed: 29.7s finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('svm_pca',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True,\n", " iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " sv...\n", " 'classifier__activation': ['relu'],\n", " 'classifier__alpha': [0.005,\n", " 0.01,\n", " 0.05,\n", " 0.1,\n", " 0.5,\n", " 1,\n", " 5],\n", " 'classifier__hidden_layer_sizes': [(10,),\n", " (10,\n", " 10),\n", " (10,\n", " 10,\n", " 10),\n", " (10,\n", " 10,\n", " 10,\n", " 10),\n", " (10,\n", " 10,\n", " 10,\n", " 10,\n", " 10)],\n", " 'classifier__solver': ['sgd']}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='hard',\n", " weights=None)" ] }, "execution_count": 43, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_quater_smotx_hard.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [], "source": [ "pred_quater_smotx_hard = vot_quater_smotx_hard.predict(X_test_quater)" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.4902\n" ] } ], "source": [ "testscore_quater_smotx_hard = metrics.f1_score(y_test_quater, pred_quater_smotx_hard, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_smotx_hard))" ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[16 9 0 0]\n", " [ 7 29 5 5]\n", " [ 3 15 6 2]\n", " [ 0 12 0 9]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, pred_quater_smotx_hard))" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_Vot_hard_smotx.pkl']" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_quater_smotx_hard, \"Quaternary_APC_Vot_hard_smotx.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Soft Voting" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [], "source": [ "quater_svm_pca_smotx = joblib.load(\"Quaternary_APC_SVM_PCA_smotx.pkl\")\n", "quater_rf_pca_smotx = joblib.load(\"Quaternary_APC_RF_PCA_smotx.pkl\")\n", "quater_ann_pca_smotx = joblib.load(\"Quaternary_APC_ANN_PCA_smotx.pkl\")\n", "quater_ann_lda_smotx = joblib.load(\"Quaternary_APC_ANN_LDA_smotx.pkl\")\n", "\n", "vot_quater_smotx_soft = VotingClassifier(estimators=[('svm_pca', quater_svm_pca_smotx),\n", " ('rf_pca', quater_rf_pca_smotx),\n", " ('ann_pca', quater_ann_pca_smotx),\n", " ('ann_lda', quater_ann_lda_smotx)], voting='soft')" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 288 candidates, totalling 1440 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 12.2s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 14.1s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 17.3s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 21.7s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 27.3s\n", "[Parallel(n_jobs=-1)]: Done 1440 out of 1440 | elapsed: 34.0s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 3.9s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 31.2s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.3min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.4min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 35 candidates, totalling 175 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 46.5s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 5.1min\n", "[Parallel(n_jobs=-1)]: Done 175 out of 175 | elapsed: 6.5min finished\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:470: ConvergenceWarning: lbfgs failed to converge (status=1):\n", "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n", "\n", "Increase the number of iterations (max_iter) or scale the data as shown in:\n", " https://scikit-learn.org/stable/modules/preprocessing.html\n", " self.n_iter_ = _check_optimize_result(\"lbfgs\", opt_res, self.max_iter)\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 35 candidates, totalling 175 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 3.7s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 20.8s\n", "[Parallel(n_jobs=-1)]: Done 175 out of 175 | elapsed: 29.8s finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('svm_pca',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True,\n", " iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " sv...\n", " 'classifier__activation': ['relu'],\n", " 'classifier__alpha': [0.005,\n", " 0.01,\n", " 0.05,\n", " 0.1,\n", " 0.5,\n", " 1,\n", " 5],\n", " 'classifier__hidden_layer_sizes': [(10,),\n", " (10,\n", " 10),\n", " (10,\n", " 10,\n", " 10),\n", " (10,\n", " 10,\n", " 10,\n", " 10),\n", " (10,\n", " 10,\n", " 10,\n", " 10,\n", " 10)],\n", " 'classifier__solver': ['sgd']}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='soft',\n", " weights=None)" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_quater_smotx_soft.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [], "source": [ "pred_quater_smotx_soft = vot_quater_smotx_soft.predict(X_test_quater)" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.4801\n" ] } ], "source": [ "testscore_quater_smotx_soft = metrics.f1_score(y_test_quater, pred_quater_smotx_soft, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_smotx_soft))" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[14 10 1 0]\n", " [ 7 29 5 5]\n", " [ 1 14 9 2]\n", " [ 1 9 4 7]]\n" ] } ], "source": [ "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, pred_quater_smotx_soft))" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_Vot_soft_smotx.pkl']" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_quater_smotx_soft, \"Quaternary_APC_Vot_soft_smotx.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# RDKit_Quaternary (w/ SMOTE)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Hard Voting" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "quater_svm_pca_smot = joblib.load(\"Quaternary_APC_SVM_PCA_smot.pkl\")\n", "quater_ann_pca_smot = joblib.load(\"Quaternary_APC_ANN_PCA_smot.pkl\")\n", "quater_xgb_lda_smot = joblib.load(\"Quaternary_APC_XGB_LDA_smot.pkl\")\n", "quater_rf_pca_smot = joblib.load(\"Quaternary_APC_RF_PCA_smot.pkl\")\n", "\n", "vot_quater_smot_hard = VotingClassifier(estimators=[('svm_pca', quater_svm_pca_smot),\n", " ('ann_pca', quater_ann_pca_smot),\n", " ('xgb_pca', quater_xgb_lda_smot),\n", " ('rf_pca', quater_rf_pca_smot)], voting='hard')" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 288 candidates, totalling 1440 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 7.0s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 9.5s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 14.5s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 21.7s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 29.9s\n", "[Parallel(n_jobs=-1)]: Done 1440 out of 1440 | elapsed: 39.9s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 35 candidates, totalling 175 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 1.7min\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 8.7min\n", "[Parallel(n_jobs=-1)]: Done 175 out of 175 | elapsed: 10.1min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 405 candidates, totalling 2025 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 6.4s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 28.3s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.1min\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 2.0min\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 3.3min\n", "[Parallel(n_jobs=-1)]: Done 1442 tasks | elapsed: 4.8min\n", "[Parallel(n_jobs=-1)]: Done 1969 tasks | elapsed: 6.7min\n", "[Parallel(n_jobs=-1)]: Done 2025 out of 2025 | elapsed: 6.9min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 5.2s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 44.0s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.8min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 2.0min finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('svm_pca',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True,\n", " iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " sv...\n", " warm_start=False))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'PCA__n_components': [1,\n", " 2,\n", " 3],\n", " 'classifier__max_depth': [5,\n", " 10,\n", " 20,\n", " 40,\n", " 80],\n", " 'classifier__n_estimators': [200,\n", " 400,\n", " 800,\n", " 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='hard',\n", " weights=None)" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_quater_smot_hard.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "pred_quater_smot_hard = vot_quater_smot_hard.predict(X_test_quater)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.5026\n" ] } ], "source": [ "from sklearn import metrics\n", "testscore_quater_smot_hard = metrics.f1_score(y_test_quater, pred_quater_smot_hard, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_smot_hard))" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[16 6 2 1]\n", " [ 6 22 11 7]\n", " [ 2 8 10 6]\n", " [ 0 7 3 11]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, pred_quater_smot_hard))" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_Vot_hard_smot.pkl']" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_quater_smot_hard, \"Quaternary_APC_Vot_hard_smot.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Soft Voting" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "quater_svm_pca_smot = joblib.load(\"Quaternary_APC_SVM_PCA_smot.pkl\")\n", "quater_ann_pca_smot = joblib.load(\"Quaternary_APC_ANN_PCA_smot.pkl\")\n", "quater_xgb_lda_smot = joblib.load(\"Quaternary_APC_XGB_LDA_smot.pkl\")\n", "quater_rf_pca_smot = joblib.load(\"Quaternary_APC_RF_PCA_smot.pkl\")\n", "\n", "vot_quater_smot_soft = VotingClassifier(estimators=[('svm_pca', quater_svm_pca_smot),\n", " ('ann_pca', quater_ann_pca_smot),\n", " ('xgb_pca', quater_xgb_lda_smot),\n", " ('rf_pca', quater_rf_pca_smot)], voting='soft')" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 288 candidates, totalling 1440 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 8.4s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 11.1s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 15.5s\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 21.9s\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 30.8s\n", "[Parallel(n_jobs=-1)]: Done 1440 out of 1440 | elapsed: 41.4s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 35 candidates, totalling 175 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 1.6min\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 8.5min\n", "[Parallel(n_jobs=-1)]: Done 175 out of 175 | elapsed: 9.9min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 405 candidates, totalling 2025 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 7.1s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 31.2s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.2min\n", "[Parallel(n_jobs=-1)]: Done 632 tasks | elapsed: 2.2min\n", "[Parallel(n_jobs=-1)]: Done 997 tasks | elapsed: 3.6min\n", "[Parallel(n_jobs=-1)]: Done 1442 tasks | elapsed: 4.9min\n", "[Parallel(n_jobs=-1)]: Done 1969 tasks | elapsed: 6.6min\n", "[Parallel(n_jobs=-1)]: Done 2025 out of 2025 | elapsed: 6.8min finished\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 75 candidates, totalling 375 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 4.1s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 35.6s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 1.4min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 1.6min finished\n" ] }, { "data": { "text/plain": [ "VotingClassifier(estimators=[('svm_pca',\n", " GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=28, shuffle=True),\n", " error_score=nan,\n", " estimator=Pipeline(memory=None,\n", " steps=[('std',\n", " MinMaxScaler(copy=True,\n", " feature_range=(0,\n", " 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True,\n", " iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " sv...\n", " warm_start=False))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'PCA__n_components': [1,\n", " 2,\n", " 3],\n", " 'classifier__max_depth': [5,\n", " 10,\n", " 20,\n", " 40,\n", " 80],\n", " 'classifier__n_estimators': [200,\n", " 400,\n", " 800,\n", " 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', refit=True,\n", " return_train_score=False,\n", " scoring='f1_macro', verbose=2))],\n", " flatten_transform=True, n_jobs=None, voting='soft',\n", " weights=None)" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "vot_quater_smot_soft.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "pred_quater_smot_soft = vot_quater_smot_soft.predict(X_test_quater)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.5217\n" ] } ], "source": [ "from sklearn import metrics\n", "testscore_quater_smot_soft = metrics.f1_score(y_test_quater, pred_quater_smot_soft, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_smot_soft))" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[16 6 2 1]\n", " [ 5 22 9 10]\n", " [ 2 9 10 5]\n", " [ 0 5 3 13]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, pred_quater_smot_soft))" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_Vot_soft_smot.pkl']" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(vot_quater_smot_soft, \"Quaternary_APC_Vot_soft_smot.pkl\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.4" } }, "nbformat": 4, "nbformat_minor": 2 }