{ "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 sklearn.pipeline import FeatureUnion\n", "from imblearn.pipeline import make_pipeline, Pipeline\n", "from sklearn.preprocessing import MinMaxScaler\n", "from sklearn.model_selection import StratifiedKFold, GridSearchCV, RandomizedSearchCV, 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", "from sklearn.ensemble import AdaBoostClassifier" ] }, { "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": [ "PCA" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "pipe_ada_pca = Pipeline([(\"std\", MinMaxScaler()),\n", " (\"thresholder\", VarianceThreshold(threshold=0.01)),\n", " (\"PCA\", PCA()),\n", " (\"smote\", SMOTE(random_state=seed)),\n", " (\"classifier\", AdaBoostClassifier(random_state=seed))])" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "random_grid_pca = [{\"PCA__n_components\": [1, 2, 3],\n", " \"classifier__n_estimators\": [200, 400, 800, 1600, 3200],\n", " \"classifier__learning_rate\": [0.2, 0.4, 0.6, 0.8, 1.0]}]" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "cv = StratifiedKFold(n_splits=5, random_state=seed, shuffle=True)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "rand_ada_pca = RandomizedSearchCV(pipe_ada_pca, random_grid_pca, n_iter=50, cv=cv, random_state=seed, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 50 candidates, totalling 250 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: 16.2s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 53.5s\n", "[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed: 1.4min finished\n" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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_solver='auto', tol=0.0,\n", " whiten=Fal...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=50, n_jobs=-1,\n", " param_distributions=[{'PCA__n_components': [1, 2, 3],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.fit(X_train_bin, y_train_bin.values.ravel())" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.5308820037439792" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.best_score_" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 200,\n", " 'classifier__learning_rate': 0.6,\n", " 'PCA__n_components': 3}" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.best_params_" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "param_grid_pca_bin = [{\"PCA__n_components\": [3],\n", " \"classifier__n_estimators\": [50, 100, 200, 300],\n", " \"classifier__learning_rate\": [0.5, 0.6, 0.7]}]" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "clf_ada_pca_bin = GridSearchCV(pipe_ada_pca, param_grid_pca_bin, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 12 candidates, totalling 60 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: 1.4s\n", "[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 3.6s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True, iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " svd_solver='auto', tol=0.0,\n", " whiten=False)),\n", " (...\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'PCA__n_components': [3],\n", " 'classifier__learning_rate': [0.5, 0.6, 0.7],\n", " 'classifier__n_estimators': [50, 100, 200, 300]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_bin.fit(X_train_bin, y_train_bin.values.ravel())" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PCA__n_components': 3,\n", " 'classifier__learning_rate': 0.7,\n", " 'classifier__n_estimators': 300}" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_bin.best_params_" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.5318919125976331" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_bin.best_score_" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.5689\n" ] } ], "source": [ "from sklearn import metrics\n", "bin_pca_predict = clf_ada_pca_bin.predict(X_test_bin)\n", "testscore_bin_pca = metrics.f1_score(y_test_bin, bin_pca_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_bin_pca))" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[68 29]\n", " [10 11]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_bin, bin_pca_predict))" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Binary_APC_AdaB_PCA.pkl']" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import joblib\n", "joblib.dump(clf_ada_pca_bin, \"Binary_APC_AdaB_PCA.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "LDA" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [], "source": [ "pipe_ada_lda = Pipeline([(\"std\", MinMaxScaler()),\n", " (\"thresholder\", VarianceThreshold(threshold=0.01)),\n", " (\"LDA\", LinearDiscriminantAnalysis()),\n", " (\"smote\", SMOTE(random_state=seed)),\n", " (\"classifier\", AdaBoostClassifier(random_state=seed))])" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [], "source": [ "random_grid_lda_bin = [{\"LDA__n_components\": [1],\n", " \"classifier__n_estimators\": [200, 400, 800, 1600, 3200],\n", " \"classifier__learning_rate\": [0.2, 0.4, 0.6, 0.8, 1.0]}]" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [], "source": [ "rand_ada_lda_bin = RandomizedSearchCV(pipe_ada_lda, random_grid_lda_bin, n_iter=50, cv=cv, random_state=seed, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_search.py:281: UserWarning: The total space of parameters 25 is smaller than n_iter=50. Running 25 iterations. For exhaustive searches, use GridSearchCV.\n", " % (grid_size, self.n_iter, grid_size), UserWarning)\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: 6.5s\n", "[Parallel(n_jobs=-1)]: Done 125 out of 125 | elapsed: 42.4s finished\n" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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", " solver='svd',\n", " store_covariance=False,...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=50, n_jobs=-1,\n", " param_distributions=[{'LDA__n_components': [1],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_bin.fit(X_train_bin, y_train_bin.values.ravel())" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.6199672416647858" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_bin.best_score_" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 800,\n", " 'classifier__learning_rate': 0.2,\n", " 'LDA__n_components': 1}" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_bin.best_params_" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [], "source": [ "param_grid_lda_bin = [{\"LDA__n_components\": [1],\n", " \"classifier__n_estimators\": [600, 800, 1000, 1200, 1400],\n", " \"classifier__learning_rate\": [0.1, 0.2, 0.3]}]" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [], "source": [ "clf_ada_lda_bin = GridSearchCV(pipe_ada_lda, param_grid_lda_bin, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 15 candidates, totalling 75 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: 18.8s\n", "[Parallel(n_jobs=-1)]: Done 75 out of 75 | elapsed: 32.1s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('LDA',\n", " LinearDiscriminantAnalysis(n_components=None,\n", " priors=None,\n", " shrinkage=None,\n", " solver='svd',\n", " store_covariance=False,\n", " tol=0....\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [1],\n", " 'classifier__learning_rate': [0.1, 0.2, 0.3],\n", " 'classifier__n_estimators': [600, 800, 1000, 1200,\n", " 1400]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_bin.fit(X_train_bin, y_train_bin.values.ravel())" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'LDA__n_components': 1,\n", " 'classifier__learning_rate': 0.2,\n", " 'classifier__n_estimators': 800}" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_bin.best_params_" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.6199672416647858" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_bin.best_score_" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.5851\n" ] } ], "source": [ "bin_lda_predict = clf_ada_lda_bin.predict(X_test_bin)\n", "testscore_bin_lda = metrics.f1_score(y_test_bin, bin_lda_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_bin_lda))" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[73 24]\n", " [11 10]]\n" ] } ], "source": [ "print(\"오차 행렬: \\n\", confusion_matrix(y_test_bin, bin_lda_predict))" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Binary_APC_AdaB_LDA.pkl']" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(clf_ada_lda_bin, \"Binary_APC_AdaB_LDA.pkl\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# AtomPairCount_Ternary" ] }, { "cell_type": "code", "execution_count": 46, "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": [ "PCA" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 50 candidates, totalling 250 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: 10.1s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 50.1s\n", "[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed: 1.4min finished\n" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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_solver='auto', tol=0.0,\n", " whiten=Fal...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=50, n_jobs=-1,\n", " param_distributions=[{'PCA__n_components': [1, 2, 3],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.fit(X_train_ter, y_train_ter.values.ravel())" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3820138280191391" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.best_score_" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 200,\n", " 'classifier__learning_rate': 1.0,\n", " 'PCA__n_components': 3}" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.best_params_" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [], "source": [ "param_grid_pca_ter = [{\"PCA__n_components\": [3],\n", " \"classifier__n_estimators\": [50, 100, 200, 300],\n", " \"classifier__learning_rate\": [0.9, 1.0]}]" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [], "source": [ "clf_ada_pca_ter = GridSearchCV(pipe_ada_pca, param_grid_pca_ter, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 8 candidates, totalling 40 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: 1.5s\n", "[Parallel(n_jobs=-1)]: Done 40 out of 40 | elapsed: 2.5s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True, iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " svd_solver='auto', tol=0.0,\n", " whiten=False)),\n", " (...\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'PCA__n_components': [3],\n", " 'classifier__learning_rate': [0.9, 1.0],\n", " 'classifier__n_estimators': [50, 100, 200, 300]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_ter.fit(X_train_ter, y_train_ter.values.ravel())" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PCA__n_components': 3,\n", " 'classifier__learning_rate': 1.0,\n", " 'classifier__n_estimators': 50}" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_ter.best_params_" ] }, { "cell_type": "code", "execution_count": 54, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.39323965955360646" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_ter.best_score_" ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.3881\n" ] } ], "source": [ "ter_pca_predict = clf_ada_pca_ter.predict(X_test_ter)\n", "testscore_ter_pca = metrics.f1_score(y_test_ter, ter_pca_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_ter_pca))" ] }, { "cell_type": "code", "execution_count": 56, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[34 23 14]\n", " [11 8 7]\n", " [ 6 6 9]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_ter, ter_pca_predict))" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Ternary_APC_AdaB_PCA.pkl']" ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(clf_ada_pca_ter, 'Ternary_APC_AdaB_PCA.pkl')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "LDA" ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [], "source": [ "random_grid_lda_ter = [{\"LDA__n_components\": [1, 2],\n", " \"classifier__n_estimators\": [200, 400, 800, 1600, 3200],\n", " \"classifier__learning_rate\": [0.2, 0.4, 0.6, 0.8, 1.0]}]" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "rand_ada_lda_ter = RandomizedSearchCV(pipe_ada_lda, random_grid_lda_ter, n_iter=100, cv=cv, random_state=seed, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_search.py:281: UserWarning: The total space of parameters 50 is smaller than n_iter=100. Running 50 iterations. For exhaustive searches, use GridSearchCV.\n", " % (grid_size, self.n_iter, grid_size), UserWarning)\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 50 candidates, totalling 250 fits\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 7.3s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 50.3s\n", "[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed: 1.5min finished\n" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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", " solver='svd',\n", " store_covariance=False,...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=100, n_jobs=-1,\n", " param_distributions=[{'LDA__n_components': [1, 2],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 60, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_ter.fit(X_train_ter, y_train_ter.values.ravel())" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.4715210460226621" ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_ter.best_score_" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 200,\n", " 'classifier__learning_rate': 0.2,\n", " 'LDA__n_components': 2}" ] }, "execution_count": 62, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_ter.best_params_" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [], "source": [ "param_grid_lda_ter = [{\"LDA__n_components\": [2],\n", " \"classifier__n_estimators\": [50, 100, 200, 300],\n", " \"classifier__learning_rate\": [0.1, 0.2, 0.3]}]" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [], "source": [ "clf_ada_lda_ter = GridSearchCV(pipe_ada_lda, param_grid_lda_ter, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 12 candidates, totalling 60 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: 1.4s\n", "[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 3.8s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('LDA',\n", " LinearDiscriminantAnalysis(n_components=None,\n", " priors=None,\n", " shrinkage=None,\n", " solver='svd',\n", " store_covariance=False,\n", " tol=0....\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [2],\n", " 'classifier__learning_rate': [0.1, 0.2, 0.3],\n", " 'classifier__n_estimators': [50, 100, 200, 300]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_ter.fit(X_train_ter, y_train_ter.values.ravel())" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'LDA__n_components': 2,\n", " 'classifier__learning_rate': 0.1,\n", " 'classifier__n_estimators': 200}" ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_ter.best_params_" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.48105004504960985" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_ter.best_score_" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.4167\n" ] } ], "source": [ "from sklearn import metrics\n", "ter_lda_predict = clf_ada_lda_ter.predict(X_test_ter)\n", "testscore_ter_lda = metrics.f1_score(y_test_ter, ter_lda_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_ter_lda))" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[46 15 10]\n", " [13 6 7]\n", " [ 3 10 8]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_ter, ter_lda_predict))" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Ternary_APC_AdaB_LDA.pkl']" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import joblib\n", "joblib.dump(clf_ada_lda_ter, 'Ternary_APC_AdaB_LDA.pkl')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Quaternary(w/o SMOTE)" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [], "source": [ "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": [ "PCA" ] }, { "cell_type": "code", "execution_count": 72, "metadata": {}, "outputs": [], "source": [ "pipe_ada_pca_smotx = Pipeline([(\"std\", MinMaxScaler()),\n", " (\"thresholder\", VarianceThreshold(threshold=0.01)),\n", " (\"PCA\", PCA()),\n", " (\"classifier\", AdaBoostClassifier(random_state=seed))])" ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [], "source": [ "rand_ada_pca_smotx = RandomizedSearchCV(pipe_ada_pca_smotx, random_grid_pca, n_iter=100, cv=cv, random_state=seed, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_search.py:281: UserWarning: The total space of parameters 75 is smaller than n_iter=100. Running 75 iterations. For exhaustive searches, use GridSearchCV.\n", " % (grid_size, self.n_iter, grid_size), UserWarning)\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: 5.9s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 42.0s\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" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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_solver='auto', tol=0.0,\n", " whiten=Fal...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=100, n_jobs=-1,\n", " param_distributions=[{'PCA__n_components': [1, 2, 3],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 74, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca_smotx.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 76, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3121702948564985" ] }, "execution_count": 76, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca_smotx.best_score_" ] }, { "cell_type": "code", "execution_count": 77, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 200,\n", " 'classifier__learning_rate': 1.0,\n", " 'PCA__n_components': 3}" ] }, "execution_count": 77, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca_smotx.best_params_" ] }, { "cell_type": "code", "execution_count": 78, "metadata": {}, "outputs": [], "source": [ "param_grid_pca_quater = [{\"PCA__n_components\": [3],\n", " \"classifier__n_estimators\": [50, 100, 200, 300],\n", " \"classifier__learning_rate\": [0.9, 1.0]}]" ] }, { "cell_type": "code", "execution_count": 79, "metadata": {}, "outputs": [], "source": [ "clf_ada_pca_smotx = GridSearchCV(pipe_ada_pca_smotx, param_grid_pca_quater, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 80, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 8 candidates, totalling 40 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: 1.3s\n", "[Parallel(n_jobs=-1)]: Done 40 out of 40 | elapsed: 2.2s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True, iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " svd_solver='auto', tol=0.0,\n", " whiten=False)),\n", " (...\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'PCA__n_components': [3],\n", " 'classifier__learning_rate': [0.9, 1.0],\n", " 'classifier__n_estimators': [50, 100, 200, 300]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 80, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_smotx.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 81, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PCA__n_components': 3,\n", " 'classifier__learning_rate': 0.9,\n", " 'classifier__n_estimators': 50}" ] }, "execution_count": 81, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_smotx.best_params_" ] }, { "cell_type": "code", "execution_count": 82, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.32215983649989444" ] }, "execution_count": 82, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_smotx.best_score_" ] }, { "cell_type": "code", "execution_count": 83, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.3580\n" ] } ], "source": [ "quater_pca_predict = clf_ada_pca_smotx.predict(X_test_quater)\n", "testscore_quater_pca = metrics.f1_score(y_test_quater, quater_pca_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_pca))" ] }, { "cell_type": "code", "execution_count": 84, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[ 7 12 5 1]\n", " [ 7 25 10 4]\n", " [ 2 13 9 2]\n", " [ 2 9 5 5]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, quater_pca_predict))" ] }, { "cell_type": "code", "execution_count": 85, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_AdaB_PCA_smotx.pkl']" ] }, "execution_count": 85, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(clf_ada_pca_smotx, 'Quaternary_APC_AdaB_PCA_smotx.pkl')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "LDA" ] }, { "cell_type": "code", "execution_count": 86, "metadata": {}, "outputs": [], "source": [ "random_grid_lda_quater = [{\"LDA__n_components\": [1, 2, 3],\n", " \"classifier__n_estimators\": [200, 400, 800, 1600, 3200],\n", " \"classifier__learning_rate\": [0.2, 0.4, 0.6, 0.8, 1.0]}]" ] }, { "cell_type": "code", "execution_count": 87, "metadata": {}, "outputs": [], "source": [ "pipe_ada_lda_smotx = Pipeline([(\"std\", MinMaxScaler()),\n", " (\"thresholder\", VarianceThreshold(threshold=0.01)),\n", " (\"LDA\", LinearDiscriminantAnalysis()),\n", " (\"classifier\", AdaBoostClassifier(random_state=seed))])" ] }, { "cell_type": "code", "execution_count": 88, "metadata": {}, "outputs": [], "source": [ "rand_ada_lda_smotx = RandomizedSearchCV(pipe_ada_lda_smotx, random_grid_lda_quater, n_iter=100, cv=cv, random_state=seed, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 89, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_search.py:281: UserWarning: The total space of parameters 75 is smaller than n_iter=100. Running 75 iterations. For exhaustive searches, use GridSearchCV.\n", " % (grid_size, self.n_iter, grid_size), UserWarning)\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: 5.8s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 42.0s\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" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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", " solver='svd',\n", " store_covariance=False,...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=100, n_jobs=-1,\n", " param_distributions=[{'LDA__n_components': [1, 2, 3],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 89, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_smotx.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 90, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3693152404348332" ] }, "execution_count": 90, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_smotx.best_score_" ] }, { "cell_type": "code", "execution_count": 91, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 200,\n", " 'classifier__learning_rate': 0.2,\n", " 'LDA__n_components': 2}" ] }, "execution_count": 91, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_smotx.best_params_" ] }, { "cell_type": "code", "execution_count": 92, "metadata": {}, "outputs": [], "source": [ "param_grid_lda_quater = [{\"LDA__n_components\": [2],\n", " \"classifier__n_estimators\": [50, 100, 200, 300],\n", " \"classifier__learning_rate\": [0.1, 0.2, 0.3]}]" ] }, { "cell_type": "code", "execution_count": 93, "metadata": {}, "outputs": [], "source": [ "clf_ada_lda_smotx = GridSearchCV(pipe_ada_lda_smotx, param_grid_lda_quater, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 94, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 12 candidates, totalling 60 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: 1.4s\n", "[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 3.6s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('LDA',\n", " LinearDiscriminantAnalysis(n_components=None,\n", " priors=None,\n", " shrinkage=None,\n", " solver='svd',\n", " store_covariance=False,\n", " tol=0....\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [2],\n", " 'classifier__learning_rate': [0.1, 0.2, 0.3],\n", " 'classifier__n_estimators': [50, 100, 200, 300]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 94, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_smotx.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 95, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'LDA__n_components': 2,\n", " 'classifier__learning_rate': 0.3,\n", " 'classifier__n_estimators': 100}" ] }, "execution_count": 95, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_smotx.best_params_" ] }, { "cell_type": "code", "execution_count": 96, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.39118734459450377" ] }, "execution_count": 96, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_smotx.best_score_" ] }, { "cell_type": "code", "execution_count": 97, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.4013\n" ] } ], "source": [ "quater_pca_predict = clf_ada_lda_smotx.predict(X_test_quater)\n", "testscore_quater_pca = metrics.f1_score(y_test_quater, quater_pca_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_pca))" ] }, { "cell_type": "code", "execution_count": 98, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[18 5 2 0]\n", " [10 20 8 8]\n", " [ 4 13 3 6]\n", " [ 2 5 5 9]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, quater_pca_predict))" ] }, { "cell_type": "code", "execution_count": 99, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_AdaB_LDA_smotx.pkl']" ] }, "execution_count": 99, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(clf_ada_lda_smotx, 'Quaternary_APC_AdaB_LDA_smotx.pkl')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Quaternary (w/ SMOTE)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "PCA" ] }, { "cell_type": "code", "execution_count": 100, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 50 candidates, totalling 250 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: 10.3s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 55.4s\n", "[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed: 1.5min finished\n" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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_solver='auto', tol=0.0,\n", " whiten=Fal...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=50, n_jobs=-1,\n", " param_distributions=[{'PCA__n_components': [1, 2, 3],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 100, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 101, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3178850027046884" ] }, "execution_count": 101, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.best_score_" ] }, { "cell_type": "code", "execution_count": 102, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 3200,\n", " 'classifier__learning_rate': 0.4,\n", " 'PCA__n_components': 3}" ] }, "execution_count": 102, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_pca.best_params_" ] }, { "cell_type": "code", "execution_count": 103, "metadata": {}, "outputs": [], "source": [ "param_grid_pca_quater_smot = [{\"PCA__n_components\": [3],\n", " \"classifier__n_estimators\": [1800, 2000, 2200, 2400, 2600, 2800, 3000, 3200, 3500],\n", " \"classifier__learning_rate\": [0.3, 0.4, 0.5]}]" ] }, { "cell_type": "code", "execution_count": 104, "metadata": {}, "outputs": [], "source": [ "clf_ada_pca_quater_smot = GridSearchCV(pipe_ada_pca, param_grid_pca_quater_smot, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 105, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 27 candidates, totalling 135 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: 21.6s\n", "[Parallel(n_jobs=-1)]: Done 135 out of 135 | elapsed: 1.8min finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('PCA',\n", " PCA(copy=True, iterated_power='auto',\n", " n_components=None,\n", " random_state=None,\n", " svd_solver='auto', tol=0.0,\n", " whiten=False)),\n", " (...\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'PCA__n_components': [3],\n", " 'classifier__learning_rate': [0.3, 0.4, 0.5],\n", " 'classifier__n_estimators': [1800, 2000, 2200, 2400,\n", " 2600, 2800, 3000, 3200,\n", " 3500]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 105, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_quater_smot.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 106, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PCA__n_components': 3,\n", " 'classifier__learning_rate': 0.4,\n", " 'classifier__n_estimators': 3500}" ] }, "execution_count": 106, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_quater_smot.best_params_" ] }, { "cell_type": "code", "execution_count": 107, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3186674356753133" ] }, "execution_count": 107, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_pca_quater_smot.best_score_" ] }, { "cell_type": "code", "execution_count": 108, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.3800\n" ] } ], "source": [ "quater_smot_pca_predict = clf_ada_pca_quater_smot.predict(X_test_quater)\n", "testscore_quater_smot_pca = metrics.f1_score(y_test_quater, quater_smot_pca_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_smot_pca))" ] }, { "cell_type": "code", "execution_count": 109, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[13 8 3 1]\n", " [12 14 12 8]\n", " [ 3 12 7 4]\n", " [ 4 5 2 10]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, quater_smot_pca_predict))" ] }, { "cell_type": "code", "execution_count": 110, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_AdaB_PCA_smot.pkl']" ] }, "execution_count": 110, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(clf_ada_pca_quater_smot, 'Quaternary_APC_AdaB_PCA_smot.pkl')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "LDA" ] }, { "cell_type": "code", "execution_count": 111, "metadata": {}, "outputs": [], "source": [ "rand_ada_lda_quater = RandomizedSearchCV(pipe_ada_lda, random_grid_lda_quater, n_iter=100, cv=cv, random_state=seed, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 112, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_search.py:281: UserWarning: The total space of parameters 75 is smaller than n_iter=100. Running 75 iterations. For exhaustive searches, use GridSearchCV.\n", " % (grid_size, self.n_iter, grid_size), UserWarning)\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: 13.3s\n", "[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 55.1s\n", "[Parallel(n_jobs=-1)]: Done 349 tasks | elapsed: 2.3min\n", "[Parallel(n_jobs=-1)]: Done 375 out of 375 | elapsed: 2.5min finished\n" ] }, { "data": { "text/plain": [ "RandomizedSearchCV(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", " solver='svd',\n", " store_covariance=False,...\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_iter=100, n_jobs=-1,\n", " param_distributions=[{'LDA__n_components': [1, 2, 3],\n", " 'classifier__learning_rate': [0.2, 0.4,\n", " 0.6, 0.8,\n", " 1.0],\n", " 'classifier__n_estimators': [200, 400,\n", " 800, 1600,\n", " 3200]}],\n", " pre_dispatch='2*n_jobs', random_state=28, refit=True,\n", " return_train_score=False, scoring='f1_macro', verbose=2)" ] }, "execution_count": 112, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_quater.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 113, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3802628461880527" ] }, "execution_count": 113, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_quater.best_score_" ] }, { "cell_type": "code", "execution_count": 114, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'classifier__n_estimators': 200,\n", " 'classifier__learning_rate': 0.2,\n", " 'LDA__n_components': 3}" ] }, "execution_count": 114, "metadata": {}, "output_type": "execute_result" } ], "source": [ "rand_ada_lda_quater.best_params_" ] }, { "cell_type": "code", "execution_count": 115, "metadata": {}, "outputs": [], "source": [ "param_grid_lda_quater_smot = [{\"LDA__n_components\": [3],\n", " \"classifier__n_estimators\": [50, 100, 200, 300],\n", " \"classifier__learning_rate\": [0.1, 0.2, 0.3]}]" ] }, { "cell_type": "code", "execution_count": 116, "metadata": {}, "outputs": [], "source": [ "clf_ada_lda_quater_smot = GridSearchCV(pipe_ada_lda, param_grid_lda_quater_smot, cv=cv, scoring='f1_macro', verbose=2, n_jobs=-1)" ] }, { "cell_type": "code", "execution_count": 117, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 12 candidates, totalling 60 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: 9.1s\n", "[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 11.3s finished\n" ] }, { "data": { "text/plain": [ "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, 1))),\n", " ('thresholder',\n", " VarianceThreshold(threshold=0.01)),\n", " ('LDA',\n", " LinearDiscriminantAnalysis(n_components=None,\n", " priors=None,\n", " shrinkage=None,\n", " solver='svd',\n", " store_covariance=False,\n", " tol=0....\n", " AdaBoostClassifier(algorithm='SAMME.R',\n", " base_estimator=None,\n", " learning_rate=1.0,\n", " n_estimators=50,\n", " random_state=28))],\n", " verbose=False),\n", " iid='deprecated', n_jobs=-1,\n", " param_grid=[{'LDA__n_components': [3],\n", " 'classifier__learning_rate': [0.1, 0.2, 0.3],\n", " 'classifier__n_estimators': [50, 100, 200, 300]}],\n", " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", " scoring='f1_macro', verbose=2)" ] }, "execution_count": 117, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_quater_smot.fit(X_train_quater, y_train_quater.values.ravel())" ] }, { "cell_type": "code", "execution_count": 118, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'LDA__n_components': 3,\n", " 'classifier__learning_rate': 0.1,\n", " 'classifier__n_estimators': 100}" ] }, "execution_count": 118, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_quater_smot.best_params_" ] }, { "cell_type": "code", "execution_count": 119, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.38368499383433113" ] }, "execution_count": 119, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clf_ada_lda_quater_smot.best_score_" ] }, { "cell_type": "code", "execution_count": 120, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "f1 score (test): 0.3908\n" ] } ], "source": [ "quater_smot_lda_predict = clf_ada_lda_quater_smot.predict(X_test_quater)\n", "testscore_quater_smot_lda = metrics.f1_score(y_test_quater, quater_smot_lda_predict, average='macro')\n", "\n", "print(\"f1 score (test): {:.4f}\".format(testscore_quater_smot_lda))" ] }, { "cell_type": "code", "execution_count": 121, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "오차 행렬: \n", " [[17 5 3 0]\n", " [13 14 6 13]\n", " [ 5 6 6 9]\n", " [ 1 3 7 10]]\n" ] } ], "source": [ "from sklearn.metrics import confusion_matrix\n", "print(\"오차 행렬: \\n\", confusion_matrix(y_test_quater, quater_smot_lda_predict))" ] }, { "cell_type": "code", "execution_count": 122, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['Quaternary_APC_AdaB_LDA_smot.pkl']" ] }, "execution_count": 122, "metadata": {}, "output_type": "execute_result" } ], "source": [ "joblib.dump(clf_ada_lda_quater_smot, 'Quaternary_APC_AdaB_LDA_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 }