[23.07.21] 머신러닝(독버섯 찾기) - 36(2)

 

 

 

 

 

 

 

In [1]:

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split

mush = pd.read_csv('../../data/mushroom.csv', header=None)
mush.head()

 

Out[1]:

	0	1	2	3	4	5	6	7	8	9	...	13	14	15	16	17	18	19	20	21	22
0	p	x	s	n	t	p	f	c	n	k	...	s	w	w	p	w	o	p	k	s	u
1	e	x	s	y	t	a	f	c	b	k	...	s	w	w	p	w	o	p	n	n	g
2	e	b	s	w	t	l	f	c	b	n	...	s	w	w	p	w	o	p	n	n	m
3	p	x	y	w	t	p	f	c	n	n	...	s	w	w	p	w	o	p	k	s	u
4	e	x	s	g	f	n	f	w	b	k	...	s	w	w	p	w	o	e	n	a	g

5 rows × 23 columns

 

In [2]:

# 데이터 변환
from sklearn.preprocessing import LabelEncoder
encoding = LabelEncoder()
for col in mush.columns:
    mush[col] = encoding.fit_transform(mush[col])
mush.head()

 

Out[2]:

	0	1	2	3	4	5	6	7	8	9	...	13	14	15	16	17	18	19	20	21	22
0	1	5	2	4	1	6	1	0	1	4	...	2	7	7	0	2	1	4	2	3	5
1	0	5	2	9	1	0	1	0	0	4	...	2	7	7	0	2	1	4	3	2	1
2	0	0	2	8	1	3	1	0	0	5	...	2	7	7	0	2	1	4	3	2	3
3	1	5	3	8	1	6	1	0	1	5	...	2	7	7	0	2	1	4	2	3	5
4	0	5	2	3	0	5	1	1	0	4	...	2	7	7	0	2	1	0	3	0	1

5 rows × 23 columns

 

In [3]:

mush.corr()

 

Out[3]:

	0	1	2	3	4	5	6	7	8	9	...	13	14	15	16	17	18	19	20	21	22
0	1.000000	0.052951	0.178446	-0.031384	-0.501530	-0.093552	0.129200	-0.348387	0.540024	-0.530566	...	-0.298801	-0.154003	-0.146730	NaN	0.145142	-0.214366	-0.411771	0.171961	0.298686	0.217179
1	0.052951	1.000000	-0.050454	-0.048203	-0.035374	-0.021935	0.078865	0.013196	0.054050	-0.006039	...	-0.032591	-0.031659	-0.030390	NaN	0.072560	-0.106534	-0.025457	-0.073416	0.063413	-0.042221
2	0.178446	-0.050454	1.000000	-0.019402	0.070228	0.045233	-0.034180	-0.282306	0.208100	-0.161017	...	0.107965	0.066050	0.068885	NaN	-0.016603	-0.026147	-0.106407	0.230364	0.021555	0.163887
3	-0.031384	-0.048203	-0.019402	1.000000	-0.000764	-0.387121	0.041436	0.144259	-0.169464	0.084659	...	-0.047710	0.002364	0.008057	NaN	0.036130	-0.005822	0.162513	-0.293523	-0.144770	0.033925
4	-0.501530	-0.035374	0.070228	-0.000764	1.000000	-0.061825	0.137359	-0.299473	-0.369596	0.527120	...	0.458983	0.083538	0.092874	NaN	0.119770	0.056788	0.692973	-0.285008	0.088137	-0.075095
5	-0.093552	-0.021935	0.045233	-0.387121	-0.061825	1.000000	-0.059590	0.063936	0.310495	-0.129213	...	0.061820	0.174532	0.169407	NaN	-0.057747	0.111905	-0.281387	0.469055	-0.043623	-0.026610
6	0.129200	0.078865	-0.034180	0.041436	0.137359	-0.059590	1.000000	0.071489	0.108984	-0.128567	...	-0.116177	0.099299	0.097160	NaN	0.897518	0.093236	-0.146689	-0.029524	0.165575	-0.030304
7	-0.348387	0.013196	-0.282306	0.144259	-0.299473	0.063936	0.071489	1.000000	-0.108333	0.100193	...	-0.213775	0.274574	0.253505	NaN	0.073363	0.243014	-0.195897	0.047323	-0.529253	-0.154680
8	0.540024	0.054050	0.208100	-0.169464	-0.369596	0.310495	0.108984	-0.108333	1.000000	-0.516736	...	0.010894	0.296548	0.278708	NaN	0.103809	-0.171362	-0.460872	0.622991	0.147682	0.161418
9	-0.530566	-0.006039	-0.161017	0.084659	0.527120	-0.129213	-0.128567	0.100193	-0.516736	1.000000	...	0.257224	-0.058299	-0.074781	NaN	-0.097583	0.096054	0.629398	-0.416135	-0.034090	-0.202972
10	-0.102019	0.063794	-0.014123	-0.456496	0.099364	0.459766	0.186485	0.080895	0.214576	-0.175699	...	-0.034399	0.223439	0.235794	NaN	0.162604	-0.293221	-0.291444	0.258831	0.087383	-0.269216
11	-0.379361	0.030191	-0.126245	0.321274	0.244188	-0.205215	0.144063	0.350548	-0.344345	0.315080	...	0.087454	0.157140	0.159805	NaN	0.156213	-0.247357	0.210155	-0.536996	-0.306747	-0.007668
12	-0.334593	-0.030417	0.089090	-0.060837	0.460824	0.118617	-0.088916	-0.212359	0.056310	0.224287	...	0.437164	0.132708	0.142835	NaN	-0.090591	0.107904	0.390091	0.100764	0.079604	-0.058076
13	-0.298801	-0.032591	0.107965	-0.047710	0.458983	0.061820	-0.116177	-0.213775	0.010894	0.257224	...	1.000000	0.106933	0.110656	NaN	-0.077284	0.040006	0.394644	0.130974	0.046797	-0.039628
14	-0.154003	-0.031659	0.066050	0.002364	0.083538	0.174532	0.099299	0.274574	0.296548	-0.058299	...	0.106933	1.000000	0.491510	NaN	0.067377	0.084917	-0.048878	0.271533	-0.240261	0.042561
15	-0.146730	-0.030390	0.068885	0.008057	0.092874	0.169407	0.097160	0.253505	0.278708	-0.074781	...	0.110656	0.491510	1.000000	NaN	0.065567	0.087580	-0.034284	0.254518	-0.242792	0.041594
16	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
17	0.145142	0.072560	-0.016603	0.036130	0.119770	-0.057747	0.897518	0.073363	0.103809	-0.097583	...	-0.077284	0.067377	0.065567	NaN	1.000000	0.036380	-0.143673	-0.003600	0.124924	-0.040581
18	-0.214366	-0.106534	-0.026147	-0.005822	0.056788	0.111905	0.093236	0.243014	-0.171362	0.096054	...	0.040006	0.084917	0.087580	NaN	0.036380	1.000000	0.058312	0.338417	-0.242020	0.235835
19	-0.411771	-0.025457	-0.106407	0.162513	0.692973	-0.281387	-0.146689	-0.195897	-0.460872	0.629398	...	0.394644	-0.048878	-0.034284	NaN	-0.143673	0.058312	1.000000	-0.487048	0.211763	-0.212080
20	0.171961	-0.073416	0.230364	-0.293523	-0.285008	0.469055	-0.029524	0.047323	0.622991	-0.416135	...	0.130974	0.271533	0.254518	NaN	-0.003600	0.338417	-0.487048	1.000000	-0.126859	0.185954
21	0.298686	0.063413	0.021555	-0.144770	0.088137	-0.043623	0.165575	-0.529253	0.147682	-0.034090	...	0.046797	-0.240261	-0.242792	NaN	0.124924	-0.242020	0.211763	-0.126859	1.000000	-0.174529
22	0.217179	-0.042221	0.163887	0.033925	-0.075095	-0.026610	-0.030304	-0.154680	0.161418	-0.202972	...	-0.039628	0.042561	0.041594	NaN	-0.040581	0.235835	-0.212080	0.185954	-0.174529	1.000000

23 rows × 23 columns

 

 

2, 4번 열만 사용했을 때¶

 

In [4]:

data = mush[[2, 4]].to_numpy()
target = mush[0].to_numpy()

train_input, test_input, train_target, test_target = train_test_split(
    data, target, test_size=0.2, random_state=42
)

 

In [5]:

# random_forest
from sklearn.model_selection import cross_validate
from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(n_jobs=-1, random_state=42)
scores = cross_validate(rf, train_input, train_target,
                        return_train_score=True, n_jobs=-1)

print(np.mean(scores['train_score']), np.mean(scores['test_score']))
rf = RandomForestClassifier(oob_score=True, n_jobs=-1, random_state=42)

rf.fit(train_input, train_target)
print("RF_acc: {:.2f}%".format(rf.oob_score_*100))

 

 

0.7487305546924704 0.7487302658850004
RF_acc: 74.87%

 

In [6]:

# SVM
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
x_train, x_test, y_train, y_test = train_test_split(data, target, 
                                                    test_size=0.2, shuffle=True, stratify=target, random_state=2019)
svc = SVC()

svc.fit(x_train, y_train)
y_pred = svc.predict(x_test)
print('SVM_acc : {:.2f}%'.format(accuracy_score(y_test, y_pred)*100))

 

 

SVM_acc : 74.95%

 

 

모든 열 사용했을 때¶

 

In [7]:

data_all = mush.drop(0, axis=1).to_numpy()
target = mush[0].to_numpy()

# target = data['class']
# feature = data.drop('class',axis = 1)

train_input, test_input, train_target, test_target = train_test_split(
    data_all, target, test_size=0.2, random_state=42
)

 

In [8]:

# random_forest
from sklearn.model_selection import cross_validate
from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(n_jobs=-1, random_state=42)
scores = cross_validate(rf, train_input, train_target,
                        return_train_score=True, n_jobs=-1)

print(np.mean(scores['train_score']), np.mean(scores['test_score']))

rf = RandomForestClassifier(oob_score=True, n_jobs=-1, random_state=42)
rf.fit(train_input, train_target)
print("RF_acc: {:.2f}%".format(rf.oob_score_*100))

 

 

1.0 1.0
RF_acc: 100.00%

 

In [9]:

# SVM
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
x_train, x_test, y_train, y_test = train_test_split(data_all, target, 
                                                    test_size=0.2, shuffle=True, stratify=target, random_state=2019)
svc = SVC()

svc.fit(x_train, y_train)
y_pred = svc.predict(x_test)
print('SVM_acc : {:.2f}%'.format(accuracy_score(y_test, y_pred)*100))

 

 

SVM_acc : 99.08%