3.다중분류문제_1_아이리스

---

layout: single
title: "jupyter notebook 변환하기!"
categories: coding
tag: [python, blog, jekyll]
toc: true
author_profile: false

---

아이리스 품종 다중분류 예측 문제

---

import warnings
warnings.filterwarnings(action='ignore')

1. scikit-learn 패키지는 머신러닝 교육을 위한 최고의 파이썬 패키지입니다.

scikit-learn를 별칭(alias) sk로 임포트하는 코드를 작성하고 실행하세요.

# 여기에 답안코드를 작성하세요.
import sklearn as sk 

2. Pandas는 데이터 분석을 위해 널리 사용되는 파이썬 라이브러리입니다.

Pandas를 사용할 수 있도록 별칭(alias)을 pd로 해서 불러오세요.

# 여기에 답안코드를 작성하세요.
import pandas as pd 

3. 모델링을 위해 분석 및 처리할 데이터 파일을 읽어오려고 합니다.

Pandas함수로 데이터 파일을 읽어 데이터프레임 변수명 df에 할당하는 코드를 작성하세요.

path = 'https://raw.githubusercontent.com/khw11044/csv_dataset/master/iris.csv'
df = pd.read_csv(path)
df.head()

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa

데이터 설명

• 아이리스 품종 중 Setosa, Versicolor, Virginica 분류

• 꽃받침(Sepal)과 꽃잎(Petal)의 길이(Length)와 너비(Width)

• Sepal.Length: 꽃받침의 길이

• Sepal.Width: 꽃받침의 너비

• Petal.Length: 꽃잎의 길이

• Petal.Width: 꽃잎의 너비

다음 문항을 풀기 전에 아래 코드를 실행하세요.

# 여기에 답안코드를 작성하세요.
import seaborn as sns 
import matplotlib.pyplot as plt
plt.rcParams['font.family'] = 'Malgun Gothic'

df['Species'].value_counts()

Species
setosa        50
versicolor    50
virginica     50
Name: count, dtype: int64

4. Species(품종)별 컬럼들의 분포를 알고 싶습니다

Species(품종)별 컬럼들의 분포도를 그리세요

• Seaborn을 활용하세요.

• histplot 함수를 사용하세요

컬럼들 모도 똑같이

plt.figure(figsize=(16,4))
plt.subplot(1,4,1)
sns.histplot(x='Sepal.Length', data = df, bins=30, kde = True)
plt.title('Sepal.Length')

plt.subplot(1,4,2)
sns.histplot(x='Sepal.Length', data=df[df['Species']=='setosa'], bins=30, kde = True)
plt.title('setosa/Sepal.Length')

plt.subplot(1,4,3)
sns.histplot(x='Sepal.Length', data=df[df['Species']=='versicolor'], bins=30, kde = True)
plt.title('versicolor/Sepal.Length')

plt.subplot(1,4,4)
sns.histplot(x='Sepal.Length', data=df[df['Species']=='virginica'], bins=30, kde = True)
plt.title('virginica/Sepal.Length')

plt.show()
# 어릴 수록 살아남았다

plt.figure(figsize=(16,4))
plt.subplot(1,4,1)
sns.histplot(x='Sepal.Width', data = df, bins=30, kde = True)
plt.title('Sepal.Width')

plt.subplot(1,4,2)
sns.histplot(x='Sepal.Width', data=df[df['Species']=='setosa'], bins=30, kde = True)
plt.title('setosa/Sepal.Width')

plt.subplot(1,4,3)
sns.histplot(x='Sepal.Width', data=df[df['Species']=='versicolor'], bins=30, kde = True)
plt.title('versicolor/Sepal.Width')

plt.subplot(1,4,4)
sns.histplot(x='Sepal.Width', data=df[df['Species']=='virginica'], bins=30, kde = True)
plt.title('virginica/Sepal.Width')

plt.show()
# 어릴 수록 살아남았다

plt.figure(figsize=(16,4))
plt.subplot(1,4,1)
sns.histplot(x='Petal.Length', data = df, bins=30, kde = True)
plt.title('Petal.Length')

plt.subplot(1,4,2)
sns.histplot(x='Petal.Length', data=df[df['Species']=='setosa'], bins=30, kde = True)
plt.title('setosa/Petal.Length')

plt.subplot(1,4,3)
sns.histplot(x='Petal.Length', data=df[df['Species']=='versicolor'], bins=30, kde = True)
plt.title('versicolor/Petal.Length')

plt.subplot(1,4,4)
sns.histplot(x='Petal.Length', data=df[df['Species']=='virginica'], bins=30, kde = True)
plt.title('virginica/Petal.Length')

plt.show()
# 어릴 수록 살아남았다

5. 각 컬럼의 상관관계를 알아 보려고 합니다. 상관관계를 통해 필요없는 컬럼을 제거할 수 있습니다.

상관관계 히트맵을 그리세요.

• numeric_only를 통해 숫자형 컬럼들만 나타내세요

• cmap은 Blues로 하세요

• cbar는 보이지 않습니다

• 소수점은 소수점 3번째 자리 까지 나타내세요

df['Species'] = df['Species'].astype('category')
df['Species'] = df['Species'].cat.codes

df.head()

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species
0	5.1	3.5	1.4	0.2	0
1	4.9	3.0	1.4	0.2	0
2	4.7	3.2	1.3	0.2	0
3	4.6	3.1	1.5	0.2	0
4	5.0	3.6	1.4	0.2	0

# 여기에 답안코드를 작성하세요.

# 상관관계 시각화 
plt.figure(figsize=(6,6))
sns.heatmap(df.corr(numeric_only=True),
           annot=True,
           cmap='Blues',
           cbar=False, # 옆에 칼라 바 제거 
           square=True,
            fmt='.3f', # 소수점
            annot_kws={'size':9}
           )    
plt.show()

# PassengerId, Age, SibSp, Parch 컬럼은 제거한다.

6. 모델링 성능을 제대로 얻기 위해서 결측치 처리는 필수입니다.

아래 가이드를 따라 결측치 처리하세요.

• 대상 데이터프레임: df

• 결측치를 확인하는 코드를 작성하세요.

• 결측치가 있는 행(raw)를 삭제 하세요.

• 전처리 반영된 결과를 새로운 데이터프레임 변수명 df_na에 저장하세요.

# NaN 값 확인
df.isnull().sum()

Sepal.Length    0
Sepal.Width     0
Petal.Length    0
Petal.Width     0
Species         0
dtype: int64

7. 훈련과 검증 각각에 사용할 데이터셋을 분리하려고 합니다.

Species(품종) 컬럼을 label값 y로, 나머지 컬럼을 feature값 X로 할당한 후 훈련데이터셋과 검증데이터셋으로 분리하세요.

• 대상 데이터프레임: df_preset

• 훈련과 검증 데이터셋 분리

  • 훈련 데이터셋 label: y_train, 훈련 데이터셋 Feature: X_train

  • 검증 데이터셋 label: y_valid, 검증 데이터셋 Feature: X_valid

  • 훈련 데이터셋과 검증데이터셋 비율은 80:20

  • random_state: 42

  • Scikit-learn의 train_test_split 함수를 활용하세요.

• 스케일링 수행

  • sklearn.preprocessing의 MinMaxScaler 함수 사용

  • 훈련데이터셋의 Feature는 MinMaxScaler의 fit_transform 함수를 활용하여 X_train 변수로 할당

  • 검증데이터셋의 Feature는 MinMaxScaler의 transform 함수를 활용하여 X_valid 변수로 할당

# 여기에 답안코드를 작성하세요.
from sklearn.model_selection import train_test_split

target = 'Species'

x = df.drop(target, axis=1)
y = df[target]

X_train, X_valid, y_train, y_valid = train_test_split(x,y, test_size=0.2, random_state=42)
print(X_train.shape, X_valid.shape, y_train.shape, y_valid.shape)

(120, 4) (30, 4) (120,) (30,)

from sklearn.preprocessing import MinMaxScaler, StandardScaler, RobustScaler

scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_valid = scaler.transform(X_valid)

8. Species(품종)을 예측하는 머신러닝 모델을 만들려고 합니다.

아래 가이드에 따라 다음 모델을 만들고 학습을 진행하세요.

• 가장 성능이 좋은 모델 이름을 답안8 변수에 저장하세요

  • 예. 답안8 = 'KNeighborsClassifier' 혹은 'DecisionTreeClassifier' 혹은 'LogisticRegression' 혹은 'RandomForestClassifier' 등등

# 1단계: 불러오기
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from xgboost import XGBClassifier
from lightgbm import LGBMClassifier

from sklearn.metrics import confusion_matrix, classification_report, roc_auc_score

models = {
    "KNeighborsClassifier": {"model":KNeighborsClassifier(n_neighbors=5)},
    "DecisionTreeClassifier": {"model":DecisionTreeClassifier()},
    "LogisticRegression": {"model":LogisticRegression()},
    "RandomForestClassifier": {"model":RandomForestClassifier()},
    "XGBClassifier": {"model":XGBClassifier()},
    "LGBMClassifier": {"model":LGBMClassifier(verbose=-1)}
}

from time import perf_counter

# Train모델 학습
for name, model in models.items():
    model = model['model']
    start = perf_counter()

    history = model.fit(X_train, y_train)

    # 학습시간과 val_accuracy 저장
    duration = perf_counter() - start
    duration = round(duration,2)
    models[name]['perf'] = duration

    y_train_pred = model.predict(X_train)
    y_val_pred = model.predict(X_valid)

    train_score = round(model.score(X_train, y_train),4)
    val_score = round(model.score(X_valid, y_valid),4)

    models[name]['train_score'] = train_score
    models[name]['val_score'] = val_score

    print(f"{name:20} trained in {duration} sec, train_score: {train_score}. val_score: {val_score}")

# Create a DataFrame with the results
models_result = []

for name, v in models.items():
    models_result.append([ name, models[name]['val_score'], 
                          models[name]['perf']])

df_results = pd.DataFrame(models_result, 
                          columns = ['model','val_score','Training time (sec)'])
df_results.sort_values(by='val_score', ascending=False, inplace=True)
df_results.reset_index(inplace=True,drop=True)
df_results

KNeighborsClassifier trained in 0.0 sec, train_score: 0.9583. val_score: 1.0
DecisionTreeClassifier trained in 0.0 sec, train_score: 1.0. val_score: 1.0
LogisticRegression   trained in 0.0 sec, train_score: 0.925. val_score: 0.9667
RandomForestClassifier trained in 0.12 sec, train_score: 1.0. val_score: 1.0
XGBClassifier        trained in 0.04 sec, train_score: 1.0. val_score: 1.0
LGBMClassifier       trained in 0.02 sec, train_score: 1.0. val_score: 1.0

	model	val_score	Training time (sec)
0	KNeighborsClassifier	1.0000	0.00
1	DecisionTreeClassifier	1.0000	0.00
2	RandomForestClassifier	1.0000	0.12
3	XGBClassifier	1.0000	0.04
4	LGBMClassifier	1.0000	0.02
5	LogisticRegression	0.9667	0.00

def check_performance_for_model(df_results):
    plt.figure(figsize = (15,5))
    sns.barplot(x = 'model', y = 'val_score', data = df_results)
    plt.title('ACC (%) on the Test set', fontsize = 15)
    plt.ylim(0,1.2)
    plt.xticks(rotation=90)
    plt.show()

check_performance_for_model(df_results)

답안8='DecisionTreeClassifier'

from sklearn.metrics import roc_auc_score, accuracy_score

model = DecisionTreeClassifier()

# 3단계: 학습하기
model.fit(X_train, y_train)

# 4단계: 예측하기
y_pred = model.predict(X_valid)

# 5단계 평가하기
print(classification_report(y_valid, y_pred))
print('Acc Score :', accuracy_score(y_valid, y_pred))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00        10
           1       1.00      1.00      1.00         9
           2       1.00      1.00      1.00        11

    accuracy                           1.00        30
   macro avg       1.00      1.00      1.00        30
weighted avg       1.00      1.00      1.00        30

Acc Score : 1.0

9. Species(품종)을 예측하는 딥러닝 모델을 만들려고 합니다.

아래 가이드에 따라 모델링하고 학습을 진행하세요.

• Tensoflow framework를 사용하여 딥러닝 모델을 만드세요.

• 히든레이어(hidden layer) 2개이상으로 모델을 구성하세요.

• 손실함수는 sparse_categorical_crossentropy 사용하세요.

• 하이퍼파라미터 epochs: 100, batch_size: 16으로 설정해주세요.

• 각 에포크마다 loss와 metrics 평가하기 위한 데이터로 X_valid, y_valid 사용하세요.

• 학습정보는 history 변수에 저장해주세요

import tensorflow as tf
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Dense, Activation, Dropout, BatchNormalization
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint
from tensorflow.keras.utils import to_categorical
from keras.optimizers import Adam
# 규제를 위해 필요한 함수 불러오기
from tensorflow.keras.regularizers import l1, l2

tf.random.set_seed(1)

nfeatures = X_train.shape[1]
outputs = len(y_valid.unique())
# Sequential 모델 만들기
model = Sequential()

model.add(Dense(32, activation='relu', input_shape=(nfeatures,), kernel_regularizer = l1(0.01)))
model.add(Dense(16, activation='relu', kernel_regularizer = l1(0.01)))
model.add(Dense(outputs, activation= 'softmax'))

model.compile(optimizer=Adam(learning_rate=0.01), loss='sparse_categorical_crossentropy',metrics=['acc'])
# es = EarlyStopping(monitor='val_loss', patience=4, mode='min', verbose=1)    # val_loss

history = model.fit(X_train, y_train, 
                    batch_size=16, 
                    epochs=100, 
                    # callbacks=[es],
                    validation_data=(X_valid, y_valid), 
                    verbose=1).history

Epoch 1/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 1s 19ms/step - acc: 0.3737 - loss: 2.2113 - val_acc: 0.7000 - val_loss: 1.8303
Epoch 2/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.6438 - loss: 1.7456 - val_acc: 0.8667 - val_loss: 1.4972
Epoch 3/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.7135 - loss: 1.4258 - val_acc: 0.9000 - val_loss: 1.2199
Epoch 4/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.8479 - loss: 1.1587 - val_acc: 0.7000 - val_loss: 0.9891
Epoch 5/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.6864 - loss: 0.9592 - val_acc: 0.7000 - val_loss: 0.8371
Epoch 6/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.6608 - loss: 0.8298 - val_acc: 0.7333 - val_loss: 0.7154
Epoch 7/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.7440 - loss: 0.7199 - val_acc: 0.9333 - val_loss: 0.6398
Epoch 8/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9447 - loss: 0.6418 - val_acc: 0.9667 - val_loss: 0.5881
Epoch 9/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9717 - loss: 0.5892 - val_acc: 0.9667 - val_loss: 0.5408
Epoch 10/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9717 - loss: 0.5424 - val_acc: 0.9667 - val_loss: 0.4945
Epoch 11/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9731 - loss: 0.5010 - val_acc: 0.9667 - val_loss: 0.4578
Epoch 12/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9771 - loss: 0.4691 - val_acc: 0.9667 - val_loss: 0.4298
Epoch 13/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9771 - loss: 0.4427 - val_acc: 0.9667 - val_loss: 0.4088
Epoch 14/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9760 - loss: 0.4241 - val_acc: 0.9667 - val_loss: 0.3933
Epoch 15/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9800 - loss: 0.4092 - val_acc: 0.9667 - val_loss: 0.3807
Epoch 16/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9800 - loss: 0.3970 - val_acc: 0.9667 - val_loss: 0.3704
Epoch 17/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9800 - loss: 0.3868 - val_acc: 0.9667 - val_loss: 0.3627
Epoch 18/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9800 - loss: 0.3781 - val_acc: 0.9667 - val_loss: 0.3551
Epoch 19/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9800 - loss: 0.3701 - val_acc: 0.9667 - val_loss: 0.3475
Epoch 20/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9800 - loss: 0.3626 - val_acc: 0.9667 - val_loss: 0.3410
Epoch 21/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9800 - loss: 0.3562 - val_acc: 0.9667 - val_loss: 0.3350
Epoch 22/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.3501 - val_acc: 0.9667 - val_loss: 0.3297
Epoch 23/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.3443 - val_acc: 0.9667 - val_loss: 0.3246
Epoch 24/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.3394 - val_acc: 0.9667 - val_loss: 0.3201
Epoch 25/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.3346 - val_acc: 0.9667 - val_loss: 0.3159
Epoch 26/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.3298 - val_acc: 0.9667 - val_loss: 0.3114
Epoch 27/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.3246 - val_acc: 0.9667 - val_loss: 0.3070
Epoch 28/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.3199 - val_acc: 0.9667 - val_loss: 0.3021
Epoch 29/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.3151 - val_acc: 0.9667 - val_loss: 0.2980
Epoch 30/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.3107 - val_acc: 0.9667 - val_loss: 0.2942
Epoch 31/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.3064 - val_acc: 0.9667 - val_loss: 0.2897
Epoch 32/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.3021 - val_acc: 0.9667 - val_loss: 0.2869
Epoch 33/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9599 - loss: 0.2989 - val_acc: 0.9667 - val_loss: 0.2821
Epoch 34/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2939 - val_acc: 0.9667 - val_loss: 0.2782
Epoch 35/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - acc: 0.9642 - loss: 0.2897 - val_acc: 0.9667 - val_loss: 0.2747
Epoch 36/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2861 - val_acc: 0.9667 - val_loss: 0.2707
Epoch 37/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9599 - loss: 0.2821 - val_acc: 0.9667 - val_loss: 0.2665
Epoch 38/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2777 - val_acc: 0.9667 - val_loss: 0.2637
Epoch 39/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2748 - val_acc: 0.9667 - val_loss: 0.2600
Epoch 40/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2713 - val_acc: 0.9667 - val_loss: 0.2563
Epoch 41/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2676 - val_acc: 0.9667 - val_loss: 0.2527
Epoch 42/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2644 - val_acc: 0.9667 - val_loss: 0.2505
Epoch 43/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2618 - val_acc: 0.9667 - val_loss: 0.2472
Epoch 44/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2590 - val_acc: 0.9667 - val_loss: 0.2445
Epoch 45/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9670 - loss: 0.2562 - val_acc: 0.9667 - val_loss: 0.2423
Epoch 46/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2540 - val_acc: 0.9667 - val_loss: 0.2401
Epoch 47/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2517 - val_acc: 0.9667 - val_loss: 0.2380
Epoch 48/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2496 - val_acc: 0.9667 - val_loss: 0.2361
Epoch 49/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9670 - loss: 0.2477 - val_acc: 0.9667 - val_loss: 0.2339
Epoch 50/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2454 - val_acc: 0.9667 - val_loss: 0.2319
Epoch 51/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2433 - val_acc: 0.9667 - val_loss: 0.2298
Epoch 52/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2411 - val_acc: 0.9667 - val_loss: 0.2284
Epoch 53/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2394 - val_acc: 0.9667 - val_loss: 0.2265
Epoch 54/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2374 - val_acc: 0.9667 - val_loss: 0.2251
Epoch 55/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2354 - val_acc: 0.9667 - val_loss: 0.2234
Epoch 56/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2333 - val_acc: 0.9667 - val_loss: 0.2217
Epoch 57/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2315 - val_acc: 0.9667 - val_loss: 0.2202
Epoch 58/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2297 - val_acc: 0.9667 - val_loss: 0.2190
Epoch 59/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2284 - val_acc: 0.9667 - val_loss: 0.2175
Epoch 60/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2269 - val_acc: 0.9667 - val_loss: 0.2162
Epoch 61/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2253 - val_acc: 0.9667 - val_loss: 0.2152
Epoch 62/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2243 - val_acc: 0.9667 - val_loss: 0.2138
Epoch 63/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2230 - val_acc: 0.9667 - val_loss: 0.2129
Epoch 64/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2219 - val_acc: 0.9667 - val_loss: 0.2112
Epoch 65/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2204 - val_acc: 0.9667 - val_loss: 0.2098
Epoch 66/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2193 - val_acc: 0.9667 - val_loss: 0.2092
Epoch 67/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2182 - val_acc: 0.9667 - val_loss: 0.2077
Epoch 68/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2168 - val_acc: 0.9667 - val_loss: 0.2059
Epoch 69/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2157 - val_acc: 0.9667 - val_loss: 0.2050
Epoch 70/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2144 - val_acc: 0.9667 - val_loss: 0.2040
Epoch 71/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2133 - val_acc: 0.9667 - val_loss: 0.2028
Epoch 72/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2123 - val_acc: 0.9667 - val_loss: 0.2016
Epoch 73/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2112 - val_acc: 0.9667 - val_loss: 0.2003
Epoch 74/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2100 - val_acc: 0.9667 - val_loss: 0.1995
Epoch 75/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2093 - val_acc: 0.9667 - val_loss: 0.1986
Epoch 76/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2082 - val_acc: 0.9667 - val_loss: 0.1973
Epoch 77/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2074 - val_acc: 0.9667 - val_loss: 0.1974
Epoch 78/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2070 - val_acc: 0.9667 - val_loss: 0.1957
Epoch 79/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2056 - val_acc: 0.9667 - val_loss: 0.1947
Epoch 80/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2045 - val_acc: 0.9667 - val_loss: 0.1937
Epoch 81/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2036 - val_acc: 0.9667 - val_loss: 0.1935
Epoch 82/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2032 - val_acc: 0.9667 - val_loss: 0.1919
Epoch 83/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2018 - val_acc: 0.9667 - val_loss: 0.1910
Epoch 84/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.2011 - val_acc: 0.9667 - val_loss: 0.1903
Epoch 85/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.2004 - val_acc: 0.9667 - val_loss: 0.1892
Epoch 86/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.1993 - val_acc: 0.9667 - val_loss: 0.1879
Epoch 87/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1983 - val_acc: 0.9667 - val_loss: 0.1873
Epoch 88/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.1974 - val_acc: 0.9667 - val_loss: 0.1863
Epoch 89/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - acc: 0.9642 - loss: 0.1966 - val_acc: 0.9667 - val_loss: 0.1851
Epoch 90/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step - acc: 0.9642 - loss: 0.1956 - val_acc: 0.9667 - val_loss: 0.1844
Epoch 91/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1946 - val_acc: 0.9667 - val_loss: 0.1828
Epoch 92/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.1934 - val_acc: 0.9667 - val_loss: 0.1820
Epoch 93/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - acc: 0.9642 - loss: 0.1926 - val_acc: 0.9667 - val_loss: 0.1805
Epoch 94/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1914 - val_acc: 0.9667 - val_loss: 0.1796
Epoch 95/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1904 - val_acc: 0.9667 - val_loss: 0.1787
Epoch 96/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1897 - val_acc: 0.9667 - val_loss: 0.1777
Epoch 97/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1886 - val_acc: 0.9667 - val_loss: 0.1767
Epoch 98/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1875 - val_acc: 0.9667 - val_loss: 0.1753
Epoch 99/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1866 - val_acc: 0.9667 - val_loss: 0.1748
Epoch 100/100
8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - acc: 0.9642 - loss: 0.1859 - val_acc: 0.9667 - val_loss: 0.1735

# 함수로 만들어서 사용합시다.
def dl_history_plot(history):
    plt.figure(figsize=(16,4))
    plt.subplot(1,2,1)
    plt.plot(history['loss'], label='loss', marker = '.')
    plt.plot(history['val_loss'], label='val_loss', marker = '.')
    plt.ylabel('Loss')
    plt.xlabel('Epochs')
    plt.legend()
    plt.grid()

    plt.subplot(1,2,2)
    plt.plot(history['acc'], label='acc', marker = '.')
    plt.plot(history['val_acc'], label='val_acc', marker = '.')
    plt.ylabel('ACC')
    plt.xlabel('Epochs')
    plt.legend()
    plt.grid()


    plt.show()

dl_history_plot(history)

import numpy as np 
from sklearn.metrics import roc_auc_score, accuracy_score

pred = model.predict(X_valid)


print(classification_report(y_valid, y_pred))
print('Acc Score :', accuracy_score(y_valid, y_pred))

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step
              precision    recall  f1-score   support

           0       1.00      1.00      1.00        10
           1       1.00      1.00      1.00         9
           2       1.00      1.00      1.00        11

    accuracy                           1.00        30
   macro avg       1.00      1.00      1.00        30
weighted avg       1.00      1.00      1.00        30

Acc Score : 1.0

# 모듈 불러오기
from sklearn.metrics import precision_score

# 성능 평가
print('정밀도(Precision):', precision_score(y_valid, y_pred, average=None))
print('정밀도(Precision):', precision_score(y_valid, y_pred, average='macro'))
print('정밀도(Precision):', precision_score(y_valid, y_pred, average='weighted'))

정밀도(Precision): [1. 1. 1.]
정밀도(Precision): 1.0
정밀도(Precision): 1.0

# 모듈 불러오기
from sklearn.metrics import recall_score

# 성능 평가
print('각각 0과 1에 대한 재현율(Recall):', recall_score(y_valid, y_pred, average=None))

각각 0과 1에 대한 재현율(Recall): [1. 1. 1.]

# 모듈 불러오기
from sklearn.metrics import f1_score

# 성능 평가
print('각각 0과 1에 대한 F1 score:', f1_score(y_valid, y_pred, average=None))

각각 0과 1에 대한 F1 score: [1. 1. 1.]