Classifier

• Iris Data Classifier
• Dry bean Data Classifier

---

■ Iris Data Classifier (분류기)

import numpy as np
import matplotlib.pyplot as plt

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

import tensorflow as tf
from tensorflow import keras

1. 데이터 로딩

: iris data를 불러온 뒤, X,y를 train/test set으로 split 한다

X, y = load_iris(return_X_y =True)
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=10)

2. 데이터 확인

print(X_train.shape)
# (112, 4)

print(X_train[:5])
# [[4.8 3.4 1.9 0.2]
#  [6.4 2.7 5.3 1.9]
#  [5.7 2.6 3.5 1. ]
#  [4.6 3.6 1.  0.2]
#  [5.6 3.  4.1 1.3]]

print(y_train)
# [0 2 1 0 1 1 2 1 1 1 2 0 2 2 1 2 0 2 0 2 0 1 1 1 0 1 0 2 2 1 1 2 0 0 0 1 0
#  0 0 1 1 2 0 2 1 0 2 1 0 0 2 0 2 0 0 0 1 2 1 0 1 2 1 0 1 1 2 1 1 0 1 2 1 0
#  2 2 2 1 0 2 2 1 1 2 1 2 1 2 0 0 0 0 0 2 1 2 2 2 0 0 1 0 1 2 2 2 0 2 0 2 0
#  1]

3. 분류 모델 생성 & 적합

model = keras.Sequential([
    keras.layers.InputLayer(input_shape=[4,]),
    keras.layers.Dense(64, activation ='relu'),
    keras.layers.Dense(32, activation ='relu'),
    keras.layers.Dense(3) # iris는 3개로 분류해야하기 떄문에, 예측해야하는 category 개수만큼 output함
])

model.compile(optimizer = 'adam', # learning_rate는 defalut 값
             loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True), 
             metrics=['accuracy']) 

h=model.fit(X_train,y_train,epochs=50)

4. 정확도 & loss값 시각화

_,axe = plt.subplots()
axe.plot(h.history['accuracy'])
axe.plot(h.history['loss'])

---

■ DryBean Data Classifier (분류기)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split

import tensorflow as tf
from tensorflow import keras

1. 데이터 로딩

data = pd.read_csv('Dry_Bean_Dataset.csv')
data.head()

X : ShapeFactor1, ShapeFactor2, ShapeFactor3, ShapeFactor4
y : Class

# X
X = data.iloc[:,12:16]


# y
encoder = LabelEncoder()
y = encoder.fit_transform(data['Class'])
# y = data['Class'].astype('category').cat.codes


# train, test set split
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=10)

2. 데이터 확인

print(X_train.shape)
# (10208, 4)

print(X_train.head())

print(np.unique(y))
# [0 1 2 3 4 5 6]

y 는 label encoding 이 제대로 되었고, X 는 따로 scaling 은 하지 않겠다.

3. 모델 생성 & fit

model = keras.Sequential([
    keras.layers.InputLayer(input_shape=[4,]),
    keras.layers.Dense(12, activation = 'relu'),
    keras.layers.Dense(7) #output layer, activation X, 7 가지로 분류.
])

model.compile(optimizer = keras.optimizers.Adam(learning_rate=0.01),
              loss = keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics =['accuracy']
              
model.summary()              

( 똑같은 정확도라면, parameter 개수가 적은 것이 더 좋은 모델이다 )

h = model.fit(X_train, y_train, epochs = 150)

4. 정확도 & loss값 시각화

_, axe = plt.subplots()
axe.plot(h.history['accuracy'])
axe.plot(h.history['loss'])

5. model evaluate

model.evaluate(X_test, y_test)

test data 에 대해서도 87% 의 정확도를 보이는 모델이다.