[DL] 딥러닝 기초

TIL

 

- 회귀 가설함수 > Wx+b

- 회귀 비용함수 > 경사하강: 그라디언트~

 

- 분류 가설함수 > 1/ 1-e^(-wx+b) -> 0~1 사이의 값으로 바꿈

    -시그모이드: 바이너리  
- 분류 비용함수->

    -소프트맥스: 다중분류 - proba
    -크로스엔트로피: CE - onehot encoding, proba에서 가장 확률 높은 것만 최고(1) 나머지 0

    -소프트맥스 안에 시그모이드 포함

 

- 분류/회귀 딥러닝

- 라이브러리 호출

import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
import matplotlib.pyplot as plt
from keras.utils import to_categorical
import tensorflow as tf
from sklearn.model_selection import train_test_split
import warnings
warnings.filterwarnings(action='ignore')
from sklearn.datasets import load_iris
from sklearn.datasets import load_boston

 

- iris : 다중분류

dataset  = load_iris()
print(dataset .keys())


df = pd.DataFrame(data=dataset.data,
                  #columns=dataset.feature_names
                  columns=['sepal_length', 'sepal_width', 'petal_length', 'petal_width']
                  )
df["target"] = dataset.target

X = df.iloc[: , :-1]
y = df.iloc[: , -1]

y_oh = to_categorical(y) 

X_train,X_test,y_train,y_test = train_test_split(X, y, test_size=0.2, random_state=160)

model = Sequential()
model.add(Dense(units=64, input_dim=4, activation='relu'))   
model.add(Dense(units=3,               activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X, y_oh, epochs=200, validation_split=0.1)

proba = model.predict(X_test)
pred = np.argmax(proba, axis=1)
eval = model.evaluate(X, y_oh)

 

- boston price : 회귀

from sklearn.datasets import load_boston

data = load_boston()
df = pd.DataFrame(data =data.data ,  columns=data.feature_names)
df["price"] = data.target

X = df.iloc[: , :-1]
y = df.iloc[: , -1]

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=160)

model = Sequential()
model.add(Dense(units=128, input_dim=13, activation='relu'))
model.add(Dense(units=64,  activation='relu'))
model.add(Dense(units=16,  activation='relu'))
model.add(Dense(units=1))
model.compile(loss='mean_squared_error', optimizer='adam')

model.fit(X_train,y_train,epochs=100, batch_size=100)
pred = model.predict(X_test).flatten()