3주차 숙제&필기

import os
os.environ['KAGGLE_USERNAME'] = 'kimtaehyoung' # username
os.environ['KAGGLE_KEY'] = 'b2df7c93d9592d296c10473a1b452dce' # key

!kaggle datasets download -d oddrationale/mnist-in-csv
!unzip mnist-in-csv.zip

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Dense
from tensorflow.keras.optimizers import Adam, SGD
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import OneHotEncoder

train_df = pd.read_csv('mnist_train.csv')

train_df.head()

test_df = pd.read_csv('mnist_test.csv')

test_df.head()

plt.figure(figsize=(16, 10))
sns.countplot(train_df['label'])
plt.show()

train_df = train_df.astype(np.float32)
x_train = train_df.drop(columns=['label'], axis=1).values
y_train = train_df[['label']].values

test_df = test_df.astype(np.float32)
x_test = test_df.drop(columns=['label'], axis=1).values
y_test = test_df[['label']].values

print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

index = 1
plt.title(str(y_train[index]))
plt.imshow(x_train[index].reshape((28, 28)), cmap='gray')
plt.show()

encoder = OneHotEncoder()
y_train = encoder.fit_transform(y_train).toarray()
y_test = encoder.fit_transform(y_test).toarray()

print(y_train.shape)

x_train = x_train / 255.
x_test = x_test / 255.

input = Input(shape=(784,))
hidden = Dense(1024, activation='relu')(input)
hidden = Dense(512, activation='relu')(hidden)
hidden = Dense(256, activation='relu')(hidden)
output = Dense(10, activation='softmax')(hidden) #원핫 인코딩을 했으므로 24종류의 출력

model = Model(inputs=input, outputs=output)

model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.001), metrics=['acc'])

model.summary()

history = model.fit(
    x_train,
    y_train,
    validation_data=(x_test, y_test), # 검증 데이터를 넣어주면 한 epoch이 끝날때마다 자동으로 검증
    epochs=20 # epochs 복수형으로 쓰기!
)