roboreport

%matplotlib inline
import matplotlib.pyplot as plt


y_pred = model.predict(X_test_t, batch_size=32)
plt.scatter(y_test, y_pred)
plt.xlabel("Price Index: $Y_i$")
plt.ylabel("Predicted price Index: $\hat{Y}_i$")
plt.title("Prices vs Predicted price Index: $Y_i$ vs $\hat{Y}_i$")

roboreport

from keras.layers import LSTM 
from keras.models import Sequential 
from keras.layers import Dense 
import keras.backend as K 
from keras.callbacks import EarlyStopping

K.clear_session()
    
model = Sequential() # Sequeatial Model 
model.add(LSTM(20, input_shape=(12, 1))) # (timestep, feature) 

roboreport

print(type(X_train))
X_train = X_train.values
print(type(X_train))
X_test= X_test.values
y_train = y_train.values
y_test = y_test.values
 

print(X_train.shape)
print(y_train.shape)

roboreport

X_train_t = X_train.reshape(X_train.shape[0], 12, 1)
X_test_t = X_test.reshape(X_test.shape[0], 12, 1)

print("최종 DATA")
print(X_train_t.shape)
print(X_train_t)
print(y_train)

roboreport

PSQL

Magic words:

psql -U postgres

Some interesting flags (to see all, use -h or --help depending on your psql version):

• -E: will describe the underlaying queries of the \ commands (cool for learning!)
• -l: psql will list all databases and then exit (useful if the user you connect with doesn't has a default database, like at AWS RDS)

roboreport

for s in range(1, 13):
    train_sc_df['shift_{}'.format(s)] = train_sc_df['trade_price_idx_value'].shift(s)
    test_sc_df['shift_{}'.format(s)] = test_sc_df['trade_price_idx_value'].shift(s)

train_sc_df.head(13)

roboreport

train_sc_df = pd.DataFrame(train_sc, columns=['trade_price_idx_value'], index=train.index)
test_sc_df = pd.DataFrame(test_sc, columns=['trade_price_idx_value'], index=test.index)
train_sc_df.head()

roboreport

from sklearn.preprocessing import MinMaxScaler

sc = MinMaxScaler()

train_sc = sc.fit_transform(train)
test_sc = sc.transform(test)

train_sc

roboreport

# 2017/1/1 까지의 데이터를 트레이닝셋.
# 그 이후 데이터를 테스트셋으로 한다.
split_date = pd.Timestamp('01-01-2017')


train = df.loc[:split_date, ['trade_price_idx_value']]
test = df.loc[split_date:, ['trade_price_idx_value']]

ax = train.plot()
test.plot(ax=ax)

roboreport

# 파일 업로드 기능 실행 
from google.colab import files
uploaded = files.upload() 

for fn in uploaded.keys():
  print('User uploaded file "{name}" with length {length} bytes'.format(name=fn, length=len(uploaded[fn])))