Python Colaboratory Ⅴ
CNN 豪ドル/円４時間足予測ファイル
CNN 豪ドル/円４時間足予測ファイル keras-go-cnn-4h.ipynb
の内容を表示します。
LSTM 豪ドル/円４時間足予測表示ファイル keras-go-lstm-4h.ipynb
との差分は赤字にしています。
import sys
sys.path.append(
'/content/drive/MyDrive/Colab Notebooks/my-modules'
)
import datetime
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from tensorflow import keras
from mplfinance.original_flavor import candlestick_ohlc
def addBusinessDays_4h(current_date, business_days_to_add_h):
# current_date : 処理する初日の日時 例) 2022-02-03 00:00:00
# business_days_to_add_h : 4時間ずつ延長する回数
cur_date8 = [] # 21/03/30 12～
cur_date4 = [] # 3/30
man_f = 1 #月曜フラグ 0 or 1
doyo_f = 0 #土曜フラグ 0 or 1
current_date0 = current_date
weekday0 = current_date0.weekday()
if(weekday0 == 0): #月
man_f = 0
while business_days_to_add_h > 0:
current_date += datetime.timedelta(hours=4)
weekday = current_date.weekday()
hour_doyo = current_date.hour
if weekday == 6: # sunday = 6
continue
if((weekday == 5) and (hour_doyo == 8)): #土
doyo_f = 1
if((weekday == 5) and (doyo_f == 1)): #土
continue
if((weekday == 0) and (man_f == 1)): #月
man_f = 0
continue
# 年/月/日 時刻として文字列にする処理
# 例 22/03/30 12～
e11 = current_date.strftime("%y/%m/%d %H")
e22 = e11.replace("/0", "/")
e22 = e22 + "～"
e33 = e22[3:] # 22/ 削除
cur_date8.append(e22)
cur_date4.append(e33)
business_days_to_add_h -= 1
return cur_date8, cur_date4
xl_df = pd.read_csv(
"drive/MyDrive/Colab Notebooks/my_data/colab_mane_chart_go_4h.csv",
encoding="cp932")
raw_data0 = xl_df["終値(売り)"].values
print("raw_data0.shape:", raw_data0.shape)
print("raw_data0")
print(raw_data0)
plt.plot(range(len(raw_data0)), raw_data0)
plt.show()
raw_data = raw_data0.copy()
# 行列の平均、標準偏差を求めます。
mean = np.mean(raw_data)
print("Mean", mean)
raw_data -= mean
std = np.std(raw_data)
print("Std ",std)
# 標準偏差値に変換
raw_data /= std
print("各標準偏差値")
print(raw_data)
# 連続デ－タとする。一つおきは、2
sampling_rate = 1
# 過去20間隔デ－タをひとまとまりとして時系列予測する
sequence_length = 20
delay = sampling_rate * sequence_length
print("delay:", delay)
batch_size = 32 # 適当
# 検証デ－タのスタ－ト値
num_half_samples = int(0.5 * len(raw_data))
train_dataset = keras.utils.timeseries_dataset_from_array(
raw_data,
targets=raw_data[delay:],
sampling_rate=sampling_rate,
sequence_length=sequence_length,
batch_size=batch_size,
)
val_dataset = keras.utils.timeseries_dataset_from_array(
raw_data[:-1],
targets=raw_data[delay:],
sampling_rate=sampling_rate,
sequence_length=sequence_length,
batch_size=batch_size,
start_index=num_half_samples,
)
test_dataset = keras.utils.timeseries_dataset_from_array(
raw_data,
targets=None,
sampling_rate=sampling_rate,
sequence_length=sequence_length,
batch_size=batch_size,
)
# numpy ndarray 配列に変換して表示
# 訓練デ－タセット表示
itr = 0
for samples, targets in train_dataset:
samples_n = samples.numpy()
targets_n = targets.numpy()
if itr == 0:
print("Start in-train:", samples_n[0])
print("Start tar-train:", targets_n[0])
itr = itr + 1
print("End in-train:", samples_n[-1])
print("End tar-train:", targets_n[-1])
# 検証デ－タセット表示
itv = 0
for samples_v, targets_v in val_dataset:
samples_vn = samples_v.numpy()
targets_vn = targets_v.numpy()
if itv == 0:
print("Start in-val:", samples_vn[0])
print("Start tar-val:", targets_vn[0])
itv = itv + 1
print("End in-val:", samples_vn[-1])
print("End tar-val:", targets_vn[-1])
# テストデ－タセット表示
i = 0
for inputs_t in test_dataset:
inputs_n = inputs_t.numpy()
if i == 0:
print("Start test:", inputs_n[0])
i = i + 1
print("End test:", inputs_n[-1])
from keras import layers
# from keras import initializers
inputs = keras.Input(shape=(sequence_length, 1))
# x = layers.LSTM(20, kernel_initializer='zeros')(inputs)
# 3行追加
x = layers.Conv1D(7, 15, activation="tanh")(inputs)
x = layers.MaxPooling1D(2)(x)
x = layers.GlobalAveragePooling1D()(x)
# カ－ネルサイズは 15 に微調整
outputs = layers.Dense(1)(x)
model = keras.Model(inputs, outputs)
print("モデルア－キテクチャ")
print(model.summary())
#---ここまで keras-test-52.ipynb
callbacks_list = [
keras.callbacks.EarlyStopping(
monitor="val_loss",
patience=6,
),
keras.callbacks.ModelCheckpoint(
"drive/MyDrive/Colab Notebooks/my_data/jena_dense_cnn_4h.keras",
save_best_only=True,
)
]
model.compile(optimizer="rmsprop", loss="mse", metrics=["mae"])
history = model.fit(
train_dataset,
epochs=40,
# verbose=0,
validation_data=val_dataset,
callbacks=callbacks_list)
loss = history.history["mae"] # 平均絶対誤差(MAE)
val_loss = history.history["val_mae"]
epochs = range(1, len(loss) + 1)
plt.plot(epochs, loss, "bo", label="Training MAE")
plt.plot(epochs, val_loss, "b", label="Validation MAE")
plt.title("Training and Validation MAE")
plt.legend()
plt.show()
#---ここまで keras-test-53.ipynb
model = keras.models.load_model(
"drive/MyDrive/Colab Notebooks/my_data/jena_dense_cnn_4h.keras")
pre = model.predict(test_dataset)
pre1 = np.reshape(pre, (-1))
print(f"Test 予測値:")
print(pre1)
future_test = inputs_t[-1:]
print("future_test 最初の配列値")
print(future_test)
future_result = []
for i in range(6):
test_data_f = np.reshape(future_test, (1, 20, 1))
batch_predict = model.predict(test_data_f)
future_test = np.delete(future_test, 0)
future_test = np.append(future_test, batch_predict)
future_result = np.append(future_result, batch_predict)
print("future_result :")
print(future_result)
# ここまで colab-21 まとめ
len_raw_data = len(raw_data)
xx1 = np.arange(sequence_length, len_raw_data + 1)
xx3 = np.arange(len_raw_data, len_raw_data + 6)
plt.plot(xx1, pre)
plt.plot(xx3, future_result)
plt.show()
#ここまで colab-22①まとめ
pre_chg = pre.copy()
pre_chg *= std
pre_chg += mean
pre_chg1 = np.reshape(pre_chg, (-1))
print("pre_chg1:")
print(pre_chg1)
f_result = future_result.copy()
f_result *= std
f_result += mean
print("f_result:")
print(f_result)
plt.plot(range(len(raw_data0)), raw_data0)
plt.plot(xx1, pre_chg)
plt.plot(xx3, f_result)
plt.show()
#ここまで colab-22②まとめ
# ここから４時間ロ－ソク足表示
Open = xl_df["始値(売り)"].values
High = xl_df["高値(売り)"].values
Low = xl_df["安値(売り)"].values
Close = xl_df["終値(売り)"].values
Date = xl_df["日付"].values
Idx = xl_df.index
# X 軸日付処理
xDate = []
xD = []
dayf = 0
for i, key in enumerate(Date):
day00 = str(key)[11:19]
if((dayf == 1) and (day00 == '00:00:00')):
dayf = 0
else:
if((dayf == 0) and (day00 == '00:00:00')):
e4 = str(key)[4:10]
e6 = e4.replace("/0", "/")
e8 = e6.lstrip("/")
xDate.append(e8)
xD.append(i)
dayf = 1
tstr = Date[-1]
if(dayf == 0):
e4l = tstr[7:14]
e6l = e4l.replace("/0", "/")
e8l = e6l.lstrip("/")
xDate.append(e8l)
xD.append(i)
# ロ－ソク４時間足表示
ohlc = zip(
Idx, Open, High, Low, Close)
fig = plt.figure(
figsize=(8.34, 5.56))
ax = fig.add_subplot(1,1,1) #④
ax.grid()
plt.plot(xx1, pre_chg)
plt.plot(xx3, f_result, 'bo')
candlestick_ohlc(
ax, ohlc, width=0.5, alpha = 1,
colorup='r', colordown='g')
plt.xticks(xD, xDate)
plt.title('AUS$ / JPY chart')
plt.xlabel('Date')
plt.ylabel('Yen')
plt.show
plt.savefig(
'colab_mane_chart_go_cnn_4h.png')
# ここから４時間足予測最終日時取得
tstr = Date[-1]
tdatetime = datetime.datetime.strptime(tstr, '%Y/%m/%d %H:%M:%S')
lastday = addBusinessDays_4h(tdatetime, 6)
lastday_pd = pd.DataFrame(lastday[0])
f_result_pd = pd.DataFrame(np.round(f_result, 3))
# 有効数字3桁に変更
df_concat = pd.concat([lastday_pd, f_result_pd], axis = 1)
df_concat.to_csv(
'colab_mane_chart_go_cnn_4h.csv',
header=False, index=False)
ここまで CNN 豪ドル/円４時間足予測ファイル keras-go-cnn-4h.ipynb がまとまりました。
引き続き本ファイルの動作確認をしていきます。