Win11 WSL2 Ubuntu Python RNN
WSL2 Python RNN 予測ファイル動作確認
ここまで、WSL2 Python RNN 予測ファイル keras-go-long-4.py をまとめました。
引き続き keras-go-long-4.py の動作確認をします。
WSL2 Ubuntu のターミナルを立ち上げます。
立ち上げ方がわからない方は
Ubuntu の起動
を見てください。
yamada@yama:~$ conda activate
として conda 環境を有効にします。
public_html/dsc-6.py ファイルを実行します。
(base) yamada@yama:~$ python3 public_html/keras-go-long-4.py
[結果]-以下は例です。
mane_chart_go_long_long.csv の内容が変わると数値は変わります。
yamada@yama:~$ conda activate (base) yamada@yama:~$ python3 public_html/keras-go-long-4.py Mean 85.13142368473694 Std 8.438399031864476 各標準偏差値 [-1.05724127 -1.06672174 -1.04657574 ... 1.0360468 1.0019171 1.02561828] raw_data_100 [88.726 88.948 89.119 89.937 89.724 90.126 90.21 90.429 90.48 89.736 89.875 88.586 88.278 88.83 90.147 91.158 91.019 90.009 89.865 91.037 91.602 91.443 91.077 90.173 90.133 91.184 90.763 91.632 91.864 91.75 92.176 91.605 91.256 91.094 91.666 91.835 91.106 90.59 91.234 92.45 92.359 93.177 93.241 93.263 93.978 94.242 94.881 95.241 96.55 97.531 97.25 95.992 96.42 96.708 95.961 95.791 96.326 95.375 95.809 96.132 96.519 96.666 96.253 95.438 95.042 94.336 93.845 94.047 95.107 94.904 94.554 94.561 94.589 94.955 95.418 95.365 95.713 94.801 93.593 93.84 95.577 94.786 93.714 93.351 93.106 93.682 93.81 93.84 94.321 94.139 94.412 93.963 94.003 93.397 93.073 93.78 93.693 93.874 93.586 93.786] Mean_100 93.06537999999999 Std_100 2.3272030370382386 テストデータ各標準偏差値 std_100 [-1.86463318 -1.7692397 -1.69576094 -1.34426604 -1.43579221 -1.26305267 -1.22695784 -1.13285345 -1.11093874 -1.43063581 -1.37090746 -1.92479123 -2.05713894 -1.81994434 -1.25402896 -0.81960189 -0.87933024 -1.31332761 -1.37520446 -0.87159563 -0.62881492 -0.69713728 -0.85440762 -1.24285675 -1.26004476 -0.80842968 -0.98933353 -0.61592391 -0.51623343 -0.56521927 -0.38216691 -0.62752582 -0.77749125 -0.84710271 -0.6013141 -0.52869474 -0.84194631 -1.0636717 -0.78694466 -0.26442901 -0.30353175 0.04796316 0.07546398 0.08491739 0.39215315 0.50559405 0.78017258 0.93486471 1.49734249 1.91887855 1.79813275 1.25756969 1.44148145 1.56523515 1.24424898 1.17119992 1.40108961 0.99244456 1.17893452 1.31772774 1.48402178 1.54718774 1.36972149 1.01951569 0.84935434 0.54598588 0.335003 0.42180247 0.87728486 0.79005569 0.63966056 0.64266846 0.65470007 0.81197041 1.01092168 0.98814756 1.13768329 0.74579655 0.22671851 0.3328545 1.07924404 0.73935105 0.27871225 0.12273102 0.01745443 0.26496184 0.31996349 0.3328545 0.53954038 0.46133491 0.57864311 0.38570764 0.40289566 0.14249724 0.00327432 0.30707248 0.26968854 0.34746431 0.22371061 0.30965068] Start in-train: [ -1.05724127 -1.06672174 -1.04657574 -1.04539068 -1.10582868 -1.22670469 -1.20300351 -1.18285751 -1.18996787 -1.24803575 -1.21011387 -1.16863681 -1.14967586 -1.2409254 -1.07857233 -1.03709527 -0.92688479 -0.89370314 -0.84037549 -0.78586278] Start tar-train: -0.7894179523369962 End in-train: [ 1.0320176 1.23786233 1.14412417 1.01708586 0.97406822 0.94503428 1.01329367 1.02846242 1.0320176 1.08901893 1.06745086 1.09980297 1.04659382 1.05133406 0.97951949 0.94112358 1.02490725 1.01459723 1.0360468 1.0019171 ] End tar-train: 1.0256182816885369 Start in-val: [ -1.86463318 -1.7692397 -1.69576094 -1.34426604 -1.43579221 -1.26305267 -1.22695784 -1.13285345 -1.11093874 -1.43063581 -1.37090746 -1.92479123 -2.05713894 -1.81994434 -1.25402896 -0.81960189 -0.87933024 -1.31332761 -1.37520446 -0.87159563] Start tar-val: -0.6288149236271134 End in-val: [ 0.3328545 1.07924404 0.73935105 0.27871225 0.12273102 0.01745443 0.26496184 0.31996349 0.3328545 0.53954038 0.46133491 0.57864311 0.38570764 0.40289566 0.14249724 0.00327432 0.30707248 0.26968854 0.34746431 0.22371061] End tar-val: 0.30965067874658775 Start test: [ -1.86463318 -1.7692397 -1.69576094 -1.34426604 -1.43579221 -1.26305267 -1.22695784 -1.13285345 -1.11093874 -1.43063581 -1.37090746 -1.92479123 -2.05713894 -1.81994434 -1.25402896 -0.81960189 -0.87933024 -1.31332761 -1.37520446 -0.87159563] End test: [ 1.07924404 0.73935105 0.27871225 0.12273102 0.01745443 0.26496184 0.31996349 0.3328545 0.53954038 0.46133491 0.57864311 0.38570764 0.40289566 0.14249724 0.00327432 0.30707248 0.26968854 0.34746431 0.22371061 0.30965068] モデルア－キテクチャ Model: "model" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_1 (InputLayer) [(None, 20)] 0 flatten (Flatten) (None, 20) 0 dense (Dense) (None, 20) 420 dense_1 (Dense) (None, 1) 21 ================================================================= Total params: 441 Trainable params: 441 Non-trainable params: 0 _________________________________________________________________ None
ここでかなり時間がかかります
Test 予測値: Test 予測値: [-9.22546625e-01 -6.62727952e-01 -7.18995988e-01 -8.86030257e-01 -1.20736241e+00 -1.24990356e+00 -8.76434505e-01 -9.76507783e-01 -7.19702780e-01 -5.55999696e-01 -5.60498774e-01 -3.71592373e-01 -5.60216844e-01 -7.59494364e-01 -8.69689286e-01 -6.70934260e-01 -5.44846296e-01 -7.93700993e-01 -1.03735459e+00 -8.37548018e-01 -3.34925413e-01 -2.94343203e-01 -4.20210417e-04 7.85623491e-02 1.13331184e-01 3.81115854e-01 5.10015249e-01 7.49273360e-01 9.12294567e-01 1.40236795e+00 1.81572783e+00 1.79149818e+00 1.34030664e+00 1.40114832e+00 1.54078543e+00 1.30806875e+00 1.20363057e+00 1.38367462e+00 1.11623406e+00 1.20963228e+00 1.34724522e+00 1.49496293e+00 1.57068789e+00 1.42967939e+00 1.10609806e+00 9.27844882e-01 6.46333277e-01 3.90410691e-01 4.06692088e-01 8.27607453e-01 8.41858864e-01 6.93829596e-01 6.69117451e-01 6.93136990e-01 8.21974754e-01 1.00238824e+00 9.95363057e-01 1.12956095e+00 8.28771532e-01 3.04095775e-01 3.08210909e-01 9.80320275e-01 8.02692294e-01 3.27893734e-01 1.33972794e-01 7.35034943e-02 2.94754714e-01 3.44368815e-01 3.23639214e-01 5.21152377e-01 5.15945554e-01 6.07655048e-01 4.43653226e-01 4.13731337e-01 1.67564973e-01 -9.73033439e-03 2.53083825e-01 3.08683068e-01 3.63162577e-01 2.46870190e-01 2.93399096e-01] future_test 最初の配列値 tf.Tensor( [[1.07924404 0.73935105 0.27871225 0.12273102 0.01745443 0.26496184 0.31996349 0.3328545 0.53954038 0.46133491 0.57864311 0.38570764 0.40289566 0.14249724 0.00327432 0.30707248 0.26968854 0.34746431 0.22371061 0.30965068]], shape=(1, 20), dtype=float64) [ 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100] [100 101 102 103 104]
Idx_100 RangeIndex(start=0, stop=100, step=1)
これで WSL2 Python RNN 予測ファイルの動作確認がほぼできました。
引き続き、実デ－タをロ－ソク足表示し、その上に予測値をプロットしたチャートを確認します。