Fix issues

Signed-off-by: Aadhitya A <[email protected]>

app-cuda.py

@@ -112,6 +112,7 @@ def modelCNNLSTM(csv_file, prax):
     trek = df.iloc[len(df)-100:,1:23]
     #print(temp_data)
     data = temp_data
+    data = data.values.astype("float64")
     sc = MinMaxScaler()
     # Split the data into training and testing sets
     train_size = int(len(data) * 0.8)
@@ -221,6 +222,8 @@ def modelCNNLSTM(csv_file, prax):
     trek = df.iloc[0:len(df), 1:23]
     Y = trek[0:len(trek)]
     YP = trek[1:len(trek)]
+    Y = Y.values.astype("float64")
+    YP = YP.values.astype("float64")
     Y1 = Y['Close']
     Y2 = YP['Close']
     Yx = pd.DataFrame(YP, index=YP.index, columns=YP.columns)
@@ -255,7 +258,6 @@ def modelCNNLSTM(csv_file, prax):
 def modelCNNLSTM_OpenGap(csv_file, prax):
     # Read the data
     df = csv_file
-    df = df['Date/Time'].values.astype("float64")
     datLength = len(df)
     df['O-C'] = 0
     for i in range(datLength):
@@ -268,6 +270,7 @@ def modelCNNLSTM_OpenGap(csv_file, prax):
     trek = df.iloc[datLength-100:,1:24]
     #print(temp_data)
     data = temp_data
+    data = data.values.astype("float64")
     sc = MinMaxScaler()
     # Split the data into training and testing sets
     train_size = int(len(data) * 0.8)
@@ -378,6 +381,8 @@ def modelCNNLSTM_OpenGap(csv_file, prax):
     trek = df.iloc[0:len(df), 1:24]
     Y = trek[0:len(trek)]
     YP = trek[1:len(trek)]
+    Y = Y.values.astype("float64")
+    YP = YP.values.astype("float64")
     Y1 = Y['Close']
     Y2 = YP['Close']
     Yx = pd.DataFrame(YP, index=YP.index, columns=YP.columns)

app.py

@@ -67,6 +67,8 @@ MAX_EPOCHS = 3
 LEARNING_RATE = 0.01
 OPTUNA = True
 ACCELERATOR = "cpu"
+# This below line is only for GPU. Don't use it for CPU
+#os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:1024"
 
 # Variables to count the number of files
 w = 7
@@ -106,6 +108,7 @@ def objective(trial, X_train, y_train, X_test, y_test):
 def modelCNNLSTM(csv_file, prax):
     # Read the data
     df = csv_file
+    df = df['Date/Time'].values.astype("float64")
     temp_data = df.iloc[0:len(df)-100, 1:23]
     trek = df.iloc[len(df)-100:,1:23]
     #print(temp_data)
@@ -114,7 +117,6 @@ def modelCNNLSTM(csv_file, prax):
     # Split the data into training and testing sets
     train_size = int(len(data) * 0.8)
     train_data, test_data = data[:train_size], data[train_size:]
-
     # Separate the input features and target variable
     X_train, y_train = train_data, train_data['Close']
     X_test, y_test = test_data, test_data['Close']
@@ -266,6 +268,7 @@ def modelCNNLSTM_OpenGap(csv_file, prax):
     trek = df.iloc[datLength-100:,1:24]
     #print(temp_data)
     data = temp_data
+    #data = data.values.astype("float64")
     sc = MinMaxScaler()
     # Split the data into training and testing sets
     train_size = int(len(data) * 0.8)
@@ -603,7 +606,7 @@ def modelTFT(csv_file, prax):
     #torch.cuda.empty_cache()
     best_model_path = trainer.checkpoint_callback.best_model_path
     best_tft = TemporalFusionTransformer.load_from_checkpoint(best_model_path)
-    actuals = torch.cat([y[0] for x, y in iter(val_dataloader)])
+    actuals = torch.cat([y[0] for x, y in iter(val_dataloader)])#.cuda()
     predictions = best_tft.predict(val_dataloader, mode="prediction")
     raw_predictions = best_tft.predict(val_dataloader, mode="raw", return_x=True)
 
@@ -835,7 +838,7 @@ def modelTFT_OpenGap(csv_file, prax):
     #torch.cuda.empty_cache()
     best_model_path = trainer.checkpoint_callback.best_model_path
     best_tft = TemporalFusionTransformer.load_from_checkpoint(best_model_path)
-    actuals = torch.cat([y[0] for x, y in iter(val_dataloader)])
+    actuals = torch.cat([y[0] for x, y in iter(val_dataloader)])#.cuda()
     predictions = best_tft.predict(val_dataloader, mode="prediction")
     raw_predictions = best_tft.predict(val_dataloader, mode="raw", return_x=True)