116 lines
4.2 KiB
Python
116 lines
4.2 KiB
Python
import pandas as pd
|
|
from sklearn.metrics import f1_score, precision_score, recall_score, accuracy_score
|
|
import features
|
|
import joblib
|
|
import os
|
|
|
|
# Suppress TensorFlow INFO and WARNING logs
|
|
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
|
|
|
|
# Suppress specialized XLA and autotuning logs
|
|
os.environ['TF_XLA_FLAGS'] = '--tf_xla_enable_xla_devices=false'
|
|
os.environ['TF_CPP_MAX_VLOG_LEVEL'] = '0'
|
|
|
|
# CPU only
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
|
|
|
|
from sklearn.model_selection import train_test_split
|
|
from keras import Sequential, layers, optimizers
|
|
from keras.callbacks import ReduceLROnPlateau
|
|
|
|
def TrainAI():
|
|
|
|
# Get the CWD for pathing due to being called from C#
|
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
DATA_DIR = os.path.join(SCRIPT_DIR, "data")
|
|
|
|
# Load the dataset
|
|
dataset = pd.read_parquet(os.path.join(DATA_DIR, "stocks.parquet"))
|
|
|
|
# Use external featuers to make sure loaded is the same
|
|
dataset = features.MakeFeatures(dataset)
|
|
|
|
# Make sure empty columns dont exist
|
|
dataset = dataset.dropna()
|
|
|
|
# Create the X, Y vareables
|
|
X, Y, X_Scaler, Y_Scaler = features.Prepare(dataset)
|
|
|
|
# Save the scalers for future use
|
|
joblib.dump(X_Scaler, os.path.join(DATA_DIR, "feature_scaler.pkl"))
|
|
joblib.dump(Y_Scaler, os.path.join(DATA_DIR, "target_scaler.pkl"))
|
|
|
|
# Show the datatypes
|
|
print(dataset.dtypes)
|
|
|
|
# Split out the test and train
|
|
train_features, test_features, train_labels, test_labels = train_test_split(X, Y, test_size=0.2, shuffle=False) # Keep the training and test data in order as its sequential
|
|
|
|
# Create the DNN
|
|
dnn_model = Sequential([
|
|
layers.Input(shape=(train_features.shape[1],)), # Load the feature count dynamically
|
|
layers.Dense(256, activation='elu'), # DNN layer
|
|
layers.BatchNormalization(), # Nomralize
|
|
layers.Dropout(0.1), # Small dropout to prevent it from memorizing noise
|
|
layers.Dense(128, activation='elu'), # DNN layer
|
|
layers.BatchNormalization(), # Nomralize
|
|
layers.Dropout(0.1), # Small dropout to prevent it from memorizing noise
|
|
layers.Dense(24, activation='elu'), # DNN layer
|
|
layers.Dense(1, activation='linear') # DNN layer
|
|
])
|
|
|
|
# Configure the model
|
|
dnn_model.compile(
|
|
optimizer=optimizers.Adam(learning_rate=0.0001, clipvalue=1.0),
|
|
loss="mse",
|
|
metrics=['mae'] # See it train while it runs
|
|
)
|
|
|
|
# Show the summary before training the model
|
|
dnn_model.summary()
|
|
|
|
# Learning rate reducer
|
|
reduce_lr = ReduceLROnPlateau(monitor='loss', factor=0.5, patience=5, min_lr=0.0000001)
|
|
|
|
# Train the model
|
|
Training_Data = dnn_model.fit(
|
|
train_features,
|
|
train_labels,
|
|
batch_size=64,
|
|
epochs=50, # Tuned to the point before overfitting
|
|
verbose=1, # Show progress
|
|
shuffle=False, # Time series data
|
|
callbacks=[reduce_lr] # Reduce the learning_rate every run
|
|
)
|
|
|
|
# Current Test Results: 0.3382711112499237
|
|
test_results = dnn_model.evaluate(
|
|
test_features, test_labels, verbose=0
|
|
)
|
|
|
|
# Perform test on test data split earlier
|
|
predictions = dnn_model.predict(test_features)
|
|
|
|
# Convert to Binary Direction (The "Signal")
|
|
y_true_binary = (test_labels > 0).astype(int)
|
|
y_pred_binary = (predictions > 0).astype(int)
|
|
|
|
# Calculate the metrics
|
|
acc = accuracy_score(y_true_binary, y_pred_binary)
|
|
prec = precision_score(y_true_binary, y_pred_binary)
|
|
rec = recall_score(y_true_binary, y_pred_binary)
|
|
f1 = f1_score(y_true_binary, y_pred_binary)
|
|
|
|
# Output the meterics; this gets spit out when training from the python file directly. The C# interop does not output these
|
|
print(f"Test Loss: {test_results[0]:.4f}")
|
|
print(f"Test MAE: {test_results[1]:.2%}")
|
|
print(f"Test Accuracy: {acc:.2%}")
|
|
print(f"Test Precision: {prec:.2%}")
|
|
print(f"Test Recall: {rec:.2%}")
|
|
print(f"F1 Score: {f1:.2%}")
|
|
|
|
# Save the model
|
|
dnn_model.save(os.path.join(DATA_DIR, "model.keras"))
|
|
|
|
if __name__ == "__main__":
|
|
TrainAI() |