92 lines
2.7 KiB
Python
92 lines
2.7 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
import datapuller
|
|
import features
|
|
import joblib
|
|
import os
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
|
|
from sklearn.model_selection import train_test_split
|
|
from keras import Sequential, layers, optimizers, losses
|
|
|
|
def TrainAI(include_pull):
|
|
|
|
if (include_pull):
|
|
# Pull New Data
|
|
datapuller.pull()
|
|
|
|
# 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"))
|
|
|
|
# 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)
|
|
|
|
# Create a normalizer to nomralize the data
|
|
normalizer = layers.Normalization(axis=-1)
|
|
normalizer.adapt(np.array(train_features))
|
|
|
|
# Create the DNN
|
|
dnn_model = Sequential([
|
|
layers.Input(shape=(train_features.shape[1],)), # Load the feature count dynamically
|
|
normalizer,
|
|
layers.Dense(64, activation='elu'),
|
|
layers.Dense(64, activation='elu'),
|
|
layers.Dense(1)
|
|
])
|
|
|
|
# Configure the model
|
|
dnn_model.compile(
|
|
optimizer=optimizers.Adam(learning_rate=0.00001, clipvalue=1.0),
|
|
loss=losses.Huber()
|
|
)
|
|
|
|
# Show the summary before training the model
|
|
dnn_model.summary()
|
|
|
|
# Train the model
|
|
Training_Data = dnn_model.fit(
|
|
train_features,
|
|
train_labels,
|
|
batch_size=64,
|
|
epochs=39, # Tuned to the point before overfitting
|
|
verbose=1, # Show progress
|
|
validation_split = 0.2 # Calculate validation results on 20% of the training data.
|
|
)
|
|
|
|
# Predict
|
|
test_predictions = dnn_model.predict(test_features).flatten()
|
|
a = plt.axes(aspect='equal')
|
|
plt.scatter(test_labels, test_predictions)
|
|
plt.xlabel('True Values')
|
|
plt.ylabel('Predictions')
|
|
lims = [0, 50]
|
|
plt.xlim(lims)
|
|
plt.ylim(lims)
|
|
_ = plt.plot(lims, lims)
|
|
|
|
|
|
# Current Test Results: 1.221876300405711e-05
|
|
test_results = dnn_model.evaluate(
|
|
test_features, test_labels, verbose=0
|
|
)
|
|
print(f"Test Results: {test_results}")
|
|
|
|
# Save the model
|
|
dnn_model.save(os.path.join(DATA_DIR, "model.keras"))
|
|
|
|
if __name__ == "__main__":
|
|
TrainAI(False) |