80 lines
2.3 KiB
Python
80 lines
2.3 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
import datapuller
|
|
import os
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
|
|
from sklearn.model_selection import train_test_split
|
|
from keras import Sequential, layers, optimizers
|
|
|
|
def TrainAI():
|
|
# Pull New Data
|
|
datapuller.pull()
|
|
|
|
# Get the CWD for pathing due to being called from C# now
|
|
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"))
|
|
X = dataset.drop('Target_Close_Tomorrow', axis=1)
|
|
Y = dataset['Target_Close_Tomorrow']
|
|
|
|
# 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))
|
|
|
|
# Start with a linear model
|
|
dnn_linear_model = Sequential([
|
|
layers.Input(shape=(train_features.shape[1],)), # Load the feature count dynamically
|
|
normalizer,
|
|
layers.Dense(64, activation='relu'),
|
|
layers.Dense(64, activation='relu'),
|
|
layers.Dense(1)
|
|
])
|
|
|
|
# Configure the model
|
|
dnn_linear_model.compile(
|
|
optimizer=optimizers.Adam(learning_rate=0.001),
|
|
loss='mean_absolute_error'
|
|
)
|
|
|
|
# Show the summary before training the model
|
|
dnn_linear_model.summary()
|
|
|
|
# Train the model
|
|
Training_Data = dnn_linear_model.fit(
|
|
train_features,
|
|
train_labels,
|
|
batch_size=1024,
|
|
epochs=100,
|
|
# Show progress
|
|
verbose=1,
|
|
# Calculate validation results on 20% of the training data.
|
|
validation_split = 0.2
|
|
)
|
|
|
|
# Predict
|
|
test_predictions = dnn_linear_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)
|
|
|
|
|
|
test_results = dnn_linear_model.evaluate(
|
|
test_features, test_labels, verbose=0
|
|
)
|
|
|
|
# Save the model
|
|
dnn_linear_model.save(os.path.join(DATA_DIR, "model.keras")) |