Welcome to nr1-github Discussions!

[shahramk]

👋 Welcome!

Hello from New Relic Labs - we are the maintainers of the nr1-github repo, and we're using Discussions as a place to connect directly with members of our community.

If you have questions to ask or ideas you'd like to share, please feel free to start a discussion.

If you'd like to report a bug, or submit a feature request, go ahead and open up an issue.

We are a small team so we might not be able to respond right away, but rest assured we are keeping an eye on this space - your input is important to us!

[monjie110]

docker run
-d
--name newrelic-infra
--network=host
--cap-add=SYS_PTRACE
--privileged
--pid=host
-v "/:/host:ro"
-v "/var/run/docker.sock:/var/run/docker.sock"
-e NRIA_LICENSE_KEY=e9bd38ce9dbffd4ed6431a7bf0306537bbf9NRAL
newrelic/infrastructure:latest

[monjie110]

import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM, Dropout, BatchNormalization

Load CSV data

def load_csv_data(csv_file_path):
data = pd.read_csv(csv_file_path)
return data

Preprocess data

def preprocess_data(data, columns_to_drop):
# Drop null values and unimportant columns
data = data.dropna()
data = data.drop(columns_to_drop, axis=1)

# Scale the data
scaler = MinMaxScaler()
data = scaler.fit_transform(data)

# Split data into training and testing sets
train_size = int(len(data) * 0.8)
train_data = data[:train_size]
test_data = data[train_size:]

# Reshape data for LSTM input
x_train, y_train = [], []
for i in range(60, len(train_data)):
    x_train.append(train_data[i-60:i])
    y_train.append(train_data[i])
x_test, y_test = [], []
for i in range(60, len(test_data)):
    x_test.append(test_data[i-60:i])
    y_test.append(test_data[i])
x_train, y_train = np.array(x_train), np.array(y_train)
x_test, y_test = np.array(x_test), np.array(y_test)

return x_train, y_train, x_test, y_test, scaler

Build LSTM model

def build_model(input_shape):
model = Sequential()
model.add(LSTM(128, return_sequences=True, input_shape=input_shape))
model.add(BatchNormalization())
model.add(Dropout(0.2))
model.add(LSTM(64, return_sequences=True))
model.add(BatchNormalization())
model.add(Dropout(0.2))
model.add(LSTM(32, return_sequences=False))
model.add(BatchNormalization())
model.add(Dense(25))
model.add(Dense(1))
return model

Train LSTM model

def train_model(model, x_train, y_train):
model.compile(optimizer='rmsprop', loss='mean_squared_error')
model.fit(x_train, y_train, batch_size=16, epochs=50)

Predict stock price and decide whether to buy or sell

def predict_price(model, x_test, scaler, last_known_price):
# Make predictions on test data
predictions = model.predict(x_test)
predictions = scaler.inverse_transform(predictions)

# Get the last known closing price
last_known_price = scaler.inverse_transform(np.array([[last_known_price]]))

# Determine whether to buy or sell
if predictions[-1] > last_known_price:
    decision = "buy"
else:
    decision = "sell"

return predictions[-1][0], decision

Evaluate model accuracy with RMSE metric

def evaluate_model(model, x_test, y_test, scaler):
# Make predictions on test data
predictions = model.predict(x_test)
predictions = scaler.inverse_transform(predictions)

# Calculate RMSE
rmse = np.sqrt(np.mean(((predictions - y_test) ** 2)))

return rmse

Add noise to data for data augmentation

def add_noise(data, noise_factor):
noisy_data = data + noise_factor * np.random.randn(*data.shape)
return noisy_data

Load and preprocess data

data = load_csv_data('stock_prices.csv')
columns_to_drop = ['Date', 'Open', 'High', 'Low', 'Adj Close', 'Volume']
x_train, y_train, x_test, y_test, scaler = preprocess_data(data, columns_to_drop)

Data augmentation by adding noise

x_train_noisy = add_noise(x_train, 0.1)

Build and train model

model_input_shape = (x_train.shape[1], x_train.shape[2])
model = build_model(model_input_shape)
train_model(model, x_train_noisy, y_train)

Evaluate model accuracy

rmse = evaluate_model(model, x_test, y_test, scaler)
print("RMSE:", rmse)

Predict future stock prices

last_known_price = data['Close'].iloc[-1]
future_prices = []
for i in range(10):
future_price, decision = predict_price(model, np.array([x_test[-1]]), scaler, last_known_price)
future_prices.append(future_price)
if decision == "buy":
print("Buy")
else:
print("Sell")
last_known_price = future_price

Print predicted future prices

print("

[monjie110]

docker run
-d
--name newrelic-infra
--network=host
--cap-add=SYS_PTRACE
--privileged
--pid=host
-v "/:/host:ro"
-v "/var/run/docker.sock:/var/run/docker.sock"
-e NRIA_LICENSE_KEY=e9bd38ce9dbffd4ed6431a7bf0306537bbf9NRAL
newrelic/infrastructure:latest

[EQemccudden]

@monjie110 - I'd advise removing your keys as per here