SOURCE CODE:
import numpy as np
import pandas as pd
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
file_path = input("Enter the path to the stock market CSV file: ")
data = pd.read_csv(file_path)
data.columns = data.columns.str.strip()
available_columns = data.columns.tolist()[1:]
print("Available stock symbols in dataset:", available_columns)
selected_column = input("Enter the stock symbol you want to analyze (e.g., 'AMZN', 'DPZ', 'BTC'): ")
if selected_column not in data.columns:
raise KeyError(f"Selected stock '{selected_column}' not found in dataset. Available stocks:
{available_columns}")
data['Date'] = pd.to_datetime(data['Date'])
date_input = input("Enter the future date to predict (YYYY-MM-DD): ")
selected_date = pd.to_datetime(date_input, errors='coerce')
prices = data[selected_column].values.reshape(-1, 1)
print(f"Using column '{selected_column}' for stock prices.")
scaler = MinMaxScaler(feature_range=(0,1))
prices_scaled = scaler.fit_transform(prices)
def create_sequences(data, seq_length):
sequences, labels = [], []
for i in range(len(data) - seq_length):
sequences.append(data[i:i+seq_length])
labels.append(data[i+seq_length])
return np.array(sequences), np.array(labels)
seq_length = 50 # User-defined sequence length
X, y = create_sequences(prices_scaled, seq_length)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = Sequential([
LSTM(50, return_sequences=True, input_shape=(seq_length, 1)),
LSTM(50, return_sequences=False),
Dense(25, activation='relu'),
Dense(1)
])
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X_train, y_train, epochs=10, batch_size=16, verbose=1)
last_sequence = prices_scaled[-seq_length:].reshape(1, seq_length, 1)
predicted_price = scaler.inverse_transform(model.predict(last_sequence))
print(f"Predicted stock price for {selected_column} on {date_input}: {predicted_price[0][0]}")
OUTPUT
Enter the path to the stock market CSV file: /portfolio_data.csv
Available stock symbols in dataset: ['AMZN', 'DPZ', 'BTC', 'NFLX']
Enter the stock symbol you want to analyze (e.g., 'AMZN', 'DPZ', 'BTC'): AMZN
Enter the future date to predict (YYYY-MM-DD): 2025-03-26
Using column 'AMZN' for stock prices.
Epoch 1/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 4s 23ms/step - loss: 0.0396
Epoch 2/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 3s 30ms/step - loss: 6.7705e-04
Epoch 3/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 2s 22ms/step - loss: 5.9535e-04
Epoch 4/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 3s 23ms/step - loss: 6.3809e-04
Epoch 5/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 3s 22ms/step - loss: 6.6923e-04
Epoch 6/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 2s 22ms/step - loss: 5.3682e-04
Epoch 7/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 2s 26ms/step - loss: 5.1026e-04
Epoch 8/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 2s 22ms/step - loss: 6.3585e-04
Epoch 9/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 2s 23ms/step - loss: 6.2295e-04
Epoch 10/10
74/74 ━━━━━━━━━━━━━━━━━━━━ 2s 23ms/step - loss: 4.2156e-04
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 217ms/step
Predicted stock price for AMZN on 2025-03-26: 1837.160400390625
