Weather Prediction Univariate Time Series.py

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

# Load data
df = pd.read_csv('https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv')

# Prepare data
scaler = MinMaxScaler()
data = scaler.fit_transform(df['Temp'].values.reshape(-1, 1))
train_data = data[:3000]
test_data = data[3000:]

# Create sequences
def create_sequences(data, seq_length):
    X = []
    y = []
    for i in range(len(data) - seq_length):
        X.append(data[i:i+seq_length])
        y.append(data[i+seq_length])
    return np.array(X), np.array(y)

seq_length = 30
X_train, y_train = create_sequences(train_data, seq_length)
X_test, y_test = create_sequences(test_data, seq_length)

# Build model
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(seq_length, 1)))
model.add(Flatten())
model.add(Dense(1, activation='linear'))

model.compile(optimizer='adam', loss='mse', metrics=['mae'])

# Train model
history = model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2, verbose=0)

# Make predictions
train_predictions = model.predict(X_train)
test_predictions = model.predict(X_test)

# Scale back the data
train_predictions = scaler.inverse_transform(train_predictions)
y_train = scaler.inverse_transform(y_train)
test_predictions = scaler.inverse_transform(test_predictions)
y_test = scaler.inverse_transform(y_test)

# Evaluate model
train_rmse = np.sqrt(mean_squared_error(y_train, train_predictions))
test_rmse = np.sqrt(mean_squared_error(y_test, test_predictions))

print(f'Train RMSE: {train_rmse:.2f}')
print(f'Test RMSE: {test_rmse:.2f}')

test_sequences = []
for i in range(seq_length, len(test_data)):
    test_sequences.append(test_data[i-seq_length:i])

test_sequences = np.array(test_sequences)
test_sequences = np.reshape(test_sequences, (test_sequences.shape[0], test_sequences.shape[1], 1))

# Generate predictions for the test data
test_predictions = model.predict(test_sequences)

# Shift predictions to the original scale
test_predictions = scaler.inverse_transform(test_predictions.reshape(-1, 1))

# Plot the results
plt.figure(figsize=(10,6))
plt.plot(df.index[3000+seq_length:], df['Temp'].values[3000+seq_length:], label='Test')
plt.plot(df.index[seq_length:3000], train_predictions.flatten(), label='Train Predictions')
plt.plot(df.index[3000+seq_length:], test_predictions.flatten(), label='Test Predictions')
plt.legend()
plt.show()