model.pkl

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
import matplotlib.pyplot as plt



input_csv_path = 'accumulated_data.csv'

df = pd.read_csv(input_csv_path)

# Drop 'dt' column as you did before
df.drop(columns=['dt'], inplace=True)

# Define the features (X) and target variable (y)
X = df.drop(columns=['pm10'])
y = df['pm10']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create and train the Linear Regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test)

# Calculate Mean Squared Error and R-squared
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"Mean Squared Error: {mse}")
print(f"R-squared: {r2}")

# Visualize the predictions vs. actual values
plt.scatter(y_test, y_pred)
plt.xlabel("Actual Values")
plt.ylabel("Predicted Values")
plt.title("Actual vs. Predicted Values")
plt.show()

# Calculate the accuracy percentage
accuracy_percentage = r2 * 100
print(f"Accuracy Percentage: {accuracy_percentage:.2f}%")