#CODE

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error


np.random.seed(42)
data = pd.DataFrame({
    'Production_Output': np.random.normal(500, 50, 1000),   # Production output in units
    'Defect_Rate': np.random.uniform(0, 0.05, 1000),        # Defect rate percentage
    'Machine_Downtime': np.random.normal(5, 2, 1000),       # Downtime in hours
    'Maintenance_Schedule': np.random.randint(1, 31, 1000), # Maintenance day of the month
    'Employee_Training_Hours': np.random.normal(10, 2, 1000) # Training hours per month
})

# Create a target variable ( Production Output for next month)
data['Next_Month_Production'] = data['Production_Output'] * (1 - data['Defect_Rate']) * (1 - (data['Machine_Downtime'] / 100))

# Split the data into training and testing sets
X = data[['Production_Output', 'Defect_Rate', 'Machine_Downtime', 'Maintenance_Schedule', 'Employee_Training_Hours']]
y = data['Next_Month_Production']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

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

# Make predictions
y_pred = model.predict(X_test)

# Calculate the mean squared error
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')

# Plot the actual vs. predicted production output
plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, alpha=0.7)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=3)
plt.xlabel('Actual Production Output')
plt.ylabel('Predicted Production Output')
plt.title('Actual vs Predicted Production Output')
plt.show()

# Plot feature importance
importance = model.coef_
features = X.columns
plt.figure(figsize=(10, 6))
sns.barplot(x=importance, y=features)
plt.xlabel('Importance')
plt.ylabel('Features')
plt.title('Feature Importance')
plt.show()

# Plot correlation heatmap
plt.figure(figsize=(10, 8))
sns.heatmap(data.corr(), annot=True, cmap='coolwarm', fmt='.2f')
plt.title('Correlation Heatmap')
plt.show()

# Plot time series of production output
plt.figure(figsize=(10, 6))
plt.plot(data.index, data['Production_Output'], label='Production Output')
plt.xlabel('Time')
plt.ylabel('Production Output')
plt.title('Production Output Over Time')
plt.legend()
plt.show()

# Plot residuals
residuals = y_test - y_pred
plt.figure(figsize=(10, 6))
plt.scatter(y_pred, residuals, alpha=0.7)
plt.axhline(y=0, color='r', linestyle='--')
plt.xlabel('Predicted Production Output')
plt.ylabel('Residuals')
plt.title('Residual Plot')
plt.show()

# Plot distribution of key variables
plt.figure(figsize=(14, 10))
plt.subplot(2, 2, 1)
sns.histplot(data['Production_Output'], kde=True, bins=30)
plt.title('Distribution of Production Output')

plt.subplot(2, 2, 2)
sns.histplot(data['Defect_Rate'], kde=True, bins=30)
plt.title('Distribution of Defect Rate')

plt.subplot(2, 2, 3)
sns.histplot(data['Machine_Downtime'], kde=True, bins=30)
plt.title('Distribution of Machine Downtime')

plt.subplot(2, 2, 4)
sns.histplot(data['Employee_Training_Hours'], kde=True, bins=30)
plt.title('Distribution of Employee Training Hours')

plt.tight_layout()
plt.show()