Untitled

import matplotlib.pyplot as plt
import seaborn as sns

# Statistical summary of the relevant columns
stat_summary = data[['IN Gross', 'Out Tare (ton)', 'Payload Netto (ton)']].describe()

# Scatter plot to visualize the relationship
plt.figure(figsize=(12, 6))

# Plotting IN Gross vs Payload Netto
plt.subplot(1, 2, 1)
sns.scatterplot(x=data['IN Gross'], y=data['Payload Netto (ton)'])
plt.title('IN Gross vs Payload Netto')
plt.xlabel('IN Gross')
plt.ylabel('Payload Netto (ton)')

# Plotting Out Tare vs Payload Netto
plt.subplot(1, 2, 2)
sns.scatterplot(x=data['Out Tare (ton)'], y=data['Payload Netto (ton)'])
plt.title('Out Tare vs Payload Netto')
plt.xlabel('Out Tare (ton)')
plt.ylabel('Payload Netto (ton)')

plt.tight_layout()
plt.show()

stat_summary


## -------------------------------------------------------------

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
import numpy as np

# Preparing the data for regression analysis
X = data[['IN Gross', 'Out Tare (ton)']]  # Predictor variables
y = data['Payload Netto (ton)']  # Target variable

# Splitting 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)

# Creating a linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Predicting and evaluating the model
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Coefficients of the model
coefficients = model.coef_
intercept = model.intercept_

# Model summary
model_summary = {
    'Mean Squared Error': mse,
    'R^2 Score': r2,
    'Coefficients': coefficients,
    'Intercept': intercept
}

model_summary