Gradient Boosting

A machine learning method called Gradient Boosting creates an ensemble by combining several weak prediction models. Decision trees, which are sequentially trained to reduce errors and increase accuracy, are commonly used as these weak models. Gradient boosting can efficiently capture intricate correlations between features by combining several decision tree regressors or decision tree classifiers.

Gradient boosting's capacity to iteratively minimize the loss function is one of its main advantages. One loss function used to assess how well a machine learning model matches actual data is Mean Squared Error (MSE). MSE determines the mean of the squared discrepancies between the observed and expected values.

USE CASE 1: Using Gradient Boosting with scikit-learn, predict the product price. The Production cost, Advertising spend, and Demand level are the independent variables.

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

# -----------------------------------
# 1. Load data from Excel
# -----------------------------------
data = pd.read_excel("product_data.xlsx")

print("Dataset Preview:")
print(data.head())

# -----------------------------------
# 2. Define features and target
# -----------------------------------
X = data[['Production_Cost', 'Advertising_Spend', 'Demand_Level']]
y = data['Product_Price']

# -----------------------------------
# 3. Split into training and testing
# -----------------------------------
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42
)

# -----------------------------------
# 4. Train themodel
# -----------------------------------
model = GradientBoostingRegressor(
    n_estimators=100,
    learning_rate=0.1,
    max_depth=3,
    random_state=42
)
model.fit(X_train, y_train)

# -----------------------------------
# 5. Model parameters
# -----------------------------------
print("\nIntercept:", model.intercept_)
print("Coefficients:")
for feature, coef in zip(X.columns, model.coef_):
    print(f"  {feature}: {coef}")

# -----------------------------------
# 6. Evaluate the model
# -----------------------------------
y_pred = model.predict(X_test)

r2 = r2_score(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)

print("\nModel Evaluation:")
print("R² Score:", r2)
print("Mean Absolute Error:", mae)
print("Mean Squared Error:", mse)

# -----------------------------------
# 7. Predict price for a new product
# -----------------------------------
new_product = [[65, 18, 275]]  # Production Cost, Advertising Spend, Demand Level
predicted_price = model.predict(new_product)

print("Predicted Product Price:", predicted_price[0])

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

# -----------------------------------
# 1. Load data from Excel
# -----------------------------------
#sample data can be exported to 
#excel from the URL
# https://pythonPlaza.com/linear_school_grade_data.html

data = pd.read_excel("student_data.xlsx")

print("Dataset Preview:")
print(data.head())

# -----------------------------------
# 2. Define features and target
# -----------------------------------
X = data[['Hours_Studied', 'Attendance_%', 'Previous_Score']]
y = data['Final_Grade']

# -----------------------------------
# 3. Split into training and testing
# -----------------------------------
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42
)

# -----------------------------------
# 4. Train the Linear Regression model
# -----------------------------------
model = LinearRegression()
model.fit(X_train, y_train)


# -----------------------------
# Predictions
y_pred = model.predict(X_test)

# -----------------------------
# Evaluation
print("Predicted grades:", y_pred)
print("Actual grades:   ", y_test)

print("\nMean Squared Error:", mean_squared_error(y_test, y_pred))
print("R² Score:", r2_score(y_test, y_pred))


Example: Predict a new student’s grade
# New student: [hours_studied, attendance %, previous_score]
new_student = np.array([[6, 85, 78]])

predicted_grade = model.predict(new_student)
print("Predicted final grade:", predicted_grade[0])

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

# -----------------------------------
# 1. Load data from Excel
# -----------------------------------
#sample data can be exported to 
#excel from the URL

  
  Get the Profit Optimization data in Excel
  

data = pd.read_excel("profit_optimization.xlsx")

print("Dataset Preview:")
print(data.head())

# -----------------------------------
# 2. Define features and target  Price (P)	
# -----------------------------------
X = data[['Price', 'Advertising', 'Units_Sold']]
y = data['Profit']

# -----------------------------------
# 3. Split into training and testing
# -----------------------------------
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42
)

# -----------------------------------
# 4. Train the Linear Regression model
# -----------------------------------
model = LinearRegression()
model.fit(X_train, y_train)


#Predict profit
y_pred = model.predict(X_test)

print("Predicted profit:", y_pred)
print("Actual profit:   ", y_test)

#Evaluate the model
print("\nMean Squared Error:", mean_squared_error(y_test, y_pred))
print("R² Score:", r2_score(y_test, y_pred))

#Profit equation (key for optimization)
print("Intercept:", model.intercept_)
print("Coefficients [Price, Advertising, Units Sold]:", model.coef_)


#Predict profit for a new business strategy
# Example: Price = 15, Advertising = 165, Units Sold = 460
new_strategy = np.array([[15, 165, 460]])

predicted_profit = model.predict(new_strategy)
print("Predicted profit:", predicted_profit[0])

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

# -----------------------------------
# 1. Load data from Excel
# -----------------------------------
#sample data can be exported to 
#excel from the URL

  
  Get the Patient Response Data in Excel
  

data = pd.read_excel("patient_dosage_response.xlsx")

print("Dataset Preview:")
print(data.head())

# -----------------------------------
# 2. Define features and target  Price (P)	
# -----------------------------------
X = data[['Dosage', 'Age', 'Weight']]
y = data['Patient_Response']

# -----------------------------------
# 3. Split into training and testing
# -----------------------------------
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42
)

# -----------------------------------
# 4. Train the Linear Regression model
# -----------------------------------
model = LinearRegression()
model.fit(X_train, y_train)


#Predict profit
y_pred = model.predict(X_test)

print("Predicted responses:", y_pred)
print("Actual responses:   ", y_test)

#Evaluate the model
print("\nMean Squared Error:", mean_squared_error(y_test, y_pred))
print("R² Score:", r2_score(y_test, y_pred))

#Profit equation (key for optimization)
print("Intercept:", model.intercept_)
print("Coefficients [Dosage, Age, Weight]:", model.coef_)


Predict response for a new patient
# New patient: Dosage=72mg, Age=36yrs, Weight=172lbs
new_patient = np.array([[72, 36, 172]])

predicted_response = model.predict(new_patient)
print("Predicted patient response:", predicted_response[0])