Monday, June 29, 2026

Logistic Regression Using Python

🟦🟩🟨 Logistic Regression Using Python

🎯 Aim

To implement the Logistic Regression algorithm using Python to classify whether a patient has a disease based on their age.

🧠 Theory

Logistic Regression is a Supervised Machine Learning algorithm used for classification problems. Unlike Linear Regression, which predicts continuous values, Logistic Regression predicts categories or classes.

Examples

📧 Spam / Not Spam
🏥 Disease / Healthy
🎓 Pass / Fail
💳 Fraud / Not Fraud

The output is usually:

0 → No
1 → Yes

Logistic Regression uses the Sigmoid Function to convert predictions into probabilities between 0 and 1.

🌍 Real-Life Example

A hospital wants to predict whether a patient has diabetes based only on Age.

Training Data

Age	Disease
20	0
25	0
30	0
35	0
40	1
45	1
50	1
55	1

Here,

0 = Healthy
1 = Disease

📝 Step 1: Import Required Libraries


from sklearn.linear_model import LogisticRegression

Explanation

sklearn → Machine Learning library.
linear_model → Contains regression algorithms.
LogisticRegression → Used for classification.

📝 Step 2: Create Input Data


X = [
    [20],
    [25],
    [30],
    [35],
    [40],
    [45],
    [50],
    [55]
]

Explanation

X stores the input feature (Age).

Each value is written inside another list because Scikit-learn expects 2D input.

📝 Step 3: Create Output Data

Explanation

y stores the output labels.

Value	Meaning
0	Healthy
1	Disease

📝 Step 4: Create the Model


model = LogisticRegression()

Explanation

This creates an empty Logistic Regression model.

At this stage:

✔ No learning

✔ No prediction

✔ Just an empty model

📝 Step 5: Train the Model


model.fit(X, y)

Explanation

fit() teaches the model using the training data.

The model learns:

Relationship between Age and Disease
Probability of Disease

This is called the Training Phase.


Training Data
      │
      ▼
Model Learning
      │
      ▼
Trained Model

📝 Step 6: Predict New Data

Suppose a new patient is 42 years old.


prediction = model.predict([[42]])

Explanation

The model compares age 42 with the learned pattern and predicts:

Either

📝 Step 7: Display Prediction


print(prediction)

Output

[1]

Meaning


Disease

📝 Step 8: Display User-Friendly Output


if prediction[0] == 1:
    print("Patient has Disease")
else:
    print("Patient is Healthy")

Output


Patient has Disease

✅ Complete Python Program


# Logistic Regression Example

from sklearn.linear_model import LogisticRegression

# Input Data (Age)
X = [
    [20],
    [25],
    [30],
    [35],
    [40],
    [45],
    [50],
    [55]
]

# Output Data
# 0 = Healthy
# 1 = Disease

y = [
    0,
    0,
    0,
    0,
    1,
    1,
    1,
    1
]

# Create Model
model = LogisticRegression()

# Train Model
model.fit(X, y)

# Predict
prediction = model.predict([[42]])

# Display Prediction
if prediction[0] == 1:
    print("Patient has Disease")
else:
    print("Patient is Healthy")

💻 Expected Output


Patient has Disease

🔍 Step-by-Step Flow


Import Library
      │
      ▼
Create Dataset
      │
      ▼
Create Logistic Regression Model
      │
      ▼
Train Model using fit()
      │
      ▼
Predict using predict()
      │
      ▼
Display Result

📌 Understanding `fit()`


model.fit(X, y)

This is the most important line.

It means:


Teach the computer using
X → Input

y → Output

After this line, the model becomes trained.

📌 Understanding `predict()`


model.predict([[42]])

Meaning:

Predict the output for a new patient whose age is 42 years.

📌 Understanding `prediction[0]`

predict() returns a list (or array).

Example:


prediction = [1]

To access the first value:


prediction[0]

Result

📊 Training Data Visualization

Age	Disease
20	Healthy
25	Healthy
30	Healthy
35	Healthy
40	Disease
45	Disease
50	Disease
55	Disease

The model learns that higher ages in this small example are associated with the "Disease" class.

📈 Why Logistic Regression?

Linear Regression	Logistic Regression
Predicts numbers	Predicts categories
Output can be any value	Output is a probability (0–1) and a class
Used for Regression	Used for Classification

⭐ Advantages

✔ Easy to implement
✔ Fast training
✔ Works well for binary classification
✔ Produces probability estimates
✔ Easy to interpret

❌ Limitations

❌ Assumes a linear relationship between features and the log-odds
❌ Less effective for highly complex, non-linear data
❌ Sensitive to outliers in some situations

🌍 Applications

🏥 Disease Prediction
📧 Spam Detection
💳 Credit Card Fraud Detection
🎓 Student Pass/Fail Prediction
🛒 Customer Purchase Prediction
🏦 Loan Approval Prediction

🎯 Viva Questions

What is Logistic Regression?
Why is it called "Regression" if it is used for classification?
What is the role of the Sigmoid Function?
What does fit() do?
What does predict() do?
Why is the input written as [[42]] instead of [42]?
What is the meaning of prediction[0]?
What types of problems can Logistic Regression solve?

📝 One-Line Revision

Logistic Regression is a supervised machine learning algorithm that predicts the probability of a data point belonging to a particular class and is mainly used for binary classification problems.

Linear Regression Using Python

Experiment 1: Linear Regression Using Python

🎯 Aim

To implement the Linear Regression algorithm using Python and predict the value of a dependent variable based on an independent variable.

📖 Theory

Linear Regression is one of the simplest Supervised Machine Learning algorithms. It is used to predict continuous numerical values by finding a best-fit straight line between the input (independent variable) and the output (dependent variable).

It assumes a linear relationship between the variables.

Mathematical Equation

Y = mX + c

Where:

Y = Predicted Output (Dependent Variable)
X = Input (Independent Variable)
m = Slope of the Line
c = Intercept

🌍 Real-Life Example

A company wants to predict an employee's salary based on their years of experience.

Experience (Years)	Salary (₹)
1	25,000
2	30,000
3	35,000
4	45,000
5	50,000
6	60,000
7	65,000
8	70,000

Now, we want to predict the salary of an employee with 9 years of experience.

🪜 Step-by-Step Algorithm

Step 1️⃣ Import Required Libraries

Import the necessary libraries.


import pandas as pd
from sklearn.linear_model import LinearRegression

Explanation

pandas → Used to create and manage datasets.
LinearRegression → Imports the Linear Regression model from scikit-learn.

Step 2️⃣ Create the Dataset


data = {
    "Experience": [1,2,3,4,5,6,7,8],
    "Salary": [25000,30000,35000,45000,50000,60000,65000,70000]
}

df = pd.DataFrame(data)

Explanation

We create a simple dataset using a Python dictionary.

The dataset has two columns:

Experience → Independent Variable (X)
Salary → Dependent Variable (Y)

The data is converted into a DataFrame for easy processing.

Step 3️⃣ Display the Dataset


print(df)

Output


   Experience  Salary
0           1   25000
1           2   30000
2           3   35000
3           4   45000
4           5   50000
5           6   60000
6           7   65000
7           8   70000

Step 4️⃣ Separate Input and Output Variables


X = df[["Experience"]]
y = df["Salary"]

Explanation

Machine Learning models require:

X → Input Features (Independent Variable)
y → Target Variable (Dependent Variable)

Here:


X = Experience

y = Salary

Step 5️⃣ Create the Linear Regression Model


model = LinearRegression()

Explanation

This creates an empty Linear Regression model.

At this stage, the model has not learned from the data.

Step 6️⃣ Train the Model


model.fit(X, y)

Explanation

The fit() function trains the model.

During training:

Reads all training data
Calculates the best-fit line
Finds the slope (m)
Finds the intercept (c)

The model is now ready for prediction.

Step 7️⃣ Predict Salary


experience = [[9]]

prediction = model.predict(experience)

Explanation

We ask the model:

"Predict the salary of an employee with 9 years of experience."

The predict() function uses the learned line to estimate the salary.

Step 8️⃣ Display the Prediction


print("Predicted Salary =", prediction[0])

Sample Output


Predicted Salary = 78809.52

(The exact value may vary slightly depending on the fitted line.)

💻 Complete Python Program


# Step 1: Import Libraries
import pandas as pd
from sklearn.linear_model import LinearRegression

# Step 2: Create Dataset
data = {
    "Experience": [1,2,3,4,5,6,7,8],
    "Salary": [25000,30000,35000,45000,50000,60000,65000,70000]
}

df = pd.DataFrame(data)

# Step 3: Display Dataset
print("Dataset:")
print(df)

# Step 4: Separate Input and Output
X = df[["Experience"]]
y = df["Salary"]

# Step 5: Create Model
model = LinearRegression()

# Step 6: Train Model
model.fit(X, y)

# Step 7: Predict Salary
experience = [[9]]
prediction = model.predict(experience)

# Step 8: Display Result
print("\nPredicted Salary for 9 years experience = ₹", round(prediction[0],2))

🔄 Workflow


Start
   │
   ▼
Import Libraries
   │
   ▼
Create Dataset
   │
   ▼
Display Dataset
   │
   ▼
Separate X and y
   │
   ▼
Create Linear Regression Model
   │
   ▼
Train Model using fit()
   │
   ▼
Predict using predict()
   │
   ▼
Display Prediction
   │
   ▼
End

📌 Explanation of Important Functions

Function	Purpose
`pd.DataFrame()`	Creates a table from data
`LinearRegression()`	Creates the regression model
`fit(X, y)`	Trains the model using the dataset
`predict()`	Predicts the output for new input

✅ Advantages

Simple and easy to implement
Fast training and prediction
Easy to interpret results
Works well for linear relationships

❌ Limitations

Only models linear relationships
Sensitive to outliers
Performance decreases if data is non-linear

🌍 Applications

Salary Prediction
House Price Prediction
Sales Forecasting
Stock Trend Analysis
Weather Forecasting
Business Revenue Prediction

⭐ Memory Trick


Import Libraries
        ↓
Create Dataset
        ↓
Separate X and y
        ↓
Create Model
        ↓
Train using fit()
        ↓
Predict using predict()
        ↓
Display Result

Easy Formula to Remember:
Import → Data → X & y → Model → Fit → Predict → Output

🎓 Viva Questions

What is Linear Regression?
Why is it called a supervised learning algorithm?
What are the independent and dependent variables?
What is the purpose of fit()?
What is the purpose of predict()?
What is the equation of a regression line?
What is the role of X and y?
Give two real-life applications of Linear Regression.

Comparison of Different Types of Machine Learning

🌈 Comparison of Different Types of Machine Learning

📊 Complete Comparison Table

📌 Feature	🟦 Supervised Learning	🟩 Unsupervised Learning	🟪 Reinforcement Learning	🟨 Semi-Supervised Learning
📖 Definition	Learns from labeled data where the correct output is already known.	Learns from unlabeled data to discover hidden patterns and relationships.	Learns by interacting with the environment using rewards and penalties.	Learns using both labeled and unlabeled data.
🏷️ Data Type	Labeled Data	Unlabeled Data	Reward-based Data	Partially Labeled Data
👨‍🏫 Teacher / Supervisor	✅ Required	❌ Not Required	❌ Not Required	✅ Small Amount of Guidance
🎯 Goal	Predict the correct output.	Find hidden patterns or groups.	Learn the best action to maximize reward.	Improve prediction using limited labeled data.
🧠 Learning Method	Learns from examples with known answers.	Learns by finding similarities among data.	Learns through trial and error.	Learns from labeled data and improves using unlabeled data.
📤 Output	Predicted Class or Value	Clusters, Groups, Patterns	Best Action (Optimal Policy)	Improved Prediction
📂 Data Labels	✅ Available	❌ Not Available	❌ Not Required	⚠️ Partially Available
📈 Accuracy Evaluation	Easy to evaluate	Difficult to evaluate	Based on total reward	Moderate
⚙️ Main Techniques	Classification, Regression	Clustering, Association, Dimensionality Reduction	Q-Learning, Deep Q Network (DQN), Policy Learning	Self-Training, Co-Training, Label Propagation
💰 Cost of Data Preparation	High (Labeling Required)	Low	Medium	Medium
⏱️ Training Time	Medium	Medium	High	Medium
🎓 Best Used When	Correct output is already known.	No labels are available.	Sequential decision-making is required.	Only a small amount of labeled data is available.

🌍 Real-Life Examples

Learning Type	Example
🟦 Supervised Learning	🏦 Bank Loan Approval
🟩 Unsupervised Learning	🛒 Customer Segmentation in a Shopping Mall
🟪 Reinforcement Learning	🤖 Delivery Robot Learning the Best Route
🟨 Semi-Supervised Learning	🏥 Medical X-ray Disease Detection

🌟 Advantages Comparison

Learning Type	Major Advantages
🟦 Supervised	✅ High Accuracy, Easy Evaluation
🟩 Unsupervised	✅ Finds Hidden Patterns, No Labels Needed
🟪 Reinforcement	✅ Learns Best Decisions Through Experience
🟨 Semi-Supervised	✅ Reduces Labeling Cost, Better Accuracy

❌ Limitations Comparison

Learning Type	Major Limitations
🟦 Supervised	❌ Requires Large Labeled Dataset
🟩 Unsupervised	❌ Results Can Be Difficult to Interpret
🟪 Reinforcement	❌ Training Takes Long Time and Many Trials
🟨 Semi-Supervised	❌ Depends on the Quality of Labeled Data

📚 Common Algorithms

Learning Type	Popular Algorithms
🟦 Supervised	Linear Regression, Logistic Regression, Decision Tree, Random Forest, SVM, KNN, Naïve Bayes
🟩 Unsupervised	K-Means, Hierarchical Clustering, DBSCAN, Apriori, PCA
🟪 Reinforcement	Q-Learning, SARSA, Deep Q Network (DQN), Actor-Critic
🟨 Semi-Supervised	Self-Training, Label Propagation, Co-Training, Semi-Supervised SVM

🎯 Quick Revision Table

Question	🟦 Supervised	🟩 Unsupervised	🟪 Reinforcement	🟨 Semi-Supervised
Uses Labeled Data?	✅ Yes	❌ No	❌ No	✅ Partially
Uses Unlabeled Data?	❌ No	✅ Yes	❌ No	✅ Yes
Uses Rewards?	❌ No	❌ No	✅ Yes	❌ No
Needs a Teacher?	✅ Yes	❌ No	❌ No	✅ Partially
Learns by Trial & Error?	❌ No	❌ No	✅ Yes	❌ No
Finds Hidden Patterns?	❌ No	✅ Yes	❌ No	⚠️ Partially
Makes Predictions?	✅ Yes	❌ No	✅ Yes (Best Action)	✅ Yes

📝 Exam Tip (Easy Memory Trick)

Learning Type	Remember As
🟦 Supervised Learning	📚 Learn with a Teacher (Labeled Data)
🟩 Unsupervised Learning	🔍 Discover Hidden Patterns (Unlabeled Data)
🟪 Reinforcement Learning	🏆 Learn by Rewards & Penalties
🟨 Semi-Supervised Learning	📖 Learn from a Few Labels + Many Unlabeled Data

⭐ One-Line Revision

Learning Type	One-Line Summary
🟦 Supervised Learning	Labeled Data → Learn → Predict Output
🟩 Unsupervised Learning	Unlabeled Data → Find Hidden Patterns
🟪 Reinforcement Learning	Action → Reward/Penalty → Learn Best Decision
🟨 Semi-Supervised Learning	Few Labels + Many Unlabeled Data → Better Prediction

Semi-Supervised Learning

#️⃣ Semi-Supervised Learning

🏥 Example: Medical Image Classification

🟦 1. 📖 Introduction

💡 Semi-Supervised Learning is a type of Machine Learning that combines a small amount of labeled data with a large amount of unlabeled data.

It is useful when labeling data is expensive, time-consuming, or requires expert knowledge. The algorithm first learns from the labeled data and then uses the unlabeled data to improve its performance.

🌟 Definition

✅ Semi-Supervised Learning is a machine learning technique that uses both labeled and unlabeled data for training. A small amount of labeled data guides the model, while a large amount of unlabeled data helps improve learning and prediction accuracy.

🟩 2. 🏥 Real-Life Example

A hospital wants to build an AI system to detect Pneumonia from chest X-ray images.

The hospital has:

📷 10,000 X-ray Images

However,

✔ Only 1,000 images have been examined and labeled by doctors.

❓ The remaining 9,000 images have no labels.

Instead of ignoring the unlabeled images, the AI learns from both labeled and unlabeled images.

🟨 3. 🔄 Step-by-Step Working

🟢 Step 1 : 📥 Collect Input Data

The hospital collects thousands of chest X-ray images.

Available Data

📷 Chest X-ray Images

👨 Patient Information

📅 Examination Date

🏥 Hospital Records

This is called the Input Dataset.

🟢 Step 2 : 🏷️ Partial Labeling

Doctors examine only a small number of images.

Example

🩻 X-ray Image	🏷️ Label
Image 1	✅ Pneumonia
Image 2	❌ Normal
Image 3	✅ Pneumonia
Image 4	❓ Unknown
Image 5	❓ Unknown

📌 Only some images have labels.

The remaining images are Unlabeled Data.

🟢 Step 3 : 🤖 Train the Machine Learning Model

The model first learns from the labeled X-ray images.

It understands important features such as:

🫁 Lung Infection

🌫 White Spots

🩻 Abnormal Lung Patterns

These features help the model recognize pneumonia.

🟢 Step 4 : 📂 Use Unlabeled Data

The model now studies the unlabeled X-ray images.

It compares them with the labeled examples.

The algorithm gradually predicts labels for images that were previously unlabeled.

🟢 Step 5 : 🧠 Improve Learning

As more unlabeled images are analyzed,

✔ The model becomes smarter.

✔ Prediction accuracy improves.

✔ The AI discovers more disease patterns.

Thus, both labeled and unlabeled data contribute to better learning.

🟢 Step 6 : 🎯 Prediction

A new patient's X-ray is provided.

Example

🩻 New X-ray Image

↓

🤖 Machine Learning Model

↓

✅ Prediction: Pneumonia Detected

❌ Prediction: Normal Lungs

🟥 4. 🔄 Semi-Supervised Learning Workflow

📥 Input Dataset
(Labeled + Unlabeled Images)
            │
            ▼
🏷️ Small Amount of Labeled Data
            │
            ▼
📂 Large Amount of Unlabeled Data
            │
            ▼
🤖 Machine Learning Model
            │
            ▼
🧠 Learns from Both Types of Data
            │
            ▼
🎯 Disease Prediction

🟪 5. 📋 Important Components

🧩 Component	📖 Description
📥 Input Data	Medical X-ray Images
🏷️ Labeled Data	Images labeled by doctors
❓ Unlabeled Data	Images without labels
🤖 Machine Learning Model	Learns from both datasets
🎯 Output	Disease Prediction

🟦 6. ⚖️ Comparison of Data

📊 Data Type	Example
🏷️ Labeled Data	1,000 X-ray images with diagnosis
❓ Unlabeled Data	9,000 X-ray images without diagnosis

🟩 7. 🌍 Applications

🏥 Medical Image Diagnosis

📧 Email Classification

😊 Face Recognition

🗣 Speech Recognition

🚗 Autonomous Vehicles

📄 Document Classification

🌾 Crop Disease Detection

🛰 Satellite Image Analysis

🟦 8. ✅ Advantages

✔ Requires fewer labeled examples

✔ Reduces labeling cost

✔ Improves prediction accuracy

✔ Makes use of large unlabeled datasets

✔ Useful when expert labeling is expensive

🟥 9. ❌ Limitations

❌ Incorrect unlabeled data may reduce accuracy

❌ More complex than supervised learning

❌ Requires careful model design

❌ Performance depends on the quality of labeled data

🟨 10. ⭐ Comparison of Learning Types

🟢 Supervised	🔵 Unsupervised	🟣 Semi-Supervised
Only labeled data	Only unlabeled data	Both labeled and unlabeled data
Teacher available	No teacher	Small amount of labeled guidance
Predicts output	Finds patterns	Improves prediction using both datasets

🟥 11. 📝 Examination Definition

💡 Semi-Supervised Learning is a machine learning technique that uses both labeled and unlabeled data for training. The model learns from a small amount of labeled data and improves its performance by utilizing a large amount of unlabeled data.

🌟 🎯 Exam Tip

🔑 Remember This Sequence

📥 Input Data

⬇️

🏷️ Small Labeled Data

➕

❓ Large Unlabeled Data

⬇️

🤖 Machine Learning Model

⬇️

🧠 Learning Process

⬇️

🎯 Prediction

⭐ One-Line Revision

📚 Semi-Supervised Learning = Small Labeled Data + Large Unlabeled Data + Better Prediction

SEM 1	SEM 2	SEM 3
SEM 4	SEM 5	SEM 6

SEM 1	SEM 2	SEM 3
SEM 4	SEM 5	SEM 6

SEM 1	SEM 2	SEM 3
SEM 4	SEM 5	SEM 6

CLASS-4	CLASS-5	CLASS-6
CLASS-7	CLASS-8	CLASS-9
CLASS10	CLASS11 application	CLASS12 application
CLASS11 science	CLASS12 science

C	C++	CORE JAVA	SQL	PYTHON
MS OFFICE	HTML	VISUAL BASIC	advanced java	8085
PROLOG	ASSEMBLY LANGUAGE	JAVA SCRIPT	SHELL PROGRAMMING	R
DIGITAL ELECTRONICS	COMPUTER ARCHITECTURE	DATA STRUCTURE	OPERATING SYSTEM	GRAPH THEORY
DISCRETE MATHEMATICS	NUMERICAL ALGORITHM	AUTOMATA	MICROPROCESSOR	NETWORKING
GRAPHICS	SOFTWARE ENGINEERING	DATABSE	ANALYSIS OF ALGORITHM	IMAGE PROCESSING
ARTIFICIAL INTELLIGENCE	BIG DATA	CLOUD COMPUTING	DATA MINING	INTERNET TECHNOLOGY

CU BSC computer science old syllabus	WBSU BSC computer science old syllabus
CU cbcs BSC computer science HONOURS syllabus 2018	WBSU cbcs BSc computer science HONOURS syllabus 2018
CU cbcs BSC computer science GENERAL syllabus 2018	WBSU cbcs BSC computer science GENERAL syllabus 2018

Total Pageviews

Monday, June 29, 2026