Course Content
Module 1: Introduction to Data Science
This module introduced Data Science basics, its applications and career scope. We learned the role of a Data Scientist, their skills & responsibilities. The workflow (collection → cleaning → analysis → modeling → deployment) was explained. We also saw common tools (Python, R, SQL, Jupyter) and the difference between Data Science, AI, ML & Deep Learning.
0/5
Lesson 1.1: What is Data Science? – Definition, Applications & Career Scope
Lesson 1.2: Role of Data Scientist – Skills & Responsibilities
Lesson 1.3: Data Science Workflow – Data Collection → Cleaning → Analysis → Modeling → Deployment
Lesson 1.4: Tools and Technologies Used in Data Science (Python, R, Jupyter, SQL, etc.)
Lesson 1.5: Difference between Data Science, AI, ML, and Deep Learning
Module 2: Python for Data Science
In this module, you learned the fundamentals of Python programming tailored for Data Science. You explored Python basics, control structures, functions, and built-in data structures. You also mastered file handling, exception handling, and essential data science libraries such as NumPy (arrays & computations), Pandas (data manipulation & cleaning), and Matplotlib/Seaborn (data visualization). 👉 After completing this module, you are now ready to analyze, clean, and visualize real-world datasets using Python.
0/10
Lesson 2.1: Python Basics – Variables, Data Types, Operators
Lesson 2.2: Control Structures – if-else, loops
Lesson 2.3: Functions and Modules in Python
Lesson 2.4: Data Structures in Python (List, Tuple, Set, Dictionary)
Lesson 2.5: File Handling & Exception Handling in Python
Lesson 2.6: NumPy – Arrays & Mathematical Operations
Lesson 2.7: Pandas – DataFrames & Data Analysis
Lesson 2.8: Matplotlib & Data Visualization
Lesson 2.9: Seaborn for Advanced Visualization
Lesson 2.10: Pandas Advanced Operations (Grouping, Merge, Join, Pivot Tables)
Module 3: Data Handling & Preprocessing
In this module, you learned how to prepare raw data for Machine Learning models: Introduction to NumPy & Pandas → Efficient libraries for data manipulation. Importing & Exploring Data → Loading datasets, checking structure, missing values. Data Cleaning → Handling missing values, duplicates, and inconsistencies. Feature Engineering → Creating new features, scaling & normalization. Encoding Categorical Data → One-hot encoding, label encoding. Handling Outliers → Detecting and treating unusual data points. Splitting Data → Train/Test Split & Cross Validation for model evaluation. ✅ By the end of this module, you now understand how to clean, transform, and prepare datasets so that ML models can learn effectively.
0/7
Lesson 3.1: Understanding Data – Structured vs Unstructured
Lesson 3.2: Data Collection Methods – APIs, Web Scraping, Databases
Lesson 3.3: Handling Missing Data – Mean/Median, Interpolation, Dropping
Lesson 3.4: Handling Outliers – IQR, Z-Score
Lesson 3.5: Data Encoding – One Hot Encoding, Label Encoding
Lesson 3.6: Feature Scaling – Normalization, Standardization
Lesson 3.7: Splitting Data – Train/Test Split, Cross Validation
Module 4: Exploratory Data Analysis (EDA)
Exploratory Data Analysis (EDA) helps to understand data using statistics and visualizations. It identifies patterns, trends, correlations, and anomalies before model building.
0/6
Lesson 4.1: Introduction to EDA – Why and How
Lesson 4.2: Descriptive Statistics – Mean, Median, Mode, Variance, Std Dev
Lesson 4.3: Data Visualization – Histogram, Scatter Plot, Box Plot, Heatmaps
Lesson 4.4: Correlation Analysis
Lesson 4.5: Identifying Patterns and Trends in Data
Lesson 4.6: Hands-on EDA Project (Titanic Dataset Example)
Module 5: Statistics & Probability for Data Science
In this module, you will learn the fundamentals of statistics and probability that form the backbone of data science. You’ll explore how to work with population and samples, understand probability distributions like Normal, Binomial, and Poisson, and perform hypothesis testing with p-values. You will also study confidence intervals, advanced tests like ANOVA and Chi-square, and finally learn to distinguish between correlation and causation. By the end of this module, you’ll have the statistical knowledge required to analyze data rigorously and make reliable, data-driven decisions.
0/6
Lesson 5.1: Basics of Statistics – Population vs Sample
Lesson 5.2: Probability & Probability Distributions (Normal, Binomial, Poisson)
Lesson 5.3: Hypothesis Testing – Null & Alternative Hypothesis, p-value
Lesson 5.4: Confidence Intervals
Lesson 5.5: ANOVA & Chi-square Test
Lesson 5.6: Correlation vs Causation
Module 6: Introduction to Machine Learning
This module introduces the fundamentals of Machine Learning (ML) – the science of building algorithms that learn from data. You will learn what ML is, its main types, the typical workflow of ML projects, and important concepts like bias, variance, underfitting, overfitting, and validation techniques. By the end, you’ll have a clear foundation for understanding and applying ML models.
0/4
Lesson 6.1: What is Machine Learning? – Definition & Types
Lesson 6.2: ML Workflow – Training, Testing, Evaluation
Lesson 6.3: Bias vs Variance – Underfitting & Overfitting
Lesson 6.4: Train/Test Split & Cross-Validation
Module 7: Supervised Learning Algorithms
This module covers Supervised Learning, where models learn from labeled data to make predictions. You will learn popular regression and classification algorithms, including Linear Regression, Logistic Regression, KNN, Decision Trees, Random Forest, SVM, and Naive Bayes. You’ll also study evaluation metrics for both regression and classification problems to measure model performance accurately. By the end of this module, you’ll be able to apply supervised learning algorithms to real-world datasets and evaluate their performance.
0/11
Lesson 7.1: Linear Regression
Lesson 7.2: Multiple Linear Regression
Lesson 7.3: Polynomial Regression
Lesson 7.4: Evaluation Metrics for Regression (MAE, MSE, R²)
Lesson 7.5: Logistic Regression
Lesson 7.6: K-Nearest Neighbors (KNN)
Lesson 7.7: Decision Trees
Lesson 7.8: Random Forest
Lesson 7.9: Support Vector Machine (SVM)
Lesson 7.10: Naive Bayes
Lesson 7.11: Evaluation Metrics for Classification (Accuracy, Precision, Recall, F1, ROC, AUC)
Module 8: Unsupervised Learning Algorithms
This module introduces Unsupervised Learning, where models learn from unlabeled data to find hidden patterns, clusters, or associations. You will explore popular clustering algorithms like K-Means, Hierarchical, and DBSCAN, understand dimensionality reduction using PCA, and learn association rule mining techniques such as Apriori for market basket analysis. By the end of this module, you’ll be able to group similar data, reduce complexity, and discover meaningful relationships in datasets.
0/5
Lesson 8.1: K-Means Clustering
Lesson 8.2: Hierarchical Clustering
Lesson 8.3: DBSCAN Clustering
Lesson 8.4: Dimensionality Reduction – PCA
Lesson 8.5: Association Rule Learning – Apriori, Market Basket Analysis
Module 9: Feature Engineering & Model Improvement
This module focuses on enhancing model performance through feature engineering and optimization techniques. You will learn how to select important features, handle imbalanced data, apply regularization, tune hyperparameters, and use advanced ensemble learning methods like Bagging, Boosting (AdaBoost, XGBoost, LightGBM) to improve model accuracy and robustness. By the end of this module, you’ll be able to build more accurate and generalizable models for real-world datasets.
0/5
Lesson 9.1: Feature Selection Techniques
Lesson 9.2: Handling Imbalanced Data – SMOTE, Undersampling/Oversampling
Lesson 9.3: Regularization – L1 (Lasso), L2 (Ridge)
Lesson 9.4: Hyperparameter Tuning – Grid Search, Random Search
Lesson 9.5: Ensemble Learning – Bagging, Boosting (AdaBoost, XGBoost, LightGBM)
Module 10: Neural Networks & Deep Learning (Basics)
This module introduces the fundamentals of Neural Networks and Deep Learning. You will learn about neurons, perceptrons, activation functions, forward and backward propagation, and get hands-on experience with TensorFlow/Keras to build a simple neural network. By the end of this module, you’ll understand how deep learning models process data and make predictions, laying the foundation for advanced neural network architectures.
0/5
Lesson 10.1: What is Neural Network? – Neurons & Perceptron
Lesson 10.2: Activation Functions – Sigmoid, ReLU, Softmax
Lesson 10.3: Forward Propagation & Backpropagation (Conceptual)
Lesson 10.4: Introduction to TensorFlow/Keras
Lesson 10.5: Building a Simple Neural Network
Module 11: Working with Real-World Data
This module focuses on applying data science and machine learning concepts to real-world datasets. You will explore datasets from Kaggle and UCI, and complete hands-on projects including regression (house prices), classification (Titanic survival), and clustering (customer segmentation). By the end of this module, you’ll gain practical experience in handling, analyzing, and modeling real-world data, preparing you for professional data science tasks.
0/4
Lesson 11.1: Introduction to Kaggle & UCI Datasets
Lesson 11.2: Project 1 – Predicting House Prices (Regression)
Lesson 11.3: Project 2 – Titanic Survival Prediction (Classification)
Lesson 11.4: Project 3 – Customer Segmentation (Clustering)
Module 12: Model Deployment (Basics)
This module introduces the basics of deploying machine learning models so that they can be used in real-world applications. You will learn how to save trained models, and deploy them using Flask or Streamlit for interactive web-based applications. By the end of this module, you’ll understand how to make your ML models accessible and usable beyond local environments.
0/4
Lesson 12.1: Introduction to Deployment
Lesson 12.2: Saving Models with Pickle/Joblib
Lesson 12.3: Deploying ML Models with Flask / Streamlit
Lesson 12.4: Hosting Models on Cloud (Heroku, AWS – Basic Intro)
Module 13: Ethics & Future of Data Science
This module focuses on the ethical, social, and professional aspects of data science and machine learning. You will learn about data privacy, security, bias, fairness, and explainable AI (XAI). The module also provides guidance on career paths, skills, and opportunities in the data science field. By the end of this module, you’ll understand the responsible and ethical use of data and be aware of future trends and career growth.
0/4
Lesson 13.1: Data Privacy & Security Issues
Lesson 13.2: Bias and Fairness in Machine Learning
Lesson 13.3: Explainable AI (XAI) – Why it Matters
Lesson 13.4: Career Paths in Data Science & ML
Data Science & Machine Learning – Final Assessment
Test your knowledge and skills from all modules of this course. This assessment evaluates your understanding of Python, data handling, ML algorithms, model deployment, and ethical AI practices.
0/1
Final Multiple Choice Questions (MCQ)
Data Science and Machine Learning Basics

Lesson 3.7: Splitting Data – Train/Test Split, Cross Validation

🔹 Train/Test Split

When building a Machine Learning model, we need to evaluate its performance on new, unseen data.
For this, the dataset is divided into:

  1. Training Set → Used to train the model.

  2. Testing Set → Used to evaluate how well the model performs.

👉 Example using Scikit-learn:

 
from sklearn.model_selection import train_test_split
import pandas as pd

# Example dataset
data = {'X1': [1,2,3,4,5,6,7,8,9,10],
'X2': [5,6,7,8,9,1,2,3,4,5],
'y': [0,1,0,1,0,1,0,1,0,1]}
df = pd.DataFrame(data)

# Split into train (80%) and test (20%)
X = df[['X1','X2']]
y = df['y']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

print("Train size:", X_train.shape)
print("Test size:", X_test.shape)

✅ This ensures that the model does not memorize the data but learns patterns.

🔹 Cross Validation

Instead of a single train-test split, Cross Validation (CV) improves model evaluation.

  • The dataset is split into k parts (folds).

  • The model is trained on k-1 folds and tested on the remaining fold.

  • This process is repeated k times, and results are averaged.

👉 Example using K-Fold Cross Validation:

 
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
import numpy as np

model = LogisticRegression()

# Perform 5-Fold Cross Validation
scores = cross_val_score(model, X, y, cv=5)

print("Cross-validation scores:", scores)
print("Average accuracy:", np.mean(scores))

✅ CV helps ensure the model works well on different subsets of the data.

📌 Summary

  • Train/Test Split → Quick evaluation (e.g., 80% train, 20% test).

  • Cross Validation → More reliable evaluation, reduces risk of overfitting/underfitting.

  • Both techniques are essential in Machine Learning pipelines.

Previous
Next
Scroll to Top