🎓 INTERMEDIATE-LEVEL DATA SCIENCE SYLLABUS

Duration: 6–10 Weeks
Prerequisite: Basics of Python, Pandas, NumPy, Matplotlib
Goal: Start building real ML models + SQL + EDA + feature engineering

⭐ Module 1: Data Wrangling & Cleaning (Intermediate)

Topics:

• Handling missing values (advanced)
  
  

• Outlier detection (IQR, Z-score)
  
  

• Data transformations:
  
  

  • Log transformation
    
    

  • Scaling (StandardScaler, MinMaxScaler)
    
    

  • Encoding (Label encoding, One-hot encoding)
    
    

• Combining & merging multiple datasets
  
  

• Feature selection basics
  
  

Hands-on:

• Clean a large CSV dataset
  
  

• Fix missing values
  
  

• Handle outliers
  
  

• Encode categorical data
  
  

⭐ Module 2: Exploratory Data Analysis (EDA)

Topics:

• Summary statistics
  
  

• Distribution analysis
  
  

• Correlation heatmaps
  
  

• Pairplot analysis
  
  

• Identifying patterns & trends
  
  

• Removing skewness
  
  

Tools:

• Matplotlib
  
  

• Seaborn
  
  

Hands-on:

• EDA on a Real Dataset (Students / Sales / House Prices)
  
  

• Create 10 charts
  
  

• Create a full EDA report
  
  

⭐ Module 3: SQL for Data Science (Intermediate)

Topics:

• GROUP BY and HAVING
  
  

• JOINs (Inner, Left, Right, Full)
  
  

• Window Functions:
  
  

  • ROW_NUMBER
    
    

  • RANK
    
    

  • SUM() OVER()
    
    

• CTEs (Common Table Expressions)
  
  

• Subqueries
  
  

Hands-on:

• Build analytics queries
  
  

• Create a mini SQL project on sales dataset
  
  

⭐ Module 4: Machine Learning (Core Algorithms)

Algorithms you learn:

• Linear Regression (review)
  
  

• Logistic Regression
  
  

• Decision Trees
  
  

• Random Forest
  
  

• KNN (K-Nearest Neighbor)
  
  

• Naive Bayes
  
  

• K-Means Clustering (unsupervised)
  
  

ML Concepts:

• Train-test split
  
  

• Cross-validation
  
  

• Bias vs Variance
  
  

• Confusion Matrix
  
  

• Precision, Recall, F1 Score
  
  

• Overfitting & Underfitting
  
  

Hands-on:

• Build classification & regression models
  
  

• Compare accuracies
  
  

• Tune hyperparameters
  
  

⭐ Module 5: Feature Engineering (Intermediate)

Topics:

• Feature scaling
  
  

• Normalization
  
  

• Binning / Bucketing
  
  

• Polynomial features
  
  

• Feature importance
  
  

• Removing multicollinearity (VIF)
  
  

Hands-on:

• Improve model accuracy with feature engineering
  
  

• Feature selection experiments
  
  

⭐ Module 6: Data Visualization & Storytelling

Topics:

• Advanced visualizations:
  
  

  • Boxplots
    
    

  • Heatmaps
    
    

  • Violin plots
    
    

  • Pairplots
    
    

• Plot styling
  
  

• Insights narration
  
  

Hands-on:

• Create an insights dashboard
  
  

• Present visual findings to a client
  
  

⭐ Module 7: Intermediate Machine Learning Project

Choose any one project:

📌 Project 1: Student Performance Predictor
📌 Project 2: Sales Forecasting Model
📌 Project 3: Customer Segmentation (K-Means)
📌 Project 4: Loan Eligibility Classification
📌 Project 5: House Price Prediction (Regression)

Deliverables:

• Data cleaning
  
  

• EDA
  
  

• Model building
  
  

• Model comparison
  
  

• Final accuracy report
  
  

• Visual presentation
  
  

⭐ Bonus (Optional: Highly Useful)

Additional Skills:

• Git & GitHub for version control
  
  

• Virtual environments
  
  

• API basics
  
  

• How to read research papers
  
  

🎯 Output After Completing the Course

You will be able to:

✔ Clean and prepare real-world datasets
✔ Perform full EDA
✔ Write advanced SQL queries
✔ Build multiple ML models
✔ Choose best model using evaluation metrics
✔ Create intermediate-level data science projects