EDA and Machine Learning Models in R and Python (Regression, Classification, Clustering, SVM, Decision Tree, Random Forest, Time-Series Analysis, Recommender System, XGBoost)
Packages/Libraries used for data analyis and building Machine learning models
| Data Operations | Python | R | |:----------------------------|:------------------- |---------------------------------------------------------------------------| | Data Manipulation | Pandas | dplyr, plyr, tidyr, stringr, data.table, lubridate(for date manipulation) | | Data Visualization | matplotlib, seaborn | ggplot2, cowplot, ggthemes, scales | | Recommender Model | | recommenderlab | | Text Mining | nltk, spaCy | tm, tidyverse | | ML Models | scikit-learn, PyCaret | randomForest, rpart, caret, lm, glm, forecast, tseries, kernlab |
ML and EDA Projects
| Projects | Algorithms | Programming Languages | |:----------------------------|:------------------------------------------------|-------------------------------| |Abnormal Blood Pressure Classification | Logistic Regression, Decision Trees, Random Forest, XGBoost, LightGBM and other classification algorithms| Python | |AirBnB Price Prediction | XGBoost | R | |Amaze Payment Solution EDA | EDA | R | |Amazon Marketplace Best Sellers Identification | K-Means | Python | |Beer Recommendation System | Collaborative Filtering, Content-Based Filtering | R | |Breast Cancer Prediction | AdaBoost | Python | |Car Pricing Model | Linear Regression | R | |Credit Card Defaulter | Random Forest | R, Python | |Credit Risk Analysis | EDA | R | |Credit Worthiness For Rural India | Linear/Lasso/Ridge/Elastic Net Regression, Decision Tree Regressor, Random Forest Regressor and other Regression algorithms | Python | |Customer Segmentation | K-Means, hierarchical clustering | R | |Digital Media Company Viewership Prediction | | Python | |Email Classification | Linear SVM | R, Python | |Employee Attrition Model | Logistic Regression | R | |Global Investment Trends | EDA | R | |Handwritten Digit Recognition| SVM (Linear and RBF) | R | |Heart Disease Classification | Decision Tree | Python | |Housing Price Prediction | Linear Regression(OLS) | Python | |Letter Recognition | SVM (Linear and RBF) | Python | |Loan Defaulter-EDA | EDA | R | |Monthly Income | Decision Tree | R | |Movie Recommendation System | Collaborative Filtering, Content-Based Filtering| R | |RTO Prediction | Logistic Regression, Decision Trees, Random Forest, XGBoost, LightGBM and other classification algorithms| Python | |SMS Classification | Multinomial and Bernoulli Naive Bayes | Python | |SaavnEcommAdsSegmentation | Clustering (k-prototype) | R | |Sales and Demand Forecasting | Time-Series (ARMA, ARIMA) | R | |Telecom Churn Model | Logistic Regression | R, Python | |Transaction-data-analysis-and-prediction | Time-Series(ARIMA) | R | |Uber Supply-Demand Gap | EDA | R |
Additional Reading
Click to expand!
- To know more about dummy variables (here)
- Why it's necessary to create dummy variables (here)
- Missing Values Imputation
- When to Normalize or Standardize the variables?
- Parametric v/s non parametric models in short and detailed
- Regression guarantees interpolation of data and not extrapolation
- Optimization Methods (here)
- Regularization in Machine Learning (here)
- A brief overview of Feature Scaling (here)
- When to standardise, when to normalise (here)
- All about When and How to do traintestsplit and pre_processing
- Dimensionality Reduction Algorithmns (here)
- Feature Selection (here)
- Naive Bayes Classification explanation (here)
- Factor Analysis
- Implementing recommendation systems
- Understanding ROC curve (here)
- Feature Engineering and it's importance (here)
- Explanation of linear or linearity in Linear Regression
- Techniques for handling Class Imbalance in Dataset
- XGBoost
- LightGBM
- Logistic Regression (here)
- Voting Ensembles
- Time-Series forecasting in Python(AR, MA, ARIMA, SARIMA and SARIMAX model) (here)
- Multivariate time-series forecasting
- Missing values Imputation
- LightGBM Vs XGBoost
- Gradient Descent
- Gradient
- Stochastic Gradient
- Clustering
- KNN Overview and finding optimal value of K (here)
- Which Classification metric to choose and when?
- Ways of Encoding Categorical variables
