Data Science Micro Projects

Repository containing portfolio of data science projects completed by me for academic, self learning, and hobby purposes. Presented in the form of iPython Notebooks & .py files( modularize codes).

Contents

---

• Machine Learning(ML) Micro Projects

  • ML Micro Project - Diabetes Prediction:

    • Predict whether a patient is diabetic or not using their medical data. Have trained a SVM model using "linear" kernel as a classifier. The code is modularized for deployment.

  • ML Micro Project - Sonar Rock vs Mine Prediction:

    • Trained a classifier on the SONAR data to predict whether the object is Rock or Mine. Have used a Logistic Regression model to train the model. The code is modularized for deployment.

  • ML Micro Project - House Price Prediction:

    • Predict the price of the house using Boston House Price dataset. Have used LGBM model and implemented hyper-parameter tuning Optuna. The code is modularized for deployment.

  _Tools & libraries: scikit-learn, Numpy, Pandas, Seaborn, Matplotlib, Optuna

---

• Deep Learning(DL) Projects

  • DL Project - NYC Taxi Fare Prediction:

    • Predict taxi fare using the NYC Taxi Fare dataset.
    • Trained a Neural Network model using pytorch to predict the fare using the avaiable coordinates data.
    • The code is modularized for deployment.

  • DL Project- Income Prediction:

    • Trained a binary classifier model to predict if an individual earns >$50k.
    • Trained a Neural Network model as classifier. The code is modularized for deployment.

  • DL Project- Alcohol Sales Prediction:

    • Trained a LSTM model to forecast future alcohol sales.

  • DL Project- CIFAR:

    • Trained a CNN Network on CIFAR dataset.

  _Tools & libraries: torch, Numpy, Pandas, Seaborn, Matplotlib*

---

• Natural Language Processing(NLP) Projects

  • ML Micro Project - Fake News Prediction:
    • Trained a classifer to predict whether an article is fake or not using only the article title.

  _Tools & libraries: spacy, NLTK, scikit-learn, Numpy, Pandas, Seaborn, Matplotlib*

---

• ML Models with Mini Project

  • Focused on implementation of Machine Learning Models on sample data. The aim of these mini projects is to perform basic EDA on the data and implement the ML model to understand the fit and evaluate their performance

  _Tools & libraries: scikit-learn, Pandas, Seaborn, Matplotlib

---

• Visualization

  • Focused on creating visualizations to perform EDA in Machine Learning Models. Have implemented functional & OOP approach to plot.

  _Tools & libraries: Seaborn, Matplotlib, Plotly, Cufflinks