Data Science Portfolio

Repository containing portfolio of data science projects completed by me for academic, self learning, and hobby purposes. Presented in the form of Jupyter Notebook.

Contents

• Data Analysis

  • IPL Dataset Analysis: Performed data cleaning,Analysis and visualization operation on ipl dataset and answering questions
  • Tiatnic Dataset Exploratory Analysis: Exploratory Analysis of the passengers onboard RMS Titanic using Pandas and Seaborn visualisations.
  • 911 Calls - Exploratory Analysis: Exploratory Data Analysis of the 911 calls dataset hosted on Kaggle. Demonstrates extraction of useful features from different variables.
  • 2016 US General Election Poll Data Analysis: Performed simple data analysis on 2016 US General Election Poll data.

• Machine Learning Algorithms From Scratch

  • Linear Regression From Scratch: Created Linear Regression algorithm from scratch with gradientDescent and applied it on a dataset
  • Logistic Regression From Scratch: Created Logistic Regression algorithm from scratch with sigmoid and cost function and applied it on iris dataset.
  • Support Vector Machine From Scratch: Created Support Vector Machine from scratch and created hyperplane with help of support vectors.
  • K Nearest Neighbour(KNN) From Scratch: Created K Nearest Neighbour (KNN) Algorithm from scratch with help of euclidean distance.

• Machine Learning Projects

  • ML with Logistic Regression: Using Logistic Regression to predict whether an internet user clicked an ad or not.
  • ML with Linear Regression: Using Linear Regression to predict whether an customer use mobile app or store website to buy product based on time spent on these.
  • ML with K Nearest Neighbours: Using KNN to classify instances from a fake dataset into two target classes, while choosing the best value for K using the elbow method.
  • ML with Support Vector Machine: Using Support Vector Machine to classify flowers from a famous iris dataset set into diffrent categories.

• Deep Neural Network Projects(AI)

  • Image Captioning By Neural Network: Created a Convolution Neural Network Which predict caption's for image's. Trained on Flickr images dataset.
  • Digit Recognition Deep Learning: Designing and implementing a Convolutional Neural Network that learns to recognize sequences of digits using synthetic data generated by concatenating images from MNIST.
  • Automatic text Generation By Neural Network: Created a Recurrence Neural Network With LSTM layer that will Automatically write text based on there previous text.
  • CNN On Fashion Dataset: Created a Convolution Neural Network on fashion dataset provided by MNIST.

• Data Visualization And Cleaning

  • Data Cleaning Operations: Performed Some data cleaning strategy and operation's on multiple dataset.
  • Data Animation and visualization:Performed data visualization operation by matplotlib,seaborn libraries on multiple data set's.

If you liked what you saw, want to have a chat with me about the portfolio, work opportunities, or collaboration, shoot an email at [email protected].