mrc03
Data Scientist | Kaggle Master | Published Author | Topmate: https://topmate.io/raj_mehrotra
UnitedHealth GroupHyderabad, Telangana
mrc03's Stars
deadskull7/New-York-Stock-Exchange-Predictions-RNN-LSTM
BEST SCORE ON KAGGLE SO FAR. Mean Square Error after repeated tuning 0.00032. Used stacked GRU + LSTM layers with optimized architecture, learning rate and batch size for best model performance. The graphs are self explanatory once you click and go inside !!!
deadskull7/lstm_anomaly_thesis
Anomaly detection for temporal data using LSTMs
deadskull7/Movie-Recommendations-using-Collaborative-Filtering
My work includes movie recommendations using collaborative filtering with a least mean square error of 0.8254. Also Experimented on embedded matrices of different sizes and feature extraction. I have experimented with the size of embedding layer , batch_size and learning rate much and came to the final conclusion that particularly for this dataset the embedding layer of 30 was best in the sizes of 30,50 and 64 . Also the mean square error was better when kept layer size small. This might be due to the fact that the data might not be that complex to have feature extraction of upto 50 or 64. Extracting features upto this limit might have led the model to memorize and thus overfitting the data.
deadskull7/Pneumonia-Diagnosis-using-XRays-96-percent-Recall
BEST SCORE ON KAGGLE SO FAR , EVEN BETTER THAN THE KAGGLE TEAM MEMBER WHO DID BEST SO FAR. The project is about diagnosing pneumonia from XRay images of lungs of a person using self laid convolutional neural network and tranfer learning via inceptionV3. The images were of size greater than 1000 pixels per dimension and the total dataset was tagged large and had a space of 1GB+ . My work includes self laid neural network which was repeatedly tuned for one of the best hyperparameters and used variety of utility function of keras like callbacks for learning rate and checkpointing. Could have augmented the image data for even better modelling but was short of RAM on kaggle kernel. Other metrics like precision , recall and f1 score using confusion matrix were taken off special care. The other part included a brief introduction of transfer learning via InceptionV3 and was tuned entirely rather than partially after loading the inceptionv3 weights for the maximum achieved accuracy on kaggle till date. This achieved even a higher precision than before.
mrc03/Titanic-Survivor-Prediction
The Titanic: Machine Learning from Disaster competiton. With data being provided of varoius passengers traveling on the ship I have used libraries like numpy,pandas to manipulate , explore and analyze the data and libraries like matplotlib and seaborn to visualise the data. Lastly I have used various machine learning models to make predictions on the formerly cleaned and preprocessed data. Then I used GridSearchCV to optimise the parameters of the various models
deadskull7/Titanic-survival-analysis-and-predictions
Data being provided of people travelling on titanic , analysis done using matplotlib and seaborn libraries along with pandas manipulation , finally a particular machine learning model after comparison is trained to obtain maximum accuracy on the data which is formerly cleaned and converted to be trained and at last the survival of a person is predicted based on the trained model .
mGalarnyk/datasciencecoursera
Data Science Repo and blog for John Hopkins Coursera Courses. Please let me know if you have any questions.
mrc03/Appdichat
Appdichat is mobile chatting application with many features. You can register and login with the application. Also you can send friend request to your friends and accept or decline the requests received. You can also chat in real time with your friends and also see a list of the people using the application. A user can also build his profile by setting his display profile picture and set the status. Also you can view the profile of all your friends and know the number of mutual friends. The application uses Java, XML and the Firebase realtime database.
mrc03/SqlitePractice
mrc03/Project
The Project is an Android application that displays the level of various gases in the atmosphere. The volume of gases in the atmosphere is stored in an Excel file. The data values stored in an Excel file is updated periodcally with data fetched from the sensors.The application reads the contents of the file and displays the results fetched in the application.
mrc03/TicTacToe
Tic Tac Toe is simple tic tac toe game developed on the android platform. The application was developed in just 2 hours for the International Organisation of Software Developers(IOSD) Hackathon.
mrc03/SAD_PROJECT
A blood bank mobile application where the user can register and login. A blood donor can register with the application and earn points. The receiver can search for donors and either call donor or locate him on the Google Maps. The application uses Java , XML and the Firebase API as backend and Google Maps API to locate the donor on the Google Maps.
Chinmayrane16/Calculator
A Simple Calculator with basic Arithmatic operations and other utilities
deadskull7/Statistical-Distributions-with-Examples
Statistical-Distributions-with-Examples , Normal Distribution ,Poison Distribution, Binomial Distribution , Measures of Spread , Quantile , RegressionPlot , TimeSeriesPlot , HeatMap , KdePlot , Statistical Inference , Median Absolute Deviation (MAD) , Point Estimates , Skewness , Confidence Intervals , Sampling Distribution and The Central Limit Theorem , Margin of Error , Statistical Hypothesis Testing: The T-Test , T-critical , One-Sample T-Test , Two-Sample T-Test , Type I & II Errors .
MathewSachin/Captura
Capture Screen, Audio, Cursor, Mouse Clicks and Keystrokes