Srinath Ravulaparthy's repositories

cmap_freight_model

CMAP’s tour-based and supply chain freight model source code

Language:RStargazers:1Issues:0Issues:0

fmlogit

Fractional Multinomial Logit using R

Language:RStargazers:1Issues:0Issues:0

cenpy

Explore and download data from Census APIs

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:0Issues:0Issues:0

Commercial-Energy

Commercial building energy consumption modeling

Language:Jupyter NotebookStargazers:0Issues:0Issues:0

crewml

Open source ML Python package for airline Crew Pairing Optimization

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

data-science-question-answer

A repo for data science related questions and answers

Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0
Language:HTMLStargazers:0Issues:1Issues:0

dispatch-optim

Constrainted based optimization

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

GeoMLA

Machine Learning algorithms for spatial and spatiotemporal data

Language:RLicense:GPL-2.0Stargazers:0Issues:1Issues:0

HDeconometrics

Set of R functions for high-dimensional econometrics

Language:RLicense:NOASSERTIONStargazers:0Issues:0Issues:0

poptools

A population synthesis toolbox for transportists, planners, demographers, and nerds.

Language:RLicense:GPL-3.0Stargazers:0Issues:0Issues:0

Residential-Energy

Residential Energy Consumption Model Scripts

Language:Jupyter NotebookStargazers:0Issues:0Issues:0

RideshareMatching

. Introduces three algorithms for rideshare matching, analysed on a simulation of real-world ridesharing data from NYC.

Language:PythonStargazers:0Issues:0Issues:0

RideSharing

The main aim of this project is to combine Individual trips to shared trips to reduce total distance travelled by taxies and to reduce the number of trips. To achieve this we have used k-means clustering and some Trip matching techniques with passenger count and delay time constraints. We also evaluated distance saved and number of trips saved before and after ridesharing. Installing Tested our approach with New york city real time data. You can download the dataset from the link below. (dataset - https://uofi.app.box.com/NYCtaxidata/2/2332219935 ) Install python in your system (2.6 or above) Install mysql database and install package mysql.connector to connect to MySQL database from python To install Graphhopper API and build the function to calculate the distance and time between two points : The New York OSM file can be obtained from: http://download.geofabrik.de/north-america/us/new-york.html Install the latest JRE and get GraphHopper Server as zip (~9MB) Upzip the GraphHopper file and put the OSM file in the same dictionary. Run the command from window cmd under the dictionary: java -jar graphhopper-web-0.6.0-with-dep.jar jetty.resourcebase=webapp config=config-example.properties osmreader.osm=new-york-latest.osm.pbf Please note that Graphhopper must be running all the time while algorithm is running. Run Run the rideshare python file from the repositories using whichever python IDE you are working on.

Language:PythonStargazers:0Issues:0Issues:0
Language:JuliaLicense:GPL-3.0Stargazers:0Issues:0Issues:0

trucksim

A national simulation of long-distance freight movements.

Language:JavaLicense:MITStargazers:0Issues:0Issues:0

trucksim_disagg

A disaggregation of the FAF4 freight flows based on economic data.

Language:RLicense:MITStargazers:0Issues:0Issues:0

trucksim_network

A network to use in a national long-distance travel microsimulation.

Language:JavaLicense:MITStargazers:0Issues:0Issues:0