Вы находитесь на странице: 1из 3

Data Preparation and Acquisition

I. Acquire Column Feature Names from TW (Location)


II. Fetch OSM Islamabad and Rawalpindi road network data
III. Necessary Conversions from Acquired Data

 Develop Understanding of Technologies for Data Preparation


I. Develop understanding of POSTGIS databases and Geo Pre-processing for TW
Segmented DATA
II. Develop understanding of POSTGIS databases and Geo Pre-processing for OSM
Fetched Data
III. Develop Understanding of traffic data aggregation using OPENLR using Pandas and
Python
IV. Organize TW data and understand the fields/ column attributes of each months
V. Trade-off between the Python Data Analysis Libraries and other Interface based BI
tools (Microsoft BI)
VI. How to measure of central tendency on TW data (month wise or road wise)?
VII. How to apply different type of distribution to sample TW data? (discrete and
continuous probability distribution)
VIII. Understanding of applying t-test on TW data
IX. Understanding of applying f-test on TW data
X. Understanding of applying z-test on TW data
XI. Understanding of applying chi-square test on TW data
XII. Understanding of applying different types of correlation
a. Pearson Correlation
b. Spearman's Correlation
c. Kendall's Tau Correlation
XIII. How to do the data wrangling with TW data?
XIV. Develop Understanding of MongoDB for final prepared data
XV. Develop understanding of MongoDB and visualization on front end
IV. File Conversions- CSV-JSON (If required)
V. Integrate Road Attributes (Speed Limits, Junctions, No of Lanes, Road Types) with TW Data
VI. Installation of Required Data Preparation Libraries (GeoPandas, PostGIS)
VII. Make Line_String from Continuous coordinate points with respect to Time
VIII. Define Segment Length (0.5 KM or Others): Research Element
IX. Split the Line_String into Sub_Strings(Road Segments)
X. Speed Aggregation for Time_Interval and Road Segments: Using Group By or Any other Related
XI. Continuous to Categorical speed Bins: Define Bins Using Cut() and unCut() from Pandas for
Analysis
XII. Factorize Text to Numeric for Machine Learning Training Purpose: Using Pandas -factorize()
method to encode value as integer
XIII. Generation of Ground Truths (3 to 5) based on cut() and unCut() function
XIV. Generation of Ground Truths based on Comaprison (If - else)
XV. Generation of Ground Truths based on Speed OSM thesis
XVI. Integrate Holidays Data: for Future Analysis
XVII. Holidays to Boolean Variable: 1 for Holiday 0 for Working Days(Machine Learning and Data
Analysis): same as Did in Traffic Count on NYC
Mobile Development Tasks
I. Create splash screen for App.
II. Create Install osmdroid dependencies on Android Studio.
III. Add mapview on osmdroid in application.
IV. Add Zooming level.
V. Add Zoom in and Zoom out.
VI. Allow device location in application.
VII. Get the current location.
VIII. Add Autocomplete Edit Text Widget.
IX. Create GEOJSON schema for Fetching data from mongodb.
X. Create Api for Autocomplete with node.js
XI. Get the response in Json format.
XII. Make Api Accessible over the local network (Wifi Extender).
XIII. Get Api Response in client (Mobile App).
XIV. Show the Response in Autcomplete.
XV. MapBox Map View
XVI. Location Permission
XVII. Enable Current Location
XVIII. Zoom-in + Zoom Out
XIX. Create Drawer activity in mobile app
XX. Add required fragments
XXI. Design the Main View of App.
XXII. Add splash screen of app.
XXIII. Add logo of the app.
XXIV. Add sleep time on first launch.
XXV. Add location permission in manifest file.
XXVI. Add location permission on run time.
XXVII. Add Zoom level on map.
XXVIII. Add compass on map
XXIX. Add zoom in and zoom out on map

Administrative Stuff
I. Minutes of Meeting with TW Dr. Khawar
II. Product Backlog
III. TPL Maps API expoloration (formates etc)
a. Extent Traffic Api
b. Road name traffic
c. Route widget API
IV. Meetings with Project Investigator (Friday, Tuesday, Wednesday)

Вам также может понравиться