Data Exploration for

Road Segments

For dataset of segments.csv

It consists of the list of crashes in the year 2018 and 2019 with the coordinates of the crash and the date and time of the crash.

We have done the following preprocessing and data exploration:

  1. Extraction of data from json files provided

  2. Data Cleaning and data merging to work on only necessary features like road segment id,road name,frequency of accidents and lane type.

  3. Finding which lane and which road has the highest number of accidents int the city.

  4. Plotting on street view manp the intensity of road accidents in particular areas.

After data cleaning and manipulation

Count of roads with 1-lane and 2-lanes

Count of accidents on each road lane-wise

road accidents according to frequency

Roads waiyaki way-trunk anf thika road-primary has very high frequency of accidents.

Inferences

  1. There are higher number of roads with 1 lane than roads with 2 lanes

  2. the frequency of accidents are higher on one lane roads

Street names with accident frequency greater than 10 in 2 years

Map view of the streets

Inferences

  1. Maximum number of accidents occur in the Waiyaki way-trunk street which is a one-lane road.

  2. From the map view we can see that this road is very close to the city center.

Map view for the crash locations

Heatmap for frequency of accidents on the street segments.