Mining the Spatial-Temporal Characteristics of Population Flow and Material Flow Using Big Data
Table 2
The data preprocessing steps.
Step 1
Obtain the longitudes and latitudes of the 331 detection sites and the counties and cities where they are located in from Google maps.
Step 2
For the convenience of the classification and statistics, use the command “copy∗.csv reslutSave.csv” to merge the record data in the M05A file by month to form twelve csv files.
Step 3
Import the twelve CSV files into an SQL server database to obtain the twelve record tables.
Step 4
Additionally, for the convenience of the classification and statistics, add fields such as [hour, week, and administrative region where the origin and destination sites are located] to each record. The values of these added fields are set according to the information from Step1.
Step 5
Write and execute statements or commands [select, group by, order by, count (…)] for obtaining the statistical information about the traffic volume of the different type of vehicles at different sites, in different road sections and in different time intervals.