Created
August 19, 2016 01:02
-
-
Save nwstephens/b3f66baeaf2ffaabddc337df256ce3e1 to your computer and use it in GitHub Desktop.
When I load data into Spark, I get an error from readr that I don't get when I use readr explicitly
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| library(sparklyr) | |
| library(dplyr) | |
| # Install spark and hadoop dependencies | |
| spark_install(version="2.0.0-preview", hadoop_version="2.7") | |
| # Download file | |
| fileIn <- "https://nycopendata.socrata.com/api/views/h9gi-nx95/rows.csv?accessType=DOWNLOAD" | |
| fileOut <- "NYPD_Motor_Vehicle_Collisions_RAW.csv" | |
| download.file(fileIn, fileOut) | |
| # Create the cluster connection and load data | |
| sc <- spark_connect(master = "local", | |
| version = "2.0.0-preview", | |
| hadoop_version = "2.7") | |
| # Load RAW data into Spark | |
| nypd_raw <- spark_read_csv(sc, "nypd_raw", "NYPD_Motor_Vehicle_Collisions_RAW.csv", overwrite=TRUE) | |
| nypd_raw # !!! Error: Variables must be length 1 or 10. !!! | |
| # Remove problematic columns | |
| dat <- readr::read_csv("NYPD_Motor_Vehicle_Collisions_RAW.csv") | |
| col_names_remove <- c('OFF_STREET_NAME', 'CONTRIBUTING_FACTOR_VEHICLE_3', 'CONTRIBUTING_FACTOR_VEHICLE_4', 'CONTRIBUTING_FACTOR_VEHICLE_5', 'VEHICLE_TYPE_CODE_3', 'VEHICLE_TYPE_CODE_4', 'VEHICLE_TYPE_CODE_5') | |
| col_ind_remove <- match(col_names_remove, gsub(" ", "_", names(dat))) | |
| readr::write_csv(select(dat, -col_ind_remove), "NYPD_Motor_Vehicle_Collisions.csv") | |
| # Load modfied data into Spark | |
| nypd <- spark_read_csv(sc, "nypd", "NYPD_Motor_Vehicle_Collisions.csv", overwrite=TRUE) | |
| nypd |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment