Fixes im Script

master
Eugen Betke 2020-08-26 11:56:41 +02:00
parent f3bf0d97a7
commit 99505661f6
1 changed files with 4 additions and 3 deletions

View File

@ -17,7 +17,8 @@ file = args[1]
data = read.csv(file)
# Columns are: jobid alg_id alg_name similarity
data$alg_id = as.factor(data$alg_id)
#data$alg_id = as.factor(data$alg_id) # EB: falsche Spalte?
data$alg_name = as.factor(data$alg_name) # EB: im Script wird diese Spalte benutzt
cat("Job count:")
cat(nrow(data))
@ -37,8 +38,8 @@ e = data %>% filter(similarity >= 0.5)
print(summary(e))
# load job information, i.e., the time series per job
jobData = read.csv("job-io-datasets/datasets/job_codings.csv")
metadata = read.csv("job-io-datasets/datasets/job_metadata.csv")
jobData = read.csv("./datasets/job_codings_v3.csv") # EB: liegt jetzt Repo. v3 hat die korrekten hexadezimalen Codings
metadata = read.csv("./datasets/job_metadata.csv") # EB: is ebenfalls im Repo
metadata$user_id = as.factor(metadata$user_id)
metadata$group_id = as.factor(metadata$group_id)