andre/uci-ml-to-r
1
0
Fork 0
mirror of https://github.com/andre-wojtowicz/uci-ml-to-r.git synced 2024-07-22 07:35:30 +02:00
Code Releases Activity

in census-income grouped education, filtered occupation and removed native country variable;

Browse Source 
added script to make release zip
This commit is contained in:
Andrzej Wójtowicz 2016-08-19 21:51:21 +02:00
parent b1a4cbab73
commit f7debcd154
7 changed files with 49 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -20,6 +20,7 @@ vignettes/*.pdf
data-collection/*/original/* data-collection/*/original/*
data-collection/*/preprocessed/* data-collection/*/preprocessed/*
data-collection.zip
# markdown outputs # markdown outputs
*.html *.html

23
README.md
View File

@ -3,14 +3,14 @@ Andrzej Wójtowicz
Document generation date: 2016-08-11 18:12:19. Document generation date: 2016-08-19 21:47:14.
This project preprocesses a few datasets from [UC Irvine Machine Learning This project preprocesses a few datasets from [UC Irvine Machine Learning
Repository](https://archive.ics.uci.edu/ml/) into tidy R object files. Repository](https://archive.ics.uci.edu/ml/) into tidy R object files.
It focuses on the binary classification datasets and saves only complete cases It focuses on the binary classification datasets and saves only complete cases
within a dataset. within a dataset.
**R software**: [Microsoft R Open](https://mran.microsoft.com/open/) (3.2.5) **R software**: [Microsoft R Open](https://mran.microsoft.com/open/) (3.3.0)
**Reproducibility library**: [checkpoint](https://github.com/RevolutionAnalytics/checkpoint) **Reproducibility library**: [checkpoint](https://github.com/RevolutionAnalytics/checkpoint)
@ -18,7 +18,11 @@ within a dataset.
1. Run *s1-download-data.R* to download original datasets. 1. Run *s1-download-data.R* to download original datasets.
2. Run *s2-preprocess-data.R* to preprocess the datasets. 2. Run *s2-preprocess-data.R* to preprocess the datasets.
3. Optionally knit s*3-make-readme.Rmd* to get an overview of the preprocessed datasets.
Optionally:
3. knit *s3-make-readme.Rmd* to get an overview of the preprocessed datasets,
4. run *s4-make-release.sh* to create zip file with preprocessed datasets.
# Table of Contents # Table of Contents
@ -302,20 +306,19 @@ https://archive.ics.uci.edu/ml/citation_policy.html
**Dataset**: **Dataset**:
```nohighlight ```nohighlight
'data.frame': 45222 obs. of 14 variables: 'data.frame': 46018 obs. of 13 variables:
$ age : int 39 50 38 53 28 37 49 52 31 42 ... $ age : int 39 50 38 53 28 37 49 52 31 42 ...
$ workclass : Factor w/ 8 levels "federal.gov",..: 7 6 4 4 4 4 4 6 4 4 ... $ workclass : Factor w/ 7 levels "federal.gov",..: 6 5 3 3 3 3 3 5 3 3 ...
$ fnlwgt : int 77516 83311 215646 234721 338409 284582 160187 209642 45781 159449 ... $ fnlwgt : int 77516 83311 215646 234721 338409 284582 160187 209642 45781 159449 ...
$ education : Ord.factor w/ 16 levels "preschool"<"x1st.4th"<..: 13 13 9 7 13 14 5 9 14 13 ... $ education : Ord.factor w/ 5 levels "school"<"highschool"<..: 4 4 2 1 4 5 1 2 5 4 ...
$ marital.status: Factor w/ 7 levels "divorced","married.af.spouse",..: 5 3 1 3 3 3 4 3 5 3 ... $ marital.status: Factor w/ 7 levels "divorced","married.af.spouse",..: 5 3 1 3 3 3 4 3 5 3 ...
$ occupation : Factor w/ 14 levels "adm.clerical",..: 1 4 6 6 10 4 8 4 10 4 ... $ occupation : Factor w/ 13 levels "adm.clerical",..: 1 3 5 5 9 3 7 3 9 3 ...
$ relationship : Factor w/ 6 levels "husband","not.in.family",..: 2 1 2 1 6 6 2 1 2 1 ... $ relationship : Factor w/ 6 levels "husband","not.in.family",..: 2 1 2 1 6 6 2 1 2 1 ...
$ race : Factor w/ 5 levels "amer.indian.eskimo",..: 5 5 5 3 3 5 3 5 5 5 ... $ race : Factor w/ 5 levels "amer.indian.eskimo",..: 5 5 5 3 3 5 3 5 5 5 ...
$ sex : Factor w/ 2 levels "female","male": 2 2 2 2 1 1 1 2 1 2 ... $ sex : Factor w/ 2 levels "female","male": 2 2 2 2 1 1 1 2 1 2 ...
$ capital.gain : int 2174 0 0 0 0 0 0 0 14084 5178 ... $ capital.gain : int 2174 0 0 0 0 0 0 0 14084 5178 ...
$ capital.loss : int 0 0 0 0 0 0 0 0 0 0 ... $ capital.loss : int 0 0 0 0 0 0 0 0 0 0 ...
$ hours.per.week: int 40 13 40 40 40 40 16 45 50 40 ... $ hours.per.week: int 40 13 40 40 40 40 16 45 50 40 ...
$ native.country: Factor w/ 41 levels "cambodia","canada",..: 39 39 39 39 5 39 23 39 39 39 ...
$ class : Factor w/ 2 levels "x..50k","x.50k": 1 1 1 1 1 1 1 2 2 2 ... $ class : Factor w/ 2 levels "x..50k","x.50k": 1 1 1 1 1 1 1 2 2 2 ...
``` ```
@ -324,7 +327,7 @@ https://archive.ics.uci.edu/ml/citation_policy.html
|Type | Frequency| |Type | Frequency|
|:--------------|---------:| |:--------------|---------:|
|factor | 7| |factor | 6|
|integer | 5| |integer | 5|
|ordered factor | 1| |ordered factor | 1|
@ -333,7 +336,7 @@ https://archive.ics.uci.edu/ml/citation_policy.html
| class A | class B | | class A | class B |
|:-------:|:-------:| |:-------:|:-------:|
| 25 % | 75 % | | 25 % | 75 % |
| 11208 | 34014 | | 11417 | 34601 |
--- ---

2
config.R
View File

@ -13,7 +13,7 @@ USER.INIT.FILE = "init.R.user"
# checkpoint library # checkpoint library
CHECKPOINT.MRAN.URL = "https://mran.microsoft.com/" CHECKPOINT.MRAN.URL = "https://mran.microsoft.com/"
CHECKPOINT.SNAPSHOT.DATE = "2016-07-01" CHECKPOINT.SNAPSHOT.DATE = "2016-06-01"
CHECKPOINT.QUICK.LOAD = TRUE # skip testing https and checking url CHECKPOINT.QUICK.LOAD = TRUE # skip testing https and checking url
# logging system # logging system

16
data-collection/census-income/preprocess.R
View File

@ -42,8 +42,20 @@ preprocess.dataset = function()
dataset = dataset %>% dataset = dataset %>%
mutate(education = factor(education, levels = education.ordered.levels, mutate(education = factor(education, levels = education.ordered.levels,
ordered = TRUE)) %>% ordered = TRUE)) %>%
select(-education.num) %>% select(-education.num, -native.country) %>% # native.country is too much
filter(complete.cases(.)) # biased into US
filter(complete.cases(.) & occupation != "Armed-Forces") %>% # only few
# cases of
# Armed-Forces
droplevels
dataset$education = factor(combine_factor(dataset$education, # combine into
c(1, 1, 1, 1, 1, # more numerous
1, 1, 1, 2, 3, # groups
3, 3, 4, 5, 5, 5)),
ordered = TRUE)
levels(dataset$education) = c("school", "highschool", "college",
"university", "science")
return(dataset) return(dataset)
} }

1
init.R
View File

@ -47,6 +47,7 @@ library(RCurl)
library(tools) library(tools)
library(yaml) library(yaml)
library(reshape)
library(plyr) library(plyr)
library(dplyr) library(dplyr)
library(foreign) library(foreign)

6
s3-make-readme.Rmd
View File

@ -26,7 +26,11 @@ within a dataset.
1. Run *s1-download-data.R* to download original datasets. 1. Run *s1-download-data.R* to download original datasets.
2. Run *s2-preprocess-data.R* to preprocess the datasets. 2. Run *s2-preprocess-data.R* to preprocess the datasets.
3. Optionally knit s*3-make-readme.Rmd* to get an overview of the preprocessed datasets.
Optionally:
3. knit *s3-make-readme.Rmd* to get an overview of the preprocessed datasets,
4. run *s4-make-release.sh* to create zip file with preprocessed datasets.
```{r show-datasets, results='asis'} ```{r show-datasets, results='asis'}

14
s4-make-release.sh Normal file
View File

@ -0,0 +1,14 @@
#!/bin/bash
OUT_ZIP_FILE="data-collection.zip"
rm -f $OUT_ZIP_FILE
zip $OUT_ZIP_FILE $(find data-collection/*/preprocessed/*.rds)
for f in $(find data-collection/*/preprocessed/*.rds) ; do
dataset_name=$(echo "$f" | sed -e 's/data-collection\/\(.*\)\/preprocessed\/.*\.rds/\1/')
echo "Renaming $f -> $dataset_name.rds"
# https://stackoverflow.com/a/16710654
printf "@ $f\n@=$dataset_name.rds\n" | zipnote -w $OUT_ZIP_FILE
done