1
0
mirror of https://github.com/andre-wojtowicz/uci-ml-to-r.git synced 2024-11-28 16:25:27 +01:00

Updated bank-marketing dataset

This commit is contained in:
Andrzej Wójtowicz 2016-07-13 13:59:25 +02:00
parent abc240bb2d
commit c49a82db43
5 changed files with 45 additions and 52 deletions

1
.gitignore vendored
View File

@ -23,3 +23,4 @@ data-collection/*/preprocessed/*
# markdown outputs
*.html
.Rproj.user

View File

@ -3,7 +3,7 @@ Andrzej Wójtowicz
Document generation date: 2016-06-23 11:44:00.
Document generation date: 2016-07-13 13:45:45.
@ -30,7 +30,7 @@ Document generation date: 2016-06-23 11:44:00.
**Source data files**:
* [bank-additional.zip](https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank-additional.zip)
* [bank.zip](https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip)
**Cite**:
```nohighlight
@ -40,24 +40,22 @@ S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of
**Dataset**:
```nohighlight
'data.frame': 38227 obs. of 18 variables:
$ age : int 56 57 37 40 56 45 59 24 25 25 ...
$ job : Factor w/ 11 levels "admin","blue.collar",..: 4 8 8 1 8 8 1 10 8 8 ...
$ marital : Factor w/ 3 levels "divorced","married",..: 2 2 2 2 2 2 2 3 3 3 ...
$ education : Ord.factor w/ 6 levels "basic.4y"<"basic.6y"<..: 1 4 4 2 4 3 5 5 4 4 ...
$ housing : Factor w/ 2 levels "no","yes": 1 1 2 1 1 1 1 2 2 2 ...
$ loan : Factor w/ 2 levels "no","yes": 1 1 1 1 2 1 1 1 1 1 ...
$ contact : Factor w/ 2 levels "cellular","telephone": 2 2 2 2 2 2 2 2 2 2 ...
'data.frame': 43193 obs. of 16 variables:
$ age : int 58 44 33 35 28 42 58 43 41 29 ...
$ job : Factor w/ 11 levels "admin","blue.collar",..: 5 10 3 5 5 3 6 10 1 1 ...
$ marital : Factor w/ 3 levels "divorced","married",..: 2 3 2 2 3 1 2 3 1 3 ...
$ education: Ord.factor w/ 3 levels "primary"<"secondary"<..: 3 2 2 3 3 3 1 2 2 2 ...
$ balance : int 2143 29 2 231 447 2 121 593 270 390 ...
$ housing : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
$ loan : Factor w/ 2 levels "no","yes": 1 1 2 1 2 1 1 1 1 1 ...
$ contact : Factor w/ 3 levels "cellular","telephone",..: 3 3 3 3 3 3 3 3 3 3 ...
$ day : int 5 5 5 5 5 5 5 5 5 5 ...
$ month : Ord.factor w/ 12 levels "jan"<"feb"<"mar"<..: 5 5 5 5 5 5 5 5 5 5 ...
$ day.of.week : Ord.factor w/ 5 levels "mon"<"tue"<"wed"<..: 1 1 1 1 1 1 1 1 1 1 ...
$ campaign : int 1 1 1 1 1 1 1 1 1 1 ...
$ pdays : int 999 999 999 999 999 999 999 999 999 999 ...
$ pdays.bin: Factor w/ 2 levels "successful","never": 2 2 2 2 2 2 2 2 2 2 ...
$ previous : int 0 0 0 0 0 0 0 0 0 0 ...
$ poutcome : Factor w/ 3 levels "failure","nonexistent",..: 2 2 2 2 2 2 2 2 2 2 ...
$ emp.var.rate : num 1.1 1.1 1.1 1.1 1.1 1.1 1.1 1.1 1.1 1.1 ...
$ cons.price.idx: num 94 94 94 94 94 ...
$ cons.conf.idx : num -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 -36.4 ...
$ euribor3m : num 4.86 4.86 4.86 4.86 4.86 ...
$ nr.employed : num 5191 5191 5191 5191 5191 ...
$ poutcome : Factor w/ 4 levels "failure","other",..: 4 4 4 4 4 4 4 4 4 4 ...
$ y : Factor w/ 2 levels "no","yes": 1 1 1 1 1 1 1 1 1 1 ...
```
@ -66,17 +64,16 @@ S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of
|Type | Frequency|
|:--------------|---------:|
|factor | 6|
|integer | 3|
|numeric | 5|
|ordered factor | 3|
|factor | 7|
|integer | 6|
|ordered factor | 2|
**Class imbalance**:
| class A | class B |
|:-------:|:--------:|
| 11 % | 89 % |
| 4254 | 33973 |
| 12 % | 88 % |
| 5021 | 38172 |
---

View File

@ -4,7 +4,7 @@ name: Bank Marketing
info: https://archive.ics.uci.edu/ml/datasets/Bank+Marketing
urls:
- https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank-additional.zip
- https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip
cite: >
S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014

View File

@ -4,8 +4,8 @@ preprocessDataset = function()
temp.dir = tempdir()
zip.file = "bank-additional.zip"
zip.dataset.path = "bank-additional/bank-additional-full.csv"
zip.file = "bank.zip"
zip.dataset.path = "bank-full.csv"
flog.debug(paste("Unzipping", zip.file))
@ -20,31 +20,25 @@ preprocessDataset = function()
flog.debug("Preprocessing loaded dataset")
dataset = dataset %>%
select(-c(duration, pdays, default)) %>%
select(-c(duration, default)) %>%
filter(job != "unknown" & marital != "unknown" & education != "unknown" &
education != "illiterate" & housing != "unknown" & loan != "unknown") %>%
education != "unknown" & housing != "unknown" & loan != "unknown") %>%
droplevels()
#dataset.yes = dataset %>% filter(y == "yes")
#dataset.no = dataset %>% filter(y == "no") %>% sample_n(nrow(dataset.yes))
#
#dataset = rbind(dataset.yes, dataset.no)
dataset = dataset %>% mutate(
education=factor(education, levels=c("basic.4y", "basic.6y",
"basic.9y", "high.school",
"professional.course",
"university.degree"),
dataset = dataset %>%
mutate(
education=factor(education, levels=c("primary", "secondary",
"tertiary"),
ordered=TRUE),
month=factor(month, levels=c("jan", "feb", "mar",
"apr", "may", "jun",
"jul", "aug", "sep",
"oct", "nov", "dec"),
ordered=TRUE),
day_of_week=factor(day_of_week, levels=c("mon", "tue", "wed",
"thu", "fri"),
ordered=TRUE)
)
pdays.bin=revalue(factor(pdays==-1),
c("TRUE"="never", "FALSE"="successful")),
pdays=as.integer(replace(pdays, pdays==-1, 999))) %>%
select(age:pdays, pdays.bin, previous:y)
return(dataset)
}

View File

@ -3,6 +3,7 @@ rm(list=ls())
source("config.R")
source("utils.R")
library(plyr)
library(dplyr)
library(foreign)
library(XLConnect)