###
###  UCI Connectionist Bench (Sonar, Mines vs. Rocks) Data
###

Local copy:
  sonar.csv

Downloaded From:
  https://www.openml.org/d/40
  (CSV file: https://api.openml.org/data/v1/get_csv/40)

Original Source:
  UCI Machine Learning Repository
  https://archive.ics.uci.edu/dataset/151/connectionist+bench+sonar+mines+vs+rocks

Variable Information:

  Name -- Data Type -- Measurement -- Description
  attribute_1 ... attribute_60 -- quantitative -- unitless, 0.0 to 1.0 -- energy within a particular frequency band, integrated over a certain period of time
  Class                        -- binary (Mine, Rock) -- none -- object that reflected the signal (M = mine, R = rock in the original UCI file) -- response variable

Summary:
  Number of instances (observations): 208
  Number of Attributes: 61
  Attribute breakdown: 60 quantitative feature variables, and 1 binary response variable
  Missing Attribute Values: None
  Class distribution: Mine = 111 (53.4%), Rock = 97 (46.6%)

Abstract:
  The task is to discriminate between sonar signals bounced off a metal cylinder
  (a mine) and those bounced off a roughly cylindrical rock. This is the data set
  Gorman and Sejnowski used in their study of classifying sonar signals with a
  neural network.

Data Characteristics:
  111 patterns were obtained by bouncing sonar signals off a metal cylinder at
  various angles and under various conditions, and 97 patterns were obtained
  from rocks under similar conditions. The transmitted signal is a
  frequency-modulated chirp, rising in frequency. The signals cover aspect angles
  spanning 90 degrees for the cylinder and 180 degrees for the rock.
  Each pattern is a set of 60 numbers in the range 0.0 to 1.0.

Notes:
  The data set was contributed to the benchmark collection by Terry Sejnowski
  (Salk Institute / UC San Diego) and developed in collaboration with R. Paul
  Gorman (Allied-Signal Aerospace Technology Center), 1988.
  The integration aperture for higher frequencies occurs later in time, because
  those frequencies are transmitted later during the chirp.
  In the original UCI file the labels carry the letter R or M, and the numbers in
  the labels are in increasing order of aspect angle but do not encode the angle
  directly.

Reference:
  Gorman, R. P., and Sejnowski, T. J. (1988). "Analysis of Hidden Units in a
  Layered Network Trained to Classify Sonar Targets" in Neural Networks, Vol. 1,
  pp. 75-89.


----------
library(tidyverse)
DF <- read_csv("sonar.csv")

DF