OpenML
Filter results by:
GEMLeR provides a collection of gene expression datasets that can be used for benchmarking gene expression oriented machine learning algorithms. They can be used for estimation of different quality…
59 runs0 likes7 downloads7 reach9 impact
1545 instances - 10937 features - 2 classes - 0 missing values
The weather problem is a tiny dataset that we will use repeatedly to illustrate machine learning methods. Entirely fictitious, it supposedly concerns the conditions that are suitable for playing some…
0 runs0 likes1 downloads1 reach1 impact
14 instances - 5 features - 2 classes - 0 missing values
Incident reports from the San Franciso Police Department between January 2003 and May 2018, provided by the City and County of San Francisco. The dataset was downloaded on 05.11.2018. from…
0 runs0 likes0 downloads0 reach0 impact
538638 instances - 7 features - 2 classes - 0 missing values
Dataset KDD98 challenge: https://kdd.ics.uci.edu/databases/kddcup98/kddcup98.html The goal is to estimate the return from a direct mailing in order to maximize donation profits. This dataset…
0 runs0 likes0 downloads0 reach0 impact
82318 instances - 478 features - 2 classes - 2399311 missing values
The KDD Cup 2009 offers the opportunity to work on large marketing databases from the French Telecom company Orange to predict the propensity of customers to switch provider (churn). Churn (wikipedia…
10984 runs0 likes16 downloads16 reach18 impact
50000 instances - 231 features - 2 classes - 8024152 missing values
Datasets for `Pattern Recognition and Neural Networks' by B.D. Ripley ===================================================================== Cambridge University Press (1996) ISBN 0-521-46086-7 The…
743 runs0 likes8 downloads8 reach8 impact
200 instances - 8 features - 2 classes - 0 missing values
Lucas, D. D., Klein, R., Tannahill, J., Ivanova, D., Brandon, S., Domyancic, D., and Zhang, Y.: Failure analysis of parameter-induced simulation crashes in climate models, Geosci. Model Dev. Discuss.,…
162436 runs0 likes21 downloads21 reach18 impact
540 instances - 21 features - 2 classes - 0 missing values
No data.
253 runs0 likes9 downloads9 reach2 impact
1076790 instances - 30 features - 2 classes - 7275 missing values
The datasets contains transactions made by credit cards in September 2013 by european cardholders. This dataset present transactions that occurred in two days, where we have 492 frauds out of 284,807…
355 runs0 likes55 downloads55 reach12 impact
284807 instances - 31 features - 2 classes - 0 missing values
Data on predicting clicks on ads in a search engine.
0 runs0 likes8 downloads8 reach6 impact
1496391 instances - 12 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and…
131 runs1 likes9 downloads10 reach8 impact
990 instances - 14 features - 2 classes - 0 missing values
* Title: Planning Relax Data Set * Abstract: The dataset concerns with the classification of two mental stages from recorded EEG signals: Planning (during imagination of motor act) and Relax state. *…
141 runs0 likes8 downloads8 reach7 impact
182 instances - 13 features - 2 classes - 0 missing values
* Dataset Title: Vertebra Column - 2 classes * Abstract: Data set containing values for six biomechanical features used to classify orthopaedic patients into 3 classes (normal, disk hernia or…
124 runs0 likes5 downloads5 reach7 impact
310 instances - 7 features - 2 classes - 0 missing values
Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a…
1078 runs0 likes11 downloads11 reach7 impact
108 instances - 8 features - 2 classes - 0 missing values
Asteroid Dataset
0 runs0 likes1 downloads1 reach1 impact
126131 instances - 34 features - 2 classes - 99 missing values
Asteroid Dataset
0 runs0 likes1 downloads1 reach2 impact
126131 instances - 34 features - 2 classes - 99 missing values
The satellite dataset comprises of features extracted from satellite observations. In particular, each image was taken under four different light wavelength, two in visible light (green and red) and…
2074 runs3 likes69 downloads72 reach22 impact
5100 instances - 37 features - 2 classes - 0 missing values
cast metal 1
111 runs0 likes9 downloads9 reach6 impact
327 instances - 38 features - 2 classes - 0 missing values
pie chart 1
102 runs0 likes5 downloads5 reach6 impact
705 instances - 38 features - 2 classes - 0 missing values
Pizza cutter 3
188 runs0 likes6 downloads6 reach7 impact
1043 instances - 38 features - 2 classes - 0 missing values
Costa madre 1
90 runs0 likes6 downloads6 reach8 impact
296 instances - 38 features - 2 classes - 0 missing values
pie chart 2
101 runs0 likes5 downloads5 reach6 impact
745 instances - 37 features - 2 classes - 0 missing values
pie chart 3
103 runs0 likes6 downloads6 reach6 impact
1077 instances - 38 features - 2 classes - 0 missing values
Mega watt
183 runs0 likes8 downloads8 reach8 impact
253 instances - 38 features - 2 classes - 0 missing values
Pizza cutter
197 runs0 likes8 downloads8 reach7 impact
661 instances - 38 features - 2 classes - 0 missing values
* Abstract: The data was created by a medical expert as a data set to test the expert system, which will perform the presumptive diagnosis of two diseases of the urinary system. * Source: Jacek…
391 runs0 likes11 downloads11 reach6 impact
120 instances - 7 features - 2 classes - 0 missing values
This is a corrected version of the previous data file in version 1, which contained a dataset (349 instances) incorrectly merged from the original training and test sets available on UCI (there are…
0 runs0 likes3 downloads3 reach5 impact
267 instances - 45 features - 2 classes - 0 missing values
* Title: Wholesale customers Data Set * Abstract: The data set refers to clients of a wholesale distributor. It includes the annual spending in monetary units (m.u.) on diverse product categories *…
161 runs0 likes10 downloads10 reach7 impact
440 instances - 9 features - 2 classes - 0 missing values
* Twonorm dataset This is an implementation of Leo Breiman's twonorm example[1]. It is a 20 dimensional, 2 class classification example. Each class is drawn from a multivariate normal distribution…
118 runs0 likes5 downloads5 reach7 impact
7400 instances - 21 features - 2 classes - 0 missing values
* Abstract: Predict the Bankruptcy from Qualitative parameters from experts. * Source: Source Information -- Creator : Mr.A.Martin(jayamartin '@' yahoo.com) Mr.J.Uthayakumar (uthayakumar17691 '@'…
147 runs0 likes11 downloads11 reach7 impact
250 instances - 7 features - 2 classes - 0 missing values
1: Abstract: This is a 20 dimensional, 2 class classification problem. Each class is drawn from a multivariate normal distribution. Class 1 has mean zero and covariance 4 times the identity. Class 2…
120 runs0 likes8 downloads8 reach7 impact
7400 instances - 21 features - 2 classes - 0 missing values
Dataset title laLSVT Voice Rehabilitation Data Set Source: The dataset was created by Athanasios Tsanas (tsanasthanasis '@' gmail.com) of the University of Oxford. Abstract: 126 samples from 14…
162 runs0 likes5 downloads5 reach6 impact
126 instances - 311 features - 2 classes - 0 missing values
* Dataset: Hill valley dataset. A noiseless version of the data set.
117 runs0 likes8 downloads8 reach8 impact
1212 instances - 101 features - 2 classes - 0 missing values
* Abstract: The data was created by a medical expert as a data set to test the expert system, which will perform the presumptive diagnosis of two diseases of the urinary system. This is a…
423 runs0 likes14 downloads14 reach6 impact
120 instances - 7 features - 2 classes - 0 missing values
* Dataset: Reduced version (10 % of the examples) of bank-marketing dataset.
104 runs1 likes16 downloads17 reach8 impact
4521 instances - 17 features - 2 classes - 0 missing values
* Dataset Title: AutoUniv Dataset data problem: autoUniv-au1-1000 * Abstract: AutoUniv is an advanced data generator for classifications tasks. The aim is to reflect the nuances and heterogeneity of…
3255 runs1 likes8 downloads9 reach16 impact
1000 instances - 21 features - 2 classes - 0 missing values
At Santander our mission is to help people and businesses prosper. We are always looking for ways to help our customers understand their financial health and identify which products and services might…
0 runs0 likes0 downloads0 reach0 impact
200000 instances - 202 features - 2 classes - 0 missing values
This data is derived from the 2012 KDD Cup. The data is subsampled to 1% of the original number of instances, downsampling the majority class (click=0) so that the target feature is reasonably…
313 runs0 likes36 downloads36 reach7 impact
399482 instances - 12 features - 2 classes - 0 missing values
Normalized version of vehicle dataset (http://www.openml.org/d/54) NAME vehicle silhouettes PURPOSE to classify a given silhouette as one of four types of vehicle, using a set of features extracted…
372 runs0 likes10 downloads10 reach3 impact
98528 instances - 101 features - 2 classes - 0 missing values
The goal of this challenge is to expose the research community to real world datasets of interest to 4Paradigm. All datasets are formatted in a uniform way, though the type of data might differ. The…
3 runs0 likes1 downloads1 reach9 impact
5418 instances - 1637 features - 2 classes - 0 missing values
The goal of this challenge is to expose the research community to real world datasets of interest to 4Paradigm. All datasets are formatted in a uniform way, though the type of data might differ. The…
10 runs0 likes1 downloads1 reach10 impact
20000 instances - 4297 features - 2 classes - 0 missing values
The goal of this challenge is to expose the research community to real world datasets of interest to 4Paradigm. All datasets are formatted in a uniform way, though the type of data might differ. The…
0 runs0 likes1 downloads1 reach8 impact
425240 instances - 79 features - 2 classes - 2734000 missing values
This dataset is taken from the MiniBooNE experiment and is used to distinguish electron neutrinos (signal) from muon neutrinos (background). This dataset is ordered. It first contains all signal…
12 runs0 likes4 downloads4 reach5 impact
130064 instances - 51 features - 2 classes - 0 missing values
The goal of this challenge is to expose the research community to real world datasets of interest to 4Paradigm. All datasets are formatted in a uniform way, though the type of data might differ. The…
4 runs0 likes2 downloads2 reach9 impact
2984 instances - 145 features - 2 classes - 0 missing values
The goal of this challenge is to expose the research community to real world datasets of interest to 4Paradigm. All datasets are formatted in a uniform way, though the type of data might differ. The…
4 runs0 likes1 downloads1 reach9 impact
5124 instances - 21 features - 2 classes - 0 missing values
Airlines Dataset Inspired in the regression dataset from Elena Ikonomovska. The task is to predict whether a given flight will be delayed, given the information of the scheduled departure.
291 runs0 likes29 downloads29 reach8 impact
539383 instances - 8 features - 2 classes - 0 missing values
Klaverjas is an example of the Jack-Nine card games, which are characterized as trick-taking games where the the Jack and nine of the trump suit are the highest-ranking trumps, and the tens and aces…
0 runs0 likes1 downloads1 reach2 impact
981541 instances - 33 features - 2 classes - 0 missing values
This is the dataset used for the 2016 IDA Industrial Challenge, courtesy of Scania. For a full description, see http://archive.ics.uci.edu/ml/datasets/IDA2016Challenge . This dataset contains both the…
7 runs0 likes1 downloads1 reach9 impact
76000 instances - 171 features - 2 classes - 1078695 missing values
Training dataset of the 'Porto Seguros Safe Driver Prediction' Kaggle challenge [https://www.kaggle.com/c/porto-seguro-safe-driver-prediction]. The goal was to predict whether a driver will file an…
2 runs0 likes0 downloads0 reach4 impact
595212 instances - 38 features - 2 classes - 846458 missing values
# Data Description This is the historical price data of the FOREX USD/CHF from Dukascopy. One instance (row) is one candlestick of one minute. The whole dataset has the data range from 1-1-2018 to…
0 runs0 likes0 downloads0 reach2 impact
375840 instances - 12 features - 2 classes - 0 missing values
Datasets from ACM KDD Cup (http://www.sigkdd.org/kddcup/index.php) KDD Cup 2009 http://www.kddcup-orange.com Converted to ARFF format by TunedIT Customer Relationship Management (CRM) is a key element…
223 runs0 likes17 downloads17 reach10 impact
50000 instances - 231 features - 2 classes - 8024152 missing values
No data.
353 runs0 likes17 downloads17 reach4 impact
120919 instances - 1002 features - 2 classes - 0 missing values
1. Data set title: Nomao Data Set 2. Abstract: Nomao collects data about places (name, phone, localization...) from many sources. Deduplication consists in detecting what data refer to the same place.…
67106 runs0 likes16 downloads16 reach19 impact
34465 instances - 119 features - 2 classes - 0 missing values
* Title: Skin Segmentation Data Set * Abstract: The Skin Segmentation dataset is constructed over B, G, R color space. Skin and Nonskin dataset is generated using skin textures from face images of…
15 runs1 likes10 downloads11 reach7 impact
245057 instances - 4 features - 2 classes - 0 missing values
### Attribute Information * The first column is the class label (1 for signal, 0 for background) * 21 low-level features (kinematic properties): lepton pT, lepton eta, lepton phi, missing energy…
14236 runs1 likes9 downloads10 reach19 impact
98050 instances - 29 features - 2 classes - 9 missing values
This dataset was retrieved 2014-11-14 from the UCI site and converted to the ARFF format. __Major changes w.r.t. version 3: dataset from UCI that matches description and data types__ ### Feature…
4202 runs0 likes6 downloads6 reach6 impact
690 instances - 15 features - 2 classes - 0 missing values
Original data from https://github.com/propublica/compas-analysis/ by ProPublica. The data was subsequently preprocessed and reduced to relevant features for classification. The target variable is…
0 runs0 likes0 downloads0 reach1 impact
5278 instances - 14 features - 2 classes - 0 missing values
At Santander our mission is to help people and businesses prosper. We are always looking for ways to help our customers understand their financial health and identify which products and services might…
0 runs0 likes1 downloads1 reach1 impact
200000 instances - 202 features - 2 classes - 0 missing values
All data is from one continuous EEG measurement with the Emotiv EEG Neuroheadset. The duration of the measurement was 117 seconds. The eye state was detected via a camera during the EEG measurement…
166397 runs3 likes93 downloads96 reach21 impact
14980 instances - 15 features - 2 classes - 0 missing values
Data Set Information: This research aimed at the case of customers’ default payments in Taiwan and compares the predictive accuracy of probability of default among six data mining methods. From…
0 runs0 likes0 downloads0 reach0 impact
30000 instances - 24 features - 2 classes - 0 missing values
Airlines Dataset Inspired in the regression dataset from Elena Ikonomovska. The task is to predict whether a given flight will be delayed, given the information of the scheduled departure. For this…
0 runs0 likes0 downloads0 reach0 impact
26969 instances - 8 features - 2 classes - 0 missing values
An artificial data set where instances belongs to several clusters with a banana shape. There are two attributes At1 and At2 corresponding to the x and y axis, respectively. The class label (-1 and 1)…
163 runs2 likes17 downloads19 reach8 impact
5300 instances - 3 features - 2 classes - 0 missing values
Each record represents 100 points on a two-dimensional graph. When plotted in order (from 1 through 100) as the Y coordinate, the points will create either a Hill (a “bump” in the terrain) or a…
183264 runs0 likes23 downloads23 reach19 impact
1212 instances - 101 features - 2 classes - 0 missing values
Multi-label dataset. The birds dataset consists of 327 audio recordings of 12 different vocalizing bird species. Each sound can be assigned to various bird species.
0 runs0 likes6 downloads6 reach5 impact
645 instances - 279 features - 2 classes - 0 missing values
sd vfv
0 runs0 likes0 downloads0 reach0 impact
4 instances - 50 features - 2 classes - 0 missing values
A dataset of steel plates' faults, classified into 7 different types. The goal was to train machine learning for automatic pattern recognition. The dataset consists of 27 features describing each…
277313 runs1 likes42 downloads43 reach19 impact
1941 instances - 34 features - 2 classes - 0 missing values
* Dataset: DBworld e-mails data set Task: dbworld-subjects-stemmed * Source: Michele Filannino, PhD University of Manchester Centre for Doctoral Training Email: filannim_AT_cs.man.ac.uk * Data Set…
71 runs0 likes2 downloads2 reach7 impact
64 instances - 230 features - 2 classes - 0 missing values
Source: David Gil, dgil '@' dtic.ua.es, Lucentia Research Group, Department of Computer Technology, University of Alicante Jose Luis Girela, girela '@' ua.es, Department of Biotechnology, University…
451 runs0 likes7 downloads7 reach7 impact
100 instances - 10 features - 2 classes - 0 missing values
The weather problem is a tiny dataset that we will use repeatedly to illustrate machine learning methods. Entirely fictitious, it supposedly concerns the conditions that are suitable for playing some…
0 runs0 likes2 downloads2 reach3 impact
14 instances - 5 features - 2 classes - 0 missing values
* Title: Thoracic Surgery Data Data Set * Abstract: The data is dedicated to classification problem related to the post-operative life expectancy in the lung cancer patients: class 1 - death within…
145 runs0 likes8 downloads8 reach8 impact
470 instances - 17 features - 2 classes - 0 missing values
The data is cleaned, regularized and encrypted global equity data. The first 21 columns (feature1 - feature21) are features, and target is the binary class you’re trying to predict.
1083 runs1 likes3 downloads4 reach9 impact
96320 instances - 22 features - 2 classes - 0 missing values
Source: http://www.ijcaonline.org/archives/volume47/number18/7291-0509 Data Set Information: In this paper, we look for to recognize the causes of users tend to cyber space in Kohkiloye and Boyer…
373 runs0 likes7 downloads7 reach7 impact
100 instances - 6 features - 2 classes - 0 missing values
PMLB version of the Titanic dataset, which only uses 3 features. See version 1 for the complete version: https://www.openml.org/d/40945
35 runs0 likes1 downloads1 reach16 impact
2201 instances - 4 features - 2 classes - 0 missing values
Forecasting skewed biased stochastic ozone days: analyses, solutions and beyond, Knowledge and Information Systems, Vol. 14, No. 3, 2008. 1 . Abstract: Two ground ozone level data sets are included in…
187955 runs0 likes16 downloads16 reach21 impact
2534 instances - 73 features - 2 classes - 0 missing values
QSAR biodegradation Data Set * Abstract: Data set containing values for 41 attributes (molecular descriptors) used to classify 1055 chemicals into 2 classes (ready and not ready biodegradable). *…
267507 runs1 likes20 downloads21 reach20 impact
1055 instances - 42 features - 2 classes - 0 missing values
__Major changes w.r.t. version 1: deactivated first two variables as they describe the batch of the experiments and should not be used for prediction. Also transformed the target from numeric to…
8775 runs0 likes3 downloads3 reach7 impact
540 instances - 21 features - 2 classes - 0 missing values
__Changes w.r.t. version 1: renamed variables such that they match description.__ ### Dataset: Wilt Data Set ### Abstract: High-resolution Remote Sensing data set (Quickbird). Small number of training…
10946 runs0 likes1 downloads1 reach14 impact
4839 instances - 6 features - 2 classes - 0 missing values
The aim of this dataset is to distinguish between nasal (class 0) and oral sounds (class 1). Five different attributes were chosen to characterize each vowel: they are the amplitudes of the five first…
218302 runs5 likes34 downloads39 reach23 impact
5404 instances - 6 features - 2 classes - 0 missing values
Current dataset was adapted to ARFF format from the UCI version. Sample code ID's were removed. ! Note that there is also a related Breast Cancer Wisconsin (Original) Data Set with a different set of…
226562 runs3 likes35 downloads38 reach21 impact
569 instances - 31 features - 2 classes - 0 missing values
### Description __Changes to version 1:__ all categorical features transformed as such. This dataset represents a set of possible advertisements on Internet pages. ### Sources (a) Creator and donor:…
1430 runs0 likes3 downloads3 reach15 impact
3279 instances - 1559 features - 2 classes - 0 missing values
####1. Summary This dataset contain attributes of dresses and their recommendations according to their sales. Sales are monitor on the basis of alternate days. The attributes present analyzed are:…
19054 runs1 likes6 downloads7 reach12 impact
500 instances - 13 features - 2 classes - 835 missing values
This data set contains 416 liver patient records and 167 non liver patient records.The data set was collected from north east of Andhra Pradesh, India. The class label divides the patients into 2…
154859 runs1 likes21 downloads22 reach20 impact
583 instances - 11 features - 2 classes - 0 missing values
#### Abstract: MADELON is an artificial dataset, which was part of the NIPS 2003 feature selection challenge. This is a two-class classification problem with continuous input variables. The difficulty…
100887 runs0 likes17 downloads17 reach20 impact
2600 instances - 501 features - 2 classes - 0 missing values
### Description Cylinder bands UCI dataset - Process delays known as cylinder banding in rotogravure printing were substantially mitigated using control rules discovered by decision tree induction.…
21477 runs0 likes8 downloads8 reach20 impact
540 instances - 40 features - 2 classes - 999 missing values
Context "Predict behavior to retain customers. You can analyze all relevant customer data and develop focused customer retention programs." [IBM Sample Data Sets] Content Each row represents a…
0 runs1 likes1 downloads2 reach2 impact
7043 instances - 20 features - 2 classes - 0 missing values
xxx
0 runs0 likes0 downloads0 reach0 impact
891 instances - 8 features - 2 classes - 689 missing values
"The speech dataset was also provided by (see citation request) and contains real world data from recorded English language. The normal class contains data from persons having an American accent…
1599 runs0 likes6 downloads6 reach15 impact
3686 instances - 401 features - 2 classes - 0 missing values
The goal of this challenge is to expose the research community to real world datasets of interest to 4Paradigm. All datasets are formatted in a uniform way, though the type of data might differ. The…
11 runs1 likes1 downloads2 reach12 impact
20000 instances - 4297 features - 2 classes - 0 missing values
Predict a biological response of molecules from their chemical properties. Each row in this data set represents a molecule. The first column contains experimental data describing an actual biological…
48338 runs2 likes37 downloads39 reach27 impact
3751 instances - 1777 features - 2 classes - 0 missing values
DESCRIPTIVE ABSTRACT: The data set contains the oral, written and combined test scores for 2003 New Haven Fire Department promotion exams. The Race and Position for each test taker are also given.…
0 runs0 likes0 downloads0 reach0 impact
118 instances - 6 features - 2 classes - 0 missing values
* Abstract: Oxford Parkinson's Disease Detection Dataset * Source: The dataset was created by Max Little of the University of Oxford, in collaboration with the National Centre for Voice and Speech,…
179 runs1 likes15 downloads16 reach13 impact
195 instances - 23 features - 2 classes - 0 missing values
Balanced version of click prediction data
36 runs0 likes14 downloads14 reach11 impact
1997410 instances - 12 features - 2 classes - 0 missing values
Prediction task is to determine whether a person makes over 50K a year. Extraction was done by Barry Becker from the 1994 Census database. A set of reasonably clean records was extracted using the…
14257 runs1 likes25 downloads26 reach34 impact
48842 instances - 15 features - 2 classes - 6465 missing values
* Title: South Africa Heart Disease Dataset * Description A retrospective sample of males in a heart-disease high-risk region of the Western Cape, South Africa. There are roughly two controls per case…
155 runs0 likes14 downloads14 reach12 impact
462 instances - 10 features - 2 classes - 0 missing values
Data taken from the Blood Transfusion Service Center in Hsin-Chu City in Taiwan -- this is a classification problem. To demonstrate the RFMTC marketing model (a modified version of RFM), this study…
467763 runs5 likes83 downloads88 reach37 impact
748 instances - 5 features - 2 classes - 0 missing values
Testing dataset
0 runs0 likes0 downloads0 reach0 impact
134731 instances - 31 features - 2 classes - 0 missing values
This data is derived from the 2012 KDD Cup. The data is subsampled to 0.1% of the original number of instances, downsampling the majority class (click=0) so that the target feature is reasonably…
63420 runs0 likes16 downloads16 reach23 impact
39948 instances - 12 features - 2 classes - 0 missing values
Multi-label dataset for text-classification. It consists of article titles and partial blurbs. Blurbs can be assigned to several categories (e.g. Science, News, Games) based on word predictors.
0 runs1 likes14 downloads15 reach14 impact
3782 instances - 1101 features - 2 classes - 0 missing values
Author: Volker Lohweg (University of Applied Sciences, Ostwestfalen-Lippe) Source: [UCI](https://archive.ics.uci.edu/ml/datasets/banknote+authentication) - 2012 Please cite:…
137675 runs5 likes30 downloads35 reach28 impact
1372 instances - 5 features - 2 classes - 0 missing values
A dataset relating characteristics of telephony account features and usage and whether or not the customer churned. Originally used in [Discovering Knowledge in Data: An Introduction to Data…
7482 runs2 likes7 downloads9 reach22 impact
5000 instances - 21 features - 2 classes - 0 missing values