OpenML
US-Accidents-(4.2-million-records)

US-Accidents-(4.2-million-records)

active ARFF CC BY-NC-SA 4.0 Visibility: public Uploaded 22-03-2022 by Dustin Carrion
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • Computer Systems Machine Learning
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
()[]

46 features

ID (ignore)string2845342 unique values
0 missing
Severitynumeric4 unique values
0 missing
Start_Timestring1959333 unique values
0 missing
End_Timestring2351505 unique values
0 missing
Start_Latnumeric1093622 unique values
0 missing
Start_Lngnumeric1120374 unique values
0 missing
End_Latnumeric1080817 unique values
0 missing
End_Lngnumeric1105411 unique values
0 missing
Distance(mi)numeric14165 unique values
0 missing
Descriptionstring1174563 unique values
0 missing
Numbernumeric46402 unique values
1743911 missing
Streetstring159651 unique values
2 missing
Sidestring3 unique values
0 missing
Citystring11681 unique values
137 missing
Countystring1707 unique values
0 missing
Statestring49 unique values
0 missing
Zipcodestring363085 unique values
1319 missing
Countrystring1 unique values
0 missing
Timezonestring4 unique values
3659 missing
Airport_Codestring2004 unique values
9549 missing
Weather_Timestampstring474214 unique values
50736 missing
Temperature(F)numeric789 unique values
69274 missing
Wind_Chill(F)numeric897 unique values
469643 missing
Humidity(%)numeric100 unique values
73092 missing
Pressure(in)numeric1068 unique values
59200 missing
Visibility(mi)numeric76 unique values
70546 missing
Wind_Directionstring24 unique values
73775 missing
Wind_Speed(mph)numeric136 unique values
157944 missing
Precipitation(in)numeric230 unique values
549458 missing
Weather_Conditionstring127 unique values
70636 missing
Amenitynominal2 unique values
0 missing
Bumpnominal2 unique values
0 missing
Crossingnominal2 unique values
0 missing
Give_Waynominal2 unique values
0 missing
Junctionnominal2 unique values
0 missing
No_Exitnominal2 unique values
0 missing
Railwaynominal2 unique values
0 missing
Roundaboutnominal2 unique values
0 missing
Stationnominal2 unique values
0 missing
Stopnominal2 unique values
0 missing
Traffic_Calmingnominal2 unique values
0 missing
Traffic_Signalnominal2 unique values
0 missing
Turning_Loopnominal1 unique values
0 missing
Sunrise_Sunsetstring2 unique values
2867 missing
Civil_Twilightstring2 unique values
2867 missing
Nautical_Twilightstring2 unique values
2867 missing
Astronomical_Twilightstring2 unique values
2867 missing
Show all 46 features

19 properties

NumberOfInstances
2845342
Number of instances (rows) of the dataset.
NumberOfFeatures
46
Number of attributes (columns) of the dataset.
NumberOfClasses
Number of distinct values of the target attribute (if it is nominal).
NumberOfMissingValues
3414349
Number of missing values in the dataset.
NumberOfInstancesWithMissingValues
1902024
Number of instances with at least one value missing.
NumberOfNumericFeatures
14
Number of numeric attributes.
NumberOfSymbolicFeatures
13
Number of nominal attributes.
Dimensionality
0
Number of attributes divided by the number of instances.
PercentageOfNumericFeatures
30.43
Percentage of numeric attributes.
MajorityClassPercentage
Percentage of instances belonging to the most frequent class.
PercentageOfSymbolicFeatures
28.26
Percentage of nominal attributes.
MajorityClassSize
Number of instances belonging to the most frequent class.
MinorityClassPercentage
Percentage of instances belonging to the least frequent class.
MinorityClassSize
Number of instances belonging to the least frequent class.
NumberOfBinaryFeatures
13
Number of binary attributes.
PercentageOfBinaryFeatures
28.26
Percentage of binary attributes.
PercentageOfInstancesWithMissingValues
66.85
Percentage of instances having missing values.
AutoCorrelation
Average class difference between consecutive instances.
PercentageOfMissingValues
2.61
Percentage of missing values.
Show all 19 properties

0 tasks

Define a new task