DC crime data source gallery
Sample document
| nid | ccn | reportdatetime | shift | offense | method | blocksiteaddress | latitude | longitude | city | state | ward | anc | smd | district | psa |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 955778 | 11012669 | Jan 29, 2011 12:00:00 AM UTC | UNK | THEFT | 2 | 1300 B/O CONNECTICUT AVE NW | 38.90992780287290 | -77.04360677659660 | WASHINGTON | DC | 2 | 2B | 2B02 | SECOND | 208.0 |
Source
{
"description": "Incident reports from the Washington, D.C. MPD",
"harvest": {
"doccount": 9314,
"harvest_status": "success,
"harvested": "Nov 2, 2012 11:26:25 AM",
"synced": "Nov 2, 2012 11:24:30 AM"
},
"isApproved": true,
"isPublic": true,
"mediaType": "Record",
"tags": [
"crime report",
"MPD",
"Washington, D.C."
],
"title": "data.dc.gov - Crime Incidents (ASP)",
"processingPipeline": [
{
"database": {
"authentication": {
"password": "PASSWORD",
"username": "USERNAME"
},
"databaseName": "washingtondc",
"databaseType": "mysql",
"deleteQuery": "",
"deltaQuery": "SELECT * FROM IncidentReport WHERE REPORTDATETIME >= (SELECT ADDDATE(CURDATE(),-7))",
"hostname": "dbserver.ikanow.com",
"port": "3306",
"primaryKey": "NID",
"publishedDate": "REPORTDATETIME",
"query": "SELECT * FROM IncidentReport",
"snippet": "OFFENSE",
"title": "CCN",
"url": "jdbc:mysql://ec2-184-72-206-97.compute-1.amazonaws.com/washingtondc/IncidentReport"
}
},
{
"docMetadata": {
"description": "$metadata.reportdatetime: $metadata.offense,$metadata.method was reported at: $metadata.blocksiteaddress",
"geotag": {
"lat": "$metadata.latitude",
"lon": "$metadata.longitude"
}
}
},
{
"textEngine": {
"engineName": "default"
}
},
{
"entities": [
{
"dimension": "What",
"disambiguated_name": "$metadata.offense,$metadata.method",
"type": "CriminalActivity"
},
{
"dimension": "Where",
"disambiguated_name": "$metadata.blocksiteaddress,$metadata.city,$metadata.state",
"geotag": {},
"type": "Place"
},
{
"dimension": "Where",
"disambiguated_name": "$metadata.ward,$metadata.city,$metadata.state",
"type": "Place"
},
{
"dimension": "Where",
"disambiguated_name": "$metadata.district,$metadata.city,$metadata.state",
"type": "Place"
}
]
},
{
"associations": [
{
"entity1": "$metadata.offense,$metadata.method",
"geotag": {},
"time_start": "$metadata.reportdatetime",
"verb": "reported",
"verb_category": "crime"
}
]
}
]
}
Sample output
{
"_id": "4eb1a6532285a1eed2af759c",
"title": "11012669",
"url": "jdbc:mysql://dbserver.ikanow.com/washingtondc/IncidentReport/955778",
"created": "Nov 2, 2011 08:21:39 PM UTC",
"modified": "Nov 2, 2011 08:21:39 PM UTC",
"publishedDate": "Jan 29, 2011 05:00:00 AM UTC",
"source": [
"data.dc.gov - Crime Incidents (ASP)"
],
"sourceKey": [
"Bergen.washingtondc.IncidentReport"
],
"mediaType": [
"Record"
],
"description": "Jan 29, 2011 12:00:00 AM: THEFT,2 was reported at: 1300 B/O CONNECTICUT AVE NW",
"entities": [
{
"disambiguated_name": "THEFT,2",
"index": "theft,2/criminalactivity",
"actual_name": "THEFT,2",
"type": "CriminalActivity",
"frequency": 1,
"totalfrequency": 2705,
"doccount": 2705,
"dimension": "What"
},
{
"disambiguated_name": "1300 B/O CONNECTICUT AVE NW,WASHINGTON,DC",
"index": "1300 b/o connecticut ave nw,washington,dc/place",
"actual_name": "1300 B/O CONNECTICUT AVE NW,WASHINGTON,DC",
"type": "Place",
"frequency": 1,
"totalfrequency": 28,
"doccount": 28,
"geotag": {
"lat": 38.9099278028729,
"lon": -77.0436067765966
},
"dimension": "Where",
"ontology_type": "point"
},
{
"disambiguated_name": "2,WASHINGTON,DC",
"index": "2,washington,dc/place",
"actual_name": "2,WASHINGTON,DC",
"type": "Place",
"frequency": 1,
"totalfrequency": 2326,
"doccount": 2326,
"dimension": "Where"
},
{
"disambiguated_name": "SECOND,WASHINGTON,DC",
"index": "second,washington,dc/place",
"actual_name": "SECOND,WASHINGTON,DC",
"type": "Place",
"frequency": 1,
"totalfrequency": 2120,
"doccount": 2120,
"dimension": "Where"
}
],
"tags": [
"crime report",
"MPD",
"Washington, D.C."
],
"communityId": [
"4c927585d591d31d7c37097b"
],
"associations": [
{
"entity1": "theft,2",
"entity1_index": "theft,2/criminalactivity",
"verb": "reported",
"verb_category": "crime",
"time_start": "2011-01-29T00:00:00",
"geotag": {
"lat": 38.9099278028729,
"lon": -77.0436067765966
},
"assoc_type": "Summary"
}
],
"metadata": {
"nid": [
[
{
"value": "955778.0"
}
]
],
"ccn": [
[
{
"value": "1.1012669E7"
}
]
],
"reportdatetime": [
[
"Jan 29, 2011 12:00:00 AM UTC"
]
],
"shift": [
[
"UNK"
]
],
"offense": [
[
"THEFT"
]
],
"method": [
[
"2"
]
],
"blocksiteaddress": [
[
"1300 B/O CONNECTICUT AVE NW"
]
],
"latitude": [
[
"38.90992780287290"
]
],
"longitude": [
[
"-77.04360677659660"
]
],
"city": [
[
"WASHINGTON"
]
],
"state": [
[
"DC"
]
],
"ward": [
[
{
"value": "2.0"
}
]
],
"anc": [
[
"2B"
]
],
"smd": [
[
"2B02"
]
],
"district": [
[
"SECOND"
]
],
"psa": [
[
{
"value": "208.0"
}
]
]
},
"docGeo": {
"lat": 38.9099278028729,
"lon": -77.0436067765966
}
}
Annex - old format Source
{
"authentication": {
"password": "PASSWORD",
"username": "USERNAME"
},
"database": {
"databaseName": "washingtondc",
"databaseType": "mysql",
"deleteQuery": "",
"deltaQuery": "SELECT * FROM IncidentReport WHERE REPORTDATETIME >= (SELECT ADDDATE(CURDATE(),-7))",
"hostname": "dbserver.ikanow.com",
"port": "3306",
"primaryKey": "NID",
"publishedDate": "REPORTDATETIME",
"query": "SELECT * FROM IncidentReport",
"snippet": "OFFENSE",
"title": "CCN"
},
"description": "Incident reports from the Washington, D.C. MPD",
"extractType": "Database",
"harvest": {
"doccount": 9314,
"harvest_message": "Error when harvesting DB: Cannot establish connection to the database : jdbc:mysql://ec2-184-72-206-97.compute-1.amazonaws.com:3306/washingtondc",
"harvest_status": "error",
"harvested": "Nov 2, 2012 11:26:25 AM",
"synced": "Nov 2, 2012 11:24:30 AM"
},
"isApproved": true,
"isPublic": true,
"mediaType": "Record",
"structuredAnalysis": {
"associations": [{
"entity1": "$metadata.offense,$metadata.method",
"geotag": {},
"time_start": "$metadata.reportdatetime",
"verb": "reported",
"verb_category": "crime"
}],
"description": "$metadata.reportdatetime: $metadata.offense,$metadata.method was reported at: $metadata.blocksiteaddress",
"docGeo": {
"lat": "$metadata.latitude",
"lon": "$metadata.longitude"
},
"entities": [
{
"dimension": "What",
"disambiguated_name": "$metadata.offense,$metadata.method",
"type": "CriminalActivity"
},
{
"dimension": "Where",
"disambiguated_name": "$metadata.blocksiteaddress,$metadata.city,$metadata.state",
"geotag": {},
"type": "Place"
},
{
"dimension": "Where",
"disambiguated_name": "$metadata.ward,$metadata.city,$metadata.state",
"type": "Place"
},
{
"dimension": "Where",
"disambiguated_name": "$metadata.district,$metadata.city,$metadata.state",
"type": "Place"
}
]
},
"tags": [
"crime report",
"MPD",
"Washington, D.C."
],
"title": "data.dc.gov - Crime Incidents (ASP)",
"url": "jdbc:mysql://ec2-184-72-206-97.compute-1.amazonaws.com/washingtondc/IncidentReport",
"useExtractor": "none"
}