Mailing-List: contact user-help@couchdb.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@couchdb.apache.org
Received-SPF: pass (nike.apache.org: domain of randall.leeds@gmail.com
 designates 209.85.218.221 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:in-reply-to:references:date:message-id:subject:from:to
         :content-type:content-transfer-encoding;
        b=aMl9lqq13ZV9bzunQjZuYNzBsZqdEiXh7H8CWjLsKo9tBN9xGzntAdhDaR8Y2SGt8q
         0LQxgIz5iAndQl/zJ4NIt3jLSCnt/rxKtgNItO1x61xLsYp8+mReZHvUSZdTq64c25lE
         m6biz7sW97Dhgn8LRuLQomf8o5/qI7rKDv8Zw=
MIME-Version: 1.0
In-Reply-To: <b7770fe31003071515s12da0550m5782b823e02eb30a@mail.gmail.com>
References: <b7770fe31003060726m3d8fe7edx89424a099aa77183@mail.gmail.com>
	 <6adfa88d1003071302x1a7e95b7k1ac303abd4a7a5f2@mail.gmail.com>
	 <b7770fe31003071515s12da0550m5782b823e02eb30a@mail.gmail.com>
Date: Sun, 7 Mar 2010 15:28:14 -0800
Message-ID: <ec7a93a1003071528v419154cfoe1eab9705a2f9091@mail.gmail.com>
Subject: Re: Map reduce and weird output question
From: Randall Leeds <randall.leeds@gmail.com>
To: user@couchdb.apache.org
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

I'm not an expert on this, but I think you need to create your own
reduce function and output the number of keys rather than the sum of
the values.

On Sun, Mar 7, 2010 at 15:15, Gregory Tappero <coulix@gmail.com> wrote:
> Thank you Pawel,
>
> If i try to follow your way it gives me the count of docs in a given
> day for each username, what i would like is the count of unique
> usernames for a given day.
>
> function(doc) {
>
> =C2=A0 =C2=A0if (doc.doc_type=3D=3D"EdoPing" && doc.em_type=3D=3D0) {
> =C2=A0 =C2=A0 =C2=A0 =C2=A0date =3D new Date().setRFC3339(doc.created_at)=
;
> =C2=A0 =C2=A0 =C2=A0 =C2=A0emit([date.getFullYear(), parseInt(date.getMon=
th())+1,
> date.getDate(), doc.em_uname] , 1);
>
> =C2=A0 =C2=A0}
> }
>
> Reduce:
> =C2=A0_count
>
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
> I get:
>
> [2010, 3, 3, "student1"] =C2=A0 =C2=A0 =C2=A0 =C2=A0 5
> [2010, 3, 4, "student1"] =C2=A0 =C2=A0 =C2=A0 =C2=A0 18
> [2010, 3, 5, "eong"] =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 77
> [2010, 3, 6, "bkante"] =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 71
> [2010, 3, 6, "jfrancillette"] =C2=A0 =C2=A072
> [2010, 3, 6, "mlouviers"] =C2=A0 =C2=A0 =C2=A0 =C2=A012
> [2010, 3, 7, "student1"] =C2=A0 =C2=A0 =C2=A0 =C2=A0 4
>
> I would like to extract the following
>
> [2010, 3, 3] =C2=A0 =C2=A0 =C2=A0 1
> [2010, 3, 4] =C2=A0 =C2=A0 =C2=A0 1
> [2010, 3, 5] =C2=A0 =C2=A01
> [2010, 3, 6] =C2=A0 =C2=A0 =C2=A0 3
> [2010, 3, 7] =C2=A0 =C2=A0 =C2=A0 1
>
>
> if i do a group_level=3D3 it sum the values.
>
> {"key":[2010,3,3],"value":5},
> {"key":[2010,3,4],"value":18},
> {"key":[2010,3,5],"value":77},
> {"key":[2010,3,6],"value":155},
> {"key":[2010,3,7],"value":4}
>
> How can i count the unique username emitter per day ?
>
>
>
>
> On Sun, Mar 7, 2010 at 10:02 PM, Pawe=C5=82 Stawicki <pawelstawicki@gmail=
.com> wrote:
>> Just emit all documents with em_type =3D 0 in map function, with [date,
>> em_uname] as key. Then count in reduce.
>>
>> Map:
>> function(doc) {
>> =C2=A0if (doc.em_type =3D 0) {
>> =C2=A0 =C2=A0//If you only want to count, you can emit anything (e.g. 1)=
 instead of
>> doc here.
>> =C2=A0 =C2=A0emit([date, em_uname], doc);
>> =C2=A0}
>> }
>>
>> Reduce:
>> function(keys, values, rereduce) {
>> =C2=A0if (!rereduce) {
>> =C2=A0 =C2=A0return count_of_values;
>> =C2=A0} else {
>> =C2=A0 =C2=A0return sum_of_values;
>> =C2=A0}
>>
>> =C2=A0//If you return 1 from emit instead of doc, then count_of_values =
=3D=3D
>> sum_of_values
>> }
>>
>> Then you can handle everything by grouping:
>> http://yourserver:5984/yourdb/_view/yourview?group_level=3D2
>> or group=3Dtrue
>>
>> Regards
>> --
>> Pawe=C5=82 Stawicki
>> http://pawelstawicki.blogspot.com
>> http://szczecin.jug.pl
>>
>>
>>
>> On Sat, Mar 6, 2010 at 16:26, Gregory Tappero <coulix@gmail.com> wrote:
>>
>>> Hello everyone,
>>>
>>> I have the following EdoPing 's type of documents
>>>
>>> {
>>> =C2=A0 "_id": "22add509c1e7bc286832edc5bfe99ce5",
>>> =C2=A0 "_rev": "1-49663ab8778f445e481143120d0d7086",
>>> =C2=A0 "doc_type": "EdoPing",
>>> =C2=A0 "em_uname": "student1",
>>> =C2=A0 "em_gid": 1,
>>> =C2=A0 "created_at": "2010-03-03T14:18:19Z",
>>> =C2=A0 "em_ip": "92.154.70.148",
>>> =C2=A0 "em_type": 0,
>>> =C2=A0 "room_url": "z2fudcvcrfa3reaydatre",
>>> =C2=A0 "room_users": [
>>> =C2=A0 =C2=A0 =C2=A0 "tutorsbox"
>>> =C2=A0 ]
>>> }
>>>
>>> i would like to count all unique em_uname of em_type 0 on a given day d=
ate.
>>>
>>> For now i used this map/reduce
>>> http://friendpaste.com/5xUUQ26bbl9d5KRB8eojwe
>>>
>>> Date.prototype.setRFC3339 =3D function(dString){
>>> =C2=A0 =C2=A0var regexp =3D
>>>
>>> /(\d\d\d\d)(-)?(\d\d)(-)?(\d\d)(T)?(\d\d)(:)?(\d\d)(:)?(\d\d)(\.\d+)?(Z=
|([+-])(\d\d)(:)?(\d\d))/;
>>>
>>> =C2=A0 =C2=A0if (dString.toString().match(new RegExp(regexp))) {
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0var d =3D dString.match(new RegExp(regexp));
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0var offset =3D 0;
>>>
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCDate(1);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCFullYear(parseInt(d[1],10));
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCMonth(parseInt(d[3],10) - 1);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCDate(parseInt(d[5],10));
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCHours(parseInt(d[7],10));
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCMinutes(parseInt(d[9],10));
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCSeconds(parseInt(d[11],10));
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0if (d[12])
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCMilliseconds(parseF=
loat(d[12]) * 1000);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0else
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setUTCMilliseconds(0);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0if (d[13] !=3D 'Z') {
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0offset =3D (d[15] * 60) + pars=
eInt(d[17],10);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0offset *=3D ((d[14] =3D=3D '-'=
) ? -1 : 1);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setTime(this.getTime() - =
offset * 60 * 1000);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0}
>>> =C2=A0 =C2=A0} else {
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0this.setTime(Date.parse(dString));
>>> =C2=A0 =C2=A0}
>>> =C2=A0 =C2=A0return this;
>>> };
>>>
>>> var seenKeys =3D new Array();
>>>
>>> function(doc) {
>>>
>>>
>>> =C2=A0 =C2=A0if (doc.doc_type=3D=3D"EdoPing" && doc.em_type=3D=3D0) {
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0date =3D new Date().setRFC3339(doc.created_a=
t);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0var key =3D doc.em_uname + String(doc.create=
d_at).substring(0,10);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0if (seenKeys[key] =3D=3D =C2=A0undefined =C2=
=A0) {
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0seenKeys[key] =3D 1;
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0emit([date.getFullYear(), pars=
eInt(date.getMonth())+1,
>>> date.getDate() ] , 1);
>>> =C2=A0 =C2=A0 =C2=A0 =C2=A0 }
>>> =C2=A0 =C2=A0}
>>> }
>>>
>>>
>>> It works when saved for this first time but as soon as new EdoPings
>>> get added it starts emitting rows it has already seen ! (same key)
>>> creating faulty count results.
>>>
>>> Is it ok to have seenKeys outside of the doc function() ?
>>> What other way could i use to get the same results ?
>>>
>>> Thanks,
>>>
>>> Greg
>>>
>>
>
>
>
> --
> Greg Tappero
> CTO co founder Edoboard
> http://www.edoboard.com
> +33 0645764425
>