This is an automated email from the ASF dual-hosted git repository.

poorejc pushed a commit to branch distill_toolkit_refactor
in repository https://gitbox.apache.org/repos/asf/incubator-flagon-distill.git

commit 6d07d65ad96d8763a9933254240fcdf5216feebc
Author: poorejc <[email protected]>
AuthorDate: Sat Sep 14 01:42:42 2019 -0400

    [FLAGON-459] Created new branch for Distill refactor
---
 README.rst                                         |   2 +-
 WIP-distill_package/.gitignore                     |  64 +++
 WIP-distill_package/DISCLAIMER                     |   7 +
 WIP-distill_package/LICENSE                        | 201 ++++++++
 WIP-distill_package/MANIFEST.in                    |  11 +
 WIP-distill_package/NOTICE                         |   6 +
 WIP-distill_package/README.md                      |   6 +
 WIP-distill_package/doap-distill.rdf               |  57 +++
 WIP-distill_package/flagon-distill/__init__.py     |  41 ++
 .../flagon-distill/graphs/__init__.py              |  14 +
 WIP-distill_package/flagon-distill/graphs/graph.py | 549 +++++++++++++++++++++
 WIP-distill_package/flagon-distill/version.py      |  22 +
 WIP-distill_package/setup.cfg                      |  37 ++
 WIP-distill_package/setup.py                       | 157 ++++++
 14 files changed, 1173 insertions(+), 1 deletion(-)

diff --git a/README.rst b/README.rst
index ca0929e..0715bd5 100644
--- a/README.rst
+++ b/README.rst
@@ -19,7 +19,7 @@
 Apache Flagon Distill
 =======================
 
-NOTE: This project is not currently maintained and will be refactored. If you 
are interested in Distill, join the discussion on our dev list: 
[email protected].
+NOTE: This project is not currently maintained and is being refactored. If you 
are interested in Distill, join the discussion on our dev list: 
[email protected].
 
 Distill is part of the `Apache Flagon <http://flagon.incubator.apache.org/>`_ 
project.
 It comprises an analytical engine for `UserALE 
<http://flagon.incubator.apache.org/userale/>`_
diff --git a/WIP-distill_package/.gitignore b/WIP-distill_package/.gitignore
new file mode 100644
index 0000000..409b2e0
--- /dev/null
+++ b/WIP-distill_package/.gitignore
@@ -0,0 +1,64 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+.DS_Store
+.idea
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# setup_tools
+setup_tools
+
+# Flask instance folder
+instance/
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Distribution / packaging
+.Python
+env*/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+/bin/
diff --git a/WIP-distill_package/DISCLAIMER b/WIP-distill_package/DISCLAIMER
new file mode 100755
index 0000000..580f8e8
--- /dev/null
+++ b/WIP-distill_package/DISCLAIMER
@@ -0,0 +1,7 @@
+Apache Flagon is an effort undergoing incubation at The Apache Software 
Foundation (ASF),
+sponsored by the Apache Incubator project. Incubation is required of all newly 
accepted
+projects until a further review indicates that the infrastructure, 
communications, and
+decision making process have stabilized in a manner consistent with other 
successful
+ASF projects. While incubation status is not necessarily a reflection of the
+completeness or stability of the code, it does indicate that the project has 
yet to be
+fully endorsed by the ASF.
diff --git a/WIP-distill_package/LICENSE b/WIP-distill_package/LICENSE
new file mode 100755
index 0000000..b38f054
--- /dev/null
+++ b/WIP-distill_package/LICENSE
@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+    Copyright [yyyy] [name of copyright owner]
+
+    Licensed under the Apache License, Version 2.0 (the "License");
+    you may not use this file except in compliance with the License.
+    You may obtain a copy of the License at
+
+        http://www.apache.org/licenses/LICENSE-2.0
+
+    Unless required by applicable law or agreed to in writing, software
+    distributed under the License is distributed on an "AS IS" BASIS,
+    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+    See the License for the specific language governing permissions and
+    limitations under the License.
diff --git a/WIP-distill_package/MANIFEST.in b/WIP-distill_package/MANIFEST.in
new file mode 100644
index 0000000..ec629be
--- /dev/null
+++ b/WIP-distill_package/MANIFEST.in
@@ -0,0 +1,11 @@
+include MANIFEST.in
+include *.rst
+include NOTICE LICENSE DISCLAIMER.txt
+include setup.py setup.cfg
+
+# Include all sources
+graft distill
+
+# Exclude
+global-exclude *.py[co]
+global-exclude __pycache__
\ No newline at end of file
diff --git a/WIP-distill_package/NOTICE b/WIP-distill_package/NOTICE
new file mode 100755
index 0000000..ed6a1a7
--- /dev/null
+++ b/WIP-distill_package/NOTICE
@@ -0,0 +1,6 @@
+Apache Flagon Distill
+Copyright 2019 The Apache Software Foundation
+
+This product includes software developed at The Apache Software Foundation 
(http://www.apache.org/),
+based on source code originally developed and generously granted to The Apache 
Software Foundation
+by The Charles Stark Draper Laboratory, Inc (http://www.draper.com/).
diff --git a/WIP-distill_package/README.md b/WIP-distill_package/README.md
new file mode 100644
index 0000000..5d73d29
--- /dev/null
+++ b/WIP-distill_package/README.md
@@ -0,0 +1,6 @@
+Apache Flagon Distill
+--------------------------------------
+
+### This is a WIP and is not currently functional. This is part of our 
refactoring of Apache Distill. Stay tuned...
+
+Distill is part of the [Apache Flagon](http://flagon.incubator.apache.org/) 
project. It comprises an analytical engine for 
[UserALE.js](http://flagon.incubator.apache.org/useralejs) to interact with 
user activity logs and apply basic analytical operations to the data.
\ No newline at end of file
diff --git a/WIP-distill_package/doap-distill.rdf 
b/WIP-distill_package/doap-distill.rdf
new file mode 100755
index 0000000..d17fbc1
--- /dev/null
+++ b/WIP-distill_package/doap-distill.rdf
@@ -0,0 +1,57 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl"?>
+<rdf:RDF xml:lang="en"
+         xmlns="http://usefulinc.com/ns/doap#";
+         xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#";
+         xmlns:asfext="http://projects.apache.org/ns/asfext#";
+         xmlns:foaf="http://xmlns.com/foaf/0.1/";>
+    <!--
+        Licensed to the Apache Software Foundation (ASF) under one or more
+        contributor license agreements.  See the NOTICE file distributed with
+        this work for additional information regarding copyright ownership.
+        The ASF licenses this file to You under the Apache License, Version 2.0
+        (the "License"); you may not use this file except in compliance with
+        the License.  You may obtain a copy of the License at
+
+             http://www.apache.org/licenses/LICENSE-2.0
+
+        Unless required by applicable law or agreed to in writing, software
+        distributed under the License is distributed on an "AS IS" BASIS,
+        WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 
implied.
+        See the License for the specific language governing permissions and
+        limitations under the License.
+    -->
+    <Project rdf:about="http://flagon.incubator.apache.org/distill/";>
+        <created>2016-11-10</created>
+        <license rdf:resource="http://usefulinc.com/doap/licenses/asl20"; />
+        <name>Apache Flagon - Distill.js</name>
+        <homepage rdf:resource="http://flagon.incubator.apache.org"; />
+        <asfext:pmc rdf:resource="http://flagon.incubator.apache.org"; />
+        <shortdesc>Distill is an analytical framework for 
UserALE.js</shortdesc>
+        <description>Distill comprises an analytical engine for UserALE.js to 
interact with user activity logs and apply basic analytical operations to the 
data</description>
+        <bug-database 
rdf:resource="https://issues.apache.org/jira/browse/FLAGON"; />
+        <mailing-list 
rdf:resource="https://cwiki.apache.org/confluence/x/whTiAw"; />
+        <download-page 
rdf:resource="https://cwiki.apache.org/confluence/x/whTiAw"; />
+        <programming-language>Python</programming-language>
+        <category 
rdf:resource="https://projects.apache.org/projects.html?category#Library"; />
+        <release>
+            <Version>
+                <name>0.1.0 release</name>
+                <created>2019-09-13</created>
+                <revision>0.0.0</revision>
+            </Version>
+        </release>
+        <repository>
+            <SVNRepository>
+                <location 
rdf:resource="https://git-wip-us.apache.org/repos/asf/incubator-flagon-distill.git"/>
+                <browse 
rdf:resource="https://github.com/apache/incubator-flagon-distill"/>
+            </SVNRepository>
+        </repository>
+        <maintainer>
+            <foaf:Person>
+                <foaf:name>Flagon Development Team</foaf:name>
+                <foaf:mbox 
rdf:resource="mailto:[email protected]"/>
+            </foaf:Person>
+        </maintainer>
+    </Project>
+</rdf:RDF>
\ No newline at end of file
diff --git a/WIP-distill_package/flagon-distill/__init__.py 
b/WIP-distill_package/flagon-distill/__init__.py
new file mode 100644
index 0000000..aa24b84
--- /dev/null
+++ b/WIP-distill_package/flagon-distill/__init__.py
@@ -0,0 +1,41 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from elasticsearch_dsl.connections import connections
+
+from distill.config.elasticsearch import ELASTICSEARCH_PARAMS
+
+
+# Unpack Elasticsearch configuration and create elasticsearch connection
+host = ELASTICSEARCH_PARAMS['host']
+port = ELASTICSEARCH_PARAMS['port']
+http_auth = ELASTICSEARCH_PARAMS['http_auth']
+use_ssl = ELASTICSEARCH_PARAMS['use_ssl']
+verify_certs = ELASTICSEARCH_PARAMS['verify_certs']
+ca_certs = ELASTICSEARCH_PARAMS['ca_certs']
+client_cert = ELASTICSEARCH_PARAMS['client_cert']
+client_key = ELASTICSEARCH_PARAMS['client_key']
+timeout = ELASTICSEARCH_PARAMS['timeout']
+
+# Initialize Elasticsearch instance
+es = connections.create_connection(hosts=host,
+                                   port=port,
+                                   http_auth=http_auth,
+                                   use_ssl=use_ssl,
+                                   verify_certs=verify_certs,
+                                   ca_certs=ca_certs,
+                                   client_cert=client_cert,
+                                   client_key=client_key,
+                                   timeout=timeout)
diff --git a/WIP-distill_package/flagon-distill/graphs/__init__.py 
b/WIP-distill_package/flagon-distill/graphs/__init__.py
new file mode 100644
index 0000000..6acb5d1
--- /dev/null
+++ b/WIP-distill_package/flagon-distill/graphs/__init__.py
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
diff --git a/WIP-distill_package/flagon-distill/graphs/graph.py 
b/WIP-distill_package/flagon-distill/graphs/graph.py
new file mode 100755
index 0000000..174e636
--- /dev/null
+++ b/WIP-distill_package/flagon-distill/graphs/graph.py
@@ -0,0 +1,549 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import itertools
+import json
+import collections
+
+from elasticsearch import helpers
+
+from distill import es
+
+class GraphAnalytics (object):
+    """
+    Distill's graph analytics package. Apply graph algorithms
+    to User Ale log data.
+    """
+
+    @staticmethod
+    def generate_graph(app,
+                       app_type='logs',
+                       log_type='raw',
+                       targets=[],
+                       events=[],
+                       time_range=['now-1h', 'now'],
+                       size=20):
+        """
+        Return all elements from an application, possible matching against
+        a specific event type (e.g. click, mouseover, etc)
+        """
+        # @TODO ref_url filter
+
+        must_not_query = [
+            {
+                "term": {
+                    "type": "mousedown"
+                }
+            },
+            {
+                "term": {
+                    "type": "mouseup"
+                }
+            }
+        ]
+
+        filter_query = [
+            {
+                "term": {
+                    "logType": log_type
+                },
+            },
+        ]
+
+        # Filtering
+        should_query = []
+        must_query = []
+
+        # Include these events in the request
+        if events:
+            include_events = {
+                "terms": {
+                    "type": events
+                }
+            }
+            filter_query.append(include_events)
+
+        target_in = targets[0]
+        target_out = targets[1]
+
+        if target_in:
+            include_targets = {
+                "terms": {
+                    "target": target_in
+                }
+            }
+
+            filter_query.append(include_targets)
+
+        # Remove these elementids from result set
+        for target in target_out:
+            res = {
+                "term": {
+                    "target": target
+                }
+            }
+            must_not_query.append(res)
+
+        # Finish off should query
+        # must_query.append({"bool": {"should": should_query}})
+
+        # Sort By Time
+        sort_query = [
+            {
+                "clientTime": {
+                    "order": "asc"
+                }
+            }
+        ]
+
+        # Timestamp range - date math
+        timestamp_query = {
+            "range": {
+                "@timestamp": {
+                    "gte": time_range[0],
+                    "lte": time_range[1]
+                }
+            }
+        }
+        filter_query.append(timestamp_query)
+
+        agg_query = dict()
+
+        # Get all unique sessions
+        session_query = {
+                "terms": {
+                    "field": "sessionID",
+                    "min_doc_count": 1
+                }
+            }
+
+        agg_query['sessions'] = session_query
+
+        # Generating all top targets and breakdowns by type, including 
path_length
+        target_query = {
+                "terms": {
+                    "field": "target",
+                    "min_doc_count": 1,
+                    "size": size
+                },
+                "aggs": {
+                    "events": {
+                        "terms": {
+                            "field": "type",
+                            "min_doc_count": 1,
+                            "size": size
+                        }
+                    },
+                    "top_target": {
+                        "top_hits": {
+                            "script_fields": {
+                                "path_length": {
+                                    "script": {
+                                        "lang": "painless",
+                                        "inline": "doc['path'].length;"
+                                    }
+                                }
+                            },
+                            "size": 1
+                        }
+                    }
+                }
+            }
+
+        agg_query['targets'] = target_query
+
+        # Main query
+        query = {
+            "sort": sort_query,
+            "query": {
+                "bool": {
+                    # "must": must_query,
+                    # "should": should_query,
+                    "filter": filter_query,
+                    "must_not": must_not_query,
+                    # "minimum_should_match": len(should_query) - 1
+                }
+            },
+            "_source": {
+                "includes": ['*'],
+            },
+            "script_fields": {
+                "path_length": {
+                    "script": {
+                        "lang": "painless",
+                        "inline": "doc['path'].length;"
+                    }
+                }
+            },
+            "aggregations": agg_query
+        }
+
+        # return query
+        # Process Aggregate Results
+        response = es.search(app, doc_type=app_type, body=query, size=0)
+        # Only want to look at aggregations
+        sessions = response['aggregations']['sessions']['buckets']
+        # allSessions = { x['key']: [] for x in sessions }
+        # intervalSessions = { x['key']: [] for x in sessions }
+
+        # Deal with bar chart
+        allTargets = response['aggregations']['targets']['buckets']
+
+        # Re-execute query to get all hits
+        iter = helpers.scan(es,
+                            query=query,
+                            index=app,
+                            doc_type=app_type,
+                            preserve_order=True)
+
+        allSessions = dict()
+        # Store all hits in the user's bucket.
+        for elem in iter:
+            data = elem['_source']
+            data['pathLength'] = elem['fields']['path_length'][0]
+            if 'sessionID' in data:
+                sessionID = data['sessionID']
+                if sessionID in allSessions:
+                    allSessions[sessionID].append(data)
+                else:
+                    allSessions[sessionID] = [data]
+
+        # This fixed sequence/interval logging that what was produced in
+        # UserALE.js v 0.2.0
+        # Possible to remove self-loops here as well 
(html->html->html->window) := (html->window)
+        intervalSessions = dict()
+        for sessionID in allSessions:
+            data = allSessions[sessionID]
+            newData = []
+            intervalLog = []
+            pairs = zip(data, data[1:])
+
+            for curr, next in pairs:
+                target1 = curr['target']
+                event1 = curr['type']
+                target2 = next['target']
+                event2 = next['type']
+                if target1 != target2: # ignore self-loops
+                    targetChange = int(True)
+                    eventChange = int(False)
+                    if event1 != event2:
+                        eventChange = int(True)
+
+                    # Starting over no matter what
+                    # Based off of curr, update the log
+                    curr['targetChange'] = targetChange
+                    curr['typeChange'] = eventChange
+                    curr['intervalCount'] = len(intervalLog)   # some number 
maybe 0
+                    if len(intervalLog) >= 2:
+                        # Calculate duration
+                        curr['duration'] = intervalLog[-1:]['clientTime'] - \
+                                           intervalLog[0]['clientTime']
+                    else:
+                        curr['duration'] = 0
+                    newData.append(curr)
+                    intervalLog = []
+                # else:
+                #     # They are the same
+                #     targetChange = int(False)
+                #     eventChange = int(False)
+                #     if event1 != event2:
+                #         eventChange = int(True)
+                #         # starting over
+                #         curr['targetChange'] = targetChange
+                #         curr['typeChange'] = eventChange
+                #         curr['intervalCount'] = len(intervalLog)
+                #         # if len(intervalLog) >= 2:
+                #         #     # Calculate duration
+                #         #     curr['duration'] = 
intervalLog[-1:]['clientTime'] - \
+                #         #                        intervalLog[0]['clientTime']
+                #         # else:
+                #         #     curr['duration'] = 0
+                #         newData.append(curr)
+                #         intervalLog = []
+                #     else:
+                #         # increase counter
+                #         intervalLog.append(curr)
+            intervalSessions[sessionID] = newData
+
+        # return intervalSessions
+        newSessions = []
+
+        # Generate all edges tied to a user
+        # [ edge list, edge list, ... ]
+        for k, v in intervalSessions.items():
+            pairs = pairwise(v) # list of edges for a user
+            newSessions.append(pairs)
+
+        # Node Map
+        node_list = []   # Need to keep 0-based index for sankey diagram
+        links = []      # Aggregate sequence list
+        node_map = []   # Final node map {"name": "foo", "id": 0"}
+
+        # Align the sequences
+        alignment = itertools.izip_longest(*newSessions)
+        src_ids = {}
+        target_ids = {}
+
+        for i, step in enumerate(alignment):
+            # print(i)
+            c = collections.Counter()
+            visitedLinks = []
+            # visitedLinksUnique = set([])
+            nodenames = set([])
+
+            for edge in step:   # for a single step look at all links
+                if edge:
+                    node1 = edge[0]
+                    node2 = edge[1]
+                    session = node1['sessionID']
+                    nodename1 = node1['target']
+                    nodename2 = node2['target']
+
+                    seqID = '%s->%s' % (nodename1, nodename2)
+                    #print(seqID)
+
+                    if nodename1 != nodename2:  #double check again for 
self-loops
+                        #print(node1)
+                        link = {
+                            'sequenceID': seqID,
+                            'sourceName': nodename1,
+                            'targetName': nodename2,
+                            'type': node1['type'],
+                            'duration': node1['duration'],
+                            'pathLength': len(node1['path']) if node1['path'] 
is not None else 0,
+                            'targetChange': node1['targetChange'],
+                            'typeChange': node1['typeChange']
+                        }
+                        visitedLinks.append(link)
+
+            # Done with visits in a step. Now calculate counts
+            counts = collections.Counter(k['sequenceID'] for k in visitedLinks 
if k.get('sequenceID'))
+            # print(counts)
+            visitedLinksUnique = { v['sequenceID']:v for v in 
visitedLinks}.values()
+            # print(visitedLinksUnique)
+
+            # Visit unique links and generate src/targetid
+            if len(node_map) == 0:
+                for link in visitedLinksUnique:
+                    # Add all sources
+                    if link['sourceName'] not in src_ids:
+                        node_map.append({"name": link['sourceName']})
+                        src_ids[link['sourceName']] = len(node_map)-1
+
+                    # Add all targets
+                    if link['targetName'] not in target_ids:
+                        node_map.append({"name": link['targetName']})
+                        target_ids[link['targetName']] = len(node_map)-1
+
+            else:
+                src_ids = target_ids    # sources were previous targets
+                target_ids = {}
+                for link in visitedLinksUnique:
+                    # Add all sources
+                    # if link['sourceName'] not in src_ids.values():
+                    #     node_map.append(link['sourceName'])
+                    #     src_ids[len(node_map)-1] = link['sourceName']
+
+                    # Add all targets
+                    if link['targetName'] not in target_ids:
+                        node_map.append({"name": link['targetName']})
+                        target_ids[link['targetName']] = len(node_map)-1
+
+            for link in visitedLinksUnique:
+                # Perform lookup for ids
+                # Perform lookup for counts
+                link['source'] = src_ids[link['sourceName']]
+                link['target'] = target_ids[link['targetName']]
+                link['value'] = counts[link['sequenceID']]
+
+                links.append(link)
+
+        # for step in alignment:
+        #     # step through every users sequence
+        #     c = collections.Counter()
+        #     visitedLinks = []
+        #     nodenames = set([])
+        #
+        #     # Process all the edges
+        #     for edge in step:
+        #         if edge:
+        #             node1 = edge[0]
+        #             node2 = edge[1]
+        #
+        #             nodename1 = node1['target']
+        #             nodename2 = node2['target']
+        #
+        #             # Add src and targetids
+        #             nodenames.add(nodename1)
+        #             nodenames.add(nodename2)
+        #
+        #             # Generate sequence ID
+        #             seqID = '%s->%s' % (nodename1, nodename2)
+        #
+        #             # @todo Ensure src and target are not the same 
(self-loop)
+        #             if nodename1 != nodename2:
+        #                 link = {
+        #                     'sequenceID': seqID,
+        #                     'sourceName': nodename1,
+        #                     'targetName': nodename2,
+        #                     'type': node1['type'],
+        #                     # 'duration': node1['duration'],
+        #                     'pathLength': len(node1['path']),
+        #                     'targetChange': node1['targetChange'],
+        #                     'typeChange': node1['typeChange']
+        #                 }
+        #                 visitedLinks.append(link)
+        #
+        #     # How many users visited a sequence at this step
+        #     counts = collections.Counter(k['sequenceID'] for k in 
visitedLinks if k.get('sequenceID'))
+        #     # print(counts)
+        #     # Append into growing node_list
+        #     map(lambda x: node_list.append(x), nodenames)
+        #
+        #     # map(lambda x: node_map.append({ "name": x}
+        #     #                                 "id": len(node_list) - 1 - 
node_list[::-1].index(x)}), nodenames)
+        #
+        #     map(lambda x: node_map.append({ "name": x}), nodenames)
+        #                                     # "id": len(node_list) - 1 - 
node_list[::-1].index(x)}), nodenames)
+        #     for v in visitedLinks:
+        #         # Pass through and update count, also generate src and 
target id
+        #         v['value'] = counts[v['sequenceID']]
+        #         # Last occurence is the src and target id
+        #         v['source'] = len(node_list) -1 - 
node_list[::-1].index(v['sourceName'])
+        #         v['target'] = len(node_list) -1 - 
node_list[::-1].index(v['targetName'])
+        #         links.append(v)
+
+        # Save everything
+        res = dict()
+        res['histogram'] = generate_bargraph(allTargets)
+        # res['sankey'] = {
+        #     # 'sessions': sessions,
+        #     'links': links,
+        #     'nodes': node_map
+        # }
+
+        res['nodes'] = node_map
+        res['links'] = links
+        res['sessions'] = sessions
+        # with open('sankey.json', 'w') as outfile:
+        #     json.dump(res, outfile, sort_keys=False, indent=4)
+
+        # with open('data.txt', 'w') as outfile:
+        #     json.dump(intervalSessions, outfile, indent=4, sort_keys=False)
+        #
+        # with open('query.json', 'w') as outfile:
+        #     json.dump(query, outfile, indent=4, sort_keys=False)
+        # Iterate first to get nodes
+        # pairs = pairwise(iter)
+        #
+        # nodes = []
+        # links = []
+
+        # for p in pairs:
+        #     node1 = p[0]['_source']
+        #     node2 = p[1]['_source']
+
+        #     # Append nodes to list
+        #     nodes.append(node1['target'])
+        #     nodes.append(node2['target'])
+
+        # Iterate again to get edges
+        # pairs = pairwise(iter2)
+
+        # srcID = targetID = None
+        # for p in pairs:
+        #     node1 = p[0]['_source']
+        #     node2 = p[1]['_source']
+        #
+        #     # Append nodes to list
+        #     nodes.append(node1['target'])
+        #     # nodes.append(node2['target'])
+        #
+        #     srcID = len(nodes) - 1
+        #     targetID = len(nodes)
+        #
+        #     # if (node1['target'] != node2['target']):
+        #     # Append links to list (remove self-loops)
+        #     link = {
+        #         'sourceID': srcID,
+        #         'targetID': targetID,
+        #         'sourceName': node1['target'],
+        #         'targetName': node2['target'],
+        #         'type': node1['type'],
+        #         'duration': node1['duration'],
+        #         'value': node1['count'],
+        #         'pathLength': len(node1['path']),
+        #         'targetChange': int(node1['targetChange']),
+        #         'typeChange': int(node1['typeChange'])
+        #     }
+        #     links.append(link)
+        #
+        # # Get all unique nodes
+        # # node_names = np.unique(nodes).tolist()
+        # node_list = []
+        #
+        # for indx, name in enumerate(nodes):
+        #     n = {'id': indx, 'name': name}
+        #     node_list.append(n)
+        #
+        # # Remove self-loops
+        # newLinks = []
+        # for indx, elem in enumerate(links):
+        #     srcID = elem['sourceID']
+        #     targetID = elem['targetID']
+        #
+        #     if srcID != targetID:
+        #         newLinks.append(elem)
+        #
+
+        #
+        return res
+
+
+def pairwise(iterable):
+    "s -> (s0, s1), (s1, s2), (s2, s3), ..."
+    a, b = itertools.tee(iterable)
+    next(b, None)
+    return itertools.izip(a, b)
+
+
+def generate_bargraph(data, filename='bargraph.json'):
+    results = []
+    for target in data:
+        target_name = target['key']
+        types = []
+        counts = []
+        type_bucket = target['events']['buckets']
+        for t in type_bucket:
+            types.append(t['key'])
+            counts.append(t['doc_count'])
+
+        top_bucket = target['top_target']['hits']['hits'][0]
+        path_length = top_bucket['fields']['path_length'][0]
+        res = {
+            "target": target_name,
+            "counts": counts,
+            "types": types,
+            "pathLength": path_length
+        }
+        results.append(res)
+
+    return results
+
+    # with open(filename, 'w') as outfile:
+    #     json.dump(results, outfile, indent=4, sort_keys=False)
+
+def generate_sankey(data, filename='sankey.json'):
+    pass
diff --git a/WIP-distill_package/flagon-distill/version.py 
b/WIP-distill_package/flagon-distill/version.py
new file mode 100644
index 0000000..d63fbb7
--- /dev/null
+++ b/WIP-distill_package/flagon-distill/version.py
@@ -0,0 +1,22 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Version information for Distill.
+
+This file is imported by ``Distill.__init__``,
+and parsed by ``setup.py``.
+"""
+
+__version__ = "0.1.0"
diff --git a/WIP-distill_package/setup.cfg b/WIP-distill_package/setup.cfg
new file mode 100644
index 0000000..e804958
--- /dev/null
+++ b/WIP-distill_package/setup.cfg
@@ -0,0 +1,37 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+[egg_info]
+tag_build = .dev
+tag_date = 1
+
+[aliases]
+test=pytest
+docs = build_sphinx
+daily = egg_info --tag-date sdist
+release = egg_info --tag-build=".rc" sdist bdist_wheel bdist_egg
+
+[tool:pytest] 
+
+[build_sphinx]
+source-dir = docs/source
+build-dir = docs/_build
+all_files = 1
+
+[upload_sphinx]
+upload-dir = docs/_build/html
+
+[bdist_wheel]
+universal = 1
\ No newline at end of file
diff --git a/WIP-distill_package/setup.py b/WIP-distill_package/setup.py
new file mode 100644
index 0000000..5b1ca6a
--- /dev/null
+++ b/WIP-distill_package/setup.py
@@ -0,0 +1,157 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import setuptools
+import io
+import os
+import sys
+
+if sys.version_info[:2] < (2, 7):
+    m = "Python 2.7 or later is required for Distill (%d.%d detected)."
+    raise ImportError(m % sys.version_info[:2])
+
+if sys.argv[-1] == 'setup.py':
+    #print("To install, run 'python setup.py install'\n")
+    #print("To run tests, run 'python setup.py test'\n")
+    #print("To build docs, run 'python setup.py docs'\n")
+    #print("To clean, run 'python setup.py clean'\n")
+
+
+class CleanCommand(setuptools.Command):
+    """
+    A command class to clean up build artifacts, including log files
+
+    python setup.py clean
+    """
+    description = "clean build artifacts"
+    user_options = []
+
+    def initialize_options(self):
+        """
+        Initialize Clean Command
+        """
+        self.cwd = None
+
+    def finalize_options(self):
+        """
+        Set Current Working directory for Clean Command
+
+        """
+        self.cwd = os.getcwd()
+
+    def run(self):
+        """
+        Execute Clean Command
+        """
+        assert os.getcwd() == self.cwd, 'Must be in package root: %s' % 
self.cwd
+        os.system('rm -rf ./docs/_build ./build ./dist ./*.egg-info')
+        os.system('rm -rf ./*.log *.xml .coverage *.html')
+
+def read(*filenames, **kwargs):
+    encoding = kwargs.get('encoding', 'utf-8')
+    sep = kwargs.get('sep', '\n')
+    buf = []
+    for filename in filenames:
+        with io.open(filename, encoding=encoding) as f:
+            buf.append(f.read())
+    return sep.join(buf)
+
+
+# Get the version string
+def get_version():
+    basedir = os.path.dirname(__file__)
+    with open(os.path.join(basedir, 'distill/version.py')) as f:
+        version = {}
+        exec (f.read(), version)
+        return version['__version__']
+    raise RuntimeError('No version info found.')
+
+
+setup_requires = [
+    'pip >= 9.0.1',
+    'setuptools >= 34.0',
+    'pytest-runner',
+]
+
+install_requires = [
+    'elasticsearch-dsl >= 5.0.0, < 6.0.0',
+    'pandas >= 0.20.2',
+    #'Flask >= 0.12.2',
+    #'celery >= 4.0.2',
+]
+
+tests_require = [
+    #'pytest >= 3.0.0',
+    #'pytest-pylint',
+    #'pytest-html',
+    #'pytest-cov',
+]
+
+docs_require = [
+    #'Sphinx >= 1.5.2',
+    #'sphinx-rtd-theme >= 0.1.9',
+]
+
+extras_require = {
+    #'test' : tests_require,
+    #'doc' : docs_require,
+    #'monitor': [
+    #    'flower'
+    #]
+}
+
+classifiers = [
+    'Development Status :: 4 - Beta',
+    'Intended Audience :: Developers',
+    'Intended Audience :: Science/Research/Development',
+    'License :: OSI Approved :: Apache Software License',
+    'Natural Language :: English',
+    'Operating System :: OS Independent',
+    'Programming Language :: Python',
+    #'Programming Language :: Python :: 2.7',
+    #'Programming Language :: Python :: 3.5',
+    'Environment :: Web Environment',
+    #'Framework :: Flask',
+    #'Topic :: Internet :: Log Analysis '
+]
+
+setuptools.setup(
+    name="Distill",
+    version=get_version(),
+    author="Joshua Poore, Michelle Beard",
+    author_email="[email protected]",
+    description="An analytical framework for UserALE.js",
+    long_description=__doc__,
+    long_description_content_type="text/markdown"
+    license="Apache Software License 2.0",
+    url="https://github.com/apache/incubator-flagon-distill";,
+    packages=setuptools.find_packages(exclude=['examples', 'tests']),
+    classifiers=classifiers,
+    keywords="userale distill",
+    include_package_data=True,
+    #zip_safe=False,
+    cmdclass={
+        'clean': CleanCommand,
+    },
+    setup_requires=setup_requires,
+    tests_require=tests_require,
+    install_requires=install_requires,
+    extras_require=extras_require,
+    entry_points={
+        'console_scripts': [
+            'dev = distill.server:dev_server'
+        ]
+    }
+)

Reply via email to