Package tidy up

.circleci/config.yml

@@ -4,7 +4,7 @@ version: 2
 jobs:
   build:
     docker:
-      - image: circleci/python:3.6.2-stretch
+      - image: circleci/python:3.6.3-stretch
       - image: circleci/postgres:9.6.5-alpine-ram
 
     steps:

.github/issue_template/bug_report.md

@@ -54,5 +54,10 @@ If applicable, add screenshots or log output to help explain your problem.
 
 ### Additional context
 <!---
-Add any other context about the problem here.
+Add any other context about the problem here. For example, if you think you know which line of code is causing the issue.
+--->
+
+### Are you interested in contributing the fix?
+<!---
+Let us know if you want to contribute the fix, and whether would need a hand getting started
 --->

.github/issue_template/feature_request.md

@@ -18,3 +18,8 @@ Is this feature database-specific? Which database(s) is/are relevant? Please inc
 
 ### Who will this benefit?
 What kind of use case will this feature be useful for? Please be specific and provide examples, this will help us prioritize properly.
+
+### Are you interested in contributing this feature?
+<!---
+Let us know if you want to contribute the feature, and whether would need a hand getting started
+--->

README.md

@@ -5,21 +5,20 @@ This [dbt package](https://docs.getdbt.com/docs/package-management):
 
 
 ## Installation instructions
-
-1. Include this package in your `packages.yml` -- check [here](https://hub.getdbt.com/fishtown-analytics/segment/latest/)
+New to dbt packages? Read more about them [here](https://docs.getdbt.com/docs/building-a-dbt-project/package-management/).
+1. Include this package in your `packages.yml` — check [here](https://hub.getdbt.com/fishtown-analytics/segment/latest/)
 for installation instructions.
 2. Run `dbt deps`
-3. Include the following in your `dbt_project.yml` directly within your
-`models:` block (making sure to handle indenting appropriately). **Update the value to point to your segment page views table**.
+3. Include the following in your `dbt_project.yml` directly within your `vars:` block (making sure to handle indenting appropriately). **Update the value to point to your segment page views table**.
 
 ```YAML
 # dbt_project.yml
+config-version: 2
 ...
 
-models:
+vars:
   segment:
-    vars:
-      segment_page_views_table: "{{ source('segment', 'pages') }}"
+    segment_page_views_table: "{{ source('segment', 'pages') }}"
 
 ```
 This package assumes that your data is in a structure similar to the test
@@ -32,15 +31,16 @@ out bad records, do this in an upstream model.
 for more details:
 ```yaml
 # dbt_project.yml
+config-version: 2
+
 ...
 
-models:
+vars:
   segment:
-    vars:
-      segment_page_views_table: "{{ source('segment', 'pages') }}"
-      segment_sessionization_trailing_window: 3
-      segment_inactivity_cutoff: 30 * 60
-      segment_pass_through_columns: []
+    segment_page_views_table: "{{ source('segment', 'pages') }}"
+    segment_sessionization_trailing_window: 3
+    segment_inactivity_cutoff: 30 * 60
+    segment_pass_through_columns: []
 
 ```
 5. Execute `dbt seed` -- this project includes a CSV that must be seeded for it

data/referrer_mapping.csv

@@ -55,7 +55,6 @@ social,Hocam.com,hocam.com
 social,Hyves,hyves.nl
 social,Taringa!,taringa.net
 social,Classmates,classmates.com
-social,Pinterest,pinterest.com
 social,Paper.li,paper.li
 social,Twitter,twitter.com
 social,Twitter,t.co

data/seeds.yml

@@ -0,0 +1,18 @@
+version: 2
+
+seeds:
+  - name: referrer_mapping
+    description: "This is a CSV version of Snowplow's [referer parser database](https://github.com/snowplow-referer-parser/referer-parser)"
+    columns:
+      - name: medium
+        tests:
+          - not_null
+
+      - name: source
+        tests:
+          - not_null
+
+      - name: host
+        tests:
+          - unique
+          - not_null

dbt_project.yml

@@ -1,5 +1,7 @@
 name: 'segment'
 version: '1.0'
+require-dbt-version: ">=0.17.0"
+config-version: 2
 
 source-paths: ["models"]
 analysis-paths: ["analysis"]
@@ -9,29 +11,26 @@ macro-paths: ["macros"]
 
 target-path: "target"
 clean-targets:
-    - "target"
-    - "dbt_modules"
+  - "target"
+  - "dbt_modules"
 
-require-dbt-version: ">=0.14.0"
+vars:
+  # location of raw data table
+  segment_page_views_table:
 
-models:
-    vars:
-        # location of raw data table
-        segment_page_views_table:
+  # number of trailing hours to re-sessionize for.
+  # events can come in late and we want to still be able to incorporate
+  # them into the definition of a session without needing a full refresh.
+  segment_sessionization_trailing_window: 3
 
-        # number of trailing hours to re-sessionize for.
-        # events can come in late and we want to still be able to incorporate
-        # them into the definition of a session without needing a full refresh.
-        segment_sessionization_trailing_window: 3
-
-        # sessionization inactivity cutoff: of there is a gap in page view times
-        # that exceeds this number of seconds, the subsequent page view will
-        # start a new session.
-        segment_inactivity_cutoff: 30 * 60
+  # sessionization inactivity cutoff: of there is a gap in page view times
+  # that exceeds this number of seconds, the subsequent page view will
+  # start a new session.
+  segment_inactivity_cutoff: 30 * 60
 
-        # If there are extra columns you wish to pass through this package,
-        # define them here. Columns will be included in the `segment_web_sessions`
-        # model as `first_<column>` and `last_<column>`. Extremely useful when
-        # using this package on top of unioned Segment sources, as you can then
-        # pass through a column indicating which source the data is from.
-        segment_pass_through_columns: []
+  # If there are extra columns you wish to pass through this package,
+  # define them here. Columns will be included in the `segment_web_sessions`
+  # model as `first_<column>` and `last_<column>`. Extremely useful when
+  # using this package on top of unioned Segment sources, as you can then
+  # pass through a column indicating which source the data is from.
+  segment_pass_through_columns: []

integration_tests/dbt_project.yml

@@ -1,10 +1,12 @@
-
 name: 'segment_integration_tests'
 version: '1.0'
+config-version: 2
 
 profile: 'integration_tests'
 
-models:
+vars:
   segment:
-    vars:
-      segment_page_views_table: "{{ ref('example_segment_pages') }}"
+    segment_page_views_table: "{{ ref('example_segment_pages') }}"
+
+seeds:
+  +quote_columns: false

models/sessionization/segment_web_page_views__sessionized.sql

@@ -130,7 +130,7 @@ session_ids as (
 
         {{dbt_utils.star(ref('segment_web_page_views'))}},
         page_view_number,
-        {{dbt_utils.surrogate_key('anonymous_id', 'session_number')}} as session_id
+        {{dbt_utils.surrogate_key(['anonymous_id', 'session_number'])}} as session_id
 
     from session_numbers
 

packages.yml

@@ -1,3 +1,3 @@
 packages:
  - package: fishtown-analytics/dbt_utils
-   version: '>=0.1.20'
+   version: [">=0.3.0", "<0.5.0"]