adding fact data modeling content to handbook

Author: EcZachly

bootcamp/materials/2-fact-data-modeling/.gitignore

@@ -0,0 +1,138 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+dump.sql
+
+# Personal workspace files
+.idea/*
+.vscode/*
+
+postgres-data/*
+homework/your_username

bootcamp/materials/2-fact-data-modeling/README.md

@@ -0,0 +1,3 @@
+# Week 2 Fact Data Modeling
+
+This repo follows the same setup as week 1. Please go to the dimensional data modeling [README](../1-dimensional-data-modeling/README.md) for instructions.

bootcamp/materials/2-fact-data-modeling/homework/.gitkeep

@@ -0,0 +1,31 @@
+# Week 2 Fact Data Modeling
+The homework this week will be using the `devices` and `events` dataset
+
+Construct the following eight queries:
+
+- A query to deduplicate `game_details` from Day 1 so there's no duplicates
+
+- A DDL for an `user_devices_cumulated` table that has:
+  - a `device_activity_datelist` which tracks a users active days by `browser_type`
+  - data type here should look similar to `MAP<STRING, ARRAY[DATE]>`
+    - or you could have `browser_type` as a column with multiple rows for each user (either way works, just be consistent!)
+
+- A cumulative query to generate `device_activity_datelist` from `events`
+
+- A `datelist_int` generation query. Convert the `device_activity_datelist` column into a `datelist_int` column 
+
+- A DDL for `hosts_cumulated` table 
+  - a `host_activity_datelist` which logs to see which dates each host is experiencing any activity
+  
+- The incremental query to generate `host_activity_datelist`
+
+- A monthly, reduced fact table DDL `host_activity_reduced`
+   - month
+   - host
+   - hit_array - think COUNT(1)
+   - unique_visitors array -  think COUNT(DISTINCT user_id)
+
+- An incremental query that loads `host_activity_reduced`
+  - day-by-day
+
+Please add these queries into a folder, zip them up and submit [here](https://bootcamp.techcreator.io)

bootcamp/materials/2-fact-data-modeling/homework/homework.md

@@ -0,0 +1,34 @@
+WITH starter AS (
+    SELECT uc.dates_active @> ARRAY [DATE(d.valid_date)]   AS is_active,
+           EXTRACT(
+               DAY FROM DATE('2023-03-31') - d.valid_date) AS days_since,
+           uc.user_id
+    FROM users_cumulated uc
+             CROSS JOIN
+         (SELECT generate_series('2023-02-28', '2023-03-31', INTERVAL '1 day') AS valid_date) as d
+    WHERE date = DATE('2023-03-31')
+),
+     bits AS (
+         SELECT user_id,
+                SUM(CASE
+                        WHEN is_active THEN POW(2, 32 - days_since)
+                        ELSE 0 END)::bigint::bit(32) AS datelist_int
+         FROM starter
+         GROUP BY user_id
+     )
+
+SELECT
+       user_id,
+       datelist_int,
+       BIT_COUNT(datelist_int) > 0 AS monthly_active,
+       BIT_COUNT(datelist_int) AS l32,
+       BIT_COUNT(datelist_int &
+       CAST('11111110000000000000000000000000' AS BIT(32))) > 0 AS weekly_active,
+       BIT_COUNT(datelist_int &
+       CAST('11111110000000000000000000000000' AS BIT(32)))  AS l7,
+
+       BIT_COUNT(datelist_int &
+       CAST('00000001111111000000000000000000' AS BIT(32))) > 0 AS weekly_active_previous_week
+FROM bits;
+
+

bootcamp/materials/2-fact-data-modeling/lecture-lab/anaylze_datelist.sql

@@ -0,0 +1,23 @@
+
+WITH starter AS (
+    SELECT uc.dates_active @> ARRAY [DATE(d.valid_date)]   AS is_active,
+           EXTRACT(
+               DAY FROM DATE('2023-03-31') - d.valid_date) AS days_since,
+           uc.user_id
+    FROM users_cumulated uc
+             CROSS JOIN
+         (SELECT generate_series('2023-02-28', '2023-03-31', INTERVAL '1 day') AS valid_date) as d
+    WHERE date = DATE('2023-03-31')
+),
+     bits AS (
+         SELECT user_id,
+                SUM(CASE
+                        WHEN is_active THEN POW(2, 32 - days_since)
+                        ELSE 0 END)::bigint::bit(32) AS datelist_int,
+                DATE('2023-03-31') as date
+         FROM starter
+         GROUP BY user_id
+     )
+
+     INSERT INTO user_datelist_int
+     SELECT * FROM bits

bootcamp/materials/2-fact-data-modeling/lecture-lab/generate_datelist.sql

@@ -0,0 +1,29 @@
+WITH yesterday AS (
+    SELECT *
+    FROM monthly_user_site_hits
+    WHERE date_partition = '2023-03-02'
+),
+     today AS (
+         SELECT user_id,
+                DATE_TRUNC('day', event_time) AS today_date,
+                COUNT(1) as num_hits
+         FROM events
+         WHERE DATE_TRUNC('day', event_time) = DATE('2023-03-03')
+         AND user_id IS NOT NULL
+         GROUP BY user_id, DATE_TRUNC('day', event_time)
+     )
+INSERT INTO monthly_user_site_hits
+SELECT
+    COALESCE(y.user_id, t.user_id) AS user_id,
+       COALESCE(y.hit_array,
+           array_fill(NULL::BIGINT, ARRAY[DATE('2023-03-03') - DATE('2023-03-01')]))
+        || ARRAY[t.num_hits] AS hits_array,
+    DATE('2023-03-01') as month_start,
+    CASE WHEN y.first_found_date < t.today_date
+        THEN y.first_found_date
+        ELSE t.today_date
+            END as first_found_date,
+    DATE('2023-03-03') AS date_partition
+    FROM yesterday y
+    FULL OUTER JOIN today t
+        ON y.user_id = t.user_id

bootcamp/materials/2-fact-data-modeling/lecture-lab/generate_monthly_array_metrics.sql

@@ -0,0 +1,7 @@
+SELECT
+       month_start,
+       SUM(hit_array[1]) as num_hits_mar_1,
+       SUM(hit_array[2]) AS num_hits_mar_2
+FROM monthly_user_site_hits
+WHERE date_partition = DATE('2023-03-03')
+GROUP BY 1

bootcamp/materials/2-fact-data-modeling/lecture-lab/quick_sum_device_hits.sql

@@ -0,0 +1,26 @@
+WITH yesterday AS (
+    SELECT * FROM users_cumulated
+    WHERE date = DATE('2023-03-30')
+),
+    today AS (
+          SELECT user_id,
+                 DATE_TRUNC('day', event_time) AS today_date,
+                 COUNT(1) AS num_events FROM events
+            WHERE DATE_TRUNC('day', event_time) = DATE('2023-03-31')
+            AND user_id IS NOT NULL
+         GROUP BY user_id,  DATE_TRUNC('day', event_time)
+    )
+INSERT INTO users_cumulated
+SELECT
+       COALESCE(t.user_id, y.user_id),
+       COALESCE(y.dates_active,
+           ARRAY[]::DATE[])
+            || CASE WHEN
+                t.user_id IS NOT NULL
+                THEN ARRAY[t.today_date]
+                ELSE ARRAY[]::DATE[]
+                END AS date_list,
+       COALESCE(t.today_date, y.date + Interval '1 day') as date
+FROm yesterday y
+    FULL OUTER JOIN
+    today t ON t.user_id = y.user_id;

bootcamp/materials/2-fact-data-modeling/lecture-lab/user_cumulated_populate.sql

@@ -0,0 +1,15 @@
+CREATE TABLE devices (
+    device_id BIGINT,
+    browser_type TEXT,
+    browser_version_major BIGINT,
+    browser_version_minor BIGINT,
+    browser_version_patch BIGINT,
+    device_type TEXT,
+    device_version_major BIGINT,
+    device_version_minor BIGINT,
+    device_version_patch BIGINT,
+    os_type TEXT,
+    os_version_major BIGINT,
+    os_version_minor BIGINT,
+    os_version_patch BIGINT
+)