Main

.vscode/settings.json

@@ -17,7 +17,6 @@
   "files.autoSave": "afterDelay",
   "screencastMode.onlyKeyboardShortcuts": true,
   "terminal.integrated.fontSize": 18,
-  "workbench.activityBar.visible": true,
   "workbench.colorTheme": "Visual Studio Dark",
   "workbench.fontAliasing": "antialiased",
   "workbench.statusBar.visible": true

nyc_parking_violations/.gitignore → nyc_parking_violations2/.gitignore

@@ -1,4 +1,4 @@
-.user.yml
+
 target/
 dbt_packages/
 logs/

nyc_parking_violations2/.user.yml

@@ -0,0 +1 @@
+id: 23096e09-b919-420a-854b-199a5ab84b4f

nyc_parking_violations/dbt_project.yml → nyc_parking_violations2/dbt_project.yml

@@ -2,12 +2,12 @@
 # Name your project! Project names should contain only lowercase characters
 # and underscores. A good package name should reflect your organization's
 # name or the intended use of these models
-name: 'nyc_parking_violations'
+name: 'nyc_parking_violations2'
 version: '1.0.0'
 config-version: 2
 
 # This setting configures which "profile" dbt uses for this project.
-profile: 'nyc_parking_violations'
+profile: 'nyc_parking_violations2'
 
 # These configurations specify where dbt should look for different types of files.
 # The `model-paths` config, for example, states that models in this project can be
@@ -31,7 +31,7 @@ clean-targets:         # directories to be removed by `dbt clean`
 # directory as views. These settings can be overridden in the individual model
 # files using the `{{ config(...) }}` macro.
 models:
-  nyc_parking_violations:
+  nyc_parking_violations2:
     # Config indicated by + and applies to all files under models/example/
     example:
       +materialized: ephemeral
@@ -49,4 +49,4 @@ models:
     gold:
       +materialized: table
 tests:
-  +store_failures: true
+  +store_failures: true

nyc_parking_violations2/models/bronze/bronze_parking_violation_codes.sql

@@ -0,0 +1,7 @@
+SELECT  
+  code AS violation_code,
+  definition,
+  manhattan_96th_st_below,
+  all_other_areas
+FROM 
+  parking_violation_codes

nyc_parking_violations2/models/bronze/bronze_parking_violations.sql

@@ -0,0 +1,23 @@
+SELECT  
+  summons_number,
+  registration_state,
+  plate_type,
+  issue_date,
+  violation_code,
+  vehicle_body_type,
+  vehicle_make,
+  issuing_agency,
+  vehicle_expiration_date,
+  violation_location,
+  violation_precinct,
+  issuer_precinct,
+  issuer_code,
+  issuer_command,
+  issuer_squad,
+  violation_time,
+  violation_county,
+  violation_legal_code,
+  vehicle_color,
+  vehicle_year,
+FROM
+  parking_violations_2023

nyc_parking_violations/models/docs/docs_blocks.md → nyc_parking_violations2/models/docs/docs_block.md

@@ -104,4 +104,4 @@ The total number of tickets issued for a specific violation code.
 
 {% docs total_revenue_usd %}
 The total revenue accumulated from tickets, based on the violation code. This sum is represented in USD.
-{% enddocs %}
+{% enddocs %}

nyc_parking_violations/models/docs/schema.yml → nyc_parking_violations2/models/docs/schema.yml

@@ -185,4 +185,4 @@ models:
       - name: registration_state
         description: '{{ doc("registration_state") }}'
       - name: ticket_count
-        description: '{{ doc("ticket_count") }}'
+        description: '{{ doc("ticket_count") }}'

nyc_parking_violations2/models/example/ref_model.sql

@@ -0,0 +1,4 @@
+SELECT 
+  COUNT(*)
+FROM 
+  {{ref('first_model')}}

nyc_parking_violations/profiles.yml → nyc_parking_violations2/profiles.yml

@@ -1,4 +1,4 @@
-nyc_parking_violations:
+nyc_parking_violations2:
   outputs:
    dev:
      type: duckdb
@@ -8,5 +8,5 @@ nyc_parking_violations:
      # note that path is slightly different as GitHub actions
      # start in the root directory and not in the
      # nyc_parking_violations directory
-     path: './data/prod_nyc_parking_violations.db'  
+     path: '../data/prod_nyc_parking_violations.db'  
   target: dev

nyc_parking_violations/tests/violation_codes_revenue.sql → nyc_parking_violations2/tests/violation_codes_revenue.sql

@@ -8,4 +8,4 @@ FROM
 GROUP BY
     violation_code
 HAVING
-    NOT(total_revenue_usd >= 1)
+    NOT(total_revenue_usd >= 1)

run_sql_queries_here.ipynb

@@ -2,27 +2,203 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "import duckdb\n",
     "import pandas as pd"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>violation_code</th>\n",
+       "      <th>total_revenue_usd</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>41</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   violation_code  total_revenue_usd\n",
+       "0              41                0.0"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sql_query = '''\n",
+    "select * from \"nyc_parking_violations\".\"main_dbt_test__audit\".\"violation_codes_revenue\"\n",
+    "'''\n",
+    "\n",
+    "with duckdb.connect('data/nyc_parking_violations.db') as con:\n",
+    "    display(con.sql(sql_query).df())"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": [
+    "sql_query_import_1 = '''\n",
+    "CREATE OR REPLACE TABLE parking_violations_code AS \n",
+    "SELECT *\n",
+    "FROM read_csv_auto(\n",
+    "  'data/dof_parking_violation_codes.csv',\n",
+    "  normalize_names=True\n",
+    "  )\n",
+    "'''\n",
+    "\n",
+    "sql_query_import_2 = '''\n",
+    "CREATE OR REPLACE TABLE parking_violations_2023 AS \n",
+    "SELECT *\n",
+    "FROM read_csv_auto(\n",
+    "  'data/parking_violations_issued_fiscal_year_2023_sample.csv',\n",
+    "  normalize_names=True\n",
+    "  )\n",
+    "'''\n",
+    "\n",
+    "with duckdb.connect('data/prod_nyc_parking_violations2.db') as con:\n",
+    "  con.sql(sql_query_import_1)\n",
+    "  con.sql(sql_query_import_2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>bronze_parking_violation_codes</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>bronze_parking_violations</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>gold_ticket_metrics</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>gold_vehicles_metrics</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>parking_violation_codes</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>parking_violations_2023</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>parking_violations_code</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>silver_violation_tickets</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>silver_violation_vehicles</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                             name\n",
+       "0  bronze_parking_violation_codes\n",
+       "1       bronze_parking_violations\n",
+       "2             gold_ticket_metrics\n",
+       "3           gold_vehicles_metrics\n",
+       "4         parking_violation_codes\n",
+       "5         parking_violations_2023\n",
+       "6         parking_violations_code\n",
+       "7        silver_violation_tickets\n",
+       "8       silver_violation_vehicles"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "sql_query = '''\n",
     "show tables\n",
     "'''\n",
     "\n",
-    "with duckdb.connect('data/nyc_parking_violations.db') as con:\n",
+    "with duckdb.connect('data/prod_nyc_parking_violations.db') as con:\n",
     "    display(con.sql(sql_query).df())"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {