gabspereira/workspace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add 'My-Data-Engineering-Portifolio/' from commit 'af9dfac5db38895dd0aacc6ea42ddede38a11ca5'

Browse Source 
git-subtree-dir: My-Data-Engineering-Portifolio
git-subtree-mainline: d606a91bd5
git-subtree-split: af9dfac5db
This commit is contained in:
@gabriel.pereira
2026-03-26 15:41:43 -03:00
parent d606a91bd5 af9dfac5db
commit 58602991b3
144 changed files with 94708 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

216
My-Data-Engineering-Portifolio/Capstone+Project/Quality-checks.ipynb Normal file
View File

@@ -0,0 +1,216 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"import configparser\n",
"import os\n",
"from pathlib import Path\n",
"from pyspark.sql import SparkSession"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"# CONFIG\n",
"config = configparser.ConfigParser()\n",
"config.read('dl.cfg')\n",
"\n",
"KEY = config.get('AWS', 'AWS_ACCESS_KEY_ID')\n",
"SECRET = config.get('AWS', 'AWS_SECRET_ACCESS_KEY')\n",
"output_data = './data/outputs'# config.get('S3', 'DEST_S3_BUCKET')\n",
"\n",
"\n",
"os.environ['AWS_ACCESS_KEY_ID']=KEY\n",
"os.environ['AWS_SECRET_ACCESS_KEY']=SECRET"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"spark = SparkSession.builder\\\n",
" .config(\"spark.jars.packages\", \"org.apache.hadoop:hadoop-aws:2.7.0\")\\\n",
" .enableHiveSupport().getOrCreate()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"s3_bucket = Path(output_data)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"editable": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Table: city_code\n",
"root\n",
" |-- city_code: string (nullable = true)\n",
" |-- city: string (nullable = true)\n",
"\n",
"Table: d_temperature\n",
"root\n",
" |-- dt: date (nullable = true)\n",
" |-- avg_temp: string (nullable = true)\n",
" |-- avg_temp_uncertnty: string (nullable = true)\n",
" |-- city: string (nullable = true)\n",
" |-- country: string (nullable = true)\n",
" |-- year: integer (nullable = true)\n",
" |-- month: integer (nullable = true)\n",
"\n",
"Table: d_citizen\n",
"root\n",
" |-- cic_id: double (nullable = true)\n",
" |-- citizen_country: double (nullable = true)\n",
" |-- residence_country: double (nullable = true)\n",
" |-- birth_year: double (nullable = true)\n",
" |-- gender: string (nullable = true)\n",
" |-- ins_num: string (nullable = true)\n",
" |-- immi_citizen_id: long (nullable = true)\n",
"\n",
"Table: d_airline\n",
"root\n",
" |-- cic_id: double (nullable = true)\n",
" |-- airline: string (nullable = true)\n",
" |-- admin_num: double (nullable = true)\n",
" |-- flight_number: string (nullable = true)\n",
" |-- visa_type: string (nullable = true)\n",
" |-- immi_airline_id: long (nullable = true)\n",
"\n",
"Table: f_immigration\n",
"root\n",
" |-- cic_id: double (nullable = true)\n",
" |-- year: double (nullable = true)\n",
" |-- month: double (nullable = true)\n",
" |-- city_code: string (nullable = true)\n",
" |-- arrive_date: date (nullable = true)\n",
" |-- departure_date: date (nullable = true)\n",
" |-- mode: double (nullable = true)\n",
" |-- visa: double (nullable = true)\n",
" |-- immigration_id: long (nullable = true)\n",
" |-- country: string (nullable = true)\n",
" |-- state_code: string (nullable = true)\n",
"\n",
"Table: d_demog_statistics\n",
"root\n",
" |-- city: string (nullable = true)\n",
" |-- state: string (nullable = true)\n",
" |-- median_age: string (nullable = true)\n",
" |-- avg_household_size: string (nullable = true)\n",
" |-- d_demog_statistics: long (nullable = true)\n",
"\n",
"Table: country_code\n",
"root\n",
" |-- country_code: string (nullable = true)\n",
" |-- country: string (nullable = true)\n",
"\n",
"Table: state_code\n",
"root\n",
" |-- state_code: string (nullable = true)\n",
" |-- state: string (nullable = true)\n",
"\n"
]
}
],
"source": [
"for file_dir in s3_bucket.iterdir():\n",
" if file_dir.is_dir():\n",
" path = str(file_dir)\n",
" df = spark.read.parquet(path)\n",
" print(\"Table: \" + path.split('/')[-1])\n",
" schema = df.printSchema()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"editable": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Table: city_code is not empty: total 660 records.\n",
"Table: d_temperature is not empty: total 687004 records.\n",
"Table: d_citizen is not empty: total 3096313 records.\n",
"Table: d_airline is not empty: total 3096313 records.\n",
"Table: f_immigration is not empty: total 3096313 records.\n",
"Table: d_demog_statistics is not empty: total 596 records.\n",
"Table: country_code is not empty: total 235 records.\n",
"Table: state_code is not empty: total 55 records.\n"
]
}
],
"source": [
"for file_dir in s3_bucket.iterdir():\n",
" if file_dir.is_dir():\n",
" path = str(file_dir)\n",
" df = spark.read.parquet(path)\n",
" record_num = df.count()\n",
" if record_num <= 0:\n",
" raise ValueError(\"This table is empty!\")\n",
" else:\n",
" print(\"Table: \" + path.split('/')[-1] + f\" is not empty: total {record_num} records.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"editable": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}