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

refactor: restructure monorepo for clean portfolio layout

Browse Source 
- Move timesfm-forecast into apps/ directory
- Flatten Udacity portfolio projects from deep URL-encoded paths
  into data-engineering/01-XX numbered directories
- Remove old My-Data-Engineering-Portifolio/ parent directory
- Rewrite root README.md: professional overview with badges,
  project table, and repo structure diagram
- Create data-engineering/README.md with per-project descriptions
- Add README.md for 02-cassandra-modeling (was missing)
- Add README.md for 05-airflow-pipelines (was missing)
- Normalize capstone readme.md -> README.md
- Update .gitignore: add *.cfg, *.env, *.zip, *.sas7bdat,
  Jupyter checkpoints, IDE dirs; remove uv.lock exclusion
- Add dwh.cfg.example and dl.cfg.example credential templates
- Untrack real credential files (dwh.cfg, dl.cfg)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@gabriel.pereira
2026-03-26 16:48:50 -03:00
parent 5c4e6075e1
commit 6796398924
160 changed files with 308 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

304
data-engineering/04-spark-data-lake/etl.ipynb Normal file
View File

@@ -0,0 +1,304 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 61,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"import configparser\n",
"from datetime import datetime\n",
"from pyspark.sql.functions import dayofweek\n",
"import os\n",
"from pyspark.sql import SparkSession\n",
"from pyspark.sql.functions import udf, col\n",
"from pyspark.sql.functions import year, month, dayofmonth, hour, weekofyear, date_format"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"def create_spark_session():\n",
" spark = SparkSession \\\n",
" .builder \\\n",
" .config(\"spark.jars.packages\", \"org.apache.hadoop:hadoop-aws:2.7.0\") \\\n",
" .getOrCreate()\n",
" return spark"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"def process_song_data(spark, input_data, output_data):\n",
" \"\"\"\n",
" This function reads the song data from S3, processes that data using Spark, and writes them back to S3\n",
"\n",
" Parameters\n",
" ----------\n",
" spark: This is the spark session\n",
" input_date: This is the path to song_date into S3 bucket\n",
" output_data: This is the path where parquet files will be written\n",
" \n",
" \"\"\"\n",
" \n",
" # get filepath to song data file\n",
" # e.g. from S3 file location: song_data/A/B/C/TRABCEI128F424C983.json\n",
" song_data = input_data + 'song_data/*/*/*/*.json'\n",
" \n",
" # read song data file\n",
" df = spark.read.json(song_data)\n",
"\n",
" # extract columns to create songs table\n",
" songs_table = df.select('song_id', 'title', 'artist_id', 'year', 'duration').dropDuplicates()\n",
" songs_table.createOrReplaceTempView('songs')\n",
" \n",
" # write songs table to parquet files partitioned by year and artist\n",
" songs_table.write.partitionBy('year', 'artist_id').parquet(os.path.join(output_data, 'songs/songs.parquet'), 'overwrite')\n",
"\n",
" # extract columns to create artists table\n",
" artists_table = df.select('artist_id', 'artist_name', 'artist_location', 'artist_latitude', 'artist_longitude') \\\n",
" .withColumnRenamed('artist_name', 'name') \\\n",
" .withColumnRenamed('artist_location', 'location') \\\n",
" .withColumnRenamed('artist_latitude', 'latitude') \\\n",
" .withColumnRenamed('artist_longitude', 'longitude').dropDuplicates()\n",
" \n",
" artists_table.createOrReplaceTempView('artists')\n",
" \n",
" \n",
" # write artists table to parquet files\n",
" artists_table.write.parquet(os.path.join(output_data, 'artists/artists.parquet'), 'overwrite')"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"def process_log_data(spark, input_data, output_data):\n",
" \"\"\"\n",
" This function reads the log data from S3, processes that data using Spark, and writes them back to S3\n",
"\n",
" Parameters\n",
" ----------\n",
" spark: This is the spark session\n",
" input_date: This is the path to log_date into S3 bucket\n",
" output_data: This is the path where parquet files will be written\n",
" \n",
" \"\"\"\n",
" \n",
" \n",
" # get filepath to log data file\n",
" # e.g. from S3 file location: log_data/2018/11/2018-11-12-events.json\n",
" log_data = input_data + 'log_data/*.json'\n",
"\n",
" # read log data file\n",
" df = spark.read.json(log_data)\n",
" \n",
" # filter by actions for song plays\n",
" # df_actions = df.filter(df.page == \"NextSong\").select('ts', 'userId', 'level', 'song', 'artist', 'sessionId', 'location', 'userAgent')\n",
" df_actions = df.where(df.page == 'NextSong')\n",
" df_actions.select('ts', 'userId', 'level', 'song', 'artist', 'sessionId', 'location', 'userAgent')\n",
" \n",
" # extract columns for users table \n",
" users_table = df.select('userId', 'firstName', 'lastName', 'gender', 'level').dropDuplicates()\n",
" users_table.createOrReplaceTempView('users')\n",
" \n",
" # write users table to parquet files\n",
" users_table.write.parquet(os.path.join(output_data, 'users/users.parquet'), 'overwrite')\n",
"\n",
" # create timestamp column from original timestamp column\n",
" get_timestamp = udf(lambda x: str(int(int(x)/1000)))\n",
" df = df.withColumn('timestamp', get_timestamp(df_actions.ts))\n",
" \n",
" # create datetime column from original timestamp column\n",
" get_datetime = udf(lambda x: str(datetime.fromtimestamp(int(x) / 1000)))\n",
" df = df.withColumn('datetime', get_datetime(df_actions.ts))\n",
" \n",
" # extract columns to create time table\n",
" time_table = df.select('datetime') \\\n",
" .withColumn('start_time', df.datetime) \\\n",
" .withColumn('hour', hour('datetime')) \\\n",
" .withColumn('day', dayofmonth('datetime')) \\\n",
" .withColumn('week', weekofyear('datetime')) \\\n",
" .withColumn('month', month('datetime')) \\\n",
" .withColumn('year', year('datetime')) \\\n",
" .withColumn('weekday', dayofweek('datetime')) \\\n",
" .dropDuplicates()\n",
" \n",
" # write time table to parquet files partitioned by year and month\n",
" time_table.write.partitionBy('year', 'month').parquet(os.path.join(output_data,'time/time.parquet'), 'overwrite')\n",
"\n",
" # read in song data to use for songplays table\n",
" song_df = spark.read.json(input_data + 'song_data/*/*/*/*.json')\n",
"\n",
" # extract columns from joined song and log datasets to create songplays table\n",
" df = df.alias('log_df')\n",
" song_df = song_df.alias('song_df')\n",
" log_and_songs = df.join(song_df, col('log_df.artist') == col('song_df.artist_name'), 'inner')\n",
" \n",
" \n",
" songplays_table = log_and_songs.select(\n",
" col('log_df.datetime').alias('start_time'),\n",
" col('log_df.userId').alias('user_id'),\n",
" col('log_df.level').alias('level'),\n",
" col('song_df.song_id').alias('song_id'),\n",
" col('song_df.artist_id').alias('artist_id'),\n",
" col('log_df.sessionId').alias('session_id'),\n",
" col('log_df.location').alias('location'), \n",
" col('log_df.userAgent').alias('user_agent'),\n",
" year('log_df.datetime').alias('year'),\n",
" month('log_df.datetime').alias('month'))\n",
"\n",
" songplays_table.createOrReplaceTempView('songplays')\n",
" \n",
" # write songplays table to parquet files partitioned by year and month\n",
" time_table = time_table.alias('timetable')\n",
"\n",
" songplays_table.write.partitionBy('year', 'month').parquet(os.path.join(output_data,'songplays/songplays.parquet'),'overwrite')\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
" '''Start spark session and define S3 locations where the files will be readed and written'''\n",
" spark = create_spark_session()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
" '''Paths for local testing'''\n",
" input_data = \"data/\"\n",
" output_data = \"data/outputs/\""
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
" '''Run above functions according to the previous parameters '''\n",
" process_song_data(spark, input_data, output_data) \n",
" process_log_data(spark, input_data, output_data)"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"editable": true
},
"outputs": [],
"source": [
"from pyspark.sql.functions import dayofweek\n",
"df = spark.read.json(\"data/log_data/*.json\")\n",
"df_actions = df.where(df.page == 'NextSong')\n",
"df_actions.select('ts', 'userId', 'level', 'song', 'artist', 'sessionId', 'location', 'userAgent')\n",
"\n",
"# create timestamp column from original timestamp column\n",
"get_timestamp = udf(lambda x: str(int(int(x)/1000)))\n",
"df = df.withColumn('timestamp', get_timestamp(df_actions.ts))\n",
"\n",
"# create datetime column from original timestamp column\n",
"get_datetime = udf(lambda x: str(datetime.fromtimestamp(int(x) / 1000)))\n",
"df = df.withColumn('datetime', get_datetime(df_actions.ts))\n",
"\n",
"# extract columns to create time table\n",
"time_table = df.select('datetime') \\\n",
" .withColumn('start_time', df.datetime) \\\n",
" .withColumn('hour', hour('datetime')) \\\n",
" .withColumn('day', dayofmonth('datetime')) \\\n",
" .withColumn('week', weekofyear('datetime')) \\\n",
" .withColumn('month', month('datetime')) \\\n",
" .withColumn('year', year('datetime')) \\\n",
" .withColumn('weekday', dayofweek('datetime')) \\\n",
" .dropDuplicates()"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {
"editable": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"+--------------------+--------------------+----+---+----+-----+----+-------+\n",
"| datetime| start_time|hour|day|week|month|year|weekday|\n",
"+--------------------+--------------------+----+---+----+-----+----+-------+\n",
"|2018-11-01 21:05:...|2018-11-01 21:05:...| 21| 1| 44| 11|2018| 5|\n",
"|2018-11-01 21:42:...|2018-11-01 21:42:...| 21| 1| 44| 11|2018| 5|\n",
"|2018-11-01 21:17:...|2018-11-01 21:17:...| 21| 1| 44| 11|2018| 5|\n",
"+--------------------+--------------------+----+---+----+-----+----+-------+\n",
"only showing top 3 rows\n",
"\n"
]
}
],
"source": [
"time_table.show(3)"
]
},
{
"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
}