Merge branch 'main' into LuluFreeDesign-patch-4

.github/workflows/github-actions-data-stack.yml

@@ -0,0 +1,14 @@
+name: Data Stack CI
+
+on:
+  push:
+    paths:
+      - analytics/**
+
+jobs:
+  deploy-dagster:
+    uses: ./.github/workflows/deploy.yml
+    with:
+      app: dagster-production
+      branch: main
+    secrets: inherit

.gitignore

@@ -33,3 +33,8 @@ yarn-error.log*
 
 /talisman_report
 .clever.json
+
+# Data Stack
+.pyc
+__pycache__
+analytics/dagster/storage/

analytics/dagster/.nux/nux.yaml

@@ -0,0 +1 @@
+seen: 1

analytics/dagster/Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.10-slim
+
+RUN pip install dagster-webserver dagster-postgres dagster-aws
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+ENV DAGSTER_HOME=/opt/dagster/dagster_home/
+
+RUN mkdir -p $DAGSTER_HOME
+
+COPY dagster.yaml workspace.yaml $DAGSTER_HOME
+
+COPY src/ $DAGSTER_HOME
+
+WORKDIR $DAGSTER_HOME
+
+EXPOSE 3000
+
+ENTRYPOINT ["dagster-webserver", "-h", "0.0.0.0", "-p", "3000"]

analytics/dagster/dagster.yaml

@@ -0,0 +1,15 @@
+storage:
+  postgres:
+    postgres_db:
+      username:
+        env: DAGSTER_PG_USERNAME
+      password:
+        env: DAGSTER_PG_PASSWORD
+      hostname:
+        env: DAGSTER_PG_HOST
+      db_name:
+        env: DAGSTER_PG_DB
+      port: 5432
+
+telemetry:
+  enabled: false

analytics/dagster/data/most_frequent_words.json

@@ -0,0 +1 @@
+{"\u2013": 9, "new": 6, "hn": 5, "why": 5, "ai": 4, "show": 4, "from": 4, "macos": 3, "language": 3, "server": 3, "at": 3, "video": 3, "may": 3, "be": 3, "using": 3, "pdf": 3, "vision": 2, "sequoia": 2, "virtual": 2, "arm": 2, "exploring": 2, "apple's": 2, "models": 2, "just": 2, "fast": 2}

analytics/dagster/data/topstory_ids.json

@@ -0,0 +1 @@
+[40643207, 40643181, 40643167, 40639506, 40642871, 40642476, 40630952, 40631796, 40639606, 40623864, 40639628, 40639450, 40644323, 40635397, 40636292, 40640927, 40632064, 40640833, 40633003, 40643071, 40638764, 40641848, 40636844, 40637102, 40632745, 40636883, 40641704, 40641795, 40633902, 40639032, 40640424, 40641615, 40641932, 40644454, 40631614, 40637374, 40632533, 40637785, 40631466, 40635697, 40631573, 40635789, 40633773, 40642801, 40644605, 40632397, 40615002, 40644111, 40630699, 40643499, 40622209, 40644459, 40627113, 40638386, 40640534, 40643744, 40636854, 40636122, 40637303, 40641388, 40631439, 40631585, 40643259, 40622671, 40619311, 40638445, 40640635, 40627563, 40637089, 40626807, 40623497, 40632773, 40641361, 40622999, 40641091, 40639742, 40631223, 40630656, 40634042, 40643998, 40638741, 40643454, 40634269, 40634774, 40642328, 40642272, 40631558, 40622191, 40634465, 40641116, 40634186, 40640076, 40641443, 40633871, 40638990, 40640499, 40636079, 40625959, 40626969, 40639299]

analytics/dagster/requirements.txt

@@ -0,0 +1,3 @@
+matplotlib
+pandas
+requests

analytics/dagster/src/__init__.py

@@ -0,0 +1 @@
+from .definitions import defs as defs

analytics/dagster/src/assets/hackernews.py

@@ -0,0 +1,98 @@
+import base64
+import json
+import os
+from io import BytesIO
+
+import matplotlib.pyplot as plt
+import pandas as pd
+import requests
+from dagster import AssetExecutionContext, MaterializeResult, MetadataValue, asset
+
+
+@asset(group_name="hackernews", compute_kind="HackerNews API")
+def topstory_ids() -> None:
+    """Get up to 100 top stories from the HackerNews topstories endpoint.
+
+    API Docs: https://github.com/HackerNews/API#new-top-and-best-stories
+    """
+    newstories_url = "https://hacker-news.firebaseio.com/v0/topstories.json"
+    top_new_story_ids = requests.get(newstories_url).json()[:100]
+
+    os.makedirs("data", exist_ok=True)
+    with open("data/topstory_ids.json", "w") as f:
+        json.dump(top_new_story_ids, f)
+
+
+@asset(deps=[topstory_ids], group_name="hackernews", compute_kind="HackerNews API")
+def topstories(context: AssetExecutionContext) -> MaterializeResult:
+    """Get items based on story ids from the HackerNews items endpoint. It may take 30 seconds to fetch all 100 items.
+
+    API Docs: https://github.com/HackerNews/API#items
+    """
+    with open("data/topstory_ids.json", "r") as f:
+        topstory_ids = json.load(f)
+
+    results = []
+    for item_id in topstory_ids:
+        item = requests.get(
+            f"https://hacker-news.firebaseio.com/v0/item/{item_id}.json"
+        ).json()
+        results.append(item)
+
+        if len(results) % 20 == 0:
+            context.log.info(f"Got {len(results)} items so far.")
+
+    df = pd.DataFrame(results)
+    df.to_csv("data/topstories.csv")
+
+    return MaterializeResult(
+        metadata={
+            "num_records": len(df),  # Metadata can be any key-value pair
+            "preview": MetadataValue.md(df.head().to_markdown()),
+            # The `MetadataValue` class has useful static methods to build Metadata
+        }
+    )
+
+
+@asset(deps=[topstories], group_name="hackernews", compute_kind="Plot")
+def most_frequent_words(context: AssetExecutionContext) -> MaterializeResult:
+    """Get the top 25 most frequent words in the titles of the top 100 HackerNews stories."""
+    stopwords = ["a", "the", "an", "of", "to", "in", "for", "and", "with", "on", "is"]
+
+    topstories = pd.read_csv("data/topstories.csv")
+
+    # loop through the titles and count the frequency of each word
+    word_counts = {}
+    for raw_title in topstories["title"]:
+        title = raw_title.lower()
+        for word in title.split():
+            cleaned_word = word.strip(".,-!?:;()[]'\"-")
+            if cleaned_word not in stopwords and len(cleaned_word) > 0:
+                word_counts[cleaned_word] = word_counts.get(cleaned_word, 0) + 1
+
+    # Get the top 25 most frequent words
+    top_words = {
+        pair[0]: pair[1]
+        for pair in sorted(word_counts.items(), key=lambda x: x[1], reverse=True)[:25]
+    }
+
+    # Make a bar chart of the top 25 words
+    plt.figure(figsize=(10, 6))
+    plt.bar(list(top_words.keys()), list(top_words.values()))
+    plt.xticks(rotation=45, ha="right")
+    plt.title("Top 25 Words in Hacker News Titles")
+    plt.tight_layout()
+
+    # Convert the image to a saveable format
+    buffer = BytesIO()
+    plt.savefig(buffer, format="png")
+    image_data = base64.b64encode(buffer.getvalue())
+
+    # Convert the image to Markdown to preview it within Dagster
+    md_content = f"![img](data:image/png;base64,{image_data.decode()})"
+
+    with open("data/most_frequent_words.json", "w") as f:
+        json.dump(top_words, f)
+
+    # Attach the Markdown content as metadata to the asset
+    return MaterializeResult(metadata={"plot": MetadataValue.md(md_content)})

analytics/dagster/src/definitions.py

@@ -0,0 +1,16 @@
+from dagster import (
+    Definitions,
+    ScheduleDefinition,
+    define_asset_job,
+    load_assets_from_package_module,
+)
+
+from . import assets
+
+daily_refresh_schedule = ScheduleDefinition(
+    job=define_asset_job(name="all_assets_job"), cron_schedule="0 0 * * *"
+)
+
+defs = Definitions(
+    assets=load_assets_from_package_module(assets), schedules=[daily_refresh_schedule]
+)

analytics/dagster/workspace.yaml

@@ -0,0 +1,2 @@
+load_from:
+  - python_module: src

analytics/docker-compose.yml

@@ -0,0 +1,27 @@
+services:
+  dagster:
+    build:
+      context: dagster/
+      dockerfile: Dockerfile
+    volumes:
+      - ./dagster:/opt/dagster/dagster_home
+    env_file:
+      - .env
+    ports:
+      - 3000:3000
+
+  postgres:
+    image: postgres:latest
+    ports:
+      - 54322:5432
+    env_file:
+      - .env
+    environment:
+      - POSTGRES_PASSWORD=${DAGSTER_PG_PASSWORD}
+      - POSTGRES_USER=${DAGSTER_PG_USERNAME}
+      - POSTGRES_DB=${DAGSTER_PG_DB}
+    volumes:
+      - dagster-postgres:/var/lib/postgresql/data
+volumes:
+  dagster-postgres:
+    driver: local