squirrels 0.4.0__tar.gz → 0.5.0rc0__tar.gz

squirrels-0.5.0rc0/.cursorignore

@@ -0,0 +1,2 @@
+database_elt/
+poetry.lock

squirrels-0.5.0rc0/.github/workflows/python-publish.yml

@@ -0,0 +1,45 @@
+name: Publish Python Package
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+          
+      - name: Extract version from tag
+        id: get_version
+        run: echo "VERSION=${GITHUB_REF#refs/tags/v}" >> $GITHUB_OUTPUT
+        
+      - name: Update version in pyproject.toml
+        run: |
+          # Use sed to replace the version in pyproject.toml
+          sed -i "s/^version = \".*\"/version = \"${{ steps.get_version.outputs.VERSION }}\"/" pyproject.toml
+          echo "Updated version in pyproject.toml to ${{ steps.get_version.outputs.VERSION }}"
+          
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+          
+      - name: Build package
+        run: python -m build
+        
+      - name: Publish to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+        run: |
+          python -m twine upload --username $TWINE_USERNAME --password $TWINE_PASSWORD dist/*

squirrels-0.5.0rc0/.gitignore

@@ -0,0 +1,81 @@
+sandbox*
+playground*
+site/
+.venv/ 
+
+# pyenv files
+.python-version
+
+# Pipenv files
+Pipfile
+Pipfile.lock
+
+### PythonVanilla ###
+# 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/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# 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/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+
+### VisualStudioCode ###
+.vscode
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide

{squirrels-0.4.0 → squirrels-0.5.0rc0}/LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2024 Tim Huang
+   Copyright 2025 Tim Huang
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

{squirrels-0.4.0 → squirrels-0.5.0rc0}/PKG-INFO

@@ -1,39 +1,39 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: squirrels
-Version: 0.4.0
+Version: 0.5.0rc0
 Summary: Squirrels - API Framework for Data Analytics
-Home-page: https://squirrels-analytics.github.io
-License: Apache-2.0
-Author: Tim Huang
-Author-email: tim.yuting@hotmail.com
-Requires-Python: >=3.10,<4.0
+Project-URL: Homepage, https://squirrels-analytics.github.io
+Project-URL: Repository, https://github.com/squirrels-analytics/squirrels
+Project-URL: Documentation, https://squirrels-analytics.github.io
+Author-email: Tim Huang <tim.yuting@hotmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
-Provides-Extra: duckdb
-Requires-Dist: cachetools (>=5.3.2,<6.0.0)
-Requires-Dist: duckdb-engine (>=0.13.0,<1.0.0) ; extra == "duckdb"
-Requires-Dist: fastapi (>=0.112.1,<0.113.0)
-Requires-Dist: gitpython (>=3.1.41,<4.0.0)
-Requires-Dist: inquirer (>=3.2.1,<4.0.0)
-Requires-Dist: jinja2 (>=3.1.3,<4.0.0)
-Requires-Dist: matplotlib (>=3.8.3,<4.0.0)
-Requires-Dist: networkx (>=3.2.1,<4.0.0)
-Requires-Dist: pandas (>=2.1.4,<3.0.0)
-Requires-Dist: pydantic (>=2.8.2,<3.0.0)
-Requires-Dist: pyjwt (>=2.8.0,<3.0.0)
-Requires-Dist: python-multipart (>=0.0.9,<0.0.10)
-Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
-Requires-Dist: sqlalchemy (>=2.0.25,<3.0.0)
-Requires-Dist: uvicorn (>=0.30.6,<0.31.0)
-Project-URL: Documentation, https://squirrels-analytics.github.io
-Project-URL: Repository, https://github.com/squirrels-analytics/squirrels
+Requires-Python: ~=3.10
+Requires-Dist: bcrypt<5,>=4.0.1
+Requires-Dist: cachetools<6,>=5.3.2
+Requires-Dist: duckdb<2,>=1.1.3
+Requires-Dist: fastapi<1,>=0.112.1
+Requires-Dist: gitpython<4,>=3.1.41
+Requires-Dist: inquirer<4,>=3.2.1
+Requires-Dist: jinja2<4,>=3.1.3
+Requires-Dist: matplotlib<4,>=3.8.3
+Requires-Dist: networkx<4,>=3.2.1
+Requires-Dist: pandas<3,>=2.1.4
+Requires-Dist: passlib<2,>=1.7.4
+Requires-Dist: polars<2,>=1.14.0
+Requires-Dist: pyarrow<19,>=18.0.0
+Requires-Dist: pydantic<3,>=2.8.2
+Requires-Dist: pyjwt<3,>=2.8.0
+Requires-Dist: python-dotenv<2,>=1.0.1
+Requires-Dist: python-multipart<1,>=0.0.9
+Requires-Dist: pyyaml<7,>=6.0.1
+Requires-Dist: sqlalchemy<3,>=2.0.25
+Requires-Dist: sqlglot<26,>=25.32.1
+Requires-Dist: uvicorn<1,>=0.30.6
 Description-Content-Type: text/markdown
 
 # Squirrels
@@ -60,7 +60,7 @@ Here are a few of the things that squirrels can do:
 - Connect to any database by specifying its SQLAlchemy url (in `squirrels.yml`) or by using its native connector library in python (in `connections.py`).
 - Configure API routes for datasets (in `squirrels.yml`) without writing code.
 - Configure parameter widgets (types include single-select, multi-select, date, number, etc.) for your datasets (in `parameters.py`).
-- Use Jinja SQL templates (just like dbt!) or python functions (that return a pandas dataframe) to define dynamic query logic based on parameter selections.
+- Use Jinja SQL templates (just like dbt!) or python functions (that return a Python dataframe such as polars or pandas) to define dynamic query logic based on parameter selections.
 - Query multiple databases and join the results together in a final view in one API endpoint/dataset!
 - Test your API endpoints with an interactive UI or by a command line that generates rendered sql queries and results (for a given set of parameter selections).
 - Define authentication logic (in `auth.py`) and authorize privacy scope per dataset (in `squirrels.yml`). The user's attributes can even be used in your query logic!
@@ -114,4 +114,3 @@ The library version is maintained in both the `pyproject.toml` and the `squirrel
 When a user initializes a squirrels project using `sqrl init`, the files are copied from the `squirrels/package_data/base_project` folder. The contents in the `database` subfolder were constructed from the scripts in the `database_elt` folder.
 
 For the Squirrels UI activated by `sqrl run`, the HTML, CSS, and Javascript files can be found in the `static` and `templates` subfolders of `squirrels/package_data`. The CSS and Javascript files are minified and built from the source files in this project: https://github.com/squirrels-analytics/squirrels-testing-ui.
-

{squirrels-0.4.0 → squirrels-0.5.0rc0}/README.md

@@ -22,7 +22,7 @@ Here are a few of the things that squirrels can do:
 - Connect to any database by specifying its SQLAlchemy url (in `squirrels.yml`) or by using its native connector library in python (in `connections.py`).
 - Configure API routes for datasets (in `squirrels.yml`) without writing code.
 - Configure parameter widgets (types include single-select, multi-select, date, number, etc.) for your datasets (in `parameters.py`).
-- Use Jinja SQL templates (just like dbt!) or python functions (that return a pandas dataframe) to define dynamic query logic based on parameter selections.
+- Use Jinja SQL templates (just like dbt!) or python functions (that return a Python dataframe such as polars or pandas) to define dynamic query logic based on parameter selections.
 - Query multiple databases and join the results together in a final view in one API endpoint/dataset!
 - Test your API endpoints with an interactive UI or by a command line that generates rendered sql queries and results (for a given set of parameter selections).
 - Define authentication logic (in `auth.py`) and authorize privacy scope per dataset (in `squirrels.yml`). The user's attributes can even be used in your query logic!

squirrels-0.5.0rc0/database_elt/expenses/.gitignore

@@ -0,0 +1 @@
+expenses.db

squirrels-0.5.0rc0/database_elt/expenses/create-expenses.py

@@ -0,0 +1,90 @@
+import sqlite3, random, polars as pl, tqdm, numpy as np
+
+def generate_expense_description(vendors=None, items=None, adjectives=None):
+    """
+    Generates a random expense description.
+
+    Args:
+        categories: A list of expense categories (e.g., ["Groceries", "Dining", "Travel", "Utilities"]).
+        vendors: A list of vendor names (e.g., ["Walmart", "Starbucks", "Amazon", "Gas Station"]).
+        items: A list of items purchased (e.g., ["Milk", "Coffee", "Laptop", "Gas"]).
+        adjectives: A list of adjectives to add variety(e.g., ["Monthly", "Quick", "Online", "Unexpected"]).
+
+    Returns:
+        A randomly generated expense description string.
+    """
+
+    if vendors is None:
+        vendors = ["Vendor A", "Vendor B", "Vendor C", "Vendor D", "Vendor E", "Online Store", "Local Shop", "Restaurant"]
+    if items is None:
+        items = ["Item 1", "Item 2", "Item 3", "Item 4", "Item 5", "Service", "Subscription", "Purchase", "Merchandise", "Goods"]
+    if adjectives is None:
+        adjectives = ["Daily", "Monthly", "Quick", "Online", "Unexpected", "Recurring", "Personal", "Business"]
+
+    description_parts = []
+
+    # Choose a category, vendor, and item
+    adjective = random.choice(adjectives)
+    vendor = random.choice(vendors)
+    item = random.choice(items)
+
+    # Build the description
+    description_parts.append(f"{adjective} {item} - {vendor}")
+
+    return " ".join(description_parts).strip()
+
+# Define the number of transactions to generate
+num_transactions = 1_000
+batches = 100
+batch_size = num_transactions // batches
+
+# Generate the data
+descriptions_df = pl.DataFrame({
+    'description': [generate_expense_description() for _ in range(10**4)]
+})
+
+df_list: list[pl.DataFrame] = []
+rng = np.random.default_rng()
+for _ in tqdm.tqdm(range(batches)):
+    df_current = descriptions_df.sample(batch_size, with_replacement=True, shuffle=True)
+    df_current = df_current.with_columns(
+        pl.lit(rng.integers(
+            np.datetime64('2024-01-01').astype(int), 
+            np.datetime64('2025-01-01').astype(int), 
+            size=batch_size
+        ).astype('datetime64[D]')).alias('date'),
+        pl.lit(rng.integers(0, 14, size=batch_size)).alias('subcategory_id'),
+        pl.lit(rng.exponential(30, size=batch_size).round(2)).alias('amount'),
+    )
+    df_list.append(df_current)
+
+df = pl.concat(df_list).select('date', 'subcategory_id', 'amount', 'description')
+df = df.sort('date').with_row_index(name='id', offset=1)
+
+# Connect to SQLite database
+conn = sqlite3.connect('expenses.db')
+
+try:
+    # Create the expenses table
+    conn.execute("DROP TABLE IF EXISTS expenses")
+    conn.execute('''
+    CREATE TABLE IF NOT EXISTS expenses (
+        id INTEGER PRIMARY KEY,
+        date DATE,
+        subcategory_id INTEGER,
+        amount DECIMAL(10,2),
+        description TEXT
+    )
+    ''')
+
+    # Convert DataFrame to records and insert into database
+    records = df.to_numpy().tolist()
+    conn.executemany(
+        'INSERT INTO expenses (id, date, subcategory_id, amount, description) VALUES (?, ?, ?, ?, ?)',
+        records
+    )
+
+    # Commit changes and close connection
+    conn.commit()
+finally:
+    conn.close()

squirrels-0.5.0rc0/database_elt/expenses/create-lookups.py

@@ -0,0 +1,55 @@
+import sqlite3
+import csv
+from io import StringIO
+
+category_id_mapping = """
+"category_id","subcategory_id"
+0,0
+0,1
+1,2
+2,3
+3,4
+1,5
+2,6
+1,7
+4,8
+4,9
+2,10
+3,11
+2,12
+4,13
+"""
+
+# Connect to the SQLite database
+conn = sqlite3.connect('expenses.db')
+try:
+    cursor = conn.cursor()
+
+    # Create the category_mapping table
+    cursor.execute('''
+    DROP TABLE IF EXISTS category_mapping
+    ''')
+    cursor.execute('''
+    CREATE TABLE category_mapping (
+        category_id INTEGER,
+        subcategory_id INTEGER,
+        PRIMARY KEY (subcategory_id)
+    )
+    ''')
+
+    # Parse the CSV string and insert data
+    csv_file = StringIO(category_id_mapping.strip())
+    csv_reader = csv.DictReader(csv_file)
+
+    # Insert the data
+    for row in csv_reader:
+        cursor.execute('''
+        INSERT OR REPLACE INTO category_mapping (category_id, subcategory_id)
+        VALUES (?, ?)
+        ''', (int(row['category_id']), int(row['subcategory_id'])))
+
+    # Commit the changes and close the connection
+    conn.commit()
+
+finally:
+    conn.close()

squirrels-0.5.0rc0/database_elt/seattle_weather/create_db.py

@@ -0,0 +1,13 @@
+import pandas as pd
+import sqlite3, os
+
+os.chdir(os.path.dirname(__file__))
+
+df = pd.read_csv('seattle-weather.csv')
+
+# Connect to SQLite database
+conn = sqlite3.connect('weather.db')
+try:
+    df.to_sql('weather', conn, index=False, if_exists='replace')
+finally:
+    conn.close()