Garrett Mooney GarrettMooney

Functional Programming in Python

https://kobzol.github.io/rust/python/2023/05/20/writing-python-like-its-rust.html for ideas on how to write python code like it's rust
https://blog.ezyang.com/2020/10/idiomatic-algebraic-data-types-in-python-with-dataclasses-and-union/ for ideas on using algebraic data types in Python

Preferences

duckdb when data processing can easily be expressed in sql
polars over pandas
simple functions over classes
inline dependencies in python scripts
uv and uvx for package management, python clis, scripts, and virtual environments

Schemas in QA but not in Prod

WITH qa AS (
    SELECT TABLE_CATALOG, TABLE_SCHEMA, TABLE_NAME
    FROM qa_edw_pstg.information_schema.tables
),
prod AS (
    SELECT TABLE_CATALOG, TABLE_SCHEMA, TABLE_NAME
    FROM prd_edw_pstg.information_schema.tables

%pip install "whatlies[sentence_tfm]"  # quotes for my fellow zsh users

import numpy as np
from whatlies.language import SentenceTFMLanguage
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression

pipe = Pipeline([
 ("embed", SentenceTFMLanguage('distilbert-base-nli-stsb-mean-tokens')),

	#!/usr/bin/env bash

	# install rustup if it doesn't exist
	if ! command -v rustup &> /dev/null
	then
	curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \| sh -s -- -y
	fi

	# install uv if it doesn't exist
	if ! command -v uv &> /dev/null

	import uuid

	import streamlit as st

	#########
	# Helpers
	#########


	def get_completion(question, session_id):

	# /// script
	# requires-python = ">=3.12"
	# dependencies = [
	# "boto3",
	# "sagemaker",
	# ]
	# ///
	import subprocess
	import time
	from time import gmtime, strftime

	# /// script
	# requires-python = ">=3.12"
	# dependencies = [
	# "duckdb",
	# "polars",
	# "pyarrow",
	# "pyathena",
	# "s3fs",
	# ]
	# ///

	"""View remote jobs in a 3 day interval."""

	BASE_URL = "https://www.linkedin.com/jobs/search/"

	def get_linkedin_jobs(search, n_days=3, remote=True):
	# time
	seconds_in_day = 86400
	n_seconds = n_days * seconds_in_day
	query = BASE_URL + "?f_TPR=r" + str(n_seconds)

	from typing import Union

	import numpy as np
	import pandas as pd

	def create_sample_weights(
	y_train: np.ndarray,
	X_train: Union[np.ndarray, pd.DataFrame]
	) -> pd.Series:
	y_series = pd.DataFrame({"y": y_train})["y"]

	from numpy import log, exp
	from scipy.special import betaln as logbeta


	def probability_B_beats_A(α_A, β_A, α_B, β_B):
	total = 0.0
	for i in range(α_B):
	total += exp(
	logbeta(α_A + i, β_B + β_A)
	- log(β_B + i)