apoorvalal’s gists

apoorvalal / _ollama_runner.py

Last active April 14, 2025 00:54

Run local llms via CLI. First install ollama, pull the model you want, and then run `./ollama_runner.py <prompt> <modelname> <outputfile>`; latter two are optional [defaults are gemma3 and empty.

	#!/Users/alal/miniforge3/envs/llm/bin/python
	# this needs to point to a python virtualenv with ollama-python
	# your system should also have ollama installed
	# if you have an nvidia gpu, install lshw first before installing ollama

	import argparse
	import ollama

	def main(msg, mod='gemma3:27b', outfile=None):
	response = ollama.chat(model=mod, messages=[

apoorvalal / casual.sh

Created November 22, 2024 19:09

	#!/bin/bash

	# Directory to search
	DIRECTORY=$1

	# Additional extensions to search, if provided
	EXTENSIONS="tex"

	if [ ! -z "$2" ]; then
	EXTENSIONS="$EXTENSIONS\|$2"

apoorvalal / lest.py

Created August 10, 2024 16:37

	# %%
	import functools
	from typing import Callable, TypeVar, Any
	import pandas as pd
	import numpy as np


	T = TypeVar("T")

	# %%

apoorvalal / linRegressionInference.R

Last active June 3, 2024 05:03

Inference for the Population Average Treatment Effect using fully interacted OLS

	library(momentfit); library(car); library(tictoc)
	set.seed(42)
	# %%
	dgp = \(n=500, k = 2){
	X = matrix(rnorm(n * 2), n, 2)
	Y1 = X[, 1] + X[, 1]^2 + runif(n, -0.5, 0.5)
	Y0 = X[, 2] + X[, 2]^2 + runif(n, -1, 1)
	Z = rbinom(n, 1, 0.6)
	Y = Z * Y1 + (1-Z) * Y0
	data.frame(Y, Z, X)

apoorvalal / linear_mediation.py

Last active May 25, 2024 16:05

	from joblib import Parallel, delayed
	import numpy as np
	import pandas as pd


	class LinearMediation:
	def __init__(self):
	pass

	def fit(self, X, W, y, store=True):

apoorvalal / texJanus.tex

Last active January 20, 2024 02:25

generate both an article and slide-deck from the same tex file using beamerswitch.

	\documentclass[%
	article,
	% beamer,
	beameroptions={ignorenonframetext,14pt},
	articleoptions={a4paper,12pt},
	also={trans,handout,article}
	]{beamerswitch}
	\handoutlayout{nup=3plus,border=1pt}
	\articlelayout{maketitle,frametitles=none}
	\mode<article>{\usepackage[hmargin=2cm,vmargin=2cm]{geometry}}

apoorvalal / ml_powered_covariate_adjustment.py

Created December 20, 2023 01:45

covariate adjustment using nonparametric regression (Wager et al 2016 PNAS)

	import numpy as np
	import pandas as pd
	from scipy.stats import norm
	from sklearn.model_selection import cross_val_predict, KFold

	# learners
	from xgboost import XGBRegressor
	from glum import GeneralizedLinearRegressorCV
	from sklearn.kernel_ridge import KernelRidge

apoorvalal / fwl_estimates_and_se.R

Created December 8, 2023 20:16

numerical verification of equality of coefficient and SE per FWL

	library(estimatr)
	data(auto)
	# %% FWL regression coefficient
	auto$ytil = lm(price ~ displacement, auto)$resid
	auto$x2til = lm(weight ~ displacement, auto)$resid
	(fwlest = lm_robust(ytil ~ x2til, auto, se_type = "HC0")
	%>% summary %>% .$coefficients %>% .[2, 1:2])
	# %%
	(fullest =
	lm_robust(price ~ weight + displacement, auto, se_type = "HC0") %>%

apoorvalal / ols_lean.py

Created November 5, 2023 17:21

lean implementation of OLS

	import numpy as np
	from scipy.linalg import lstsq
	np.random.seed(42)
	# %%
	def ols(X, y, vcov = 'HC1', driver = 'gelsy'):
	"""
	Fast, minimal implementation of least squares regression with robust SEs

	Args:
	X: n X p array of covariates

apoorvalal / simulate_adjustment_strategies.R

Last active November 2, 2023 22:53

compare bias and variance properties of regression adjustment strategies https://www.degruyter.com/document/doi/10.1515/ijb-2021-0072/html

	# %%
	pacman::p_load(knitr, tidyverse, DeclareDesign, glmnet)
	set.seed(42)

	# %% estimator functions
	p_hacker = function(data) {
	fit_1 = lm_robust(Y ~ Z + X1, data = data)
	fit_3 = lm_robust(Y ~ Z + X1 + X2, data = data)
	fit_2 = lm_robust(Y ~ Z + X2 + X3 + X4, data = data)
	fit_4 = lm_robust(Y ~ Z + X3 + X4 + X5 + X6 + X7 + X8 + X9, data = data)

Apoorva Lal apoorvalal