martinctc

library(tidyverse)
library(PostcodesioR)

# Customize with your own path
df_with_postcodes <- read_csv(
  "path/data/postcodes.csv" 
)

# Update with column name containing postcode
postcode_column <- df_with_postcodes[["postcode"]]

martinctc

#' @title Apply Noise to Specified Columns in a Data Frame
#'
#' @description This function applies a normal distribution-based noise to
#'   specified columns in a data frame, grouped by a specified variable. The
#'   noise is scaled to a range of -0.2 to 0.2.
#' 
#' @param df Data frame to apply the normal distribution to for creating noise.
#' @param group_var String specifying the grouping variable. 
#' @param cols Vector of column names to apply the noise to.
#' @param scale_from Numeric value specifying the lower bound of the scaling range.

martinctc

# This script simulates a dataset, duplicates it over time, and modifies it to
# create a bell curve-like distribution.

# Set up
library(tidyverse)
library(uuid)

# Simulate dataset
temp_df <- 
  tibble(

martinctc

#' @title Perform a Statistical Test
#'
#' @description This function performs a statistical test (e.g., chi-squared, t-test) given a data frame, variable names, and any other parameters needed.
#'
#' @details Insert more detailed information here about what the function does, the assumptions it makes, and how it should be used.
#'
#' @param data A data frame containing the variables of interest.
#' @param var1 A string or symbol specifying the first variable.
#' @param var2 A string or symbol specifying the second variable (if applicable).
#' @param ... Additional arguments passed to the underlying test function.

martinctc

#' @title Convert a numeric value into a natural language approximation string
#' 
#' @description 
#' This function takes a numeric value and returns a string that approximates the value in natural language.
#' 
#' @param x A numeric value.
#' 
#' @examples 
#' approx_num(0.5)
#' # [1] "increased by a half"

martinctc

# data cleaning and utility
import numpy as np
import pandas as pd
import vivainsights as vi
import os

# timing code
import time 
import random
import sys

martinctc

import requests
import pandas as pd

package_name = "vivainsights"
api_endpoint = f"https://pypistats.org/api/packages/{package_name}/overall"

response = requests.get(api_endpoint)

if response.status_code == 200:
    data = response.json()

martinctc

# See <https://rpubs.com/mbounthavong/sample_size_power_analysis_R>

library(pwr)

# Sample size estimations for two proportions
# `pwr::ES.h()` computes effect size for two proportions
# n provides required sample size

p0 <- pwr.2p.test(h = ES.h(p1 = 0.60, p2 = 0.50), sig.level = 0.05, power = .80)
plot(p0)

martinctc

# estimate sample size via power analysis
from statsmodels.stats.power import TTestIndPower

# parameters for power analysis
effect = 0.8
alpha = 0.05
power = 0.8

# perform power analysis
analysis = TTestIndPower()

martinctc

#' @title
#' Rank a data frame by grouping variable using base R
#'
#' @description
#' This function ranks a specified column in a data frame by group using entirely base R functions. 
#' The underlying function is `rank()`, where additional arguments can be passed with `...`. 
#' The grouping variable is specified as a string using the argument `group_var`, and the variable to rank is 
#' specified using the argument `rank_var`. The operation is analogous to using `group_by()` followed by 
#' `mutate()` in {dplyr}.
#' See example below using the base dataset `iris`.