FrankRuns

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import dowhy
from dowhy import CausalModel
import networkx as nx
import math
import sklearn 
from sklearn import preprocessing
from sklearn.model_selection import train_test_split

FrankRuns

# Replicate Bob's results from this LinkedIn post:
# https://www.linkedin.com/posts/bob-wilson-77a22ab_people-sometimes-say-ab-testing-requires-activity-7152792859878871040-X1Sr?utm_source=share&utm_medium=member_desktop


### Implement Fisher's Exact Test

# Create the contingency table
contingency_table <- matrix(c(0, 4, 7, 3), nrow = 2)
dimnames(contingency_table) <- list(c("Control", "Treatment"),

FrankRuns

# Load Required Libraries
if (!require("MASS")) install.packages("MASS")
library(MASS)

# Define TV Shows
# A vector of TV show titles
tv_shows <- c(
  "Breaking Bad", "Game of Thrones", "The Wire", 
  "Stranger Things", "The Crown", "Mad Men", 
  "The Sopranos", "Friends", "The Office", 

FrankRuns

# load packages
library(tidyverse)
library(tidytuesdayR) # Used for loading datasets from the TidyTuesday project

# load datasets
tuesdata <- tidytuesdayR::tt_load('2023-11-28')
drwho_episodes <- tuesdata$drwho_episodes
drwho_directors <- tuesdata$drwho_directors
drwho_writers <- tuesdata$drwho_writers

FrankRuns

# purpose: visualize linear trend for all data and subset of data

# libraries
library(dplyr)
library(ggplot2)

# read data 
d <- read.csv("mycsvfile.csv")

# quickl look

FrankRuns

# purpose: helper script to determine my max heart rate

# load libraries
library(dplyr)
library(rethinking)

#### Read and Filter Data ----

# grab data

FrankRuns

---
title: "Is-Behavior-Change-Happening"
author: "frank-corrigan"
date: "3/9/2022"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)

FrankRuns

---
title: "Marathon-Insights"
author: "frank-corrigan"
date: "3/1/2022"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)

FrankRuns

# toy simulation to determine how likely or
# unlikely the poll results from blog post
# are (Do you plan to relocate in 2022?) 

# load packages
library(dplyr)
library(ggplot2)


# Single Instance ----

FrankRuns

from tabula.io import read_pdf
import pandas as pd
import matplotlib.pyplot as plt

# set path to file
pdf_path = "Container-Vessels-In-Port.pdf"

# creates a python list, each page is a list item stored as pandas df
dfs = read_pdf(pdf_path, stream=True, pages='2-10')