t-redactyl

set.seed(567)

# Sample of 30 (29 from the Poisson distribution and an outlier of 260)
sample1 <- c(rpois(29, lambda = 220), 260)

# Sample of 10 (9 from the Poisson distribution and an outlier of 260)
sample2 <- c(rpois(9, lambda = 220), 260)

t-redactyl

# Defining lambda and n
lambda <- 220
n <- 30

# Calculating SEM
sem <- sqrt(lambda / n)

t-redactyl

require(ggplot2); require(gridExtra)

# Set the colours for the graphs
barfill <- "#4271AE"
barlines <- "#1F3552"
line1 <- "black"
line2 <- "#FF3721"

# Plotting histogram of sample of daily page views
g1 <- ggplot(data=as.data.frame(sample), aes(sample)) + 

t-redactyl

av_peds_2 <- ddply(p.subset, c("date", "collapsed_sensors_2"), summarise,
                 n_peds = sum(Hourly_Counts))

# Extract weekday versus weekend
av_peds_2$day <- weekdays(av_peds_2$date, abbreviate = FALSE)
av_peds_2$weekend <- ifelse((av_peds_2$day == "Saturday" | av_peds_2$day == "Sunday"), 
                           "Weekend", "Weekday")
av_peds_2$weekend <- as.factor(av_peds_2$weekend)

# Extract time of day

t-redactyl

library(ggplot2); library(gridExtra)
g1 <- ggplot(data=mtcars, aes(x=wt, y=mpg)) + 
        geom_point(alpha = 0.7, colour = "#0971B2") +
        ylab("Miles per gallon") + 
        ylim(10, 35) +
        xlab("Weight (`000 lbs)") +
        ggtitle("Untransformed Weight") + 
        geom_vline(xintercept = 0) +
        theme_bw()

t-redactyl

mtcars$am.f <- as.factor(mtcars$am); levels(mtcars$am.f) <- c("Automatic", "Manual")
mtcars$cyl.f <- as.factor(mtcars$cyl); levels(mtcars$cyl.f) <- c("4 cyl", "6 cyl", "8 cyl")
mtcars$vs.f <- as.factor(mtcars$vs); levels(mtcars$vs.f) <- c("V engine", "Straight engine")
mtcars$gear.f <- as.factor(mtcars$gear); levels(mtcars$gear.f) <- c("3 gears", "4 gears", "5 gears")
mtcars$carb.f <- as.factor(mtcars$carb)

t-redactyl

# Load in the packages
library(ggplot2)
library(extrafont)
font_import()
loadfonts()

# Read in the base Christmas tree data
ChristmasTree <- read.csv("https://raw.githubusercontent.com/t-redactyl/Blog-posts/master/Christmas%20tree%20base%20data.csv")

# Generate the "lights"

t-redactyl

# Import the relevant packages
import numpy as np
import re

# Create 6 new dummy variables which indicate whether one of the words associated with a resolution is present in the tweet.
twitter_df['Physical Health'] = np.where(twitter_df['Tweet'].str.contains('(?:^|\W)(weight|fit|exercise|gym|muscle|health|water|smoking|alcohol|drinking|walk|run|swim)(?:$|\W)', 
    flags = re.IGNORECASE), 1, 0)

twitter_df['Learning and Career'] = np.where(twitter_df['Tweet'].str.contains('(?:^|\W)(business|job|career|professional|study|learn|develop|advance|grades|school|university| read|study|skill|education)(?:$|\W)', 
    flags = re.IGNORECASE), 1, 0)

t-redactyl

# This code is not mine! Copied from https://gist.github.com/nealrs/96342d8231b75cf4bb82, but with suggested alteration to include text.lower() in the function.

import re
cList = {
  "ain't": "am not",
  "aren't": "are not",
  "can't": "cannot",
  "can't've": "cannot have",
  "'cause": "because",
  "could've": "could have",

t-redactyl