arthurwuhoo

################################################################
# Reading in 2015-2016 Weather Data for Cape Town
################################################################

library(rvest)

tables <- read_html("https://www.wunderground.com/history/airport/FACT/2015/6/21/CustomHistory.html?dayend=21&monthend=6&yearend=2016&req_city=&req_state=&req_statename=&reqdb.zip=&reqdb.magic=&reqdb.wmo=")


raw_weather <- tables %>% html_nodes(css="#obsTable") %>% .[[1]] %>% html_table(header = TRUE, fill = TRUE)

arthurwuhoo

# ------------------------------------------------------------------
# DAY 14: CLUSTERING EXERCISES
# ------------------------------------------------------------------
# ------------------------------------------------------------------
# EXERCISE 1
# Use kk Means Clustering to group the observations in the mtcars data. Is it 
#important to standardise these data first? Vary the number of clusters and choose 
# an appropriate value for kk. Interpret the clusters.
# ------------------------------------------------------------------ 

arthurwuhoo

# ------------------------------------------------------------------
# DAY 12 EXERCISES - CROSS VALIDATION
# ------------------------------------------------------------------

# ------------------------------------------------------------------
# EXERCISE 1
# Build a Logistic Regression model classifying the credit status of 
# customers (good or bad) in this data. Without using any packages, apply 5
# -fold cross-validation on the model. Once you have five models (and five 
# sets of predicted values), average them to in order to create a new 

arthurwuhoo

sample.data <- read.csv("svm_sample.csv")
sample.data <- sample.data[,-1] #getting rid of id variables


library(caret)
train_index <- createDataPartition(sample.data$color, 0.8)[[1]]

sample.data.train <- sample.data[train_index,]
sample.data.test <- sample.data[-train_index,]

arthurwuhoo

# ------------------------------------------------------------------
# DAY 12 EXERCISES - DECISION TREES
# ------------------------------------------------------------------

# ------------------------------------------------------------------
# EXERCISE 1
# Complete the iris modelling exercise. This is a multiclass problem. Some models
# support multiclass problems, others don’t. Decision trees do. Divide the data 
# in a 60% training and 40% testing split. Create a model based on the training 
# data.

arthurwuhoo

# ------------------------------------------------------------------
# DAY 12 EXERCISES - LOGISTIC REGRESSION
# ------------------------------------------------------------------

# ------------------------------------------------------------------
# EXERCISE 1
# Create a parsimonious model for the myopia data. Does its performance differ 
# substantially from the full model?
# ------------------------------------------------------------------

arthurwuhoo

# ------------------------------------------------------------------
# EXERCISE 3
# Use the birthwt data in the MASS package to construct a model for low birth 
# weight. Are there any features which should be excluded from the model?
# ------------------------------------------------------------------

library(MASS)
library(caret)

arthurwuhoo

##############################################################

# DAY 11: LINEAR REGRESSION EXERCISES

##############################################################

# 1) Height and Mass. Scrape the height and mass data from here.
# ----------------------------------------------------------------------------

library(rvest)

arthurwuhoo

##############################################################

# DAY 11: LINEAR REGRESSION EXERCISES

##############################################################

# 1) Height and Mass. Scrape the height and mass data from here.
# ----------------------------------------------------------------------------

library(rvest)

arthurwuhoo

# =====================================================================================================================
# OUTLIERS
# =====================================================================================================================

library(dplyr)
library(corrgram)

# Focus our attention on a subset of the baseball data.
#
baseball = select(baseball, Name, Atbatc:Walksc)