Awuor87

bank= read.csv("bank-additional-full.csv", header=TRUE)
dim(bank)
head(bank)

# split the datasert into train and validation dataset

train.prop= .75 # set the training dataset at 75%

train.cases= sample(nrow(bank), nrow(bank)*train.prop)

Awuor87

bank= read.csv("bank-additional-full.csv", header=TRUE)
dim(bank)
head(bank)

# split the datasert into train and validation dataset

train.prop= .75 # set the training dataset at 75%

train.cases= sample(nrow(bank), nrow(bank)*train.prop)

Awuor87

crosstab<- read.csv("CrossTab_Example.csv", header= TRUE)

View(crosstab)
accountsize<- table(crosstab[,2]) # accountsize
dimnames(accountsize)<- list(c("small", "medium","large"))

dim(crosstab) # check the data has expected number of rows and columns
library(gmodels)
cbc.df<- read.csv("http://goo.gl/5xQObB")
View(cbc.df)

Awuor87

import glob
import codecs
import numpy
from pandas import DataFrame
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import KFold
from sklearn.metrics import confusion_matrix, f1_score

Awuor87

import networkx
from operator import itemgetter
import matplotlib.pyplot

# read the data from the amazon-books.txt;
# populate amazonProducts nested dicitonary;
# key = ASIN; value = MetaData associated with ASIN
fhr = open('./amazon-books.txt', 'r', encoding='utf-8', errors='ignore')
amazonBooks = {}
fhr.readline()

Awuor87

## What is dplyr?
  # dplyr is a grammar that makes data manipulation quick and easy.

# Install the dplyr library
install.packages('dplyr')

# load the dplyr library
library(dplyr)

Awuor87

### ggplot2 is the most common used graphics package in R.  It has great flexibility, 
### allows for a wide variety of graphs, and has an easy to understand grammar.

# Install the ggplot2 library and load it.
install.packages("ggplot2")
library(ggplot2)

# Assign the diamonds data
diamond=diamonds

Awuor87

# Define 2^2 test matrix
FullFact.2.2 <- function() {
a <- c(-1,1,-1,1)
b <- c(-1,-1,1,1)
ab <- a *b
df <- data.frame(a,b, ab)
rownames(df)<- c("(1)", "a", "b", "ab")
return(df)
}
(ff22<- FullFact.2.2())

Awuor87

salarydata<- read.csv ("Salary_Data.csv", header = TRUE)
Salary= salarydata[,2]
Age= salarydata[,3]

Genderfactor= as.factor(salarydata[,4])#it converts the data to a discrete variable
resl= lm(Salary~Age+ Genderfactor)

# interaction
res2= lm(Salary~Age+ Genderfactor+ Age: Genderfactor)
summary(res2)