Raghu_606_Project

require(lubridate)

## Loading required package: lubridate

## 
## Attaching package: 'lubridate'

## The following object is masked from 'package:base':
## 
##     date

require(dplyr)

## Loading required package: dplyr

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:lubridate':
## 
##     intersect, setdiff, union

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

require(tidyr)

## Loading required package: tidyr

require(stringr)

## Loading required package: stringr

require(RMySQL)

## Loading required package: RMySQL

require(doBy)

## Loading required package: doBy

require(knitr)

## Loading required package: knitr

require(ggplot2)

## Loading required package: ggplot2

require(reshape)

## Loading required package: reshape

## 
## Attaching package: 'reshape'

## The following objects are masked from 'package:tidyr':
## 
##     expand, smiths

## The following object is masked from 'package:dplyr':
## 
##     rename

## The following object is masked from 'package:lubridate':
## 
##     stamp

knitr::opts_chunk$set(echo = TRUE)

Data Preparation

yr_2013 <- read.csv(file = ("https://raw.githubusercontent.com/raghu74us/606/master/2013_shooter.csv"),sep =",")

#not including the columns that are not needed for analysis.
yr_2013 <- yr_2013[ , c('date', 'killed', 'wounded', 'location')]
     #split state and city based on location
     str(yr_2013)

## 'data.frame':    363 obs. of  4 variables:
##  $ date    : Factor w/ 210 levels "1/1/13","1/10/13",..: 1 1 1 1 10 11 11 11 2 3 ...
##  $ killed  : int  4 1 0 1 4 5 2 3 3 1 ...
##  $ wounded : int  0 3 4 4 0 0 2 1 2 4 ...
##  $ location: Factor w/ 249 levels "Aguas Buenas, PR",..: 199 87 135 122 9 228 76 50 154 229 ...

     head(yr_2013,5)

##     date killed wounded       location
## 1 1/1/13      4       0 Sacramento, CA
## 2 1/1/13      1       3  Hawthorne, CA
## 3 1/1/13      0       4 McKeesport, PA
## 4 1/1/13      1       4     Lorain, OH
## 5 1/5/13      4       0     Aurora, CO

     cit_st <- strsplit( as.character(yr_2013$location), ", " , fixed=TRUE) 
     mat  <- matrix(unlist(cit_st), ncol=2, byrow=TRUE)
     df   <- as.data.frame(mat)
     yr_2013_cit_st   <- cbind(yr_2013, df)
     colnames(yr_2013_cit_st) <- c('date', 'killed', 'wounded', 'location', "City", "State")
     
     #Add month and year based on date.
     yr_2013_cit_st$date <- mdy(yr_2013_cit_st$date)
     
     str(yr_2013_cit_st)

## 'data.frame':    363 obs. of  6 variables:
##  $ date    : Date, format: "2013-01-01" "2013-01-01" ...
##  $ killed  : int  4 1 0 1 4 5 2 3 3 1 ...
##  $ wounded : int  0 3 4 4 0 0 2 1 2 4 ...
##  $ location: Factor w/ 249 levels "Aguas Buenas, PR",..: 199 87 135 122 9 228 76 50 154 229 ...
##  $ City    : Factor w/ 244 levels "Aguas Buenas",..: 195 87 131 119 9 223 76 50 150 224 ...
##  $ State   : Factor w/ 49 levels "AL","AZ","CA",..: 3 3 37 34 4 36 28 46 18 1 ...

     y1<-year(yr_2013_cit_st$date)
     m1<-as.character(yr_2013_cit_st$date, format="%b")
     d1<-as.character(yr_2013_cit_st$date, format="%d")
     
     df1  <- cbind(d1,m1,y1)
     colnames(df1)  <- c('day','month','year')
     
     yr_2013_df2 <- cbind(yr_2013_cit_st , df1)
     #str(yr_2013_df2)
    
    #summarize by total killed and wounded in each state  
     yr_2013_df2_kw <- yr_2013_df2  %>%
        select(year,State,month,killed,wounded) %>%
         filter( str_length(yr_2013_df2$State) == 2) %>%
          group_by(year,State,month )  %>%
           summarise_each(funs(sum) ) %>%
             arrange(year,State,month)
     
    #summarize by total incidents in each state        
        yr_2013_df2_inc <- yr_2013_df2  %>%
        select(year,State,month,killed,wounded) %>%
         filter( str_length(yr_2013_df2$State) == 2) %>%
          group_by(year,State,month )  %>%
            summarise( total_incidents= n() )  %>%
             arrange(year,State,month)
              
     kable(yr_2013_df2_kw)

year	State	month	killed	wounded
2013	AL	Dec	6	6
2013	AL	Jan	1	4
2013	AL	Jul	1	7
2013	AL	Mar	3	1
2013	AL	May	0	4
2013	AL	Oct	4	0
2013	AZ	Apr	2	4
2013	AZ	Jan	3	1
2013	AZ	May	5	4
2013	AZ	Nov	5	3
2013	AZ	Oct	5	4
2013	CA	Apr	3	13
2013	CA	Aug	3	12
2013	CA	Dec	4	0
2013	CA	Feb	12	25
2013	CA	Jan	5	7
2013	CA	Jul	6	15
2013	CA	Jun	10	12
2013	CA	Mar	7	23
2013	CA	May	6	16
2013	CA	Nov	2	23
2013	CA	Oct	4	35
2013	CA	Sep	6	19
2013	CO	Feb	3	1
2013	CO	Jan	4	0
2013	CO	Jun	0	4
2013	CO	Sep	0	5
2013	CT	Dec	4	0
2013	CT	Jul	0	4
2013	CT	Oct	1	5
2013	CT	Sep	1	4
2013	DC	Jan	0	5
2013	DC	Jul	0	4
2013	DC	Mar	0	13
2013	DC	Nov	0	4
2013	DC	Sep	14	11
2013	DE	Aug	0	4
2013	DE	Dec	0	4
2013	DE	Feb	3	2
2013	DE	Sep	0	4
2013	FL	Apr	1	8
2013	FL	Aug	3	2
2013	FL	Dec	7	10
2013	FL	Feb	2	2
2013	FL	Jul	12	17
2013	FL	Mar	0	9
2013	FL	Nov	7	1
2013	FL	Oct	2	10
2013	FL	Sep	4	13
2013	GA	Feb	0	8
2013	GA	Jul	1	3
2013	GA	Jun	0	7
2013	GA	Mar	1	3
2013	GA	May	0	4
2013	GA	Nov	0	4
2013	GA	Sep	3	1
2013	IA	Mar	1	3
2013	IL	Apr	6	1
2013	IL	Aug	2	7
2013	IL	Feb	0	4
2013	IL	Jul	5	21
2013	IL	Jun	8	31
2013	IL	Mar	0	7
2013	IL	May	0	8
2013	IL	Sep	1	21
2013	IN	Aug	0	8
2013	IN	Dec	1	3
2013	IN	Jun	0	4
2013	IN	Mar	1	3
2013	IN	May	4	0
2013	IN	Nov	0	4
2013	IN	Sep	2	4
2013	KA	Apr	4	0
2013	KA	Dec	4	0
2013	KA	Nov	4	0
2013	KA	Sep	1	6
2013	KS	Jul	1	8
2013	KY	Apr	1	4
2013	KY	Aug	4	0
2013	KY	Dec	0	4
2013	KY	Jul	2	2
2013	KY	Jun	3	1
2013	KY	Nov	1	3
2013	LA	Dec	5	10
2013	LA	Feb	0	4
2013	LA	Jan	4	10
2013	LA	Jun	0	4
2013	LA	Mar	1	3
2013	LA	May	0	19
2013	MA	Apr	2	2
2013	MD	Aug	3	8
2013	MD	Jul	0	4
2013	MD	Jun	2	7
2013	ME	Jul	1	3
2013	MI	Aug	0	5
2013	MI	Dec	1	3
2013	MI	Feb	0	4
2013	MI	Jul	1	15
2013	MI	Mar	0	4
2013	MI	May	3	14
2013	MI	Nov	3	12
2013	MI	Sep	3	5
2013	MN	Aug	2	2
2013	MN	Feb	1	4
2013	MN	Jun	2	2
2013	MN	Nov	1	3
2013	Mo	Aug	1	3
2013	MO	Aug	2	6
2013	MO	Jan	1	4
2013	MO	Jun	7	20
2013	MO	Mar	1	4
2013	MO	Sep	2	6
2013	MS	Jul	0	4
2013	MS	Mar	2	2
2013	NC	Apr	0	5
2013	NC	Aug	0	4
2013	NC	Dec	0	8
2013	NC	Feb	3	5
2013	NC	Jan	2	2
2013	NC	Jul	1	3
2013	NC	Jun	0	9
2013	NC	Mar	0	4
2013	NC	May	4	4
2013	NC	Oct	3	6
2013	NC	Sep	0	12
2013	NE	Aug	4	0
2013	NE	Oct	0	4
2013	NJ	Aug	2	11
2013	NJ	Dec	4	6
2013	NJ	Jul	2	7
2013	NJ	Jun	1	4
2013	NJ	May	0	18
2013	NM	Jan	5	0
2013	NM	Jul	1	7
2013	NM	Oct	0	4
2013	NV	Dec	2	2
2013	NV	Jun	2	2
2013	NV	May	5	0
2013	NV	Oct	3	6
2013	NV	Sep	0	4
2013	NY	Aug	2	6
2013	NY	Dec	5	8
2013	NY	Jul	1	12
2013	NY	Jun	0	9
2013	NY	Mar	7	8
2013	NY	Nov	4	5
2013	NY	Oct	0	4
2013	NY	Sep	0	4
2013	OH	Apr	4	0
2013	OH	Aug	3	10
2013	OH	Dec	2	2
2013	OH	Jan	2	7
2013	OH	Jul	0	5
2013	OH	May	0	5
2013	OH	Nov	3	5
2013	OH	Sep	0	4
2013	OK	Aug	4	0
2013	OK	Feb	1	3
2013	OK	Jan	5	0
2013	OK	Jul	1	3
2013	OK	Nov	4	1
2013	OK	Oct	2	7
2013	PA	Apr	4	12
2013	PA	Aug	5	10
2013	PA	Jan	0	4
2013	PA	Jun	0	4
2013	PA	May	0	12
2013	PA	Nov	0	4
2013	PA	Oct	3	17
2013	PA	Sep	4	0
2013	PR	May	7	9
2013	RI	Jun	0	4
2013	SC	Apr	1	4
2013	SC	Aug	2	8
2013	SC	Jul	2	2
2013	SC	Jun	3	1
2013	SC	Oct	6	0
2013	TN	Dec	4	0
2013	TN	Feb	2	7
2013	TN	Jun	1	7
2013	TN	May	5	7
2013	TN	Sep	5	4
2013	TX	Aug	4	4
2013	TX	Dec	0	5
2013	TX	Jul	4	5
2013	TX	Jun	1	3
2013	TX	Mar	4	6
2013	TX	May	3	5
2013	TX	Nov	6	21
2013	TX	Oct	9	4
2013	TX	Sep	5	0
2013	UT	Feb	3	1
2013	VA	Apr	2	7
2013	VA	Aug	1	4
2013	VA	Jan	3	1
2013	VA	Jun	1	19
2013	VA	May	5	8
2013	WA	Apr	5	2
2013	WA	Jul	0	4
2013	WA	Mar	3	1
2013	WA	Sep	0	6
2013	WI	Jun	0	4
2013	WV	Dec	1	3
2013	WV	Jul	4	0
2013	WV	Sep	0	6

     kable(yr_2013_df2_inc)

year	State	month	total_incidents
2013	AL	Dec	2
2013	AL	Jan	1
2013	AL	Jul	2
2013	AL	Mar	1
2013	AL	May	1
2013	AL	Oct	1
2013	AZ	Apr	1
2013	AZ	Jan	1
2013	AZ	May	2
2013	AZ	Nov	2
2013	AZ	Oct	2
2013	CA	Apr	4
2013	CA	Aug	3
2013	CA	Dec	1
2013	CA	Feb	7
2013	CA	Jan	3
2013	CA	Jul	5
2013	CA	Jun	4
2013	CA	Mar	6
2013	CA	May	5
2013	CA	Nov	5
2013	CA	Oct	5
2013	CA	Sep	5
2013	CO	Feb	1
2013	CO	Jan	1
2013	CO	Jun	1
2013	CO	Sep	1
2013	CT	Dec	1
2013	CT	Jul	1
2013	CT	Oct	1
2013	CT	Sep	1
2013	DC	Jan	1
2013	DC	Jul	1
2013	DC	Mar	1
2013	DC	Nov	1
2013	DC	Sep	2
2013	DE	Aug	1
2013	DE	Dec	1
2013	DE	Feb	1
2013	DE	Sep	1
2013	FL	Apr	2
2013	FL	Aug	1
2013	FL	Dec	4
2013	FL	Feb	1
2013	FL	Jul	4
2013	FL	Mar	2
2013	FL	Nov	2
2013	FL	Oct	3
2013	FL	Sep	4
2013	GA	Feb	1
2013	GA	Jul	1
2013	GA	Jun	1
2013	GA	Mar	1
2013	GA	May	1
2013	GA	Nov	1
2013	GA	Sep	1
2013	IA	Mar	1
2013	IL	Apr	1
2013	IL	Aug	2
2013	IL	Feb	1
2013	IL	Jul	5
2013	IL	Jun	7
2013	IL	Mar	1
2013	IL	May	2
2013	IL	Sep	3
2013	IN	Aug	2
2013	IN	Dec	1
2013	IN	Jun	1
2013	IN	Mar	1
2013	IN	May	1
2013	IN	Nov	1
2013	IN	Sep	1
2013	KA	Apr	1
2013	KA	Dec	1
2013	KA	Nov	1
2013	KA	Sep	1
2013	KS	Jul	2
2013	KY	Apr	1
2013	KY	Aug	1
2013	KY	Dec	1
2013	KY	Jul	1
2013	KY	Jun	1
2013	KY	Nov	1
2013	LA	Dec	2
2013	LA	Feb	1
2013	LA	Jan	3
2013	LA	Jun	1
2013	LA	Mar	1
2013	LA	May	1
2013	MA	Apr	1
2013	MD	Aug	2
2013	MD	Jul	1
2013	MD	Jun	2
2013	ME	Jul	1
2013	MI	Aug	1
2013	MI	Dec	1
2013	MI	Feb	1
2013	MI	Jul	3
2013	MI	Mar	1
2013	MI	May	4
2013	MI	Nov	2
2013	MI	Sep	2
2013	MN	Aug	1
2013	MN	Feb	1
2013	MN	Jun	1
2013	MN	Nov	1
2013	Mo	Aug	1
2013	MO	Aug	2
2013	MO	Jan	1
2013	MO	Jun	5
2013	MO	Mar	1
2013	MO	Sep	2
2013	MS	Jul	1
2013	MS	Mar	1
2013	NC	Apr	1
2013	NC	Aug	1
2013	NC	Dec	2
2013	NC	Feb	2
2013	NC	Jan	1
2013	NC	Jul	1
2013	NC	Jun	2
2013	NC	Mar	1
2013	NC	May	2
2013	NC	Oct	2
2013	NC	Sep	3
2013	NE	Aug	1
2013	NE	Oct	1
2013	NJ	Aug	3
2013	NJ	Dec	2
2013	NJ	Jul	2
2013	NJ	Jun	1
2013	NJ	May	4
2013	NM	Jan	1
2013	NM	Jul	2
2013	NM	Oct	1
2013	NV	Dec	1
2013	NV	Jun	1
2013	NV	May	1
2013	NV	Oct	2
2013	NV	Sep	1
2013	NY	Aug	2
2013	NY	Dec	3
2013	NY	Jul	3
2013	NY	Jun	1
2013	NY	Mar	3
2013	NY	Nov	2
2013	NY	Oct	1
2013	NY	Sep	1
2013	OH	Apr	1
2013	OH	Aug	3
2013	OH	Dec	1
2013	OH	Jan	2
2013	OH	Jul	1
2013	OH	May	1
2013	OH	Nov	2
2013	OH	Sep	1
2013	OK	Aug	1
2013	OK	Feb	1
2013	OK	Jan	1
2013	OK	Jul	1
2013	OK	Nov	1
2013	OK	Oct	2
2013	PA	Apr	4
2013	PA	Aug	3
2013	PA	Jan	1
2013	PA	Jun	1
2013	PA	May	3
2013	PA	Nov	1
2013	PA	Oct	3
2013	PA	Sep	1
2013	PR	May	2
2013	RI	Jun	1
2013	SC	Apr	1
2013	SC	Aug	2
2013	SC	Jul	1
2013	SC	Jun	1
2013	SC	Oct	1
2013	TN	Dec	1
2013	TN	Feb	2
2013	TN	Jun	2
2013	TN	May	3
2013	TN	Sep	2
2013	TX	Aug	1
2013	TX	Dec	1
2013	TX	Jul	2
2013	TX	Jun	1
2013	TX	Mar	2
2013	TX	May	1
2013	TX	Nov	3
2013	TX	Oct	3
2013	TX	Sep	1
2013	UT	Feb	1
2013	VA	Apr	2
2013	VA	Aug	1
2013	VA	Jan	1
2013	VA	Jun	4
2013	VA	May	3
2013	WA	Apr	1
2013	WA	Jul	1
2013	WA	Mar	1
2013	WA	Sep	1
2013	WI	Jun	1
2013	WV	Dec	1
2013	WV	Jul	1
2013	WV	Sep	1

   yr_2013_df2_inc %>% 
    ggplot( aes(x=total_incidents, y=State)) + 
    geom_segment(aes(yend=State), xend=0, color='blue') + 
    geom_point(size=4, aes(color=month)) + 
    geom_text(aes(label=total_incidents), vjust=-1, hjust=.5,color='black') +
    scale_color_brewer(palette="Set2", limits=c('Jan', 'Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec')) + 
     ggtitle("Total Incidents by State and Month") +
    xlab("Incidents by month") + ylab("City")

## Warning in RColorBrewer::brewer.pal(n, pal): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

## Warning: Removed 68 rows containing missing values (geom_point).

knitr::opts_chunk$set(echo = TRUE)

Research question

Is mass shooting predictable in a State based on the prior data ?. I will be using 2013 data for analysis.

Cases

What are the cases, and how many are there?

Each case represents a City and State in the united states. There observations in the given data set.

Data collection

Describe the method of data collection.

Data is available in Buzfeed News. There are data files for each year from 2013 to 2015.

Type of study

What type of study is this (observational/experiment)?

This study is observational.

Data Source

Data is available under the below link. https://github.com/BuzzFeedNews/2015-12-mass-shooting-intervals/tree/master/data

Response

What is the response variable, and what type is it (numerical/categorical)?

Response variable is the number of incidents in a month in a city, State. It is numerical.

Explanatory

What is the explanatory variable, and what type is it (numerical/categorival)?

Number of incidents each month. Has the incidents happened each month what is the count of it. This need to be done for atleast 3 years to decide which city has highest incident and the reoccurrence chances each month.

Relevant summary statistics

Provide summary statistics relevant to your research question. For example, if you’re comparing means across groups provide means, SDs, sample sizes of each group. This step requires the use of R, hence a code chunk is provided below. Insert more code chunks as needed.

Raghu_606_Project_Proposal

Raghu Ramnath

3/11/2017