Organized Exploratory Data Analysis into common format

mritunjay31591 · Mar 1, 2017 · d745451 · d745451
1 parent 44cd33f
commit d745451
Show file tree

Hide file tree

Showing 21 changed files with 429 additions and 2 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/4_Exploratory_Data_Analysis/.DS_Store b/4_Exploratory_Data_Analysis/.DS_Store
diff --git a/4_Exploratory_Data_Analysis/README.md b/4_Exploratory_Data_Analysis/README.md
@@ -5,12 +5,12 @@ Author: Michael Galarnyk <br />
 
 Project # | Link 
 --- | --- 
-1 |  [Exploratory Data Analysis Project 1](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/README.md)
+1 |  [Exploratory Data Analysis Project 1](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project1/README.md)
 
 ## Quizzes
 Quiz # | Link 
 --- | --- 
-1 | [Quiz](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/quiz_week1.R)
+1 | [Quiz](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/quizzes/quiz_week1.R)
 
 ## Contributors
 FirstName | LastName | Email

diff --git a/4_Exploratory_Data_Analysis/data/.DS_Store b/4_Exploratory_Data_Analysis/data/.DS_Store
diff --git a/...ploratory_Data_Analysis/project/README.md → 4_Exploratory_Data_Analysis/data/README.md b/...ploratory_Data_Analysis/project/README.md → 4_Exploratory_Data_Analysis/data/README.md
diff --git a/...ploratory_Data_Analysis/project/plot1.png → ...ratory_Data_Analysis/data/placeholder.png b/...ploratory_Data_Analysis/project/plot1.png → ...ratory_Data_Analysis/data/placeholder.png
diff --git a/4_Exploratory_Data_Analysis/project1/.DS_Store b/4_Exploratory_Data_Analysis/project1/.DS_Store
diff --git a/4_Exploratory_Data_Analysis/project1/README.md b/4_Exploratory_Data_Analysis/project1/README.md
@@ -0,0 +1,142 @@
+## Exploratory Data Analysis Project 1
+
+This assignment uses data from the UC Irvine Machine Learning Repository, a popular repository for machine learning datasets. In particular, we will be using the “Individual household electric power consumption Data Set” which I have made available on the course web site:
+
+Dataset:
+[Electric power consumption](https://d396qusza40orc.cloudfront.net/exdata%2Fdata%2Fhousehold_power_consumption.zip) [20Mb]
+</br>Description: Measurements of electric power consumption in one household with a one-minute sampling rate over a period of almost 4 years. Different electrical quantities and some sub-metering values are available.
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+                             )
+
+# Prevents histogram from printing in scientific notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Change Date Column to Date Type
+powerDT[, Date := lapply(.SD, as.Date, "%d/%m/%Y"), .SDcols = c("Date")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(Date >= "2007-02-01") & (Date <= "2007-02-02")]
+
+png("plot1.png", width=480, height=480)
+
+## Plot 1
+hist(powerDT[, Global_active_power], main="Global Active Power", 
+     xlab="Global Active Power (kilowatts)", ylab="Frequency", col="Red")
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot1.png)
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+)
+
+# Prevents Scientific Notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Making a POSIXct date capable of being filtered and graphed by time of day
+powerDT[, dateTime := as.POSIXct(paste(Date, Time), format = "%d/%m/%Y %H:%M:%S")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(dateTime >= "2007-02-01") & (dateTime < "2007-02-03")]
+
+png("plot2.png", width=480, height=480)
+
+## Plot 2
+plot(x = powerDT[, dateTime]
+     , y = powerDT[, Global_active_power]
+     , type="l", xlab="", ylab="Global Active Power (kilowatts)")
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot2.png)
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+)
+
+# Prevents Scientific Notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Making a POSIXct date capable of being filtered and graphed by time of day
+powerDT[, dateTime := as.POSIXct(paste(Date, Time), format = "%d/%m/%Y %H:%M:%S")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(dateTime >= "2007-02-01") & (dateTime < "2007-02-03")]
+
+png("plot3.png", width=480, height=480)
+
+# Plot 3
+plot(powerDT[, dateTime], powerDT[, Sub_metering_1], type="l", xlab="", ylab="Energy sub metering")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_2],col="red")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_3],col="blue")
+legend("topright"
+       , col=c("black","red","blue")
+       , c("Sub_metering_1  ","Sub_metering_2  ", "Sub_metering_3  ")
+       ,lty=c(1,1), lwd=c(1,1))
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot3.png)
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+)
+
+# Prevents Scientific Notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Making a POSIXct date capable of being filtered and graphed by time of day
+powerDT[, dateTime := as.POSIXct(paste(Date, Time), format = "%d/%m/%Y %H:%M:%S")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(dateTime >= "2007-02-01") & (dateTime < "2007-02-03")]
+
+png("plot4.png", width=480, height=480)
+
+par(mfrow=c(2,2))
+
+# Plot 1
+plot(powerDT[, dateTime], powerDT[, Global_active_power], type="l", xlab="", ylab="Global Active Power")
+
+# Plot 2
+plot(powerDT[, dateTime],powerDT[, Voltage], type="l", xlab="datetime", ylab="Voltage")
+
+# Plot 3
+plot(powerDT[, dateTime], powerDT[, Sub_metering_1], type="l", xlab="", ylab="Energy sub metering")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_2], col="red")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_3],col="blue")
+legend("topright", col=c("black","red","blue")
+       , c("Sub_metering_1  ","Sub_metering_2  ", "Sub_metering_3  ")
+       , lty=c(1,1)
+       , bty="n"
+       , cex=.5) 
+
+# Plot 4
+plot(powerDT[, dateTime], powerDT[,Global_reactive_power], type="l", xlab="datetime", ylab="Global_reactive_power")
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot4.png)
diff --git a/4_Exploratory_Data_Analysis/project/plot1.R → 4_Exploratory_Data_Analysis/project1/plot1.R b/4_Exploratory_Data_Analysis/project/plot1.R → 4_Exploratory_Data_Analysis/project1/plot1.R
diff --git a/4_Exploratory_Data_Analysis/project1/plot1.png b/4_Exploratory_Data_Analysis/project1/plot1.png
diff --git a/4_Exploratory_Data_Analysis/project/plot2.R → 4_Exploratory_Data_Analysis/project1/plot2.R b/4_Exploratory_Data_Analysis/project/plot2.R → 4_Exploratory_Data_Analysis/project1/plot2.R
diff --git a/...ploratory_Data_Analysis/project/plot2.png → ...loratory_Data_Analysis/project1/plot2.png b/...ploratory_Data_Analysis/project/plot2.png → ...loratory_Data_Analysis/project1/plot2.png
diff --git a/4_Exploratory_Data_Analysis/project/plot3.R → 4_Exploratory_Data_Analysis/project1/plot3.R b/4_Exploratory_Data_Analysis/project/plot3.R → 4_Exploratory_Data_Analysis/project1/plot3.R
diff --git a/...ploratory_Data_Analysis/project/plot3.png → ...loratory_Data_Analysis/project1/plot3.png b/...ploratory_Data_Analysis/project/plot3.png → ...loratory_Data_Analysis/project1/plot3.png
diff --git a/4_Exploratory_Data_Analysis/project/plot4.R → 4_Exploratory_Data_Analysis/project1/plot4.R b/4_Exploratory_Data_Analysis/project/plot4.R → 4_Exploratory_Data_Analysis/project1/plot4.R
diff --git a/...ploratory_Data_Analysis/project/plot4.png → ...loratory_Data_Analysis/project1/plot4.png b/...ploratory_Data_Analysis/project/plot4.png → ...loratory_Data_Analysis/project1/plot4.png
diff --git a/4_Exploratory_Data_Analysis/quizzes/.DS_Store b/4_Exploratory_Data_Analysis/quizzes/.DS_Store
diff --git a/4_Exploratory_Data_Analysis/quizzes/README.md b/4_Exploratory_Data_Analysis/quizzes/README.md
@@ -0,0 +1,142 @@
+## Exploratory Data Analysis Project 1
+
+This assignment uses data from the UC Irvine Machine Learning Repository, a popular repository for machine learning datasets. In particular, we will be using the “Individual household electric power consumption Data Set” which I have made available on the course web site:
+
+Dataset:
+[Electric power consumption](https://d396qusza40orc.cloudfront.net/exdata%2Fdata%2Fhousehold_power_consumption.zip) [20Mb]
+</br>Description: Measurements of electric power consumption in one household with a one-minute sampling rate over a period of almost 4 years. Different electrical quantities and some sub-metering values are available.
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+                             )
+
+# Prevents histogram from printing in scientific notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Change Date Column to Date Type
+powerDT[, Date := lapply(.SD, as.Date, "%d/%m/%Y"), .SDcols = c("Date")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(Date >= "2007-02-01") & (Date <= "2007-02-02")]
+
+png("plot1.png", width=480, height=480)
+
+## Plot 1
+hist(powerDT[, Global_active_power], main="Global Active Power", 
+     xlab="Global Active Power (kilowatts)", ylab="Frequency", col="Red")
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot1.png)
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+)
+
+# Prevents Scientific Notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Making a POSIXct date capable of being filtered and graphed by time of day
+powerDT[, dateTime := as.POSIXct(paste(Date, Time), format = "%d/%m/%Y %H:%M:%S")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(dateTime >= "2007-02-01") & (dateTime < "2007-02-03")]
+
+png("plot2.png", width=480, height=480)
+
+## Plot 2
+plot(x = powerDT[, dateTime]
+     , y = powerDT[, Global_active_power]
+     , type="l", xlab="", ylab="Global Active Power (kilowatts)")
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot2.png)
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+)
+
+# Prevents Scientific Notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Making a POSIXct date capable of being filtered and graphed by time of day
+powerDT[, dateTime := as.POSIXct(paste(Date, Time), format = "%d/%m/%Y %H:%M:%S")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(dateTime >= "2007-02-01") & (dateTime < "2007-02-03")]
+
+png("plot3.png", width=480, height=480)
+
+# Plot 3
+plot(powerDT[, dateTime], powerDT[, Sub_metering_1], type="l", xlab="", ylab="Energy sub metering")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_2],col="red")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_3],col="blue")
+legend("topright"
+       , col=c("black","red","blue")
+       , c("Sub_metering_1  ","Sub_metering_2  ", "Sub_metering_3  ")
+       ,lty=c(1,1), lwd=c(1,1))
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot3.png)
+```R
+library("data.table")
+
+setwd("~/Desktop/datasciencecoursera/4_Exploratory_Data_Analysis/project/data")
+
+#Reads in data from file then subsets data for specified dates
+powerDT <- data.table::fread(input = "household_power_consumption.txt"
+                             , na.strings="?"
+)
+
+# Prevents Scientific Notation
+powerDT[, Global_active_power := lapply(.SD, as.numeric), .SDcols = c("Global_active_power")]
+
+# Making a POSIXct date capable of being filtered and graphed by time of day
+powerDT[, dateTime := as.POSIXct(paste(Date, Time), format = "%d/%m/%Y %H:%M:%S")]
+
+# Filter Dates for 2007-02-01 and 2007-02-02
+powerDT <- powerDT[(dateTime >= "2007-02-01") & (dateTime < "2007-02-03")]
+
+png("plot4.png", width=480, height=480)
+
+par(mfrow=c(2,2))
+
+# Plot 1
+plot(powerDT[, dateTime], powerDT[, Global_active_power], type="l", xlab="", ylab="Global Active Power")
+
+# Plot 2
+plot(powerDT[, dateTime],powerDT[, Voltage], type="l", xlab="datetime", ylab="Voltage")
+
+# Plot 3
+plot(powerDT[, dateTime], powerDT[, Sub_metering_1], type="l", xlab="", ylab="Energy sub metering")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_2], col="red")
+lines(powerDT[, dateTime], powerDT[, Sub_metering_3],col="blue")
+legend("topright", col=c("black","red","blue")
+       , c("Sub_metering_1  ","Sub_metering_2  ", "Sub_metering_3  ")
+       , lty=c(1,1)
+       , bty="n"
+       , cex=.5) 
+
+# Plot 4
+plot(powerDT[, dateTime], powerDT[,Global_reactive_power], type="l", xlab="datetime", ylab="Global_reactive_power")
+
+dev.off()
+```
+![](https://github.com/mGalarnyk/datasciencecoursera/blob/master/4_Exploratory_Data_Analysis/project/plot4.png)
diff --git a/4_Exploratory_Data_Analysis/quizzes/placeholder.png b/4_Exploratory_Data_Analysis/quizzes/placeholder.png