ExData_Plotting1/plot3.R at master · fengkehh/ExData_Plotting1 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
## Plot line graph of energy sub meterings vs datetimes
## Assumes household_power_consumption.txt is in the current work folder.
##
## ARGUMENTS:
## file: filepath to txt holding the data.
##
## device: graphical output device (default to png). The only other accetable
## value is 'display'
##
## data: optional argument to pass in formatted dataframe object for the plot

plot3 <- function(file = 'household_power_consumption.txt', device='png',
                  data = NULL) {

    # Date when data was downloaded if the internal download routine was used.
    file_name <- 'Existing data used.'

    # check if file exists. If it doesn't, try default. If still fails,
    # download & extract, then set file back to default.
    if (!file.exists(file)) {
        if (!file.exists('household_power_consumption.txt')) {
            # Set file name to the download date.
            file_name <- paste(as.Date(Sys.time()), '.zip')

            download.file('https://d396qusza40orc.cloudfront.net/exdata%2Fdata%2Fhousehold_power_consumption.zip',
                          destfile = file_name)

            unzip(file_name)
        }


        file <- 'household_power_consumption.txt'

    }

    ## Data parser to read the Electric power consumption data
    ## Hardcoded to start from the first entry on 2007-02-01 and stop at last
    ## entry for 2007-02-02.
    ##
    ##
    ## ARGUMENTS
    ## file: string indicating file path to the txt file holding the data.
    ##
    ## RETURNS
    ## data: parsed data stored in a table
    data_parser <- function(file = 'household_power_consumption.txt') {

        # Compute number of lines that must be skipped.
        txt <- readLines(file)

        # grep matching date string using regexp for both 2007-02-01 and 2007-02-02
        grep_result <- grep('^[12]/2/2007', txt)

        # number of lines to skip is right before the first matched index
        skip_num <- grep_result[1] - 1

        # number of lines to read is just the number of index matched
        nrows <- length(grep_result)

        # Only really start reading when the line starts with the starting date.
        raw_data <- read.table(file, skip = skip_num, nrows = nrows, header = FALSE,
                               sep = ';', na.strings = '?')

        # add the column names
        colnames(raw_data) <- names(read.table(file, nrows = 1, header = TRUE,
                                               sep = ';'))

        # Create time stamps from raw_data using datetime objects
        Timestamps <- strptime(mapply(paste, raw_data$Date, raw_data$Time,
                                      MoreArgs = list(sep = ' '), SIMPLIFY = TRUE),
                               format = '%d/%m/%Y %H:%M:%S', tz = 'GMT')


        # Create new data frame with R datetime objects within range
        data <- data.frame(Timestamps, raw_data[3:length(raw_data)])

    }


    if (device == 'png' || device == 'display') {

        if (is.null(data)) {
            # Parse data
            data <- data_parser(file)
        }

        if (device == 'png') {
            # open PNG device
            png('plot3.png')
        }

        # Plot line graphs

        # color array
        cols <- c('black', 'red', 'blue')

        # submeter 1 and set up y label
        plot(data$Timestamps, data$Sub_metering_1, type = 'l', col = cols[1],
             ylab = 'Energy sub metering', xlab = '')

        # submeter 2
        lines(data$Timestamps, data$Sub_metering_2, type = 'l', col = cols[2])

        # submeter 3
        lines(data$Timestamps, data$Sub_metering_3, type = 'l', col = cols[3])

        # add legend
        legend('topright', legend =
                   names(data)[(length(names(data)) - 2):length(names(data))],
               col = cols, lty = 1)

        if (device == 'png') {
            # save and close device
            dev.off()
        }
    } else {
        stop('invalid graphic device')
    }

    # Return name of the current data zip or mention existing data used.
    file_name
}