library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
df <- read.csv("/Users/manojdannana/Desktop/Manoj/IUPUI/class work/intro to statistics/datasets/Occupancy_Estimation.csv")
df$Datetime <- as.POSIXct(paste(df$Date, df$Time), format="%d/%m/%y %H:%M:%S")
Grouping Categorical Columns and Aggragating
‘Room_Occupancy_Count’
grouped_df1 <- aggregate(Room_Occupancy_Count ~ S1_Light, data=df, FUN=mean)
print(grouped_df1)
## S1_Light Room_Occupancy_Count
## 1 0 0.001026518
## 2 1 0.000000000
## 3 2 0.142857143
## 4 3 0.600000000
## 5 4 0.547826087
## 6 5 0.334532374
## 7 6 0.108108108
## 8 7 0.331034483
## 9 8 0.344827586
## 10 9 0.663716814
## 11 10 0.591743119
## 12 11 0.000000000
## 13 12 0.000000000
## 14 13 0.000000000
## 15 14 0.000000000
## 16 15 0.000000000
## 17 16 0.000000000
## 18 17 0.000000000
## 19 18 0.000000000
## 20 19 0.000000000
## 21 20 0.000000000
## 22 91 0.000000000
## 23 93 1.000000000
## 24 101 1.000000000
## 25 105 1.000000000
## 26 107 1.000000000
## 27 108 1.000000000
## 28 111 1.000000000
## 29 112 1.000000000
## 30 113 2.000000000
## 31 114 1.982456140
## 32 115 1.723076923
## 33 116 1.602941176
## 34 117 1.724489796
## 35 118 1.559523810
## 36 119 1.275590551
## 37 120 1.000000000
## 38 121 1.000000000
## 39 122 1.000000000
## 40 123 1.021739130
## 41 124 1.031250000
## 42 125 1.000000000
## 43 133 3.000000000
## 44 140 3.000000000
## 45 141 2.500000000
## 46 142 2.416666667
## 47 143 2.400000000
## 48 144 3.000000000
## 49 145 2.125000000
## 50 146 2.035714286
## 51 147 2.238095238
## 52 148 2.907407407
## 53 149 3.000000000
## 54 150 2.984210526
## 55 151 2.857142857
## 56 153 2.000000000
## 57 154 2.000000000
## 58 155 1.961538462
## 59 156 2.030303030
## 60 157 2.000000000
## 61 158 2.666666667
## 62 159 2.333333333
## 63 160 2.139534884
## 64 161 2.060606061
## 65 162 2.344827586
## 66 163 2.862068966
## 67 164 2.933333333
## 68 165 2.733333333
grouped_df2 <- aggregate(Room_Occupancy_Count ~ S6_PIR, data=df, FUN=mean)
print(grouped_df2)
## S6_PIR Room_Occupancy_Count
## 1 0 0.2204861
## 2 1 2.1960570
grouped_df3 <- aggregate(Room_Occupancy_Count ~ S7_PIR, data=df, FUN=mean)
print(grouped_df3)
## S7_PIR Room_Occupancy_Count
## 1 0 0.2159176
## 2 1 2.5111663
Identify the lowest probability group in each grouping
min_prob_group1 <- grouped_df1[which.min(grouped_df1$Room_Occupancy_Count), 'S1_Light']
print(min_prob_group1)
## [1] 1
min_prob_group2 <- grouped_df2[which.min(grouped_df2$Room_Occupancy_Count), 'S6_PIR']
print(min_prob_group2)
## [1] 0
min_prob_group3 <- grouped_df3[which.min(grouped_df3$Room_Occupancy_Count), 'S7_PIR']
print(min_prob_group3)
## [1] 0
Assigning Special Tags to Minimum Probability Groups and Appending
to main DataFrame
df$Special_Tag1 <- ifelse(df$S1_Light == min_prob_group1, 'Lowest_Prob_Group1', 'Other')
df$Special_Tag2 <- ifelse(df$S6_PIR == min_prob_group2, 'Lowest_Prob_Group2', 'Other')
df$Special_Tag3 <- ifelse(df$S7_PIR == min_prob_group3, 'Lowest_Prob_Group3', 'Other')
head(df)
## Date Time S1_Temp S2_Temp S3_Temp S4_Temp S1_Light S2_Light S3_Light
## 1 22/12/17 10:49:41 24.94 24.75 24.56 25.38 121 34 53
## 2 22/12/17 10:50:12 24.94 24.75 24.56 25.44 121 33 53
## 3 22/12/17 10:50:42 25.00 24.75 24.50 25.44 121 34 53
## 4 22/12/17 10:51:13 25.00 24.75 24.56 25.44 121 34 53
## 5 22/12/17 10:51:44 25.00 24.75 24.56 25.44 121 34 54
## 6 22/12/17 10:52:14 25.00 24.81 24.56 25.44 121 34 54
## S4_Light S1_Sound S2_Sound S3_Sound S4_Sound S5_CO2 S5_CO2_Slope S6_PIR
## 1 40 0.08 0.19 0.06 0.06 390 0.7692308 0
## 2 40 0.93 0.05 0.06 0.06 390 0.6461538 0
## 3 40 0.43 0.11 0.08 0.06 390 0.5192308 0
## 4 40 0.41 0.10 0.10 0.09 390 0.3884615 0
## 5 40 0.18 0.06 0.06 0.06 390 0.2538462 0
## 6 40 0.13 0.06 0.06 0.07 390 0.1653846 0
## S7_PIR Room_Occupancy_Count Datetime Special_Tag1
## 1 0 1 2017-12-22 10:49:41 Other
## 2 0 1 2017-12-22 10:50:12 Other
## 3 0 1 2017-12-22 10:50:42 Other
## 4 0 1 2017-12-22 10:51:13 Other
## 5 0 1 2017-12-22 10:51:44 Other
## 6 0 1 2017-12-22 10:52:14 Other
## Special_Tag2 Special_Tag3
## 1 Lowest_Prob_Group2 Lowest_Prob_Group3
## 2 Lowest_Prob_Group2 Lowest_Prob_Group3
## 3 Lowest_Prob_Group2 Lowest_Prob_Group3
## 4 Lowest_Prob_Group2 Lowest_Prob_Group3
## 5 Lowest_Prob_Group2 Lowest_Prob_Group3
## 6 Lowest_Prob_Group2 Lowest_Prob_Group3
Visualizations for all groups
library(ggplot2)
ggplot(grouped_df1, aes(x=S1_Light, y=Room_Occupancy_Count)) +
geom_bar(stat='identity') +
labs(title='Average Room Occupancy Count by S1_Light')
ggplot(grouped_df2, aes(x=S6_PIR, y=Room_Occupancy_Count)) +
geom_bar(stat='identity') +
labs(title='Average Room Occupancy Count by S6_PIR')
ggplot(grouped_df3, aes(x=S7_PIR, y=Room_Occupancy_Count)) +
geom_bar(stat='identity') +
labs(title='Average Room Occupancy Count by S7_PIR')
Hypothesis based on Lowest Probability Groups
- The occupancy of the room is low when the temperature of the rooms
are low.
- The lower probability group of S6_PIR might indicate that the rooms
which have no motion being detected might have very low to no
occupancy.
- The lower probability group of S6_PIR and S7_PIR both indicate that
the rooms which have no motion being detected might have very low to no
occupancy.
Finding a combination for S1_Light and S6_PIR that doesn’t
exist
all_combinations <- expand.grid(unique(df$S1_Light), unique(df$S6_PIR))
all_combinations_string <- paste(as.character(all_combinations$Var1), as.character(all_combinations$Var2), sep="_")
existing_combinations_string <- paste(df$S1_Light, df$S6_PIR, sep="_")
missing_combinations <- setdiff(all_combinations_string, existing_combinations_string)
print(missing_combinations)
## [1] "101_0" "153_0" "107_0" "140_0" "93_0" "108_0" "154_0" "91_0" "105_0"
## [10] "133_0" "144_0" "20_1" "17_1" "15_1" "112_1" "1_1" "125_1" "111_1"
Reasons for missing combinations
- From some of the missing combinations of S1_Light and S6_PIR and It
seems that at very high luminosity the rooms might not be occupied and
hence motion wasn’t detected or that the data collected didn’t just
record for these observations.
Most Frequent and In-Frequent Combinations
combination_freq <- table(paste(df$S1_Light, df$S6_PIR))
most_common_combination <- names(combination_freq)[which.max(combination_freq)]
least_common_combination <- names(combination_freq)[which.min(combination_freq)]
print(most_common_combination)
## [1] "0 0"
print(least_common_combination)
## [1] "101 1"
Observations
- It seems that most of our observations were taken in a dark room
hence there is no motion detected.
- It seems that higher luminous rooms have motion detected. This
occurred the least number of times simply because the observations at
that combination weren’t recorded.
Visualization
subset_df <- df[df$S1_Light == 101 & df$S6_PIR == 1, ]
# Create a bar plot
ggplot(subset_df, aes(x = factor(Room_Occupancy_Count), fill = factor(Room_Occupancy_Count))) +
geom_bar() +
labs(title = 'Room Occupancy Count for Least Common Combination', x = 'Room Occupancy Count', y = 'Frequency')
All the insights and observations have been written below each
cell