StreamCardinalityEstimation/plot_latency.r at master · Elkoumy/StreamCardinalityEstimation · 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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
library(ggplot2)
library(scales)
library(magrittr) # need to run every time you start R and want to use %>%
library(dplyr)
library(ggplot2)

query_time =read.csv("C:\\Gamal Elkoumy\\PhD\\OneDrive - Tartu Ülikool\\University of Tartu Courses\\Big Data\\CourseProject\\StreamCardinality\\Results\\query_time_result.csv")
insertion_time =read.csv("C:\\Gamal Elkoumy\\PhD\\OneDrive - Tartu Ülikool\\University of Tartu Courses\\Big Data\\CourseProject\\StreamCardinality\\Results\\insertion_time_result3_edited.csv")

query_time=na.omit(query_time)
insertion_time=na.omit(insertion_time)

# approximate=c("CKMS","Frugal","GK","MPQ","QD","SQ","SumQ","TD","CM")
# exact=c("DH", "RB","SL" , "VEB" )

approximate=c("LL","AC","HLL","LC","FM","HLLP","KMV","BF")


query_aggregate_approximate=query_time %>%
  filter(algorithm %in% approximate)%>%
  group_by(approach,algorithm,data_distribution,tps) %>%
  summarise( query_time_mean = mean(query_time_mean), query_time_median = median(query_time_median))

ggplot(query_aggregate_approximate, aes(x=algorithm , y=query_time_mean, fill=approach)) +
  geom_bar(stat="identity", position = "dodge")+
  scale_y_continuous(labels = scales::comma,trans='log10')+
  ggtitle("Approximate Algorithms Query Time")+
  labs(x="Algorithm", y="Mean of Query Time log(n sec)")+
  facet_grid(data_distribution~ tps, switch = "y")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        panel.background = element_blank(),strip.background = element_blank(),
        strip.placement = "outside",axis.text.x = element_text(angle = 90, hjust = 1))
ggsave("C:\\Gamal Elkoumy\\PhD\\OneDrive - Tartu Ülikool\\University of Tartu Courses\\Big Data\\CourseProject\\StreamCardinality\\Results\\approximate_queryTime_mean.png")

ggplot(query_aggregate_approximate, aes(x=algorithm , y=query_time_median, fill=approach)) +
  geom_bar(stat="identity", position = "dodge")+
  scale_y_continuous(labels = scales::comma,trans='log10')+
  ggtitle("Approximate Algorithms Query Time")+
  labs(x="Algorithm", y="Median of Query Time log(n sec)")+
  facet_grid(data_distribution~ tps, switch = "y")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        panel.background = element_blank(),strip.background = element_blank(),
        strip.placement = "outside",axis.text.x = element_text(angle = 90, hjust = 1))
ggsave("C:\\Gamal Elkoumy\\PhD\\OneDrive - Tartu Ülikool\\University of Tartu Courses\\Big Data\\CourseProject\\StreamCardinality\\Results\\approximate_queryTime_median.png")

#######################################################################
########## insertion time
###########################################################################

insertion_aggregate_approximate=insertion_time %>%
  filter(algorithm %in% approximate)%>%
  group_by(approach,algorithm,data_distribution,tps) %>%
  summarise( insertion_time_mean = mean(insertion_time_mean), insertion_time_median = median(insertion_time_median))

ggplot(insertion_aggregate_approximate, aes(x=algorithm , y=insertion_time_mean, fill=approach)) +
  geom_bar(stat="identity", position = "dodge")+
  # scale_y_continuous(labels = scales::comma,trans='log10')+
  ggtitle("Approximate Algorithms insertion Time")+
  labs(x="Algorithm", y="Mean of insertion Time (n sec)")+
  facet_grid(data_distribution~ tps, switch = "y")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        panel.background = element_blank(),strip.background = element_blank(),
        strip.placement = "outside",axis.text.x = element_text(angle = 90, hjust = 1))
ggsave("C:\\Gamal Elkoumy\\PhD\\OneDrive - Tartu Ülikool\\University of Tartu Courses\\Big Data\\CourseProject\\StreamCardinality\\Results\\approximate_insertionTime_mean.png")

ggplot(insertion_aggregate_approximate, aes(x=algorithm , y=insertion_time_median, fill=approach)) +
  geom_bar(stat="identity", position = "dodge")+
  # scale_y_continuous(labels = scales::comma,trans='log10')+
  ggtitle("Approximate Algorithms insertion Time")+
  labs(x="Algorithm", y="Median of insertion Time (n sec)")+
  facet_grid(data_distribution~ tps, switch = "y")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        panel.background = element_blank(),strip.background = element_blank(),
        strip.placement = "outside",axis.text.x = element_text(angle = 90, hjust = 1))
ggsave("C:\\Gamal Elkoumy\\PhD\\OneDrive - Tartu Ülikool\\University of Tartu Courses\\Big Data\\CourseProject\\StreamCardinality\\Results\\approximate_insertionTime_median.png")


#
#
#
#
#
#
# query_aggregate_exact=query_time %>%
#   filter(algorithm %in% exact & approach=="scotty")%>%
#   group_by(approach,algorithm,data_distribution,tps) %>%
#   summarise( query_time_mean = mean(query_time_mean), query_time_median = median(query_time_median))
#
# ggplot(query_aggregate_exact, aes(x=algorithm , y=query_time_mean, fill=approach)) +
#   geom_bar(stat="identity", position = "dodge")+
#   scale_y_continuous(labels = scales::comma,trans='log10')+
#   ggtitle("Exact Algorithms Query Time")+
#   labs(x="Algorithm", y="Mean of Query Time (n sec)")+
#   facet_grid(data_distribution~ tps, switch = "y")+
#   theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
#         panel.background = element_blank(),strip.background = element_blank(),
#         strip.placement = "outside")
#
#
#
# ggplot(query_aggregate_exact, aes(x=algorithm , y=query_time_median, fill=approach)) +
#   geom_bar(stat="identity", position = "dodge")+
#   scale_y_continuous(labels = scales::comma,trans='log10')+
#   ggtitle("Exact Algorithms Query Time")+
#   labs(x="Algorithm", y="Median of Query Time (n sec)")+
#   facet_grid(data_distribution~ tps, switch = "y")+
#   theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
#         panel.background = element_blank(),strip.background = element_blank(),
#         strip.placement = "outside")
#
#
#
# insertion_aggregate_exact=insertion_time %>%
#   filter(algorithm %in% exact & approach=="scotty")%>%
#   group_by(approach,algorithm,data_distribution,tps) %>%
#   summarise( insertion_time_mean = mean(insertion_time_mean), insertion_time_median = median(insertion_time_median))
#
# ggplot(insertion_aggregate_exact, aes(x=algorithm , y=insertion_time_mean, fill=approach)) +
#   geom_bar(stat="identity", position = "dodge")+
#   scale_y_continuous(labels = scales::comma,trans='log10')+
#   ggtitle("Exact Algorithms insertion Time")+
#   labs(x="Algorithm", y="Mean of insertion Time (n sec)")+
#   facet_grid(data_distribution~ tps, switch = "y")+
#   theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
#         panel.background = element_blank(),strip.background = element_blank(),
#         strip.placement = "outside")
#
#
#
# ggplot(insertion_aggregate_exact, aes(x=algorithm , y=insertion_time_median, fill=approach)) +
#   geom_bar(stat="identity", position = "dodge")+
#   scale_y_continuous(labels = scales::comma,trans='log10')+
#   ggtitle("Exact Algorithms insertion Time")+
#   labs(x="Algorithm", y="Median of insertion Time (n sec)")+
#   facet_grid(data_distribution~ tps, switch = "y")+
#   theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
#         panel.background = element_blank(),strip.background = element_blank(),
#         strip.placement = "outside")