DataVisualization_Uber_R/uber_data_visualization.R at master · shoninouye/DataVisualization_Uber_R · 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
library(ggplot2)
library(plotly)
library(ggmap)
library(plyr)
library(dplyr)

uber_apr14 <- read.csv("/Users/Shon/Documents/MyProjects/Data Science/uber data visualization/uber-pickups-in-new-york-city/uber-raw-data-apr14.csv")
###
#This produces a plotly graph showing the total rides per day.
uber_apr14$Date.Time <- as.Date(uber_apr14$Date.Time, "%m/%d/%Y")
uber_apr14$Day <- format(as.Date(uber_apr14$Date.Time, format = "%m/%d/%Y"), "%d") #adds a Day column
#counting the rides for each day
newber <- count(uber_apr14, as.numeric(Day))
colnames(newber)[1] <- "Day"
colnames(newber)[2] <- "Number of Rides"

line <- ggplot(newber, aes(x = Day, y = `Number of Rides`)) +
  geom_area(alpha = 1, position = position_dodge(width = 0.05), color = '#99cc00', fill = '#787a76') +
  xlab("Day") + ylab("Total Rides per Day") +
  ggtitle("Total Uber Rides in New York City in the month of April") +
  theme_minimal()

ggplotly(line)

###

apr14_plot <- geom_point(data = uber_apr14,
                         aes(x = Lon, y = Lat),
                         colour = '#000066',
                         size = 0.1, alpha = 0.5, na.rm = TRUE)

apr14_plot

nyMap <- qmap("New York City")

fullMap <- nyMap + apr14_plot
fullMap


###PLOT BY BASES
base_plot <- nyMap +
  geom_point(data = uber_apr14,
             mapping = aes(x = Lon, y = Lat, colour = factor(uber_apr14$Base)),
             size = 0.1, alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#008080", "#7F462c", "#FF2400", "#2B60DE", "#CA226B"))

base_plot

#COLOR:
# + scale_fill_manual(values = c("__", "___", "___"))

### SEPARATING DATA BASED ON UBER BASE ###
uber_baseB02512 <- filter(uber_apr14, Base == "B02512")
uber_baseB02598 <- filter(uber_apr14, Base == "B02598")
uber_baseB02617 <- filter(uber_apr14, Base == "B02617")
uber_baseB02682 <- filter(uber_apr14, Base == "B02682")
uber_baseB02764 <- filter(uber_apr14, Base == "B02764")

## CREATE BAR GRAPH OF UBER DATA BY BASE ###

numrow_B02512 <- nrow(uber_baseB02512)
numrow_B02598 <- nrow(uber_baseB02598)
numrow_B02617 <- nrow(uber_baseB02617)
numrow_B02682 <- nrow(uber_baseB02682)
numrow_B02764 <- nrow(uber_baseB02764)

basedata <- plot_ly(x = c("B02512", "B02598", "B02617", "B02682", "B02764"),
                    y = c(numrow_B02512, numrow_B02598, numrow_B02617, numrow_B02682, numrow_B02764),
                    name = "Uber Pickups by TLC Base Code",
                    type = "bar")
basedata


### PLOT DATA BY UBER BASE ###

#Base B02512
base_B02512 <- nyMap +
  geom_point(data = uber_baseB02512,
             mapping = aes(x = Lon, y = Lat,  colour = factor(uber_baseB02512$Base)),
             alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#008080"))

#Base B02598
base_B02598 <- nyMap +
  geom_point(data = uber_baseB02598,
             mapping = aes(x = Lon, y = Lat,  colour = factor(uber_baseB02598$Base)),
             alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#7F462c"))

#Base B02617
base_B02617 <- nyMap +
  geom_point(data = uber_baseB02617,
             mapping = aes(x = Lon, y = Lat,  colour = factor(uber_baseB02617$Base)),
             alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#FF2400"))

#Base B02682
base_B02682 <- nyMap +
  geom_point(data = uber_baseB02682,
             mapping = aes(x = Lon, y = Lat,  colour = factor(uber_baseB02682$Base)),
             alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#2B60DE"))

#Base B02764
base_B02764 <- nyMap +
  geom_point(data = uber_baseB02764,
             mapping = aes(x = Lon, y = Lat,  colour = factor(uber_baseB02764$Base)),
             alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#CA226B"))

plot(base_B02512)
plot(base_B02598)
plot(base_B02617)
plot(base_B02682)
plot(base_B02764)

ggplot(data = uber_apr14,
           aes(x = Lon, y = Lat,  colour = factor(uber_apr14$Base))) +
  geom_point(size = 0.1, alpha = 0.4, na.rm = TRUE) +
  scale_color_manual(values = c("#008080", "#7F462c", "#FF2400", "#2B60DE", "#CA226B")) +
  facet_wrap(~ Base)

#Plotyly to plot map data?

table(uber_apr14$Base)
table(uber_baseB02512$Base)