-
Notifications
You must be signed in to change notification settings - Fork 1
/
LaundryAnalysis.Rmd
418 lines (306 loc) · 12.4 KB
/
LaundryAnalysis.Rmd
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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
---
title: "Laundry Analysis"
author: "Gabe Cederberg"
date: "2/15/2020"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(janitor)
library(tidyverse)
library(lubridate)
library(readxl)
```
```{r, echo = FALSE}
# Merging the sheets into one dataframe
a <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "10 DEWOLFE STREET") %>%
mutate(location = "10 DEWOLFE STREET") %>%
clean_names()
b <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "1201 MASS AVE 3RD FLR LR") %>%
mutate(location = "1201 MASS AVE 3RD FLR LR") %>%
clean_names()
c <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "1202 MASS AVE 4TH FLR LR") %>%
mutate(location = "1202 MASS AVE 4TH FLR LR") %>%
clean_names()
d <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "1306 MASS AVE") %>%
mutate(location = "1306 MASS AVE") %>%
clean_names()
e <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "20 DEWOLFE STREET") %>%
mutate(location = "20 DEWOLFE STREET") %>%
clean_names()
f <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "20 PRESCOTT ST") %>%
mutate(location = "20 PRESCOTT ST") %>%
clean_names()
g <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "22 PRESCOTT ST") %>%
mutate(location = "22 PRESCOTT ST") %>%
clean_names()
h <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "24 PRESCOTT ST") %>%
mutate(location = "24 PRESCOTT ST")%>%
clean_names()
i <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "65 MOUNT AUBURN STREET") %>%
mutate(location = "65 MOUNT AUBURN STREET")%>%
clean_names()
j <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "8 PLYMPTON STREET") %>%
mutate(location = "8 PLYMPTON STREET") %>%
clean_names()
k <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CABOT HOUSE - BERTRAM HALL") %>%
mutate(location = "CABOT HOUSE - BERTRAM HALL")%>%
clean_names()
l <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CABOT HOUSE - BRIGGS HALL") %>%
mutate(location = "CABOT HOUSE - BRIGGS HALL")%>%
clean_names()
m <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CABOT HOUSE - ELLIOT HALL") %>%
mutate(location = "CABOT HOUSE - ELLIOT HALL") %>%
clean_names()
n <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CABOT HOUSE - WHITMAN HALL") %>%
mutate(location = "CABOT HOUSE - WHITMAN HALL")%>%
clean_names()
o <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CURRIER HOUSE - BINGHAM HALL") %>%
mutate(location = "CURRIER HOUSE - BINGHAM HALL")%>%
clean_names()
p <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CURRIER HOUSE - DANIELS HALL") %>%
mutate(location = "CURRIER HOUSE - DANIELS HALL") %>%
clean_names()
q <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CURRIER HOUSE - GILBERT HALL") %>%
mutate(location = "CURRIER HOUSE - GILBERT HALL")%>%
clean_names()
r <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CURRIER HOUSE - TUCHMAN HALL") %>%
mutate(location = "CURRIER HOUSE - TUCHMAN HALL")%>%
clean_names()
s <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "PFORZHEIMER HOUSE - COMSTOCK HA") %>%
mutate(location = "PFORZHEIMER HOUSE - COMSTOCK HA") %>%
clean_names()
t <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "PFORZHEIMER HOUSE - HOLMES HALL") %>%
mutate(location = "PFORZHEIMER HOUSE - HOLMES HALL")%>%
clean_names()
u <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "PFORZHEIMER HOUSE - JORDAN NORT") %>%
mutate(location = "PFORZHEIMER HOUSE - JORDAN NORT")%>%
clean_names()
v <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "PFORZHEIMER HOUSE - JORDAN SOUT") %>%
mutate(location = "PFORZHEIMER HOUSE - JORDAN SOUT") %>%
clean_names()
w <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "PFORZHEIMER HOUSE - MOORS HALL") %>%
mutate(location = "PFORZHEIMER HOUSE - MOORS HALL")%>%
clean_names()
x <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "PFORZHEIMER HOUSE - WOLBACH HAL") %>%
mutate(location = "PFORZHEIMER HOUSE - WOLBACH HAL")%>%
clean_names()
y <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "ADAMS HOUSE") %>%
mutate(location = "ADAMS HOUSE") %>%
clean_names()
z <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CLAVERLY HALL") %>%
mutate(location = "CLAVERLY HALL")%>%
clean_names()
aa <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "LOWELL HOUSE D") %>%
mutate(location = "LOWELL HOUSE D")%>%
clean_names()
bb <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "LOWELL HOUSE G") %>%
mutate(location = "LOWELL HOUSE G") %>%
clean_names()
cc <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "LOWELL HOUSE N") %>%
mutate(location = "LOWELL HOUSE N")%>%
clean_names()
dd <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "NEW QUINCY-6TH FLOOR") %>%
mutate(location = "NEW QUINCY-6TH FLOOR")%>%
clean_names()
ee <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "NEW QUINCY-BASEMENT STUDENT LAU") %>%
mutate(location = "NEW QUINCY-BASEMENT STUDENT LAU") %>%
clean_names()
ff <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "STONE HALL") %>%
mutate(location = "STONE HALL")%>%
clean_names()
gg <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "DUNSTER HOUSE") %>%
mutate(location = "DUNSTER HOUSE")%>%
clean_names()
hh <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "LEVERETT HOUSE F TOWER") %>%
mutate(location = "LEVERETT HOUSE F TOWER")%>%
clean_names()
ii <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "LEVERETT HOUSE G TOWER") %>%
mutate(location = "LEVERETT HOUSE G TOWER")%>%
clean_names()
jj <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "LEVERETT HOUSE MCKINLOCK") %>%
mutate(location = "LEVERETT HOUSE MCKINLOCK")%>%
clean_names()
kk <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "MATHER HOUSE HIGH-RISE") %>%
mutate(location = "MATHER HOUSE HIGH-RISE")%>%
clean_names()
ll <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "MATHER HOUSE LOW-RISE") %>%
mutate(location = "MATHER HOUSE LOW-RISE")%>%
clean_names()
mm <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "ELIOT HOUSE J") %>%
mutate(location = "ELIOT HOUSE J")%>%
clean_names()
nn <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "KIRKLAND HOUSE G") %>%
mutate(location = "KIRKLAND HOUSE G")%>%
clean_names()
oo <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "KIRKLAND HOUSE J") %>%
mutate(location = "KIRKLAND HOUSE J")%>%
clean_names()
pp <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "WINTHROP - GORE") %>%
mutate(location = "WINTHROP - GORE")%>%
clean_names()
qq <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "WINTHROP - STANDISH") %>%
mutate(location = "WINTHROP - STANDISH")%>%
clean_names()
rr <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "APLEY COURT") %>%
mutate(location = "APLEY COURT")%>%
clean_names()
ss <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "CANADAY HALL") %>%
mutate(location = "CANADAY HALL")%>%
clean_names()
tt <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "GREENOUGH HALL") %>%
mutate(location = "GREENOUGH HALL")%>%
clean_names()
uu <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "HURLBUT HALL") %>%
mutate(location = "HURLBUT HALL")%>%
clean_names()
vv <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "MATTHEWS HALL") %>%
mutate(location = "MATTHEWS HALL")%>%
clean_names()
ww <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "STOUGHTON HALL") %>%
mutate(location = "STOUGHTON HALL")%>%
clean_names()
xx <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "THAYER HALL") %>%
mutate(location = "THAYER HALL")%>%
clean_names()
yy <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "WELD HALL") %>%
mutate(location = "WELD HALL")%>%
clean_names()
zz <- read_excel("Copy of LaundryView Data.xlsx",
sheet = "WIGGLESWORTH HALL") %>%
mutate(location = "WIGGLESWORTH HALL")%>%
clean_names()
full_data <- bind_rows(a, b, c, d, e, f, g, h, i, j, k, l, m, n, o, p, q, r, s, t, u, v, w, x, y, z,
aa, bb, cc, dd, ee, ff, gg, hh, ii, jj, kk, ll, mm, nn, oo, pp, qq, rr, ss, tt, uu, vv, ww, xx, yy, zz) %>%
select(timestamp = "timestamp",
day = "day_of_week",
time = "time_of_day",
location,
avail_wash = "available_washers",
unavail_wash = "unavailable_washers",
avail_dryers = "available_dryers",
unavail_dryers = "unavailable_dryers")
save(full_data, file ="data/full_data.Rdata")
full_data
full_data %>%
mutate(no_washers = ifelse(avail_wash == 0, 1, 0)) %>%
group_by(location, time) %>%
summarize(pct_no_wash = mean(no_washers)) %>%
mutate(pct_wash_available = 1 - pct_no_wash)
```
```{r, echo = FALSE}
test <- full_data %>%
group_by(time) %>%
mutate(avg_unav = mean(unavail_wash))
a <- full_data
```
```{r, echo = FALSE}
# Running a couple different analyses
# ggplot(test, aes(time_of_day, avg_unav)) + geom_point()
```
```{r, echo = FALSE}
ggplot(test, aes(x = time_of_day, y = avg_unav)) + geom_col(position = "dodge")
```
```{r, echo = FALSE}
busiest <- full_data %>%
group_by(location) %>%
summarize(mean_busy = mean(unavailable_washers)) %>%
arrange(desc(mean_busy))
actual_busiest <- full_data %>%
group_by(location) %>%
summarize(washers = max(available_washers),
avg_busy = mean(unavailable_washers),
adjusted = (avg_busy / washers)) %>%
arrange(desc(adjusted)) %>%
head(10)
actual_busiest
ggplot(actual_busiest, aes(time_of_day, avg_unav)) + geom_point()
busiest <- full_data %>%
filter(location == "22 PRESCOTT ST" |
location == "20 PRESCOTT ST" |
location == "ADAMS HOUSE" |
location == "NEW QUINCY-6TH FLOOR" |
location == "PFORZHEIMER HOUSE - MOORS HALL" |
location == "STONE HALL") %>%
group_by(time_of_day, location) %>%
summarize(mean_busy = mean(unavailable_washers))
ggplot(busiest, aes(time_of_day, mean_busy, color = location)) +
geom_line()
prescott22 <- full_data %>%
filter(location == "22 PRESCOTT ST")
prescott22
xy <- full_data %>%
group_by(time_of_day, location) %>%
summarize(mean_busy = mean(unavailable_washers))
ggplot(xy, aes(time_of_day, mean_busy)) +
facet_wrap(~ location) +
geom_line()
full_data
full_data %>%
```
```{r}
houses <- read_excel("houses.xlsx") %>%
clean_names()
houses %>% ggplot(aes(house, people_to_washer_ratio_5, fill = people_to_washer_ratio_5)) +
geom_col() +
theme_classic() +
labs(x = "House",
y = "Students Per Washing Machine",
title = "Student to Washer Ratio in Each House"
# subtitle = "N = 525"
) +
theme(legend.position = "none",
axis.text.x = element_text(angle = 30, vjust= .7))
ggsave("fixed_plot.jpg", plot = last_plot(), width = 8, height = 5)
```