-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path2.Taph_Setup.R
308 lines (241 loc) · 10.6 KB
/
2.Taph_Setup.R
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
################################################################################
######## TAPHONOMIC CONTROLS ON A MULTI-ELEMENT SKELETAL FOSSIL RECORD #########
################################################################################
# Jeffrey R. Thompson, Christopher D. Dean, Madeline Ford, Timothy A. M. Ewin
# 2024
# Script written by Christopher D. Dean
################################################################################
# FILE 2: SETUP #
################################################################################
################################################################################
# 1. SETUP
################################################################################
# Set working directory
setwd(dirname(rstudioapi::getActiveDocumentContext()$path))
# Load data
m.dat <- read.csv("Specimen_data/Final_Database_for_analysis.csv")
m.dat[m.dat == "?"] <- NA
m.dat[m.dat == ""] <- NA
# Remove occurrences without taph. grade and Triassic occurrences
m.dat <- m.dat %>%
filter(Max_period != "Triassic") %>%
filter(Min_period != "Triassic") %>%
filter(Max_period != "Triassic/Jurassic") %>%
filter(Min_period != "Triassic/Jurassic") %>%
filter(Max_period != "Jurassic") %>%
filter(Min_period != "Jurassic") %>%
filter(is.na(Preservation_score) == F)
# Sort stages - Deeptime
data(stages)
data(periods)
names(stages)[names(stages) == "max_age"] <- "max_ma"
names(stages)[names(stages) == "min_age"] <- "min_ma"
stages$bin <- 1:nrow(stages)
# Resolve promise
periods
################################################################################
# 2. ASSIGNING AGES
################################################################################
# Separate datasets
period <- m.dat %>%
dplyr::filter(Age_resolution == "Period" | Age_resolution == "Series")
stage <- m.dat %>%
dplyr::filter(Age_resolution == "Stage")
# Assign numerical ages to periods
names(period)[names(period) == "Max_period"] <- "max_ma"
names(period)[names(period) == "Min_period"] <- "min_ma"
period <- look_up(occdf = period, early_interval = "max_ma", late_interval = "min_ma")
# Assign numerical ages to stages
names(stage)[names(stage) == "max_stage"] <- "max_ma"
names(stage)[names(stage) == "min_stage"] <- "min_ma"
stage <- look_up(occdf = stage, early_interval = "max_ma", late_interval = "min_ma")
# Reorganise column headings
stage <- stage[,-c(31:32)]
period <- period[,-c(31:32)]
colnames(period)[29:30] <- c("Max_period", "Min_period")
# Bind datasets
m.dat <- rbind(period, stage)
# Rename columns
names(m.dat)[names(m.dat) == "interval_max_ma"] <- "max_ma"
names(m.dat)[names(m.dat) == "interval_min_ma"] <- "min_ma"
# Remove NAs (NOTE CAN REMOVE THIS LATER!)
m.dat <- m.dat %>%
filter(is.na(max_ma) == F)
# Assign occurrences to bins
m.dat <- bin_time(occdf = m.dat, bins = stages, method = 'majority')
# Create factors for later
order_ind <- c("Permian", "Pennsylvanian", "Mississippian", "Devonian", "Silurian", "Ordovician")
m.dat$Max_period <- as.factor(m.dat$Max_period)
m.dat$Min_period <- as.factor(m.dat$Min_period)
m.dat$Min_period <- factor(m.dat$Max_period, levels = order_ind)
m.dat$Min_period <- factor(m.dat$Min_period, levels = order_ind)
# Load periods and rename columns for binning
data(periods)
colnames(periods)[1] <- "bin"
colnames(periods)[2] <- "max_ma"
colnames(periods)[3] <- "min_ma"
##### PERIOD LEVEL TIME #####
# Bin into periods
m.dat.period <- bin_time(occdf = m.dat, bins = periods, method = 'majority')
# Create factors
order_ind <- c("Permian", "Carboniferous", "Devonian", "Silurian", "Ordovician")
m.dat.period$bin_assignment <- as.factor(m.dat.period$bin_assignment)
m.dat.period$bin_assignment <- factor(m.dat.period$bin_assignment, levels = order_ind)
# Load period colour information
df <- palaeoverse::GTS2020
df <- df[155:159,]
myColours <- df$colour
# Assign colours
names(myColours) <- levels(m.dat.period$bin_assignment)
custom_colours <- scale_colour_manual(name = "bin_assignment", values = myColours[1:5])
##### SERIES LEVEL TIME #####
# Load series data
series <- read.csv("Additional_data/series.csv")
# Bin into series
order_ind <- c("Permian", "Pennsylvanian", "Mississippian", "Devonian", "Silurian", "Ordovician")
m.dat.series <- palaeoverse::bin_time(occdf = m.dat, bins = series, method = 'majority')
m.dat.series$bin_assignment <- as.factor(m.dat.series$bin_assignment)
m.dat.series$bin_assignment <- factor(m.dat.series$bin_assignment, levels = order_ind)
# Assign colours
myColours <- series$color
names(myColours) <- levels(m.dat.series$bin_assignment)
custom_colours <- scale_colour_manual(name = "bin_assignment", values = myColours[1:6])
# Adjust names for gggeo_scale
series2 <- series %>%
dplyr::rename(name = bin,
max_age = max_ma,
min_age = min_ma)
################################################################################
# 3. PALAEOROTATION
################################################################################
# Filter for specimens which have geographic coords and make numeric
m.dat.rotate <- m.dat %>%
filter(is.na(lat) != T)
m.dat.rotate$lat <- as.numeric(m.dat.rotate$lat)
m.dat.rotate$lng <- as.numeric(m.dat.rotate$lng)
# Palaeorotate
m.dat.rotate <- palaeorotate(m.dat.rotate,
lng = 'lng',
lat = 'lat',
age = "bin_midpoint",
model = "PALEOMAP",
method = "point")
##### LAT/P-LAT BINS #####
# Filter for specimens without palaeo lat
m.dat.rotate <- m.dat.rotate %>%
dplyr::filter(is.na(p_lat) == F)
# Make lat bins
lbins <- lat_bins_degrees(size = 20)
# Bin palaeolatitude
m.dat.rotate <- bin_lat(occdf = m.dat.rotate, bins = lbins, lat = "p_lat")
# Change column names
names(m.dat.rotate)[names(m.dat.rotate) == 'lat_bin'] <- "p_lat_bin"
names(m.dat.rotate)[names(m.dat.rotate) == 'lat_max'] <- "p_lat_max"
names(m.dat.rotate)[names(m.dat.rotate) == 'lat_mid'] <- "p_lat_mid"
names(m.dat.rotate)[names(m.dat.rotate) == 'lat_min'] <- "p_lat_min"
# Bin latitude
m.dat.rotate <- bin_lat(occdf = m.dat.rotate, bins = lbins, lat = "lat")
# Make label
lbins$label <- paste(lbins$min, " to ", lbins$max, sep = "")
# Make new column for palaeo lat. bin categories
m.dat.rotate$p_lat_bin_2 <- lbins$label[match(m.dat.rotate$p_lat_bin, lbins$bin)]
order_ind <- rev(lbins$label)
m.dat.rotate$p_lat_bin_2 <- factor(m.dat.rotate$p_lat_bin_2, levels = order_ind)
# Make new column for palaeo lat. bin categories
m.dat.rotate$lat_bin_2 <- lbins$label[match(m.dat.rotate$lat_bin, lbins$bin)]
m.dat.rotate$lat_bin_2 <- factor(m.dat.rotate$lat_bin_2, levels = order_ind)
################################################################################
# 4. MACROSTRAT SETUP
################################################################################
# Read in data using rmacrostrat
carb.macro <- get_units(lithology_type = "carbonate", environ_class = "marine")
sili.macro <- get_units(lithology_type = "siliciclastic", environ_class = "marine")
# Change column names
names(carb.macro)[names(carb.macro) == 't_age'] <- "min_ma"
names(carb.macro)[names(carb.macro) == 'b_age'] <- "max_ma"
names(sili.macro)[names(sili.macro) == 't_age'] <- "min_ma"
names(sili.macro)[names(sili.macro) == 'b_age'] <- "max_ma"
# Filter to relevant data
carb.macro <- carb.macro %>%
filter(max_ma < 485.41) %>%
filter(min_ma > 251.901)
sili.macro <- sili.macro %>%
filter(max_ma < 485.40) %>%
filter(min_ma > 251.901)
##### STAGE #####
# Bin data
carb.macro <- bin_time(occdf = carb.macro, bins = stages, method = "all")
sili.macro <- bin_time(occdf = sili.macro, bins = stages, method = "all")
# Count
carb.macro.count <- carb.macro %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = n(), lith = "carb")
sili.macro.count <- sili.macro %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = n(), lith = "sili")
# Col_area
carb.macro.area <- carb.macro %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = sum(col_area), lith = "carb")
sili.macro.area <- sili.macro %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = sum(col_area), lith = "sili")
macro.area <- rbind(carb.macro.area, sili.macro.area)
macro.count <- rbind(carb.macro.count, sili.macro.count)
##### PERIOD #####
# Bin data
carb.macro.period <- bin_time(occdf = carb.macro, bins = series, method = "majority")
sili.macro.period <- bin_time(occdf = sili.macro, bins = series, method = "majority")
# Count
carb.macro.count.period <- carb.macro.period %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = n(), lith = "carb")
sili.macro.count.period <- sili.macro.period %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = n(), lith = "sili")
# Col_area
carb.macro.area.period <- carb.macro.period %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = sum(col_area), lith = "carb")
sili.macro.area.period <- sili.macro.period %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarise(count = sum(col_area), lith = "sili")
macro.area.period <- rbind(carb.macro.area.period, sili.macro.area.period)
macro.count.period <- rbind(carb.macro.count.period, sili.macro.count.period)
################################################################################
# 5. SETUP FOR ANALYSIS
################################################################################
##### LITHOLOGY #####
# Remove data without lithological info
l.m.dat <- m.dat %>%
filter(is.na(Finalised_lith) == F)
##### GRAIN SIZE #####
# Make dataset for grain size
g.m.dat <- m.dat %>%
filter(is.na(Finalised_grainsize) == F)
# Assign specific grain size categories into either "Fine Grained" or "Coarse Grained"
g.m.dat <- simple.grain(g.m.dat)
# Remove remaining specimens without grain size
g.m.dat <- g.m.dat %>%
filter(is.na(Finalised_grainsize) == F)
##### FAMILY #####
# Make plot of preservation scores against family, NA values removed
f.m.dat <- m.dat %>%
filter(is.na(Family) == F) %>%
#filter(Family != 'Triadotiaridae') %>%
#filter(Family != 'Cravenechinidae') %>%
filter(Family != 'Archaeocidaridae or miocidaridae')
################################################################################
# 6. ADDITIONAL DATA
################################################################################
# Sea level
sea.lvl <- read.csv("Additional_data/vanderMeer_2022.csv")
sea.lvl$max_ma <- sea.lvl$Ma+0.0001
names(sea.lvl)[names(sea.lvl) == "Ma"] <- "min_ma"
sea.lvl <- sea.lvl %>%
dplyr::filter(max_ma < 538) %>%
dplyr::filter(min_ma > 0)
sea.lvl <- bin_time(occdf = sea.lvl, bins = stages, method = "mid")
sea.lvl <- sea.lvl %>%
dplyr::group_by(bin_midpoint) %>%
dplyr::summarize(mean_sl = mean(TGE_SL_isocorr_m))