-
Notifications
You must be signed in to change notification settings - Fork 0
/
renamer.py
282 lines (244 loc) · 9.82 KB
/
renamer.py
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
"""
Arguments: input_file.csv [corelist.csv]
You can specify a core list file name, but if none is specified it looks for a file
in the same directory named corelist.csv to use. It will fail if no file is
specified and corelist.csv doesn't exist.
Examples:
$ python3 renamer.py DCH_MSCL_raw.csv
$ python3 renamer.py YLAKE_XYZ.csv YLAKE_core_list.csv
Incorrect command line usage will print an explanation.
"""
import argparse
import csv
import locale
import timeit
import chardet
version = "1.2.1"
def guess_file_encoding(input_file, verbose=False):
with open(input_file, "rb") as f:
rawdata = f.read()
enc = chardet.detect(rawdata)
if verbose:
print(f'Guess on encoding of {input_file}: {enc["encoding"]}')
return enc["encoding"]
def apply_names(input_file, core_list_filename, **kwargs):
verbose = kwargs["verbose"] if "verbose" in kwargs else False
if verbose:
start_time = timeit.default_timer()
# Default values
header_row = 0
units_row = 1
start_row = 2
### Import the data
mscl_data = []
section_list = []
enc = guess_file_encoding(input_file, verbose)
with open(input_file, "r", encoding=enc) as f:
mscl_data = [r.strip().split(",") for r in f.read().splitlines()]
# Find the section number column:
# 1) check if it was passed via command line/GUI
# 2) search the row of headers for one of the expected names
# 3) if neither of those succeed, exit and print an error message
if "section_column" in kwargs and kwargs["section_column"]:
section_column = kwargs["section_column"]
if verbose:
print(f"Section column passed at command line: {section_column}")
else:
for col_name in ["SECT NUM", "Section", "SectionID"]:
if col_name in mscl_data[header_row]:
section_column = mscl_data[header_row].index(col_name)
if verbose:
print(
f"Section number column found in column {section_column} with name '{col_name}'"
)
break
else:
print(
"ERROR: Cannot find section number column. Please change section number column name to 'Section', 'SectionID', or 'SECT NUM'."
)
exit(1)
# Find the section depth column:
# 1) check if it was passed via command line/GUI
# 2) search the row of headers for one of the expected names
# 3) if neither of those succeed, exit and print an error message
if "depth_column" in kwargs and kwargs["depth_column"]:
section_depth_column = kwargs["depth_column"]
if verbose:
print(
f"Section depth column passed at command line: {section_depth_column}"
)
else:
for col_name in ["Section Depth", "SECT DEPTH"]:
if col_name in mscl_data[header_row]:
section_depth_column = mscl_data[header_row].index(col_name)
if verbose:
print(
f"Section depth column found in column {section_depth_column} with name '{col_name}'"
)
break
else:
print(
"ERROR: Cannot find section depth column. Please change section number column name to 'Section Depth' or 'SECT DEPTH'."
)
exit(1)
# Build the section list
enc = guess_file_encoding(core_list_filename, verbose)
with open(core_list_filename, "r", encoding=enc) as f:
rows = [row for row in f.read().splitlines() if row != ","]
section_list = [
[int(core_num), core_name]
for core_name, core_num, *_ in [map(str.strip, r.split(",")) for r in rows]
]
# Add the filepart_section notation field to the section log
num_sections = 1
for i, row in enumerate(section_list):
if i == 0:
row.append("1_" + str(section_list[i][0]))
elif i > 0:
if section_list[i][0] <= section_list[i - 1][0]:
num_sections += 1
row.append(str(num_sections) + "_" + str(section_list[i][0]))
# Build a dictionary for lookup from the list
sectionDict = {section[2]: section[1] for section in section_list}
# Add the part_section notation field to the mscl data
num_sections = 1
for i, row in enumerate(mscl_data):
if i == header_row:
row.append("Part_Section")
elif i == units_row:
row.append("")
elif i == start_row:
row.append(str(num_sections) + "_" + mscl_data[i][section_column])
elif i > start_row:
if int(mscl_data[i][section_column]) < int(
mscl_data[i - 1][section_column]
):
num_sections += 1
elif (
int(mscl_data[i][section_column])
== int(mscl_data[i - 1][section_column])
) and (
float(mscl_data[i][section_depth_column])
< float(mscl_data[i - 1][section_depth_column])
):
num_sections += 1
row.append(str(num_sections) + "_" + mscl_data[i][section_column])
else:
if verbose:
print(
f"Ignored row {i} (not header or units row and before start row):\n{row}"
)
### Build the export lists
matched_data = []
unmatched_data = []
unmatched_identifiers = set()
# Build the export lists, replacing the geotek file section number with the
# coreID and removing the extra part_section column if the row was matched.
for row in mscl_data[start_row:]:
if row[-1] in sectionDict.keys():
row[section_column] = sectionDict[row[-1]]
matched_data.append(row[:-1])
else:
unmatched_data.append(row)
unmatched_identifiers.add(row[-1])
# Build export names
if "output_filename" in kwargs and kwargs["output_filename"]:
matched_filename = kwargs["output_filename"]
elif "unnamed" in input_file:
matched_filename = input_file.replace("_unnamed", "")
else:
matched_filename = ".".join(input_file.split(".")[:-1]) + "_coreID.csv"
unmatched_filename = ".".join(input_file.split(".")[:-1]) + "_unmatched.csv"
### Export matched data
with open(
matched_filename, "w", encoding=locale.getpreferredencoding(), newline=""
) as f:
csvwriter = csv.writer(
f, delimiter=",", quotechar='"', quoting=csv.QUOTE_MINIMAL
)
csvwriter.writerow(mscl_data[header_row][:-1])
csvwriter.writerow(mscl_data[units_row][:-1])
for r in matched_data:
csvwriter.writerow(r)
### Export unmatched data
if len(unmatched_data):
with open(
unmatched_filename, "w", encoding=locale.getpreferredencoding(), newline=""
) as f:
csvwriter = csv.writer(
f, delimiter=",", quotechar='"', quoting=csv.QUOTE_MINIMAL
)
csvwriter.writerow(mscl_data[header_row])
csvwriter.writerow(mscl_data[units_row])
for r in unmatched_data:
csvwriter.writerow(r)
print(f"There was data for {len(unmatched_identifiers)} unmatched cores:")
unmatched_identifiers = sorted(list(unmatched_identifiers))
for unmid in unmatched_identifiers:
print(f"\t{unmid}")
### Reporting stuff
# Create a set to check unique cores names
named_set = set()
for row in matched_data[start_row:]:
named_set.add(row[section_column])
core_name_list = list(sectionDict.values())
for core_name in sorted(list(set(core_name_list))):
core_name_count = core_name_list.count(core_name)
if core_name_count > 1:
print(
f"WARNING: Core {core_name} appears in {core_list_filename} {str(core_name_count)} times."
)
count_diff = len(set(sectionDict.values())) - len(named_set)
if count_diff > 0:
print(f"\nWARNING: Not all cores in {core_list_filename} were used.")
print(
f"The following {str(count_diff)} core{'IDs were' if count_diff != 1 else 'ID was'} not used:"
)
for v in sorted(list(set(sectionDict.values()))):
if v not in named_set:
print(f"\t{v}")
print()
print(f"{len(matched_data)} rows had section names assigned ({matched_filename}).")
print(
"There were no unmatched rows."
if len(unmatched_data) == 0
else f"There were {str(len(unmatched_data))} unmatched rows ({unmatched_filename})."
)
if verbose:
end_time = timeit.default_timer()
print(f"Completed in {round((end_time - start_time),2)} seconds.")
def main():
parser = argparse.ArgumentParser(
description="Apply CoreIDs to the output from Geotek MSCL software."
)
parser.add_argument("input_file", type=str, help="Name of input file.")
parser.add_argument("corelist", type=str, help="Name of the core list file.")
parser.add_argument(
"-o", "--output_filename", type=str, help="Name of the output file."
)
parser.add_argument(
"-v", "--verbose", action="store_true", help="Increase verbosity."
)
parser.add_argument(
"-s",
"--section_column",
type=int,
help="Column number the section numbers are in (count starts at 0).",
)
parser.add_argument(
"-d",
"--depth_column",
type=int,
help="Column number the section depths are in (count starts at 0).",
)
args = parser.parse_args()
apply_names(
args.input_file,
args.corelist,
section_column=args.section_column,
depth_column=args.depth_column,
output_filename=args.output_filename,
verbose=args.verbose,
)
if __name__ == "__main__":
main()