-
Notifications
You must be signed in to change notification settings - Fork 0
/
infra_collab_calc.py
239 lines (187 loc) · 6.27 KB
/
infra_collab_calc.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
import pandas as pd
# get the data
infra = pd.read_excel(
"Data/2023/SciLifeLab_publications_Infrastucture_2023.xlsx",
sheet_name="Publications 20231204-1239",
header=0,
engine="openpyxl",
keep_default_na=False,
)
# filter as needed (just latest year, only need a couple of columns)
infra_collabs = infra[(infra["Year"] == 2023)] # set year here!!
infra_collabs = infra_collabs[["DOI", "Labels"]]
# Replace string values with respect to the rules set out by OO
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("Genome Engineering Zebrafish", "")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("National Genomics Infrastructure", "")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("|National Genomics Infrastructure", "")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("|Bioinformatics Compute and Storage", "")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("Bioinformatics Compute and Storage|", "")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("Bioinformatics Compute and Storage", "")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"Bioinformatics Long-term Support WABI",
"Bioinformatics Support, Infrastructure and Training",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"Systems Biology", "Bioinformatics Support, Infrastructure and Training"
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"Bioinformatics Support and Infrastructure",
"Bioinformatics Support, Infrastructure and Training",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Stockholm (Genomics Applications)",
"NGI Short-read and Genotyping",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Stockholm (Genomics Production)",
"NGI Short-read and Genotyping",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Uppsala (SNP&SEQ Technology Platform)",
"NGI Short-read and Genotyping",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Long read",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Uppsala (Uppsala Genome Center)",
"NGI Long-read",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Other",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Proteomics",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Short read",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI SNP genotyping",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Single cell",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"NGI Spatial omics",
"",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"Affinity Proteomics Stockholm",
"Affinity Proteomics",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace(
"Affinity Proteomics Uppsala",
"Affinity Proteomics",
)
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: x.replace("||||", "|")
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(lambda x: x.replace("|||", "|"))
infra_collabs["Labels"] = infra_collabs["Labels"].apply(lambda x: x.replace("||", "|"))
# Count was incorrect when NGI at front because it often started with "|"" after others deleted
# corrected this by conditionally replacing based on start value
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: f"Bioinformatics Compute and Storage"
if x.startswith("|Bioinformatics Compute and Storage")
else x
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: f"National Genomics Infrastructure"
if x.startswith("|National Genomics Infrastructure")
else x
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: f"NGI Long-read" if x.startswith("|NGI Long-read") else x
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: f"NGI Short-read and Genotyping"
if x.startswith("NGI Short-read and Genotyping|")
else x
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: f"NGI Short-read and Genotyping|NGI Long-read"
if x.startswith("|NGI Short-read and Genotyping|NGI Long-read")
else x
)
infra_collabs["Labels"] = infra_collabs["Labels"].apply(
lambda x: f"NGI Short-read and Genotyping"
if x.startswith("|NGI Short-read and Genotyping")
else x
)
# split values to different columns, so there is one unit per column
new_bits = infra_collabs["Labels"].str.split("|", expand=True)
new_bits = new_bits.apply(
lambda row: pd.Series(row).drop_duplicates(keep="first"), axis="columns"
)
# Now count the number of 'non empty columns' in each row
# This will how how many units worked on a publication
new_bits["No_units"] = new_bits.count(axis=1)
# This file is a test file you can use to check everything looks correct
# new_bits.to_excel("TESTCHECK_collaborations.xlsx")
# Need to work out a percantage to use in the report
Perc_collab = (
(new_bits["No_units"].map(lambda x: x > 1).sum()) / (new_bits["No_units"].count())
) * 100
# Output percentage, so that it can be communicated to OO
print(Perc_collab)
# noticed that there are some errors in the automatic counts, so need to make manual adjustments
print((new_bits["No_units"].map(lambda x: x > 1).sum()) + 7)
print(new_bits["No_units"].count())
Perc_collab = (
(new_bits["No_units"].map(lambda x: x > 1).sum() + 7)
/ (new_bits["No_units"].count())
) * 100
# Output percentage, so that it can be communicated to OO
print(Perc_collab)
# should be 10.14