-
Notifications
You must be signed in to change notification settings - Fork 0
/
cli_utils.py
180 lines (152 loc) · 5.02 KB
/
cli_utils.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
import materials_chempy.utils as mcpyut
import pandas as pd
import materials_chempy.database_analysis.dban_functions as dbanmcpy
import os
def gen_args(args):
"""
Parameters
----------
args : argparse.Namespace
argparse aroguments
Returns
-------
input_path : str or None
output_path : str or None
"""
input_path = None
output_path = None
if args.help:
mcpyut.client_help()
if args.mplcfg:
mcpyut.matplotlib_config()
if args.input:
input_path = args.input
if args.output:
output_path = args.output
return input_path, output_path
def ms_args(args):
"""
Parameters
----------
args : argparse.Namespac
argparse arguments
Returns
-------
resolution_thrs : float, default 0.3
minimum m/z difference between two plotted peaks
n_highest : int, default 15
Number of peaks to be plotted, based on intensity
n_labels : int, default 5
Number of most intense peaks to be labeled with m/z
manual_peak_df : DataFrame
labeling argument in form m/z1 label1 m/z2 label2
label1 : str, default 'Ion Trap ESI-MS'
Top right box first annotation
label2 : strm, default 'Direct injection'
Top right box second annotation
"""
resolution_thrs = 0.3
n_highest = 15
n_labels = 5
manual_peak_df = pd.DataFrame({})
label1 = 'Ion Trap ESI-MS'
label2 = 'Direct injection'
if args.resolution:
resolution_thrs = args.resolution
if args.n:
n_highest = args.n
if args.N:
n_labels = args.N
if args.manual_peak:
manual_peak_df = mcpyut.manual_peaks_sepparation(args.manual_peak)
if args.label1:
label1 = args.label1
if args.label2:
label2 = args.label2
return resolution_thrs, n_highest, n_labels, manual_peak_df, label1, label2
def mpl_args(args):
"""
Parameters
----------
args : argparse.Namespace
argparse arguments
Returns
-------
subtitle : str
Define the plot subtitle
title : str
Define the plot title
"""
title = None
subtitle = "default"
if args.title:
title = args.title
if args.subtitle:
subtitle = args.subtitle
return title, subtitle
def dban_args(args, output_path):
"""
Parameters
----------
args : argparse.Namespace
argparse arguments
output_path : str
String of the path to save a csv queryied
Returns
-------
pubdf : DataFrame
Pandas dataframe with number of published articles per date columns
"""
year_1 = 1996
year_2 = 2023
pubdf = None
if args.dailypubmed or args.pubmed or args.springer or args.scopus:
for n in [args.pubmed, args.dailypubmed, args.springer, args.scopus]:
if n:
if len(n) == 1:
keyword = n[0]
if len(n) == 2:
keyword = n[0]
output_path = n[1]
elif len(n) == 3:
keyword = n[0]
year_1 = int(n[1])
year_2 = int(n[2])
elif len(n) == 4:
keyword = n[0]
year_1 = int(n[1])
year_2 = int(n[2])
output_path = n[3]
if args.pubmed:
pubdf = dbanmcpy.pubmedfetcher(keyword, year_1, year_2,
save_path=output_path)
elif args.dailypubmed:
pubdf = dbanmcpy.big_pubmedfetcher(keyword, year_1,
year_2,
save_path=output_path)
elif args.springer:
pubdf = dbanmcpy.fetch_springer(keyword, year_1, year_2,
save_path=output_path)
elif args.scopus:
pubdf = dbanmcpy.scopusfetcher(keyword, year_1, year_2,
save_path=output_path)
return pubdf, output_path
def barplot_args(input_path, output_path, title, pubdf, args):
if args.barplot:
if len(args.barplot) == 1:
if args.barplot[0].lower().endswith('.csv'):
pubdf = pd.read_csv(args.barplot, index_col=0)
pubdf = dbanmcpy.df_statistics(pubdf)
elif len(args.barplot) == 2:
if args.barplot[0].lower().endswith('.csv'):
pubdf = pd.read_csv(args.barplot[0], index_col=0)
pubdf = dbanmcpy.df_statistics(pubdf)
output_path = args.barplot[1]
dbanmcpy.bar_plot_df(save_path=output_path, df=pubdf,
title=title)
return pubdf
def inbarplot_args(pubdf, output_path, title, args):
if args.inbarplot:
pubdf = dbanmcpy.df_statistics(pubdf)
dbanmcpy.bar_plot_df(save_path=output_path, df=pubdf,
title=title)