extract-gcs-curadores_v1.py
13.1 KB
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
import plotly.graph_objects as go
import numpy as np
import os
import pandas as pd
def extract_gcs_curadores_SG(path_input, file_input, path_output, file_output, file_all_gcs, file_all_gcs_x):
df_output_table = pd.DataFrame()
# df_output_table_bin = pd.DataFrame()
df_input_table = pd.read_csv(os.path.join(path_input, file_input), sep="\t")
print("Shape df_input_table: {}".format(df_input_table.shape))
print(df_input_table.head())
hash_all_gcs_control = {}
hash_all_gcs_num_control = {}
hash_all_gcs_test = {}
hash_all_gcs_num_test = {}
hash_gc_classes = {0: 'ORGANISM', 1: 'GENETIC_BACKGROUND', 2: 'MEDIUM',
3: 'MEDIUM_SUPPLEMENTS', 5: 'TEMPERATURE', 8: 'OPTICAL_DENSITY', 9: 'GROWTH_PHASE',
10: 'AGITATION_SPEED', 11: 'AERATION', 12: 'pH'}
idx = 0
for ind in df_input_table.index:
hash_gcs_table = {}
hash_gcs = {}
num_gcs = 0
pmid = df_input_table['Reference'][ind]
hash_gcs_table['pmid'] = str(pmid)
# print("Control_Growth_Condition...")
gcs_control = df_input_table['Control_Growth_Condition'][ind]
list_gcs_control = gcs_control.split('|')
hash_gcs_table['idx'] = idx
hash_gcs_table['gc_type'] = 'control'
for gc in list_gcs_control:
if gc != '':
gc_class = hash_gc_classes[list_gcs_control.index(gc)]
# print("gc_class: {}".format(gc_class))
hash_gcs_table[gc_class] = gc
hash_gcs[gc_class] = gc
num_gcs += 1
str_gcs = ", ".join(hash_gcs.keys())
if str_gcs in hash_all_gcs_control:
hash_all_gcs_control[str_gcs] += 1
else:
hash_all_gcs_control[str_gcs] = 1
hash_all_gcs_num_control[str_gcs] = num_gcs
df_output_table = df_output_table.append(hash_gcs_table, ignore_index=True)
hash_gcs_table = {}
hash_gcs = {}
num_gcs = 0
hash_gcs_table['pmid'] = str(pmid)
# print("Test_Growth_Condition...")
gcs_test = df_input_table['Test_Growth_Condition'][ind]
list_gcs_test = gcs_test.split('|')
hash_gcs_table['idx'] = idx
hash_gcs_table['gc_type'] = 'test'
for gc in list_gcs_test:
if gc != '':
gc_class = hash_gc_classes[list_gcs_test.index(gc)]
# print("gc_class: {}".format(gc_class))
hash_gcs_table[gc_class] = gc
hash_gcs[gc_class] = gc
num_gcs += 1
# hash_gcs_bin[gc_class] = int(1)
str_gcs = ", ".join(hash_gcs.keys())
# print(str_gcs)
if str_gcs in hash_all_gcs_test:
hash_all_gcs_test[str_gcs] += 1
else:
hash_all_gcs_test[str_gcs] = 1
hash_all_gcs_num_test[str_gcs] = num_gcs
df_output_table = df_output_table.append(hash_gcs_table, ignore_index=True)
idx += 1
df_output_table = df_output_table.replace(np.nan, '')
# df.sort_values(by=['Country', 'Continent'],
# ascending=[False, True])
# print(df_output_table_bin)
df_output_table.to_csv(os.path.join(path_output, file_output), sep='\t', index=False, header=True)
df_all_gcs = pd.DataFrame()
df_all_gcs_num = pd.DataFrame()
print(hash_all_gcs_control)
print(hash_all_gcs_test)
# quit()
for all_gcs, num_gcs in hash_all_gcs_control.items():
# https://www.geeksforgeeks.org/how-to-append-a-list-as-a-row-to-a-pandas-dataframe-in-python/
# df = df.append(pd.DataFrame(list, columns=['Name', 'Age', 'City', 'Country']), ignore_index=True)
df_all_gcs = df_all_gcs.append(pd.DataFrame([['control', all_gcs, num_gcs]],
columns=['class_type', 'gc_phrase', 'num_gc_phrases']), ignore_index=True)
for all_gcs, num_gcs in hash_all_gcs_test.items():
df_all_gcs = df_all_gcs.append(pd.DataFrame([['test', all_gcs, num_gcs]],
columns=['class_type', 'gc_phrase', 'num_gc_phrases']), ignore_index=True)
print(df_all_gcs)
for all_gcs, num_gcs in hash_all_gcs_num_control.items():
df_all_gcs_num = df_all_gcs_num.append(pd.DataFrame([['control', all_gcs, num_gcs]],
columns=['class_type', 'gc_phrase', 'num_gc_classes']), ignore_index=True)
for all_gcs, num_gcs in hash_all_gcs_num_test.items():
df_all_gcs_num = df_all_gcs_num.append(pd.DataFrame([['test', all_gcs, num_gcs]],
columns=['class_type', 'gc_phrase', 'num_gc_classes']), ignore_index=True)
print(df_all_gcs_num)
# quit()
df_join = df_all_gcs.join(df_all_gcs_num.set_index(['class_type', 'gc_phrase']), on=['class_type', 'gc_phrase'], lsuffix='_all', rsuffix='_num')
print(df_join)
# quit()
# df_all_gcs_table = df_all_gcs.set_index('0').join(df_all_gcs_num.set_index('0'))
# df_all_gcs_table = df_join[['0_all', '1_num', '1_all']].copy()
# df_all_gcs_table.columns = ['Clases de condiciones (frase)', 'Número de clases', 'Numero de repeticiones de la frase']
# df_all_gcs_table.columns = ['gc_phrase', 'num_gc_classes', 'num_gc_phrases']
df_all_gcs_table = df_join.copy()
df_all_gcs_table.to_csv(os.path.join(path_output, file_all_gcs), sep='\t', index=False, header=True)
quit()
df_all_gcs_table_x = pd.DataFrame()
for ind in df_all_gcs_table.index:
hash_gcs_table_x = {}
phrase = df_all_gcs_table['gc_phrase'][ind]
list_phrase = phrase.split(',')
for gc_class in list_phrase:
gc_class = gc_class.strip()
hash_gcs_table_x[gc_class] = 'X'
hash_gcs_table_x['num_gc_classes'] = df_all_gcs_table['num_gc_classes'][ind]
hash_gcs_table_x['num_gc_phrases'] = df_all_gcs_table['num_gc_phrases'][ind]
df_all_gcs_table_x = df_all_gcs_table_x.append(hash_gcs_table_x, ignore_index=True)
df_all_gcs_table_x_out = df_all_gcs_table_x[['ORGANISM', 'GENETIC_BACKGROUND', 'MEDIUM',
'MEDIUM_SUPPLEMENTS', 'TEMPERATURE', 'OPTICAL_DENSITY', 'GROWTH_PHASE',
'AGITATION_SPEED', 'AERATION', 'pH', 'num_gc_classes', 'num_gc_phrases']].copy()
df_all_gcs_table_x_out.to_csv(os.path.join(path_output, file_all_gcs_x), sep='\t', index=False, header=True)
# https://plotly.com/python/table/
fig = go.Figure(data=[go.Table(
header=dict(
values=['ORGANISM', 'GENETIC_BACKGROUND', 'MEDIUM',
'MEDIUM_SUPPLEMENTS', 'TEMPERATURE', 'OPTICAL_DENSITY', 'GROWTH_PHASE',
'AGITATION_SPEED', 'AERATION', 'pH', 'num_gc_classes', 'num_gc_phrases'],
line_color='white', fill_color='white',
align='center', font=dict(color='black', size=12)
),
cells=dict(
values=[df_all_gcs_table_x_out.ORGANISM, df_all_gcs_table_x_out.GENETIC_BACKGROUND,
df_all_gcs_table_x_out.MEDIUM, df_all_gcs_table_x_out.MEDIUM_SUPPLEMENTS,
df_all_gcs_table_x_out.TEMPERATURE, df_all_gcs_table_x_out.OPTICAL_DENSITY,
df_all_gcs_table_x_out.GROWTH_PHASE, df_all_gcs_table_x_out.AGITATION_SPEED,
df_all_gcs_table_x_out.AERATION, df_all_gcs_table_x_out.pH,
df_all_gcs_table_x_out.num_gc_classes, df_all_gcs_table_x_out.num_gc_phrases],
# line_color=[df.Color], fill_color=[df.Color],
align='center', font=dict(color='black', size=11)
))
])
fig.show()
def extract_gcs_curadores_PL(path_input, file_input, path_output, file_output, file_all_gcs, file_all_gcs_x):
df_output_table = pd.DataFrame()
# df_output_table_bin = pd.DataFrame()
df_input_table = pd.read_csv(os.path.join(path_input, file_input), sep="\t")
print("Shape df_input_table: {}".format(df_input_table.shape))
# print(df_input_table.head())
hash_all_gcs = {}
hash_all_gcs_num = {}
for ind in df_input_table.index:
hash_gcs_table = {}
hash_gcs = {}
num_gcs = 0
# hash_gcs_bin = {}
pmid = df_input_table['PMID'][ind]
coleccion = df_input_table['Colección'][ind]
hash_gcs_table['pmid'] = str(pmid)
# hash_gcs_bin['pmid'] = str(pmid)
hash_gcs_table['coleccion'] = coleccion
gcs = df_input_table['GC'][ind]
list_gcs = gcs.split('|')
for gc in list_gcs:
list_gc = gc.split(':')
gc_class = list_gc[0]
gc_class = gc_class.strip()
gc_class = gc_class.strip("'")
gc_term = list_gc[1]
gc_term = gc_term.strip()
gc_term = gc_term.strip("'")
hash_gcs_table[gc_class] = gc_term
hash_gcs[gc_class] = gc_term
num_gcs += 1
# hash_gcs_bin[gc_class] = int(1)
str_gcs = ", ".join(hash_gcs.keys())
# print(str_gcs)
if str_gcs in hash_all_gcs:
hash_all_gcs[str_gcs] += 1
else:
hash_all_gcs[str_gcs] = 1
hash_all_gcs_num[str_gcs] = num_gcs
df_output_table = df_output_table.append(hash_gcs_table, ignore_index=True)
# df_output_table_bin = df_output_table_bin.append(hash_gcs_bin, ignore_index=True)
# print(df_output_table)
# quit()
# df_output_table_bin = df_output_table_bin.replace(np.nan, 0)
# df_output_table_bin = pd.DataFrame(np.sort(df_output_table_bin.values, axis=0), index=df_output_table_bin.index, columns=df_output_table_bin.columns)
df_output_table = df_output_table.replace(np.nan, '')
# df.sort_values(by=['Country', 'Continent'],
# ascending=[False, True])
# print(df_output_table_bin)
df_output_table.to_csv(os.path.join(path_output, file_output), sep='\t', index=False, header=True)
# df_output_table_bin.to_csv(os.path.join(path_output, file_bin), sep='\t', index=False, header=True)
df_all_gcs = pd.DataFrame(list(hash_all_gcs.items()))
df_all_gcs_num = pd.DataFrame(list(hash_all_gcs_num.items()))
df_join = df_all_gcs.join(df_all_gcs_num, lsuffix='_all', rsuffix='_num')
# df_all_gcs_table = df_all_gcs.set_index('0').join(df_all_gcs_num.set_index('0'))
df_all_gcs_table = df_join[['0_all', '1_num', '1_all']].copy()
# df_all_gcs_table.columns = ['Clases de condiciones (frase)', 'Número de clases', 'Numero de repeticiones de la frase']
df_all_gcs_table.columns = ['gc_phrase', 'num_gc_classes', 'num_gc_phrases']
df_all_gcs_table.to_csv(os.path.join(path_output, file_all_gcs), sep='\t', index=False, header=True)
df_all_gcs_table_x = pd.DataFrame()
for ind in df_all_gcs_table.index:
hash_gcs_table_x = {}
phrase = df_all_gcs_table['gc_phrase'][ind]
list_phrase = phrase.split(',')
for gc_class in list_phrase:
gc_class = gc_class.strip()
hash_gcs_table_x[gc_class] = 'X'
hash_gcs_table_x['num_gc_classes'] = df_all_gcs_table['num_gc_classes'][ind]
hash_gcs_table_x['num_gc_phrases'] = df_all_gcs_table['num_gc_phrases'][ind]
df_all_gcs_table_x = df_all_gcs_table_x.append(hash_gcs_table_x, ignore_index=True)
df_all_gcs_table_x_out = df_all_gcs_table_x[['ORGANISM', 'GENETIC_BACKGROUND', 'MEDIUM',
'MEDIUM_SUPPLEMENTS', 'TEMPERATURE', 'OPTICAL_DENSITY', 'GROWTH_PHASE',
'AGITATION_SPEED', 'AERATION', 'pH', 'num_gc_classes', 'num_gc_phrases']].copy()
df_all_gcs_table_x_out.to_csv(os.path.join(path_output, file_all_gcs_x), sep='\t', index=False, header=True)
# https://plotly.com/python/table/
fig = go.Figure(data=[go.Table(
header=dict(
values=['ORGANISM', 'GENETIC_BACKGROUND', 'MEDIUM',
'MEDIUM_SUPPLEMENTS', 'TEMPERATURE', 'OPTICAL_DENSITY', 'GROWTH_PHASE',
'AGITATION_SPEED', 'AERATION', 'pH', 'num_gc_classes', 'num_gc_phrases'],
line_color='white', fill_color='white',
align='center', font=dict(color='black', size=12)
),
cells=dict(
values=[df_all_gcs_table_x_out.ORGANISM, df_all_gcs_table_x_out.GENETIC_BACKGROUND,
df_all_gcs_table_x_out.MEDIUM, df_all_gcs_table_x_out.MEDIUM_SUPPLEMENTS,
df_all_gcs_table_x_out.TEMPERATURE, df_all_gcs_table_x_out.OPTICAL_DENSITY,
df_all_gcs_table_x_out.GROWTH_PHASE, df_all_gcs_table_x_out.AGITATION_SPEED,
df_all_gcs_table_x_out.AERATION, df_all_gcs_table_x_out.pH,
df_all_gcs_table_x_out.num_gc_classes, df_all_gcs_table_x_out.num_gc_phrases],
# line_color=[df.Color], fill_color=[df.Color],
align='center', font=dict(color='black', size=11)
))
])
fig.show()
path_in = "/home/cmendezc/Documents/ccg/gitlab-automatic-extraction-growth-conditions/data-sets/data-curation/data_sets_curadores"
path_out = "/home/cmendezc/Documents/ccg/gitlab-automatic-extraction-growth-conditions/data-sets/data-curation/data_sets_curadores"
# Curator: PL
file_in = "PL&VT_GC-PMID.tsv"
file_out = "PL&VT_GC-PMID-GCs.tsv"
file_gcs = "PL&VT_GC-PMID-GCs-All.tsv"
file_gcs_x = "PL&VT_GC-PMID-GCs-All-X.tsv"
### extract_gcs_curadores_PL(path_in, file_in, path_out, file_out, file_gcs, file_gcs_x)
# Curator: SG
file_in = "GC-Catalog_resumido-sgama.tsv"
file_out = "GC-Catalog_resumido-sgama-GCs.tsv"
file_gcs = "GC-Catalog_resumido-sgama-GCs-All.tsv"
file_gcs_x = "GC-Catalog_resumido-sgama-GCs-All-X.tsv"
extract_gcs_curadores_SG(path_in, file_in, path_out, file_out, file_gcs, file_gcs_x)