-
Notifications
You must be signed in to change notification settings - Fork 0
/
extractdata.py
215 lines (166 loc) · 7.43 KB
/
extractdata.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
import os
import re
import glob
from itertools import groupby
from config import Config
config = Config()
class ExtractData :
raw_data_path = "./raw-data"
def serialize_raw(self, path) :
all_trials_str = ""
for infile in glob.glob(os.path.join(path, '*')):
review_file = open(infile,'r').read()
#add new file str and remove "File:" line from file headers
all_trials_str = all_trials_str + review_file.split("\n",2)[2]
all_trials = all_trials_str.split("\n\n\n")
#compile trial data into json
serialized_dd_trials, ignored_trials, err = self.serialize_trials(all_trials)
if err :
print(err)
else :
print("Data extracted from raw files")
return serialized_dd_trials
def serialize_trials(self, all_trials) :
serialized_trials = []
ignored_trials = {
"amanda" : 0,
"cano" : 0,
"unnamed" : 0
}
for trial_str in all_trials :
trial = {
"rat_name" : "not found",
"date" : "not found",
"program" : "not found",
"start_time": "not found",
"end_time": "not found",
"total_ll" : -1,
"total_ss" : -1,
"block_0s" : {
"ll" : -1,
"ss" : -1,
"entries" : []
},
"block_4s" : {
"ll" : -1,
"ss" : -1,
"entries" : []
},
"block_8s" : {
"ll" : -1,
"ss" : -1,
"entries" : []
},
"block_16s" : {
"ll" : -1,
"ss" : -1,
"entries" : []
},
"block_32s" : {
"ll" : -1,
"ss" : -1,
"entries" : []
}
}
try :
#split text to extract values
rat_name = trial_str.split("Subject: ")[1].split("\n")[0]
date = trial_str.split("Start Date: ")[1].split("\n")[0]
start_time = trial_str.split("Start Time: ")[1].split("\n")[0]
end_time = trial_str.split("End Time: ")[1].split("\n")[0]
program = trial_str.split("MSN: ")[1].split("\n")[0]
trial["rat_name"] = rat_name.lower()
trial["date"] = date
trial["program"] = program
trial["start_time"] = start_time
trial["end_time"] = end_time
except :
return False, False, "error extracting name, date, or program name for: \n" + trial_str
#remove phase 1 and 2 data
if program in config.irrelevant_programs :
ignored_trials[program.split("-")[0]] += 1
continue
#remove trials missing subject name
if rat_name == "0" :
ignored_trials["unnamed"] += 1
continue
try :
#process ll array
ll_blocks_str = trial_str.split("B:\n")[1].split("C:\n")[0].replace("\n", "")
#remove med-pc indicies "0: , 5: , 10: "
ll_blocks = self.remove_indicies(ll_blocks_str)
trial["total_ll"] = int(float(ll_blocks[0])) / 3
trial["block_0s"]["ll"] = int(float(ll_blocks[1])) / 3
trial["block_4s"]["ll"] = int(float(ll_blocks[2])) / 3
trial["block_8s"]["ll"] = int(float(ll_blocks[3])) / 3
trial["block_16s"]["ll"] = int(float(ll_blocks[4])) / 3
trial["block_32s"]["ll"] = int(float(ll_blocks[5])) / 3
#process ss array
ss_blocks_str = trial_str.split("D:\n")[1].split("I:\n")[0].replace("\n", "")
#remove med-pc indicies "0: , 5: , 10: "
ss_blocks = self.remove_indicies(ss_blocks_str)
trial["total_ss"] = float(ss_blocks[0])
trial["block_0s"]["ss"] = float(ss_blocks[1])
trial["block_4s"]["ss"] = float(ss_blocks[2])
trial["block_8s"]["ss"] = float(ss_blocks[3])
trial["block_16s"]["ss"] = float(ss_blocks[4])
trial["block_32s"]["ss"] = float(ss_blocks[5])
except :
return False, False, "error extracting LL or SS values in 'B' or 'D' var for: \n" + trial_str
#process head entries
all_entries = trial_str.split("V:\n")[1]
all_trial_entries = self.remove_indicies(all_entries)
#remove edge case trials where interface was not on when trial started
if self.all_equal(all_trial_entries) :
continue
try :
entries_json = self.extract_entries(all_trial_entries)
for key in entries_json :
trial[key]["entries"] = entries_json[key]["entries"]
except :
return False, False, "error extracting entries in 'V' var for: \n" + trial_str
serialized_trials.append(trial)
#print(json.dumps(trial, sort_keys=False, indent=4))
return serialized_trials, ignored_trials, False
def extract_entries(self, all_trial_entries) :
all_entries = {
"block_4s" : {
"entries" : []
},
"block_8s" : {
"entries" : []
},
"block_16s" : {
"entries" : []
},
"block_32s" : {
"entries" : []
}
}
block_indicators = [-32, -16, -8, -4]
curr_entries = []
prev_entry = -32
for i, entry in enumerate(reversed(all_trial_entries)) :
floated_entry = float(entry)
if floated_entry in block_indicators :
entry_block = "block_" + str(-1*prev_entry).split(".")[0] + "s"
#add all found positive entries into dict
all_entries[entry_block]["entries"] = [curr_entries] + all_entries[entry_block]["entries"]
#refresh entries for next trial with entries
curr_entries = []
prev_entry = floated_entry
elif floated_entry > 0 :
curr_entries = [floated_entry] + curr_entries
#add last (chronologically first) entry set into dict
all_entries[entry_block]["entries"] = [curr_entries] + all_entries[entry_block]["entries"]
return all_entries
def remove_indicies(self, string) :
no_indicies = re.sub('([0-9]+):', '', string)
not_empty = [x for x in no_indicies.split(" ") if x]
trimmed = []
for item in not_empty :
trimmed.append(item.replace(" ", "").replace("\n", ""))
return trimmed
def all_equal(self, iterable):
g = groupby(iterable)
return next(g, True) and not next(g, False)