-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathconvert_xls.py
executable file
·189 lines (150 loc) · 6.3 KB
/
convert_xls.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
# -*- coding: utf-8 -*-
import xlrd
import string
import ast
from collections import defaultdict
from optparse import OptionParser
import numpy as np
parser = OptionParser()
parser.add_option("-i", "--input", dest="input",
help="Input XLS", metavar="FILE")
parser.add_option("-o", "--output", dest="output",
help="output CSV")
parser.add_option("-n", "--inds", dest="inds_num",
help="Number of individuals")
parser.add_option("-v", "--vistas", dest="vistas",
help="Vistas coordinates like (1,'A'), (10,'B')")
parser.add_option("-d", "--dists", dest="distances",
help="Distances coordinates like (1,'A'), (10,'B')")
(options, args) = parser.parse_args()
def cell_name_idx(s):
b = 1
n = 0
for i in [string.lowercase.index(string.lower(c)) for c in reversed(s)]:
n += b*(i+1)
b *= (string.lowercase.index('z') + 1)
return n-1
def get_points_names(data, vistas):
d = defaultdict(list)
for i, coords in enumerate(vistas):
line = int(coords[0] + 1)
col = coords[1]
p = data.cell(line, col)
while p.value != '':
d[data.cell(*vistas[i]).value].append((p.value, (line, col)))
line += 1
p = data.cell(line, col)
return d
def read_all_points(data, vistas, num_mes=1):
INFO_COL = 1
points = []
line = 0
i = 0
points_info = get_points_names(data, vistas)
points_lines_max = max(map(len, points_info.values()))
parsed = 0
while parsed < num_mes:
points.append({})
# Get Info
points[-1]['info'] = []
l = line + 1
p = data.cell(l, INFO_COL).value
while p != '':
points[-1]['info'].append(p)
l += 1
p = data.cell(l, INFO_COL).value
for v in vistas:
vname = data.cell(*v).value
points[-1][vname] = {}
for i, p in enumerate(points_info[vname]):
points[-1][vname][p[0]] = {}
# Get X
points[-1][vname][p[0]]['x'] = []
points[-1][vname][p[0]]['x'].append(data.cell(p[1][0] + line, p[1][1]+1).value)
points[-1][vname][p[0]]['x'].append(data.cell(p[1][0] + line, p[1][1]+4).value)
# Get Y
points[-1][vname][p[0]]['y'] = []
points[-1][vname][p[0]]['y'].append(data.cell(p[1][0] + line, p[1][1]+2).value)
points[-1][vname][p[0]]['y'].append(data.cell(p[1][0] + line, p[1][1]+5).value)
# Get Z
points[-1][vname][p[0]]['z'] = []
points[-1][vname][p[0]]['z'].append(data.cell(p[1][0] + line, p[1][1]+3).value)
points[-1][vname][p[0]]['z'].append(data.cell(p[1][0] + line, p[1][1]+6).value)
line += points_lines_max + 3
parsed += 1
return points
def get_distance_names(data, columns):
dists_names = defaultdict(list)
for c in columns:
line = c[0] + 1
col = cell_name_idx(c[1])
vista = data.cell(line - 2, col).value
dist = data.cell(line, col).value
while dist != '':
dists_names[vista].append(dist)
line += 1
dist = data.cell(line, col).value
for k in dists_names.keys():
dists_names[k] = map(lambda d: d.split('-'), dists_names[k])
dists_names[k] = [[p[0].rstrip(), p[1].rstrip()] for p in dists_names[k]]
return dists_names
def calc_distances(points, dist_names, i):
ps = points[i]
distances = {}
for v in dist_names.keys():
distances[v] = {}
for dp in dist_names[v]:
dist_key = '{}-{}'.format(dp[0], dp[1])
if dp[1][-1] == 'e' or dp[1][-1] == 'd':
pk = dp[0] + ' ' + dp[1][-1]
if ps[v].has_key(pk):
if ps[v].has_key(dp[1]):
point1_key = pk
point2_key = dp[1]
else:
point1_key = pk
point2_key = dp[1][:-2]
else:
point1_key = dp[0]
point2_key = dp[1]
else:
point1_key = dp[0]
point2_key = dp[1]
dist1_x = ps[v][point1_key]['x'][0]- ps[v][point2_key]['x'][0]
dist1_y = ps[v][point1_key]['y'][0]- ps[v][point2_key]['y'][0]
dist1_z = ps[v][point1_key]['z'][0]- ps[v][point2_key]['z'][0]
dist2_x = ps[v][point1_key]['x'][1]- ps[v][point2_key]['x'][1]
dist2_y = ps[v][point1_key]['y'][1]- ps[v][point2_key]['y'][1]
dist2_z = ps[v][point1_key]['z'][1]- ps[v][point2_key]['z'][1]
distances[v][dist_key] = []
distances[v][dist_key].append(np.sqrt(dist1_x**2 + dist1_y**2 + dist1_z**2))
distances[v][dist_key].append(np.sqrt(dist2_x**2 + dist2_y**2 + dist2_z**2))
return distances
def avg_distances(distances):
avg_distances = {}
for vista in distances.keys():
avg_distances[vista] = {}
for d in distances[vista].keys():
if d[-1] == 'e':
if distances[vista].has_key(d[:-1] + 'd'):
avg_distances[vista][d[:-1]] = np.average([np.average(distances[vista][d]), np.average(distances[vista][d[:-1] + 'd'])])
else:
avg_distances[vista][d] = np.average(distances[vista][d])
elif d[-1] == 'd':
if distances[vista].has_key(d[:-1] + 'e'):
avg_distances[vista][d[:-1]] = np.average([np.average(distances[vista][d]), np.average(distances[vista][d[:-1] + 'e'])])
else:
avg_distances[vista][d] = np.average(distances[vista][d])
else:
avg_distances[vista][d] = np.average(distances[vista][d])
return avg_distances
workbook = xlrd.open_workbook(options.input)
data = workbook.sheet_by_name('dados')
vistas_c = ast.literal_eval(options.vistas)
vistas_c = [(v[0], cell_name_idx(v[1])) for v in vistas_c]
dists_c = ast.literal_eval(options.distances)
dist_names = get_distance_names(data, dists_c)
points = read_all_points(data, vistas_c, num_mes=int(options.inds_num))
dists = [calc_distances(points, dist_names, i) for i in xrange(int(options.inds_num))]
avg_dist = [avg_distances(d) for d in dists]
print avg_dist