An error occurred while loading the file. Please try again.
-
Gaetano Raffaele authored95a977fa
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
import matplotlib
matplotlib.use('Agg')
from matplotlib.patches import Rectangle
import matplotlib.pyplot as plt
from sklearn.metrics import ConfusionMatrixDisplay, classification_report, accuracy_score, cohen_kappa_score
from fpdf import FPDF
import numpy as np
import rasterio
from rasterio.enums import Resampling
from pyproj import Transformer as T
from datetime import datetime
import os
def parse_colormap_file(fn):
labels = []
colors = []
class_names = []
with open(fn, 'r') as f:
for l in f.read().splitlines():
sl = l.split(' ')
labels.append(int(sl[0]))
colors.append((int(sl[1]),int(sl[2]),int(sl[3]),int(sl[4])))
class_names.append(' '.join(sl[5:]))
z = sorted(zip(labels,class_names,colors))
labels = [x[0] for x in z]
class_names = [x[1] for x in z]
colors = [x[2] for x in z]
return labels, class_names, colors
def generate_report_figures(map, yt_yp, palette_fn, out_dir, map_name=None):
labels, class_names, colors = parse_colormap_file(palette_fn)
colors_norm = [(x[0]/255,x[1]/255,x[2]/255,x[3]/255) for x in colors]
with plt.ioff():
font = {'family': 'Arial',
'weight': 'normal',
'size': 8}
plt.rc('font', **font)
if not os.path.exists(out_dir):
os.makedirs(out_dir)
if not isinstance(yt_yp, list):
yt_yp = [yt_yp]
of = {}
of['conf_matrices'] = []
for i,r in enumerate(yt_yp):
cm = ConfusionMatrixDisplay.from_predictions(r[0], r[1], normalize='true', include_values=True)
of['conf_matrices'].append('{}/conf_matrix_{}.png'.format(out_dir, str(i).zfill(2)))
cm.ax_.set_xticklabels(class_names, rotation=45, ha='right')
cm.ax_.set_yticklabels(class_names)
cm.ax_.set_xlabel("Predicted label", labelpad=10)
cm.ax_.set_ylabel("True label", labelpad=15)
cm.figure_.tight_layout()
cm.figure_.savefig(of['conf_matrices'][-1], dpi=300)
of['cl_rep'] = []
summary = []
for r in yt_yp:
of['cl_rep'].append(classification_report(r[0], r[1], output_dict=True, target_names=class_names))
fsc = [np.array([x[c]['f1-score'] for x in of['cl_rep']]) for c in class_names]
fsc_m = [np.mean(x) for x in fsc]
fsc_s = [np.std(x) for x in fsc]
fig, ax = plt.subplots()
ax.bar(range(len(class_names)), fsc_m, yerr=fsc_s, align="center", ecolor='black', capsize=10, color=colors_norm)
ax.set_xticks(range(len(class_names)))
ax.set_xticklabels(class_names, rotation=45, ha='right')
ax.set_title('Per-class F1-scores', fontsize=12, fontweight='bold', pad=10)
ax.yaxis.grid(True)
plt.tight_layout()
of['summary'] = '{}/f1scores.png'.format(out_dir)
plt.savefig(of['summary'], dpi=300)
if map_name is None:
map_name = 'output'
of['quicklook'] = create_map_quicklook_and_legend(map, labels, colors, class_names, yt_yp, out_dir, map_name)
return of
def create_map_quicklook_and_legend(map, labels, colors, class_names, yt_yp, out_dir, name='', qkl_height=1024):
if not os.path.exists(out_dir):
os.makedirs(out_dir)
oa,k = [],[]
for yt,yp in yt_yp:
oa.append(accuracy_score(yt, yp))
k.append(cohen_kappa_score(yt, yp))
oam, oas = np.mean(np.array(oa)), np.std(np.array(oa))
km, ks = np.mean(np.array(k)), np.std(np.array(k))
with rasterio.open(map) as ds:
tr = ds.transform
crs = ds.crs.to_epsg()
smap = ds.read(1,
out_shape=(1, qkl_height, int(ds.width * (qkl_height/ds.height))),
resampling=Resampling.nearest
)
cmap = np.zeros((np.max(labels)+1,4))
cmap[labels] = np.array([np.array(list(c)) for c in colors])
img = cmap[smap].astype(int)
font = {'family': 'Arial',
'weight': 'normal',
'size': 6}
plt.rc('font', **font)
fig, ax = plt.subplots()
ax.imshow(img)
custom_leg = [Rectangle([0,0], 0, 0, fill=True, edgecolor=(0,0,0),
facecolor=([x[0]/255,x[1]/255,x[2]/255,x[3]/255])) for x in colors]
ax.legend(custom_leg, class_names, loc='center left', bbox_to_anchor=(1, 0.5), fontsize=6)
conv = T.from_crs(crs, 4326, always_xy=True)
xt, yt = ax.get_xticks(), ax.get_yticks()
xpos = ['{:.3f}°'.format(conv.transform(tr[2] + tr[0]*x,0)[0]) for x in xt[1:-1]]
ypos = ['{:.3f}°'.format(conv.transform(0, tr[5] + tr[4] * x)[1]) for x in yt[1:-1]]
ax.set_xticks(xt[1:-1])
ax.set_yticks(yt[1:-1])
ax.set_xticklabels(xpos, rotation=45, ha='right')
ax.set_yticklabels(ypos)
ax.set_title("Final Classification Map Quicklook", fontsize=12, fontweight='bold', pad=15)
ax.set_xlabel("Overall Map Accuracy : {:.2f} +/- {:.2f}\nCohen's Kappa : {:.2f} +/- {:.2f}".format(oam,oas,km,ks),
fontsize=10, fontweight='bold', labelpad=15)
plt.tight_layout()
out_fn = '{}/{}_QKL.png'.format(out_dir,name)
plt.savefig(out_fn, dpi=300)
return out_fn
def generate_pdf(of, out_pdf, name='output'):
pdf = FPDF('P', 'mm', 'A4')
pdf.set_font("helvetica", 'B', 16)
# Page 1 - Summary (OA/Kappa/Quickview)
pdf.add_page()
pdf.set_xy(0,16)
txt = 'Moringa Final Report for Chain {}, {}'.format(name, datetime.now().strftime('%Y-%m-%d %Hh%M'))
pdf.cell(0, txt=txt, align='C')
pdf.image(of['quicklook'], 14, 24, h=140)
pdf.image(of['summary'], 22, 170, h=120)
# Pages 2-end, Per-fold assessment
for i,(cm,rep) in enumerate(zip(of['conf_matrices'], of['cl_rep'])):
pdf.add_page()
pdf.set_xy(0, 16)
pdf.set_font("helvetica", '', 14)
pdf.cell(0, txt="Per-fold assessment - Fold #{}".format(str(i+1).zfill(2)), align='C')
pdf.image(cm, 14,24,h=120)
table_data = [["Class", "Precision", "Recall", "F1-score", "Support"]]
for k in list(rep.keys())[:-3] + list(rep.keys())[-2:]:
table_data.append([k, rep[k]['precision'], rep[k]['recall'], rep[k]['f1-score'], rep[k]['support']])
pdf.set_xy(0, 150)
pdf.set_font("helvetica", '', 10)
with pdf.table(width=140, col_widths=(60,20,20,20,20)) as table:
row = table.row()
for datum in table_data[0]:
row.cell(datum, align='C')
for data_row in table_data[1:-2]:
row = table.row()
row.cell(data_row[0])
for datum in data_row[1:4]:
row.cell('{:.4f}'.format(datum), align='R')
row.cell('{}'.format(data_row[-1]), align='R')
row = table.row()
row.cell('Summary')
for data_row in table_data[-2:]:
row = table.row()
row.cell(data_row[0])
for datum in data_row[1:4]:
row.cell('{:.4f}'.format(datum), align='R')
row.cell('{}'.format(data_row[-1]), align='R')
row = table.row()
row.cell('Accuracy')
row.cell('{:.2f}%'.format(rep['accuracy']*100), align='R')
pdf.output(out_pdf)