import knn_trainer_helper
from sklearn.neighbors import LSHForest
import time
import border
import matplotlib.pyplot as plt
import mahotas
import numpy as np
from sklearn.decomposition import PCA
import metrics
import cPickle
img = mahotas.imread('results/predict_img_PCA_k20p19s1024n100e20c20m4.tif')
label = mahotas.imread('labels/test/0.tif')
precisions, recalls = metrics.get_precision_recall_values(img, label, 50, True)
thresh = np.linspace(.01,.99,50)
f_scores=2.0*(precisions*recalls)/(precisions+recalls)
plt.figure(2)
plt.plot(thresh, f_scores, 's')
max_thresh=thresh[np.argmax(f_scores)]
threshPrediction = img>max_thresh
plt.figure(3)
plt.imshow(threshPrediction, cmap='gray')
plt.show()
train_data_transform=pca.transform(train_input[:])
del train_input
train_data=train_data_transform#np.vstack((train_data_fit,train_data_transform))
test_data=pca.transform(test_input)
for val in param_values:
candidates=val
lshf = LSHForest(n_estimators=estimators,n_candidates=candidates,min_hash_match=minhash,n_neighbors=k,random_state=1).fit(train_data)
approx_neighbors = lshf.kneighbors(test_data, return_distance=False)
gray_prediction=[]
for query in approx_neighbors:
nbrs = []
for j in query:
nbrs.append(train_label[j][0])
gray_val=np.mean(nbrs)
gray_prediction.append(gray_val)
precisions, recalls = metrics.get_precision_recall_values(gray_prediction, test_label.flatten(), 50, False)
f_scores=2.0*(precisions*recalls)/(precisions+recalls)
f_max = np.nanmax(f_scores)
values.append(val)
f_maxes.append(f_max)
print f_max
plt.plot(values,f_maxes,'o')
plt.show()
gray_line = []
# looks at the labels of returned nearest neighbors, and puts that into the greater prediction image
for query in approx_neighbors:
nbrs = []
for j in query:
nbrs.append(train_label[j])
gray_val = np.mean(nbrs)
gray_line.append(gray_val)
full_predicted.append(gray_line)
t3 = time.time()
print "predict line " + str(i) + " took " + str(t3 - predict_start)
output = np.array(full_predicted) # .reshape((side,side))
# get accuracy information
precisions, recalls = metrics.get_precision_recall_values(full_predicted, label, 100, True)
# formats the prediction image, as well as giving it a title and description based on the params used
print "total time: " + str(round(time.time() - start, 2)) + "s"
fname = (
"k"
+ str(k)
+ "p"
+ str(pad)
+ "s"
+ str(side)
+ "n"
+ str(numpoints)
+ "e"
+ str(estimators)
+ "c"
