From ed157f6efc9a021af5b1b9fcb5b73528b1e64e42 Mon Sep 17 00:00:00 2001
From: Kelvin Davis <273degreeskelvin@gmail.com>
Date: Wed, 23 May 2018 22:52:58 +1000
Subject: [PATCH] Precision, recall and f_measure.

---
 mini_proj/waldo_model.py | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/mini_proj/waldo_model.py b/mini_proj/waldo_model.py
index 0d9aa43..ef5c75d 100644
--- a/mini_proj/waldo_model.py
+++ b/mini_proj/waldo_model.py
@@ -7,7 +7,7 @@ os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 #from keras.models import Sequential
 from keras.layers import Dense, Dropout, Activation, Flatten, Input
 from keras.layers import Conv2D, MaxPooling2D, ZeroPadding2D
-from keras.models import Model 
+from keras.models import Model
 
 from sklearn import svm, tree, naive_bayes, ensemble
 from _image_classifier import ImageClassifier
@@ -35,21 +35,37 @@ def FCN():
     conv3 = Conv2D(32, (2, 2), activation='relu', padding='same')(m_pool2)
     drop2 = Dropout(0.2)(conv3) # Drop some portion of features to prevent overfitting
     m_pool2 = MaxPooling2D(pool_size=(2, 2))(drop2)
-    
+
     conv4 = Conv2D(164, (2, 2), activation='relu', padding='same')(m_pool2)
 
     flat = Flatten()(conv4)                             # Makes data 1D
     dense = Dense(64, activation='relu')(flat)         # Fully connected layer
-    drop3 = Dropout(0.2)(dense)                         
+    drop3 = Dropout(0.2)(dense)
     classif = Dense(2, activation='softmax')(drop3)    # Final layer to classify
 
     ## Define the model structure
     model = Model(inputs=inputs, outputs=classif)
     # Optimizer recommended Adadelta values (lr=0.01)
-    model.compile(optimizer=Adadelta(lr=0.1), loss='sparse_categorical_crossentropy', metrics=['accuracy'])  
+    model.compile(optimizer=Adadelta(lr=0.1), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
 
     return model
 
+def precision(y_true, y_pred):
+    y_pred = np.round(y_pred)
+    num = np.sum(np.logical_and(y_true, y_pred))
+    den = np.sum(y_pred)
+    return np.divide(num, den)
+
+def recall(y_true, y_pred):
+    y_pred = np.round(y_pred)
+    num = np.sum(np.logical_and(y_true, y_pred))
+    den = np.sum(y_true)
+    return np.divide(num, den)
+
+def f_measure(y_true, y_pred):
+    p = precision(y_true, y_pred)
+    r = recall(y_true, y_pred)
+    return 2 * p * r / (p + r)
 
 ## Open data
 im_train = np.load('Waldo_train_data.npy')
@@ -65,7 +81,7 @@ naive_bayes_iclf = ImageClassifier(naive_bayes.GaussianNBd)
 ensemble_iclf = ImageClassifier(ensemble.RandomForestClassifier)
 
 ## Define training parameters
-epochs = 20             # an epoch is one forward pass and back propogation of all training data 
+epochs = 20             # an epoch is one forward pass and back propogation of all training data
 batch_size = 5
 #lrate = 0.01
 #decay = lrate/epochs
@@ -131,4 +147,3 @@ pred_lbl = model.predict(im_test, verbose=1, batch_size=batch_size)
 end = t.time()
 print("Images generated in {} seconds".format(end - start))
 np.save('predicted_results.npy', pred_lbl)
-