fixed loss function

libra/modeling/prediction_model_creation.py

@@ -5,7 +5,7 @@
 from tensorflow.python.keras.layers import Dense, Input
 import numpy as np
 from keras.models import model_from_json
-import os 
+import os
 
 # Creates a regression neural network
 
@@ -67,7 +67,7 @@ def get_keras_model_class(dataset, i, num_classes, add_layer):
         while len(key)>0:
             model.add(key[0])
             del key[0]
-            
+
         if (i < 5):
             model.add(
                 Dense(
@@ -81,18 +81,18 @@ def get_keras_model_class(dataset, i, num_classes, add_layer):
                     kernel_initializer="normal",
                     activation="relu"))
 
-    if num_classes == 2:
-        model.add(Dense(1, activation="sigmoid"))
-        model.compile(
-            loss='binary_crossentropy',
-            optimizer='adam',
-            metrics=['accuracy'])
-    elif num_classes > 2:
-        model.add(Dense(num_classes, activation="softmax"))
-        model.compile(
-            loss='categorical_crossentropy',
-            optimizer='adam',
-            metrics=['accuracy'])
+    # if num_classes == 2:
+    #     model.add(Dense(1, activation="sigmoid"))
+    #     model.compile(
+    #         loss='binary_crossentropy',
+    #         optimizer='adam',
+    #         metrics=['accuracy'])
+    # elif num_classes > 2:
+    model.add(Dense(num_classes, activation="softmax"))
+    model.compile(
+        loss='categorical_crossentropy',
+        optimizer='adam',
+        metrics=['accuracy'])
 
     return model
 

libra/query/feedforward_nn.py

@@ -24,7 +24,6 @@
 from sklearn.preprocessing import StandardScaler
 import numpy as np
 
-
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 
 counter = 0
@@ -77,14 +76,16 @@ def logger(instruction, found=""):
 
 
 def get_folder_dir(self):
-    dir_path= tkFileDialog.askdirectory()
+    dir_path = tkFileDialog.askdirectory()
     return dir_path
 
+
 def get_file():
     filename = tkFileDialog.askopenfilename()
     if os.path.isfile(filename):
         return filename
-    else: print ('No file chosen')
+    else:
+        print('No file chosen')
 
 
 def regression_ann(
@@ -153,7 +154,7 @@ def regression_ann(
 
     i = 0
 
-    #add_layer format: {<object> : list of indexs}
+    # add_layer format: {<object> : list of indexs}
     # get the first 3 layer model
     model = get_keras_model_reg(data, i, add_layer)
 
@@ -200,8 +201,8 @@ def regression_ann(
         print((" " * 2 * counter) + "| " + ("".join(word.ljust(col_width)
                                                     for word in row)) + " |")
     datax = []
-    #while all(x > y for x, y in zip(losses, losses[1:])):
-    while (len(losses)<=2 or losses[len(losses)-1] < losses[len(losses)-2]):
+    # while all(x > y for x, y in zip(losses, losses[1:])):
+    while (len(losses) <= 2 or losses[len(losses) - 1] < losses[len(losses) - 2]):
         model = get_keras_model_reg(data, i, add_layer)
         history = model.fit(
             X_train,
@@ -312,12 +313,12 @@ def classification_ann(instruction,
 
     num_classes = len(np.unique(y))
 
-    X_train = data['train']
-    X_test = data['test']
-
     if num_classes < 2:
         raise Exception("Number of classes must be greater than or equal to 2")
 
+    X_train = data['train']
+    X_test = data['test']
+
     if num_classes >= 2:
         # ANN needs target one hot encoded for classification
         one_hot_encoder = OneHotEncoder()
@@ -400,8 +401,8 @@ def classification_ann(instruction,
         print((" " * 2 * counter) + "| " + ("".join(word.ljust(col_width)
                                                     for word in row)) + " |")
     datax = []
-    #while all(x < y for x, y in zip(accuracies, accuracies[1:])):
-    while (len(accuracies)<=2 or accuracies[len(accuracies)-1] > accuracies[len(accuracies)-2]):
+    # while all(x < y for x, y in zip(accuracies, accuracies[1:])):
+    while (len(accuracies) <= 2 or accuracies[len(accuracies) - 1] > accuracies[len(accuracies) - 2]):
         model = get_keras_model_class(data, i, num_classes, add_layer)
         history = model.fit(
             X_train,
@@ -498,7 +499,7 @@ def convolutional(instruction=None,
     :return dictionary that holds all the information for the finished model.
     '''
 
-    #data_path = get_folder_dir()
+    # data_path = get_folder_dir()
 
     logger("Generating datasets for classes")
 
@@ -633,9 +634,11 @@ def convolutional(instruction=None,
         else:
             # Randomly initialized weights
             if arch_lower == "vggnet16":
-                model = VGG16(include_top=True, weights=None, classes=num_classes, classifier_activation = output_layer_activation)
+                model = VGG16(include_top=True, weights=None, classes=num_classes,
+                              classifier_activation=output_layer_activation)
             elif arch_lower == "vggnet19":
-                model = VGG19(include_top=True, weights=None, classes=num_classes, classifier_activation = output_layer_activation)
+                model = VGG19(include_top=True, weights=None, classes=num_classes,
+                              classifier_activation=output_layer_activation)
             elif arch_lower == "resnet50":
                 model = ResNet50(include_top=True, weights=None, classes=num_classes)
             elif arch_lower == "resnet101":
@@ -688,7 +691,6 @@ def convolutional(instruction=None,
             activation="softmax"
         ))
 
-
     model.compile(
         optimizer="adam",
         loss=loss_func,
@@ -756,4 +758,3 @@ def convolutional(instruction=None,
             'validation_accuracy': history.history['val_accuracy']},
         'num_classes': (2 if num_classes == 1 else num_classes),
         'data_sizes': {'train_size': processInfo['train_size'], 'test_size': processInfo['test_size']}}
-

tests/tests.py

@@ -20,7 +20,7 @@ def compare(a, b):
 unittest.defaultTestLoader.sortTestMethodsUsing = compare
 
 class TestQueries(unittest.TestCase):
-    newClient = client('tools/data/structured_data/housing.csv')
+    newClient = client('/Users/anasawadalla/PycharmProjects/libra/tools/data/structured_data/housing2.csv')
     """
     TEST QUERIES