Merge branch 'IT18116984_WeerasundaraD.A' into 'master'

Add the required accuracy graph to the research paper

See merge request !16

disease_prediction/.gitignore

-.idea
\ No newline at end of file

disease_prediction/.idea/.gitignore

+# Default ignored files
+/workspace.xml

disease_prediction/.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

disease_prediction/.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/disease_prediction.iml" filepath="$PROJECT_DIR$/.idea/disease_prediction.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

disease_prediction/.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$/.." vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

disease_prediction/disease_prediction_model.py

@@ -2,6 +2,7 @@ import numpy
 import pandas as pd
 import tensorflow as tf
 from sklearn.model_selection import train_test_split
+import matplotlib.pyplot as plt
 
 model = tf.keras.models.Sequential()
 
@@ -9,28 +10,49 @@ def trainModel(model, datasetFilePath):
     model.add(tf.keras.layers.Flatten())
     model.add(tf.keras.layers.Dense(256, activation=tf.nn.relu))
     model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
-    model.add(tf.keras.layers.Dense(46, activation=tf.nn.softmax))
+    model.add(tf.keras.layers.Dense(11, activation=tf.nn.softmax))
     model.compile(optimizer='adam',
                   loss='sparse_categorical_crossentropy',
                   metrics=['accuracy'])
     model_df = pd.read_csv(datasetFilePath)
-    X = model_df.values[:,0:15]
-    y = model_df.values[:,15]
+    print(model_df.shape)
+    X = model_df.values[:,0:18]
+    y = model_df.values[:,18]
     print(y)
     x_train,x_test,y_train,y_test = train_test_split(X,y, stratify=y,test_size=0.2)
 
     x_train = tf.keras.utils.normalize(x_train, axis=1)
     x_test = tf.keras.utils.normalize(x_test, axis=1)
-    model.fit(x_train, y_train, epochs=3)
+    history = model.fit(x_train, y_train, epochs=50, validation_data=(x_test, y_test))
 
     val_loss, val_acc = model.evaluate(x_test, y_test)
-    print(val_loss)
-    print(val_acc)
+    print("Loss: ",val_loss)
+    print("Accuracy: ",val_acc*100, "%")
 
     model.save('model.h5')
+
+    print(history.history)
+    # summarize history for accuracy
+    plt.plot(history.history['acc'])
+    plt.plot(history.history['val_acc'])
+    plt.title('model accuracy')
+    plt.ylabel('accuracy')
+    plt.xlabel('epoch')
+    plt.legend(['train', 'test'], loc='upper left')
+    plt.show()
+    # summarize history for loss
+    plt.plot(history.history['loss'])
+    plt.plot(history.history['val_loss'])
+    plt.title('model loss')
+    plt.ylabel('loss')
+    plt.xlabel('epoch')
+    plt.legend(['train', 'test'], loc='upper left')
+    plt.show()
+
     return model
 
 def predict(model, data):
     return model.predict(numpy.array(data))
 
 trainModel(model, "data.csv")
+

disease_prediction/predict_disease.py

@@ -10,7 +10,7 @@ model = tf.keras.models.Sequential()
 model.add(tf.keras.layers.Flatten())
 model.add(tf.keras.layers.Dense(256, activation=tf.nn.relu))
 model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
-model.add(tf.keras.layers.Dense(46, activation=tf.nn.softmax))
+model.add(tf.keras.layers.Dense(11, activation=tf.nn.softmax))
 
 model.compile(optimizer='adam',
               loss='sparse_categorical_crossentropy',
@@ -21,4 +21,6 @@ def predict(data):
     return model.predict(numpy.array(data))
 
 # Test prediction
-print(numpy.argmax(predict([[1,3,1,1,1,0,0,1,1,0,1,0,0,1,1]])))
+print(predict([[1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0]]))
+print(numpy.argmax(predict([[1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0]])))
+print(disease_labels[numpy.argmax(predict([[1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0]]))])