changes

disease_prediction/.gitignore

+.idea
\ No newline at end of file

disease_prediction/disease_prediction_model.py

+import numpy
+import pandas as pd
+import tensorflow as tf
+from sklearn.model_selection import train_test_split
+
+model = tf.keras.models.Sequential()
+
+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.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(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)
+
+    val_loss, val_acc = model.evaluate(x_test, y_test)
+    print(val_loss)
+    print(val_acc)
+
+    model.save('model.h5')
+    return model
+
+def predict(model, data):
+    return model.predict(numpy.array(data))
+
+trainModel(model, "data.csv")

disease_prediction/predict_disease.py

+disease_labels = ["Canine Scabies","Canine demodicosis","Fungal dermatitis","Allergic dermatitis","Ehrlichiosis","Canine babesiosis","Immune Mediated Haemolytic Anaemia","Acquired Thrombocytopenia","Hypoglycemia","Hypocalcemia","Canine parvo virus infection","Canine corona virus infection","Sphingomyelinase","Rabies","Bacterial prostatitis","Balanoposthitis","Canine brucellosis","Canine Cirrhosis","Bang's Disease","Candidiasis","Canine distemper","Canine influenza","Canine lymphoma","Lyme disease","Kidney disease","Kennel Cough","Diarrhoea","Gastritis","Gastroenteritis","Hepatitis","Giardia infection","Canine herpes virus","Galucoma","Gastric ulcer","Hepatic Encephalopathy","Hepatic lipidosis","Pneumonia","Diabetes","Ear infections","Heartworm","Anemia","Canine Leptospirosis","HEATSTROKE","Canine Hip Dysplasia","Canine Elbow Dysplasia"]
+print(len(disease_labels))
+
+import numpy
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+
+model = tf.keras.models.Sequential()
+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.compile(optimizer='adam',
+              loss='sparse_categorical_crossentropy',
+              metrics=['accuracy'])
+model = load_model('model.h5')
+
+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]])))